10th week of 2022 patent applcation highlights part 50 |
Patent application number | Title | Published |
20220075991 | Stabilizing Video by Accounting for a Location of a Feature in a Stabilized View of a Frame - The subject matter described in this disclosure can be embodied in methods and systems for stabilizing video. A computing system determines a stabilized location of a facial feature in a frame of video accounting for its location in a previous frame. The computing system determines a physical camera pose in virtual space and maps the frame into virtual space. The computing system determines an optimized virtual camera pose using an optimization process that determines (1) a difference between the stabilized location of the facial feature and a location of the facial feature when viewed from a potential virtual camera pose, (2) a difference between the potential virtual camera pose and a previous virtual camera pose, and (3) a difference between the potential virtual camera pose and the physical camera pose. The computing system generates the stabilized view of the frame using the optimized virtual camera pose. | 2022-03-10 |
20220075992 | ILLUMINATION DETECTION METHOD AND APPARATUS FOR FACE IMAGE, AND DEVICE AND STORAGE MEDIUM - An illumination detection method comprises acquiring a face image to be detected and a three-dimensional face mesh template; deforming the three-dimensional face mesh template according to the face image to obtain a reconstructed face mesh model; according to the deformation positions, in the reconstructed face mesh model, of key feature points in the three-dimensional face mesh template, determining the brightness of feature points, corresponding to the key feature points, in the face image; and according to the relationship between the predetermined brightness of the key feature points and the illumination, and the brightness of the feature points, corresponding to the key feature points, in the face image, determining illumination information of the face image. | 2022-03-10 |
20220075993 | FACIAL AUTHENTICATION DEVICE, FACIAL AUTHENTICATION METHOD, AND PROGRAM RECORDING MEDIUM - This facial authentication device is provided with: a detecting means for detecting a plurality of facial feature point candidates, using a plurality of different techniques, for at least one facial feature point of a target face, from a plurality of facial images containing the target face; a reliability calculating means for calculating a reliability of each facial image, from statistical information obtained on the basis of the plurality of detected facial feature point candidates; and a selecting means for selecting a facial image to be used for authentication of the target face, from among the plurality of facial images, on the basis of the calculated reliabilities. | 2022-03-10 |
20220075994 | REAL-TIME FACIAL LANDMARK DETECTION - Embodiments of the present disclosure enable and accurate detection of facial landmarks on mobile devices in real-time. An architecture of a facial landmark detection model is provided including one or more of an attention mechanism (e.g., an attention network), a graph convolution model (e.g., a two-dimensional facial geometry graph convolution model), a multiscale coarse-to-fine mechanism, a patch-facial landmark detachment mechanism, and error estimation techniques. The attention mechanism may increase the accuracy of the facial landmark detection model by attending to meaningful patches. The graph convolution network may improve patch feature aggregation by considering the facial landmarks' geometry. The coarse-to-fine mechanism reduces a network convergence to two cycles (e.g., two facial landmark detection iterations). A patch-facial landmark detachment mechanism reduces the computation burden without significant accuracy degradation. Error estimation techniques provide accurate estimation of the regression error to the computation load and increase the accuracy of the model. | 2022-03-10 |
20220075995 | Videoconferencing Using Hybrid Edge/Cloud Inference with Machine-Learned Systems - Systems and methods for providing a multi-step identification process using a hybrid edge/server infrastructure to generate machine learned inferences are provided. One example method includes obtaining sensor data of an environment including one or more user. The method includes selecting at least a portion of the sensor data that is associated with the one or more users. The method includes generating, using one or more machine learning models, an intermediate representation of the selected portion of the sensor data that represents the face of the one or more users. The method includes transmitting the intermediate representation and a request for a user identification based on the intermediate representation, the remote computing system configured to perform additional steps of the multi-step identification process using the intermediate representation and the machine-learned system. The method includes receiving a user identifier for the one or more users. | 2022-03-10 |
20220075996 | METHOD AND DEVICE FOR DETERMINING OPERATION BASED ON FACIAL EXPRESSION GROUPS, AND ELECTRONIC DEVICE - This application provides an operation determination method based on expression groups, apparatus and electronic device therefor, and relates to the technical field of image processing. The method is executed by an electronic device. The method comprises: obtaining a current human face image of a target object; performing a live body human face identification on the target object based on the current human face image, determining whether an identity of the target object is legal according to an identification result; the live body human face identification comprises a live body identification and a human face identification; if legal, obtaining a current expression group of the current human face image; determining an instruction to be executed corresponding to the current expression group; performing an operation corresponding to the instruction to be executed. This application uses human face identification technology, and while continuing the identity authentication function of human face identification, with addition of user-defined facial expressions, it may ensure that a user will not display these actions in unconscious states such as work, sleep or coma etc., which greatly protects the safety of the user's face, to improve the safety and reliability of the electronic device to determine the operation. | 2022-03-10 |
20220075997 | FACE FEATURES MATCHING BASED TRACKER - Systems, and method and computer readable media that store instructions for features matching based tracker. | 2022-03-10 |
20220075998 | SECURE FACE IMAGE TRANSMISSION METHOD, APPARATUSES, AND ELECTRONIC DEVICE - This application discloses a secure face image transmission method performed by an electronic device. In this application, when a camera component of the electronic device acquires any face image, face image information can be read from a buffer. The face image information is used for indicating a quantity of all face images historically acquired by the camera component. Identification information is embedded in the face image to obtain the face image carrying the identification information. The identification information is used for indicating the face image information but not perceivable by a human being. The face image carrying the identification information is transmitted to a remote server for authenticating the face image using the identification information. Therefore, the security of the face image acquired by the camera component is improved, and the security of the face image transmission process is effectively ensured. | 2022-03-10 |
20220075999 | SPOOFING DETECTION DEVICE, SPOOFING DETECTION METHOD, AND RECORDING MEDIUM - To provide a technology of more accurately detecting spoofing in face authentication, without increasing a scale of a device configuration and a burden on a user. A spoofing detection device includes a facial image sequence acquisition unit, a line-of-sight change detection unit, a presentation information display unit, and a spoofing determination unit. The facial image sequence acquisition unit acquires a facial image sequence indicating the face of a user. The line-of-sight change detection unit detects information about a temporal change in the line-of-sight from the facial image sequence. The presentation information display unit displays presentation information presented to the user as part of an authentication process. The spoofing determination unit determines the likelihood of the face indicated by the facial image sequence being spoofing on the basis of the information about the temporal change in the line-of-sight with respect to the presentation information. | 2022-03-10 |
20220076000 | Image Processing Method And Apparatus - An image processing method and apparatus are provided. The image processing method includes: obtaining a face image; separately obtaining a left face image and a right face image based on the face image; inputting the left face image into a first target key point convolutional neural network model, and outputting coordinates of a first left face key point; inputting the right face image into a second target key point convolutional neural network model, and outputting coordinates of a first right face key point; and obtaining coordinates of a face key point of the face image based on the coordinates of the first left face key point and the coordinates of the first right face key point. | 2022-03-10 |
20220076001 | INFORMATION PROCESSING DEVICE - An information processing device according to the present invention includes a person extraction means that extracts a person in a captured image, an action extraction means that extracts an action of a person group including a plurality of persons other than a given person in the captured image, and an identification means that identifies a given person group based on a result of extraction of the action of the person group. | 2022-03-10 |
20220076002 | ACTION RECOGNITION METHOD AND APPARATUS, COMPUTER STORAGE MEDIUM, AND COMPUTER DEVICE - An action recognition method includes: obtaining original feature submaps of each of temporal frames on a plurality of convolutional channels by using a multi-channel convolutional layer; calculating, by using each of the temporal frames as a target temporal frame, motion information weights of the target temporal frame on the convolutional channels according to original feature submaps of the target temporal frame and original feature submaps of a next temporal frame, and obtaining motion information feature maps of the target temporal frame on the convolutional channels according to the motion information weights; performing temporal convolution on the motion information feature maps of the target temporal frame to obtain temporal motion feature maps of the target temporal frame; and recognizing an action type of a moving object in image data of the target temporal frame according to the temporal motion feature maps of the target temporal frame on the convolutional channels. | 2022-03-10 |
20220076003 | ACTION RECOGNITION APPARATUS, LEARNING APPARATUS, AND ACTION RECOGNITION METHOD - An action recognition apparatus performs: a detection process of detecting a shape of an object to be recognized from to-be-analyzed data; a component analysis process of generating one or more components and respective contribution ratios of said components through the component analysis, based on the shape of the object to be recognized; a determination process of determining an ordinal number indicating each dimension of said components based on a cumulative contribution ratio attained from the respective contribution ratios; a selection process of selecting, among the group of action classification models, a specific action classification model in which learning was performed with the same component group as a specific component group including the components with the ordinal number indicating the dimension; and an action recognition process of inputting the specific component group into the specific action classification model, thereby outputting recognition results indicating actions of the object to be recognized. | 2022-03-10 |
20220076004 | MODEL PARAMETER LEARNING METHOD AND MOVEMENT MODE PARAMETER DETERMINATION METHOD - In a learning method, a time series of a movement direction when a reference pedestrian M | 2022-03-10 |
20220076005 | PERSON AUTHENTICATION APPARATUS, CONTROL METHOD, AND NON-TRANSITORY STORAGE MEDIUM - A person authentication apparatus ( | 2022-03-10 |
20220076006 | METHOD AND DEVICE FOR IMAGE PROCESSING, ELECTRONIC DEVICE AND STORAGE MEDIUM - A method for image processing includes: performing human shape detection for a target image to obtain a human shape detection result, the target image being acquired in a present scene in real time; determining a region of interest in the target image according to the human shape detection result of the target image; and determining, based on brightness distribution in the region of interest, a target parameter value for image acquisition in the present scene. | 2022-03-10 |
20220076007 | DYNAMIC DETECTION OF CROSS-DOCUMENT ASSOCIATIONS - Systems and methods are configured to generate a set of related document objects for a predictive entity and/or to generate an optimal document sequence for a set of related document objects. In one embodiment, a set of related document objects for a predictive entity is generated by processing entity metadata features associated with the predictive entity using an entity-document correlation machine learning model, and an optimal document sequence is generated for the set of related document objects by processing the set of related document objects using a document sequence optimization machine learning model. | 2022-03-10 |
20220076008 | SYSTEMS AND METHODS FOR ENROLLMENT AND IDENTITY MANAGEMENT USING MOBILE IMAGING - Systems and methods for automatic enrollment and identity verification based upon processing a captured image of a document are disclosed herein. Various embodiments enable, for example, a user to enroll in a particular service by taking a photograph of a particular document (e.g., his driver license) with a mobile device. One or more algorithms can then extract relevant data from the captured image. The extracted data (e.g., the person's name, gender, date of birth, height, weight, etc.) can then be used to automatically populate various fields of an enrollment application, thereby reducing the amount of information that the user has to manually input into his mobile device in order to complete the enrollment process. In some embodiments, a set of internal and/or external checks can be run against the data to ensure that the data is valid, has been read correctly, and is consistent with other data. | 2022-03-10 |
20220076009 | METHODS AND SYSTEMS OF RESUME BUILDER FEEDBACK MODULES - A computer-implemented method comprising: detecting that a user focuses on a text area to edit; fetching a corresponding feedback from a feedback object; based on the feedback show a suggested feedback; determine that the element is an essential element; with a tracker functionality, displaying with an indicator for each tracker; adding more content by displaying an additional material; adding more content step by opening a tool on the right side in synchronization with an editing panel; displaying category suggestions when a section has no sub section type structure; and enabling a suggestions API to directly access from a categories server. | 2022-03-10 |
20220076010 | METHOD OF GENERATING TEXT FEATURES FROM A DOCUMENT - A method of generating text features from a document comprises one or more processors grouping text comprised in the document into multiple logical text blocks, wherein each of the logical text blocks comprises one or more tokens. One of the logical text blocks is selected for generating features. Thereafter, logical text blocks neighbouring the selected logical block are identified. Further, the processer qualifies one or more of the neighbouring logical text blocks for generating features. The processor generates features for one or more of the tokens in the selected logical block using the qualified logical text blocks. | 2022-03-10 |
20220076011 | METHOD AND SYSTEM FOR SUSTAINABILITY MEASUREMENT - Sustainability measurement is critical to determine whether industry performance is heading in intended direction. State of the art systems in the field of sustainability measurement fail to consider many parameters which are indicative of the sustainability of industries. The disclosure herein generally relates to industry monitoring, and, more particularly, to a method and system for sustainability measurement in an industrial environment. The system calculates similarity score which indicates similarity between different sentences and indicators, and used the calculated similarity scores and extracted features to classify the sentences as belonging to specific classes. This information is in turn used for measuring sustainability of organization from which input data have been collected. | 2022-03-10 |
20220076012 | VISION-BASED CELL STRUCTURE RECOGNITION USING HIERARCHICAL NEURAL NETWORKS AND CELL BOUNDARIES TO STRUCTURE CLUSTERING - Methods, systems, and computer program products for vision-based cell structure recognition using hierarchical neural networks and cell boundaries to structure clustering are provided herein. A computer-implemented method includes detecting a style of the given table using at least one style classification model; selecting, based at least in part on the detected style, a cell detection model appropriate for the detected style; detecting cells within the given table using the selected cell detection model; and outputting, to at least one user, information pertaining to the detected cells comprising image coordinates of one or more bounding boxes associated with the detected cells. | 2022-03-10 |
20220076013 | INFORMATION PRESENTATION SYSTEM, CONTROL METHOD THEREOF, AND NON-TRANSITORY COMPUTER-READABLE STORAGE MEDIUM - An information presentation system comprising an obtainment unit obtaining a feature of an object, a specification unit specifying the object from the feature, a display, a storage storing specification information and a communication unit communicating with an external server and obtaining related information of the object is provided. The specification unit specifies the object by searching for the specification information. The specification information includes a plurality of pieces of feature information observation targets and a plurality of pieces of object information which are associated with the plurality of pieces of feature information and related to the observation targets. The display displays the related information. In a case in which the specification unit has specified the object and there is a difference between the related information and the object information, the object information is updated based on the related information. | 2022-03-10 |
20220076014 | INFORMATION PROCESSING DEVICE, AND INFORMATION PROCESSING SYSTEM - The present disclosure makes it possible to more accurately estimate information relating to crop infection, on the basis of more appropriate cultivation information. Provided is an information processing device comprising: a feature quantity conversion unit that generates a feature quantity by performing a feature quantity conversion of at least one of piece of information among information pieces relating to three factors causing disease in crops, namely a primary cause, a predisposition and an inducement; and an estimation unit that estimates crop infection information on the basis of an infection estimation model which is used to estimate infection information relating to infection of the crop, which is generated on the basis of a machine-learning algorithm, and which uses as input the information relating to the three factors, including the feature quantity. | 2022-03-10 |
20220076015 | FAST MULTI-MODAL OBJECT RECOGNITION SYSTEM - A method for object recognition at an interactive information system (IIS) includes capturing, using an imaging device of the IIS, a first image of a first representative object which represents a first one or more object disposed about the IIS; analyzing, by a computer processor of the IIS and based on a category model, the first image to determine a first representative category of the first one or more object; retrieving, by the computer processor and based on the first representative category, a first representative object model of a plurality of object models that are stored on a remote server; and analyzing, by the computer processor and based on the first representative object model, the first image to determine a first representative inventory identifier of the first representative object, which represents a first one or more inventory identifier corresponding to the first one or more object respectively. | 2022-03-10 |
20220076016 | REAL-TIME POWER PLANT OPERATIONAL DATA FOR AUGMENTED REALITY ASSISTANCE - A power plant control system includes a memory; and a processor coupled to the memory and configured to process events in the processor according to a method. The system identifies an adjustable component of a power plant based on an image of at least a portion of the adjustable component, the adjustable component controlling at least one operational parameter of the power plant. An operational instruction is generated for the adjustable component from a database based on the image, the operational instruction capable of being rendered visually in an augmented reality (AR) system. The operational instruction is transmitted to the AR system for implementing by a user; and real-time operational data is transmitted to the AR system. The real-time operational data including a change to the at least one operational parameter based on an adjustment made to the adjustable component. | 2022-03-10 |
20220076017 | AUGMENTED REALITY TYPOGRAPHY PERSONALIZATION SYSTEM - Disclosed are augmented reality (AR) personalization systems to enable a user to edit and personalize presentations of real-world typography in real-time. The AR personalization system captures an image depicting a physical location via a camera coupled to a client device. For example, the client device may include a mobile device that includes a camera configured to record and display images (e.g., photos, videos) in real-time. The AR. personalization system causes display of the image at the client device, and scans the image to detect occurrences of typography within the image (e.g., signs, billboards, posters, graffiti). | 2022-03-10 |
20220076018 | Determining Regions of Interest for Photographic Functions - Apparatus and methods related to photography are provided. A computing device can receive an input image. An object detector of the computing device can determine an object region of interest of the input image that is associated with an object detected in the input image. A trained machine learning algorithm can determine an output photographic region of interest for the input image based on the object region of interest and the input image. The machine learning algorithm can be trained to identify an output photographic region of interest that is suitable for use by a photographic function for image generation. The computing device can generate an output related to the output photographic region of interest. | 2022-03-10 |
20220076019 | Automated Analysis Of Image Contents To Determine The Acquisition Location Of The Image - Techniques are described for using computing devices to perform automated operations for determining the acquisition location of an image using an analysis of the image's visual contents. In at least some situations, images to be analyzed include panorama images acquired at acquisition locations in an interior of a multi-room building, and the determined acquisition location information includes a location on a floor plan of the building and in some cases orientation direction information—in at least some such situations, the acquisition location determination is performed without having or using information from any distance-measuring devices about distances from an image's acquisition location to objects in the surrounding building. The acquisition location information may be used in various automated manners, including for controlling navigation of devices (e.g., autonomous vehicles), for display on one or more client devices in corresponding graphical user interfaces, etc. | 2022-03-10 |
20220076020 | USER PRESENCE/ABSENCE RECOGNITION DURING ROBOTIC SURGERIES USING DEEP LEARNING - Disclosed are various user-presence/absence recognition techniques based on deep learning. More specifically, various user-presence/absence recognition techniques include building/training a CNN-based image recognition model including a user-presence/absence classifier based on training images collected from the user-seating area of a surgeon console under various clinically-relevant conditions/cases. The trained user-presence/absence classifier can then be used during teleoperation/surgical procedures to monitor/track users in the user-seating area of the surgeon console, and continuously classify the real-time video images of the user-seating area as either a user-presence state or a user-absence state. In some embodiments, the disclosed techniques can be used to detect a user-switching event at the surgeon console when a second user is detected to have entered the user-seating area after a first user is detected to have exited the user-seating area. If the second user is identified as a new user, the disclosed techniques can trigger a recalibration procedure for the new user. | 2022-03-10 |
20220076021 | System and method for automatic visual inspection with deep learning - The present invention provides a visual inspection system implemented by a product manufacturing site wherein the system comprising an input module, a processing module, and an output module. The input module is configured for receiving a video stream of at least one or more products on a conveyor belt. The processing module is enabled to extract at least plurality of frames horn the video stream of the at least one or more products, received by the input module, select at least one or more frames from the at least plurality of frames haying an image of a product, and extract area of interest, excluding a background region, from the at least one or more dames having the image of the product. The processing module is configured to generate a product boundary lines including annotating the product boundary lines, from the extracted area of interest using an annotation deep learning module and generate at least one or more data points of the product from the annotated product boundary lines utilizing a data point deep learning module. Further, the processing module is configured to generate at least one indication, upon comparison of the generated at least one or more data points of the product with at least predefined data points of a sample product by using a product inspection deep learning module. The output module is configured to display the at least one indication. In some embodiments, the processing module uses at least one deep learning module to extract area of interest. | 2022-03-10 |
20220076022 | SYSTEM AND METHOD FOR OBJECT TRACKING USING FEATURE-BASED SIMILARITIES - An embodiment of the present invention discloses an object tracking system for tracking objects across a first frame and a second frame of a video. The object tracking system comprises of a processor, a non-transitory storage element coupled to the processor and encoded instructions stored in the non-transitory storage element. The encoded instructions when implemented by the processor, configure the object tracking system to detect one or more objects in the first frame of the video, and one or more candidate objects in the second frame of the video. | 2022-03-10 |
20220076023 | SEGMENTATION AND HIERARCHICAL CLUSTERING OF VIDEO - Embodiments are directed to segmentation and hierarchical clustering of video. In an example implementation, a video is ingested to generate a multi-level hierarchical segmentation of the video. In some embodiments, the finest level identifies a smallest interaction unit of the video—semantically defined video segments of unequal duration called clip atoms. Clip atom boundaries are detected in various ways. For example, speech boundaries are detected from audio of the video, and scene boundaries are detected from video frames of the video. The detected boundaries are used to define the clip atoms, which are hierarchically clustered to form a multi-level hierarchical representation of the video. In some cases, the hierarchical segmentation identifies a static, pre-computed, hierarchical set of video segments, where each level of the hierarchical segmentation identifies a complete set (i.e., covering the entire range of the video) of disjoint (i.e., non-overlapping) video segments with a corresponding level of granularity. | 2022-03-10 |
20220076024 | INTERACTING WITH HIERARCHICAL CLUSTERS OF VIDEO SEGMENTS USING A METADATA PANEL - Embodiments are directed to techniques for interacting with a hierarchical video segmentation using a metadata panel with a composite list of video metadata. The composite list is segmented into selectable metadata segments at locations corresponding to boundaries of video segments defined by a hierarchical segmentation. In some embodiments, the finest level of a hierarchical segmentation identifies the smallest interaction unit of a video—semantically defined video segments of unequal duration called clip atoms, and higher levels cluster the clip atoms into coarser sets of video segments. One or more metadata segments can be selected in various ways, such as by clicking or tapping on a metadata segment or by performing a metadata search. When a metadata segment is selected, a corresponding video segment is emphasized on the video timeline, a playback cursor is moved to the first video frame of the video segment, and the first video frame is presented. | 2022-03-10 |
20220076025 | VIDEO SEARCH SEGMENTATION - Embodiments are directed to video segmentation based on a query. Initially, a first segmentation such as a default segmentation is displayed (e.g., as interactive tiles in a finder interface, as a video timeline in an editor interface), and the default segmentation is re-segmented in response to a user query. The query can take the form of a keyword and one or more selected facets in a category of detected features. Keywords are searched for detected transcript words, detected object or action tags, or detected audio event tags that match the keywords. Selected facets are searched for detected instances of the selected facets. Each video segment that matches the query is re-segmented by solving a shortest path problem through a graph that models different segmentation options. | 2022-03-10 |
20220076026 | THUMBNAIL VIDEO SEGMENTATION IDENTIFYING THUMBNAIL LOCATIONS FOR A VIDEO - Embodiments are directed to a thumbnail segmentation that defines the locations on a video timeline where thumbnails are displayed. Candidate thumbnail locations are determined from boundaries of feature ranges of the video indicating when instances of detected features are present in the video. In some embodiments, candidate thumbnail separations are penalized for being separated by less than a minimum duration corresponding to a minimum pixel separation (e.g., the width of a thumbnail) between consecutive thumbnail locations on a video timeline. The thumbnail segmentation is computed by solving a shortest path problem through a graph that models different thumbnail locations and separations. As such, a video timeline is displayed with thumbnails at locations on the timeline defined by the thumbnail segmentation, with each thumbnail depicting a portion of the video associated with the thumbnail location. | 2022-03-10 |
20220076027 | AMBIENT INVENTORYING ARRANGEMENTS - Inventory on a rack of store shelves is monitored by a camera-equipped system that senses when items have been removed. Image data is desirably sensed at plural spectral bands, to enhance item identification by digital watermark and/or other image recognition techniques. The system can be alert to the presence of nearby shoppers, and change its mode of operation in response, e.g., suppressing flash illumination or suspending image capture. The system may self-calibrate to the geometry of shelving in its field of view, and affine-correct captured imagery based on the camera's viewpoint. A great many other features and arrangements are also detailed. | 2022-03-10 |
20220076028 | VIDEO SURVEILLANCE SYSTEM, VIDEO PROCESSING APPARATUS, VIDEO PROCESSING METHOD, AND VIDEO PROCESSING PROGRAM - A video processing apparatus includes a video analyzer that analyzes video data captured by a surveillance camera, detects an event belonging to a specific category, and outputs a detection result, a display controller that displays, together with a video of the video data, a category setting screen for setting a category of an event included in the video, and a learning data accumulator that accumulates, as learning data together with the video data, category information set in accordance with an operation by an operator to the category setting screen. The video analyzer performs learning processing by using the learning data accumulated in the learning data accumulator. | 2022-03-10 |
20220076029 | FOREIGN MATTER DETECTION SYSTEM - Provided are an image capturing device for capturing an image in a target area, transmission parts through which an outside can be visually observed from inside of the target area and polarizing filters on an light path from the transmission parts to the image capturing device. The front- and depth-side polarizing filters relative to the image capturing device are arranged so as to have polarizing directions crossing each other. A foreign matter in the target area is detected on the basis of the image acquired by the image capturing device. | 2022-03-10 |
20220076030 | ANNOTATED SURFEL MAPS - Methods, systems, and apparatus, including computer programs encoded on computer storage media, for the generation and use of a surfel map with semantic labels. One of the methods includes receiving a surfel map that includes a plurality of surfels, wherein each surfel has associated data that includes one or more semantic labels; obtaining sensor data for one or more locations in the environment, the sensor data having been captured by one or more sensors of a first vehicle; determining one or more surfels corresponding to the one or more locations of the obtained sensor data; identifying one or more semantic labels for the one or more surfels corresponding to the one or more locations of the obtained sensor data; and performing, for each surfel corresponding to the one or more locations of the obtained sensor data, a label-specific detection process for the surfel. | 2022-03-10 |
20220076031 | Remote Image Processing Control - A technology for remote object imaging processing. An example of the technology can include calculating geographic coordinates for an object using in part a line-of-sight distance to the object from a camera coupled to a vehicle, calculating an angle of the sun relative to the object using sun position data that corresponds to a time and date and the geographic coordinates for the object, determining a white balance setting based in part on the angle of the sun relative to the object, and applying the white balance setting as a parameter used to process an image of the object captured using the camera coupled to the vehicle. | 2022-03-10 |
20220076032 | ADAPTIVE OBJECT TRACKING ALGORITHM FOR AUTONOMOUS MACHINE APPLICATIONS - In various examples, lane location criteria and object class criteria may be used to determine a set of objects in an environment to track. For example, lane information, freespace information, and/or object detection information may be used to filter out or discard non-essential objects (e.g., objects that are not in an ego-lane or adjacent lanes) from objects detected using an object detection algorithm. Further, objects corresponding to non-essential object classes may be filtered out to generate a final filtered set of objects to be tracked that may be of a lower quantity than the actual number of detected objects. As a result, object tracking may only be executed on the final filtered set of objects, thereby decreasing compute requirements and runtime of the system without sacrificing object tracking accuracy and reliability with respect to more pertinent objects. | 2022-03-10 |
20220076033 | OBJECT TRACKING FOR WORK MACHINES - A system and method for monitoring objects in the vicinity of a work machine that is in motion includes obtaining, using a camera associated with the work machine, first image data of a field-of-view of the camera at a first position; identifying an object-of-interest within the first image data; associating an alarm with the object-of-interest, the alarm configured to indicate the presence of the object-of-interest; presenting the alarm through an output device; receiving an input to snooze the alarm for the object-of-interest; generating a mask for the object-of-interest using image coordinates of the object-of-interest within the first image data; obtaining, using the camera, second image data of the field-of-view of the camera at a second position during motion of the work machine; identifying an object within the second image data; and selectively aborting the alarm presentation through the output device in response to determining, using the mask, that the object is the object-of-interest. | 2022-03-10 |
20220076034 | METHODS AND SYSTEMS FOR DISPLAYING ANIMAL ENCOUNTER WARNINGS IN VEHICLES - A method of displaying a message associated with a likelihood of an animal appearing within a proximity of vehicle is provided. The method includes detecting, using a sensor of a vehicle, an animal warning sign in an area external to the vehicle at a particular time. The method further includes accessing in real time, using a computing device, a database including data associated with the animal depicted on the animal warning sign, determining in real time, using the computing device of the vehicle, a likelihood of the animal appearing within a proximity of the vehicle based on the accessed data, and displaying in real time, on a user interface associated with the computing device of the vehicle, a message based on the likelihood of the animal appearing within the proximity of the vehicle. | 2022-03-10 |
20220076035 | COARSE-TO-FINE ATTENTION NETWORKS FOR LIGHT SIGNAL DETECTION AND RECOGNITION - A vehicle light signal detection and recognition method, system, and computer program product include bounding, using a coarse attention module, one or more regions of an image of an automobile including at least one of a brake light and a signal light generated by automobile signals which include illuminated sections to generate one or more bounded region, removing, using a fine attention module, noise from the one or more bounded regions to generate one or more noise-free bounded regions, and identifying the at least one of the brake light and the signal light from the one or more noise-free bounded regions. | 2022-03-10 |
20220076036 | Redundant Camera Detection Paths - Systems and methods are provided for vehicle navigation. The systems and methods may detect traffic lights. For example, one or more traffic lights may be detected using detection-redundant camera detection paths, a fusion of information from a traffic light transmitter and one or more cameras, based on contrast enhancement for night images, and based on low resolution traffic light candidate identification followed by high resolution candidate analysis. Additionally, the systems and methods may navigation based on a worst time to red estimation. | 2022-03-10 |
20220076037 | Traffic Light Navigation Based on Worst Time to Red Estimation - Systems and methods are provided for vehicle navigation. The systems and methods may detect traffic lights. For example, one or more traffic lights may be detected using detection-redundant camera detection paths, a fusion of information from a traffic light transmitter and one or more cameras, based on contrast enhancement for night images, and based on low resolution traffic light candidate identification followed by high resolution candidate analysis. Additionally, the systems and methods may navigation based on a worst time to red estimation. | 2022-03-10 |
20220076038 | METHOD FOR CONTROLLING VEHICLE AND ELECTRONIC DEVICE - A method for controlling a vehicle, an electronic device and a storage medium are disclosed. The method includes: obtaining a plurality of images when the vehicle is driving, and determining lane line information included in the plurality of images by recognizing lane lines in the plurality of images; in response to a type of lane line in an image being a specified type, determining a region to be detected of the image based on a position of the specified type of lane line; determining traffic light information included in the image by detecting traffic lights in the region to be detected; and determining a current driving mode of the vehicle based on the traffic light information included in the image and a current driving state of the vehicle and driving the vehicle in the current driving mode. | 2022-03-10 |
20220076039 | VIDEO-BASED ACTIVITY RECOGNITION - Systems and techniques are provided for performing video-based activity recognition. For example, a process can include extracting, using a first machine learning model, first one or more features from a first frame and second one or more features from a second frame. The first one or more features and the second one or more features are associated with a person driving a vehicle. The process can include processing, using a second machine learning model, the first one or more features and the second one or more features. The process can include determining, based on processing of the first one or more features and the second one or more features using the second machine learning model, at least one activity associated with the person driving the vehicle. | 2022-03-10 |
20220076040 | DEVICE AND METHOD FOR DETECTING THE DISTRACTION OF A DRIVER OF A VEHICLE - A device for detecting the distraction of a driver of a vehicle is disclosed. The device includes an image acquisition assembly to acquire at least one image of a detection area located in said vehicle, said detection area comprising at least part of the driver of the vehicle, a processing module for processing the acquired image, designed to determine: a direction associated with the head of the driver, and a position of at least one hand of the driver, and an analysis module designed to detect the distraction of said driver by determining, on the basis of the direction associated with the head and the position of at least one hand, the possible presence of at least one hand in the direction associated with the head of the driver. A method for detecting the distraction of a driver of a vehicle is also disclosed. | 2022-03-10 |
20220076041 | QUALITY ASSESSMENT OF DIGITAL MEDIA - A method for quality assessment of digital media. The method includes dividing the digital media to a plurality of frame subsets, generating a plurality of frame-level feature sets by generating an m | 2022-03-10 |
20220076042 | TRANSLATION PEN AND CONTROL METHOD THEREFOR - A translation pen includes: a pen body, an indication component, an image collector and a first processor. The pen body has a pen tip end. The indication component is arranged on the pen tip end. The image collector is arranged on the pen body, and the image collector is configured to: collect an image including a text to be translated according to a position indicated by the indication component, and send the image collected. The first processor is arranged in the pen body and electrically connected to the image collector, and the first processor is configured to: receive the image sent by the image collector, and recognize the text to be translated in the image | 2022-03-10 |
20220076043 | METHOD FOR CORRECTING OPTICAL CHARACTER RECOGNITION TEXT POSITION, STORAGE MEDIUM AND ELECTRONIC DEVICE - The present disclosure provides a method for correcting an OCR text position, a storage medium and an electronic device. The method includes: determining a first slope of each text block in an OCR recognition result of a to-be-processed image; fitting a tilt field function in accordance with the first slope of each text block; determining an offset value of each text block in accordance with the tilt field function; and correcting a position of each text block in accordance with the offset value. | 2022-03-10 |
20220076044 | DEVICE AND METHOD FOR TRAINING A NORMALIZING FLOW - A computer-implemented method for training a normalizing flow. The normalizing flow predicts a first density value based on a first input image. The first density value characterizes a likelihood of the first input image to occur. The first density value is predicted based on an intermediate output of a first convolutional layer of the normalizing flow. The intermediate output is determined based on a plurality of weights of the first convolutional layer. The method for training includes: determining a second input image; determining an output, wherein the output is determined by providing the second input image to the normalizing flow and providing an output of the normalizing flow as output; determining a second density value based on the output tensor and on the plurality of weights; determining a natural gradient of the plurality of weights with respect to the second density value; adapting the weights according to the natural gradient. | 2022-03-10 |
20220076045 | IMAGE PROCESSING APPARATUS - An image processing apparatus includes a first extractor, a first object identifier, a region defining unit, a second extractor, a selector, and a second object identifier. The first extractor extracts a first feature quantity included in a captured image. The first object identifier identifies an object on the basis of the first feature quantity. The region defining unit defines an image region in the captured image. The second extractor extracts a second feature quantity included in an image in the image region. The selector selects, on the basis of data related to the image region defined by the region defining unit, a part of the first feature quantity extracted by the first extractor. The second object identifier identifies the object on the basis of the second feature quantity and the part of the first feature quantity selected by the selector. | 2022-03-10 |
20220076046 | EXPLOITING CAMERA ROLLING SHUTTER TO DETECT HIGH FREQUENCY SIGNALS - A method of extracting high-frequency temporal information from images or video recorded with a rolling shutter-based imager includes the steps of acquiring image data using a rolling shutter-based imager; and extracting time-domain frequency information from the image based on two or more lines of pixels in the image. | 2022-03-10 |
20220076047 | CONTENT GENERATION SYSTEM AND METHOD - A system for generating one or more images for display, the system comprising an image obtaining unit operable to obtain an image of a user's face, a geometry information unit operable to identify geometry information for the user's face using the obtained image, a lighting information unit operable to obtain lighting information for a virtual environment, a representation generation unit operable to generate a representation of the user's face generated using the obtained lighting information, and an image output unit operable to generate an output image comprising the generated representation and an image of the virtual environment. | 2022-03-10 |
20220076048 | GRAPH-BASED CONFIGURATION OF USER INTERFACE FOR SELECTION OF FEATURES IN VISUALIZATION APPLICATIONS - This disclosure involves generating, from a user data set, a ranked list of recommended secondary variables in a user interface field similar to primary variable selected in another user interface field. A system receives a data set having variables and corresponding sets of values. The data visualization system determines a feature vector for each variable based on statistics of a corresponding values set. The system generates a variable similarity graph having nodes representing variables and links representing degrees of similarity between feature vectors of variables. The system receives a selection of a first variable via a first field of the user interface, detects a selection of a second field, and identifies a relationship between the first field and the second field. The system generates a contextual menu of recommended secondary variables for use with the selected first variable based on similarity value of the links in the variable similarity graph. | 2022-03-10 |
20220076049 | IMPORTANCE ANALYSIS APPARATUS, METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM - According to one embodiment, the importance analysis apparatus includes an importance calculator and a distribution calculator. Based on a trained model and a plurality of input data samples, the importance calculator calculates an importance of each of a plurality of feature amounts of each of the input data samples. The distribution calculator calculates a distribution of the importances of each of the feature amounts across the input data samples. | 2022-03-10 |
20220076050 | WASTE COLLECTING DEVICE, BUILDING, AND METHOD - A waste collecting device includes an inlet unit, an acquisition unit configured to acquire waste information on waste thrown into the inlet unit, and a control unit configured to specify a category of the waste based on the waste information, determine whether the category of the waste matches a predetermined category, and output a determination result via an output unit. | 2022-03-10 |
20220076051 | Systems and Methods for Identifying Threats and Locations, Systems and Method for Augmenting Real-Time Displays Demonstrating the Threat Location, and Systems and Methods for Responding to Threats - Systems for identifying threat materials such as CBRNE threats and locations are provided. The systems can include a data acquisition component configured to determine the presence of a CBRNE threat; data storage media; and processing circuitry operatively coupled to the data acquisition device and the storage media. Methods for identifying a CBRNE threat are provided. The methods can include: determining the presence of a CBRNE threat using a data acquisition component; and acquiring an image while determining the presence of the CBRNE threat. Methods for augmenting a real-time display to include the location and/or type of CBRNE threat previously identified are also provided. Methods for identifying and responding to CBRNE threats are provided as well. | 2022-03-10 |
20220076052 | SIMILARITY DETERMINING METHOD AND DEVICE, NETWORK TRAINING METHOD AND DEVICE, SEARCH METHOD AND DEVICE, AND ELECTRONIC DEVICE AND STORAGE MEDIUM - A method and device of similarity determination, network training, and search, an electronic device, and a storage medium are provided. The data similarity determination method includes: acquiring first data of a first object; mapping the first sub-data as a first semantic representation in a semantic comparison space, where the semantic comparison space enables a similarity between a semantic representation obtained by mapping data of the first modality to the semantic comparison space and a semantic representation obtained by mapping data of the second modality to the semantic comparison space to be computed; acquiring second data of a second object; mapping the second sub-data as a second semantic representation in the semantic comparison space; and calculating a similarity between the first data and the second data based on at least the first semantic representation and the second semantic representation. | 2022-03-10 |
20220076053 | System and method for detecting anomalies in images - Anomalies in images are detected. A generative network and/or an autoencoder (“G/A-Network”), a Siamese network, a first training-dataset of normal images and a second training-dataset of abnormal images are provided. The G/A-network is trained to produce latent data from input images and output images from the latent data, wherein the training is performed with images of the first training-dataset, wherein a loss function is used for training at least at the beginning of training, and the loss function enhances the similarity of the input images and respective output images. The Siamese network is trained to generate similarity measures between input images and respective output images, wherein the training is performed with images of the first training-dataset and the second training-dataset in that images of both training-datasets are used as input images for the G/A-network and output images of the G/A-network are compared with their respective input images by the Siamese network. | 2022-03-10 |
20220076054 | System and Method for Player Reidentification in Broadcast Video - A system and method of re-identifying players in a broadcast video feed are provided herein. A computing system retrieves a broadcast video feed for a sporting event. The broadcast video feed includes a plurality of video frames. The computing system generates a plurality of tracks based on the plurality of video frames. Each track includes a plurality of image patches associated with at least one player. Each image patch of the plurality of image patches is a subset of the corresponding frame of the plurality of video frames. For each track, the computing system generates a gallery of image patches. A jersey number of each player is visible in each image patch of the gallery. The computing system matches, via a convolutional autoencoder, tracks across galleries. The computing system measures, via a neural network, a similarity score for each matched track and associates two tracks based on the measured similarity. | 2022-03-10 |
20220076055 | SYSTEMS, METHODS, AND COMPUTER READABLE MEDIA FOR PREDICTIVE ANALYTICS AND CHANGE DETECTION FROM REMOTELY SENSED IMAGERY - Systems and methods are provided for automatically detecting a change in a feature. For example, a system includes a memory and a processor configured to analyze a change associated with a feature over a period of time using a plurality of remotely sensed time series images. Upon execution, the system would receive a plurality of remotely sensed time series images, extract a feature from the plurality of remotely sensed time series images, generate at least two time series feature vectors based on the feature, where the at least two time series feature vectors correspond to the feature at two different times, create a neural network model configured to predict a change in the feature at a specified time, and determine, using the neural network model, the change in the feature at a specified time based on a change between the at least two time series feature vectors. | 2022-03-10 |
20220076056 | EFFICIENT DATA LAYOUTS FOR CONVOLUTIONAL NEURAL NETWORKS - Systems and methods for efficient implementation of a convolutional layer of a convolutional neural network are disclosed. In one aspect, weight values of kernels in a kernel stack of a convolutional layer can be reordered into a tile layout with tiles of runnels. Pixel values of input activation maps of the convolutional layer can be reordered into an interleaved layout comprising a plurality of clusters of input activation map pixels. The output activation maps can be determined using the clusters of the input activation map pixels and kernels tile by tile. | 2022-03-10 |
20220076057 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING SYSTEM AND INFORMATION PROCESSING METHOD - Learning data representing the relationship between explanatory variables and objective variables is acquired by an acquirer. In the learning data acquired by the acquirer, a hierarchical relationship among a plurality of items included in the objective variable is determined by a hierarchy determiner. A construction algorithm to be executed among a plurality of construction algorithms for construction of a learning model is determined by an algorithm determiner based on the hierarchical relationship determined by the hierarchy determiner. A first learning model is constructed by execution of the construction algorithm determined by the algorithm determiner by a learner. | 2022-03-10 |
20220076058 | ESTIMATION DEVICE, ESTIMATION METHOD, AND COMPUTER PROGRAM PRODUCT - According to an embodiment, an estimation device includes one or more processors configured to: generate, from first point cloud data, second point cloud data obtained by combining an attention point and observation points; estimate an attribute of the attention point by an attribute indicated by an estimation result label having a higher belonging probability among belonging probabilities output from an attribute estimation neural network; estimate reliability of the estimation result label by a reliability estimation neural network; and display, on a display device, first display information generated by performing rendering on an object including an attention point whose attribute is estimated by an attribute of the estimation result label whose reliability is higher than a first threshold, and generated by not performing rendering on an object including an attention point whose attribute is estimated by an attribute of the estimation result label whose reliability is the first threshold or less. | 2022-03-10 |
20220076059 | Multi-Stage Neural Network Process for Keypoint Detection In An Image - Embodiments include systems and methods that may be performed by a processor of a computing device. Embodiments may be applied for keypoint detection in an image. In embodiments, the processor of the computing device may apply to an image a first-stage neural network to define and output a plurality of regions, apply to each of the plurality of regions a respective second-stage neural network to output a plurality of keypoints in each of the plurality of regions, and apply to the plurality of keypoints a third-stage neural network to determine a correction for each of the plurality of keypoints to provide corrected keypoints. | 2022-03-10 |
20220076060 | INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND NON-TRANSITORY COMPUTER READABLE MEDIUM - According to one embodiment, an information processing apparatus includes: a processor configured to select a first case based on subject data including at least one feature, and acquire a first prediction value that is a value of an objective variable included in the first case; a first estimator configured to estimate frequency data indicating frequencies of observation values of the objective variable, based on a history of observation values of the objective variable; a second estimator configured to estimate first frequency data indicating frequencies of first prediction values, based on a history of first prediction values acquired before the first prediction value is acquired; and a corrector configured to correct the first prediction value acquired by the processor, based on the frequency data and the first frequency data. | 2022-03-10 |
20220076061 | METHOD AND APPARATUS FOR CREATING HIGH-FIDELITY, SYNTHETIC IMAGERY FOR ARTIFICIAL INTELLIGENCE MODEL TRAINING AND INFERENCE IN SECURITY AND SCREENING APPLICATIONS - New software systems and capabilities that facilitate the rapid development, evaluation, and deployment of advanced inspection and detection systems using high-fidelity synthetic imagery. The present invention generates high-fidelity synthetic imagery for detection systems that analyze data across the electromagnetic spectrum in an automated, random, directed, or semi-directed manner. | 2022-03-10 |
20220076062 | IMAGE PROCESSING DEVICE AND OPERATION METHOD THEREOF - The present disclosure relates to an image processing device including: a memory configured to store one or more instructions; and a processor configured to execute the one or more instructions stored in the memory to: extract one or more input patches based on an input image; extract one or more pieces of feature information respectively corresponding to the one or more input patches, based on a dictionary including mapping information indicating mappings between a plurality of patches and pieces of feature information respectively corresponding to the plurality of patches; and obtain a final image by performing a convolution operation between the extracted one or more pieces of feature information and a filter kernel. | 2022-03-10 |
20220076063 | STUDY-LEVEL MULTI-VIEW PROCESSING SYSTEM - One or more processors may identify a missing image in the set of multi-view images. Each of the images is associated with a particular view type. The one or more processors may generate, utilizing a replacement AI model, a replacement image for the missing image in the set of multi-view images. The replacement image is generated utilizing an AI model trained to generate a replacement image using training images from two or more time-adjacent sets of images. The one or more processors may identify a duplicate image in the set of multi-view images. The one or more processors may generate, utilizing a quality generative AI model, a characteristic improved image based on the duplicate image for the set of multi-view images. The one or more processors may output the replacement image and the characteristic improved image. | 2022-03-10 |
20220076064 | SYSTEM AND METHOD FOR OPTIMIZING PERFORMANCE OF AT LEAST ONE DOWNSTREAM TASK - A system for optimizing the performance of at least one downstream task includes one or more processors and a memory having one or more modules. The one or more modules cause the one or more processors to generate visual semantic segmentation data of a scene by a visual semantic segmentation model, generate labeled point cloud data of the scene by a vision model based on raw point cloud data of the scene and the visual semantic segmentation data, generate one or more clusters of the scene by a cluster generator model based on the labeled point cloud data, determine a clustering loss error between the one or more clusters generated by the cluster generator and one or more ground truth clusters and adjust, based on the clustering loss error, one or more model weights the visual semantic segmentation model and/or the vision model. | 2022-03-10 |
20220076065 | SYSTEM AND METHOD FOR RAILWAY WEEDING - A weeding system for a railway weeding vehicle including at least one camera for mounting on a railway vehicle to acquire an image of a portion of a railway track while the railway vehicle is moving. The system also includes a spraying unit to be mounted on the railway vehicle, a control unit to receive images from the camera, generate a weed species detection signal and selectively cause the spraying of a chemical agent on the basis of the weed species detection signal. The control unit executes a training-based algorithm based on a set of reference images labeled to indicate the presence or not of at least one weed species in the images. | 2022-03-10 |
20220076066 | USING GENERATIVE ADVERSARIAL NETWORKS (GANS) TO ENABLE SHARING OF SENSITIVE DATA - A method generates synthetic data by a data collection system where the synthetic data meets a first threshold for accuracy and a second threshold for protecting sensitive data from recovery from the synthetic data. The method includes collecting data including sensitive data and non-sensitive data, executing a first machine learning model to generate the synthetic data from the collected data where the synthetic data meets the first threshold, executing a second machine learning model to update the synthetic data to meet the second threshold, checking whether the updated synthetic data meets the first threshold, releasing the updated synthetic data where the first threshold is met, and re-executing the first machine learning model and second machine learning model to update the synthetic data where the first threshold is not met during the checking. | 2022-03-10 |
20220076067 | BIOLOGICAL IMAGE TRANSFORMATION USING MACHINE-LEARNING MODELS - Described are systems and methods for training a machine-learning model to generate image of biological samples, and systems and methods for generating enhanced images of biological samples. The method for training a machine-learning model to generate images of biological samples may include obtaining a plurality of training images comprising a training image of a first type, and a training image of a second type. The method may also include generating, based on the training image of the first type, a plurality of wavelet coefficients using the machine-learning model; generating, based on the plurality of wavelet coefficients, a synthetic image of the second type; comparing the synthetic image of the second type with the training image of the second type; and updating the machine-learning model based on the comparison. | 2022-03-10 |
20220076068 | METHOD FOR CONSTRUCTING A CONVOLUTION NEURAL NETWORK BASED ON FARMLAND IMAGES, ELECTRONIC DEVICE USING THE SAME - A method for constructing a convolutional neural network model based on farmland images is applied in an electronic device. The method includes following steps: obtaining a number of farmland images of at least one farmland; obtaining a plurality of standard segmentation farmland images corresponding to each of the farmland images; dividing the farmland images and the standard segmentation farmland images into a training image set and a test image set; taking the farmland images and the standard segmentation farmland images in the training image set as input of a convolutional neural network, and constructing a convolutional neural network model based on the farmland images; and verifying the convolutional neural network model by using the farmland images in the test image set and the standard segmentation farmland images, and optimizing a plurality of parameters of the convolutional neural network model based on the farmland images. | 2022-03-10 |
20220076069 | DATA AUGMENTATION - A method for generating data representing the volume of part of a body, the method comprising generating a point distribution model “PDM” based on an input dataset comprising data representing at least one surface of part of a body, the PDM defining a surface model dataset based on an average dataset and one or more weight-eigenvector pairs, generating a first surface model dataset based on the PDM by modifying at least one weight of the one or more weight-eigenvector pairs, wherein the first surface model dataset is different from the average dataset, and generating an output volume dataset based on the first surface model dataset and a first reference dataset, the first reference dataset comprising data representing the volume of a corresponding part of a body, the output volume dataset comprising data representing a deformed volume of the corresponding part of the body. | 2022-03-10 |
20220076070 | SENSOR AND METHOD FOR GENERATING TRAINING DATA FOR A MACHINE LEARNING CLASSIFIER IN A SENSOR - A sensor and a method for generating training data for a machine learning classifier in a sensor. The method includes: detecting a first sensor signal and a second sensor signal with the aid of the sensor; ascertaining whether the machine learning classifier classifies the first sensor signal as a predefined user motion pattern; ascertaining whether a classification model classifies the second sensor signal as a predefined user input for controlling a device, the user input being assigned to the user motion pattern; ascertaining a training data vector for the machine learning classifier if the second sensor signal has been classified as the predefined user input, and if the first sensor signal has not been classified as the user motion pattern, ascertaining a training data vector for the machine learning classifier, the training data vector including the first sensor signal as well as the user motion pattern. | 2022-03-10 |
20220076071 | IMAGE PROCESSING METHOD, IMAGE PROCESSING APPARATUS, LEARNING METHOD, LEARNING APPARATUS, AND STORAGE MEDIUM - A method for processing an image uses a generator which is a machine learning model. The generator converts an input low resolution image into a first feature map. From the first feature map, a first intermediate image and a second intermediate image each having resolution higher than resolution of the low resolution image are generated. Based on the first intermediate image and the second intermediate image, an estimated image having higher resolution than the resolution of the low resolution image is generated. | 2022-03-10 |
20220076072 | SYSTEM AND METHOD USING AUGMENTED REALITY FOR EFFICIENT COLLECTION OF TRAINING DATA FOR MACHINE LEARNING - One embodiment provides a system that facilitates efficient collection of training data. During operation, the system obtains, by a recording device, a first image of a physical object in a scene which is associated with a three-dimensional (3D) world coordinate frame. The system marks, on the first image, a plurality of vertices associated with the physical object, wherein a vertex has 3D coordinates based on the 3D world coordinate frame. The system obtains a plurality of second images of the physical object in the scene while changing one or more characteristics of the scene. The system projects the marked vertices on to a respective second image to indicate a two-dimensional (2D) bounding area associated with the physical object. | 2022-03-10 |
20220076073 | MEMORY INCLUDING EXAMPLES OF CALCULATING HAMMING DISTANCES FOR NEURAL NETWORK AND DATA CENTER APPLICATIONS - Examples of systems and method described herein provide for the processing of image codes (e.g., a binary embedding) at a memory die. Such images codes may generated by various endpoint computing devices, such as Internet of Things (IoT) computing devices. Such devices can generate a Hamming processing command, having an image code of the image, to compare that representation of the image to other images (e.g., in an image dataset) to identify a match or a set of neural network results. Advantageously, examples described herein may be used in neural networks to facilitate the processing of datasets, so as to increase the rate and amount of processing of such datasets. For example, comparisons of image codes can be performed on a memory die itself, like a memory die of a NAND memory device. | 2022-03-10 |
20220076074 | MULTI-SOURCE DOMAIN ADAPTATION WITH MUTUAL LEARNING - In embodiments of the present disclosure, a method, device and computer-readable medium for multi-source domain adaptation are provided. The method comprises generating a first representation of a target image through a first trained classifier, generating a second representation of the target image through a second trained classifier, and generating a third representation of the target image through a third trained classifier. A mutual learning is conducted among the first, second and third classifiers during the training. The method further comprises determining a classification label of the target image based on the first, second and third representations. The present disclosure proposes a mutual learning network for multi-source domain adaptation, which can improve the accuracy of label generation for images. | 2022-03-10 |
20220076075 | Generative Adversarial Network Medical Image Generation for Training of a Classifier - Mechanisms are provided to implement a machine learning training model. The machine learning training model trains an image generator of a generative adversarial network (GAN) to generate medical images approximating actual medical images. The machine learning training model augments a set of training medical images to include one or more generated medical images generated by the image generator of the GAN. The machine learning training model trains a machine learning model based on the augmented set of training medical images to identify anomalies in medical images. The trained machine learning model is applied to new medical image inputs to classify the medical images as having an anomaly or not. | 2022-03-10 |
20220076076 | SYSTEM FOR AUTOMATIC ERROR ESTIMATE CORRECTION FOR A MACHINE LEARNING MODEL - A computing device computes curve descriptive values to correct an error estimate of a prediction. A predefined number of times, an input dataset is split into a training dataset and a validation dataset, a predictive model and a domain model are trained, the trained predictive model and the trained domain model are validated, a predictive error value, a residual value, and a domain error value are computed, and each value is stored in output data. A domain threshold value is computed from the stored domain error values. Each predictive error value and each residual value stored in the output data is stored in in-domain output data when a respective domain error value is less than or equal to the computed domain threshold value. Curve descriptive values are computed to describe a relationship between the residual values as a function of the prediction error values stored in the in-domain output data. | 2022-03-10 |
20220076077 | QUALITY ESTIMATION MODEL TRAINED ON TRAINING SIGNALS EXHIBITING DIVERSE IMPAIRMENTS - This document relates to training and employing a quality estimation model. One example includes a method or technique that can be performed on a computing device. The method or technique can include obtaining training signals exhibiting diverse impairments introduced when the training signals are captured or diverse artifacts introduced by different processing characteristics of a plurality of data enhancement models. The method or technique can also include obtaining quality labels for the training signals, and training a quality estimation model to estimate signal quality based at least on the training signals and the quality labels. | 2022-03-10 |
20220076078 | MACHINE LEARNING CLASSIFIER USING META-DATA - Some embodiments are directed to training method a classifier. The classifier receives sensor data as input and produces a label as output. A quality estimator is applied to meta-data of a training sample, obtaining a quality estimation of a ground-truth label of the training sample. The classifier may be trained on the training sample taking into account the quality of the ground-truth label. | 2022-03-10 |
20220076079 | DISTRIBUTED MACHINE LEARNING SCORING - An embodiment of the invention may include a method, computer program product, and system for scoring AI models. An embodiment may include a first computing system that determines a result of an AI model based on input data. An embodiment may include a first computing system that sends, to a second computing system, the result of the AI model. An embodiment may include a first computing system that receives, from the second computing system, a scoring result of the AI model. | 2022-03-10 |
20220076080 | System and a Method for Assessment of Robustness and Fairness of Artificial Intelligence (AI) Based Models - A system for the assessment of robustness and fairness of AI-based ML models, comprising a data/model profiler for creating an evaluation profile in the form of data and model profiles, based on the dataset and the properties of the ML model; a test recommendation engine that receives data and model profiles from the data/model profiler and recommends the relevant tests to be performed; a test repository that contains all the tests that can be examined; a test execution environment for gathering data related to all the tests that were recommended by the test recommendation engine; a final fairness score aggregation module for aggregating the executed tests results into a final fairness score of the examined model and dataset. | 2022-03-10 |
20220076081 | MODULAR MACHINE LEARNING SYSTEMS AND METHODS - A computer system is provided that is designed to handle multi-label classification. The computer system includes multiple processing instances that are arranged in a hierarchal manner and execute differently trained classification models. The classification task of one processing instance and the executed model therein may rely on the results of classification performed by another processing instance. Each of the models may be associated with a different threshold value that is used to binarize the probability output from the classification model. | 2022-03-10 |
20220076082 | CROSS-MODAL SENSOR DATA ALIGNMENT - Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining an alignment between cross-modal sensor data. In one aspect, a method comprises: obtaining (i) an image that characterizes a visual appearance of an environment, and (ii) a point cloud comprising a collection of data points that characterizes a three-dimensional geometry of the environment; processing each of a plurality of regions of the image using a visual embedding neural network to generate a respective embedding of each of the image regions; processing each of a plurality of regions of the point cloud using a shape embedding neural network to generate a respective embedding of each of the point cloud regions; and identifying a plurality of region pairs using the embeddings of the image regions and the embeddings of the point cloud regions. | 2022-03-10 |
20220076083 | OBJECT DETECTION BASED ON OBJECT RELATION - Various embodiments described herein provide for detection of a particular object within a scene depicted by image data by using a coarse-to-fine approach/strategy based on one or more relationships of objects depicted within the scene. | 2022-03-10 |
20220076084 | RESPONDING TO MACHINE LEARNING REQUESTS FROM MULTIPLE CLIENTS - A method includes receiving, with a computing device, a first client request from a first client that identifies a machine learning model and a sensor. The method includes sending, with the computing device, a call to a server to apply the identified machine learning model to a set of data from the identified sensor, in response to the first client request. The method includes receiving, with the computing device, a second client request from a second client that identifies a same machine learning model and sensor as the first client request. The method includes sending, with the computing device, response data from the identified machine learning model to both the first client and the second client without sending an additional call to the server in response to the second client request. | 2022-03-10 |
20220076085 | IMAGE FORMING APPARATUS - An image forming apparatus can include a print head, a detector, a controller, and a power source. The print head includes one or more light emitting element rows, each light emitting element row composed of a plurality of light emitting elements. The detector detects the number of light emitting elements that emit light according to image data. The controller controls a driving voltage for driving the light emitting element based on a detection result. The power source supplies the driving voltage to the print head. | 2022-03-10 |
20220076086 | IMAGE FORMING APPARATUS AND CONTROL METHOD OF IMAGE FORMING APPARATUS - An image forming apparatus includes a fixing device having a fixing belt assembly including a heater, a fixing belt, a heater temperature sensor, and a belt temperature sensor, and a pressure roller; a drive current sensor; and a life information acquisition portion. The heater temperature sensor detects the temperature of the heater. The belt temperature sensor detects the temperature of the fixing belt. The pressure roller presses against the fixing belt. The drive current sensor detects a drive current of a drive motor that drives the pressure roller. The life information acquisition portion acquires life information of the fixing belt assembly. A controller selects a failure prediction processing mode based on the detection result of the drive current sensor and selects a driving method based on the detection results of the temperature sensors and the acquisition result of the life information acquisition portion in each mode. | 2022-03-10 |
20220076087 | IMAGE FORMING SYSTEM, IMAGE FORMING APPARATUS, AND PROGRAM - An image forming system includes: an image forming apparatus including an image former that forms an image on a recording material; a recording material supplier that supplies the recording material conveyed from a recording material storage that stores the recording material to the image former; a characteristic detector that detects a characteristic of the recording material supplied from the recording material supplier; and a hardware processor that determines, in a case where a job is interrupted, whether recording material information corresponding to a characteristic of a recording material before the interruption matches recording material information corresponding to a characteristic of a recording material after the interruption, and restarts execution of the interrupted job in a case where the recording material information corresponding to the characteristic of the recording material before the interruption matches the recording material information corresponding to the characteristic of the recording material after the interruption. | 2022-03-10 |
20220076088 | METALLIC TRANSACTION CARDS - A transaction card includes an anodized card body having a front and rear face. Various information and security features may be provided on the front face and on the rear face. A magnetic stripe may be provided on the rear face of the anodized card body. The magnetic stripe may be adhered within a slot formed within the rear face of the anodized body. Alternatively, the magnetic stripe may be provided via an overlay that is adhered to the rear face of the anodized body, and the magnetic stripe may be integral with the overlay or adhered to the overlay after the overlay is applied to the anodized card body. The transaction card may also include a hologram. The hologram may be integral with the overlay or may be applied to the overlay that has been arranged on the anodized card body. | 2022-03-10 |
20220076089 | MICROCIRCUIT CARD CUSTOMIZATION - A microcircuit card is provided with a fingerprint sensor. Customization of the microcircuit card is accomplished by the use of an exchange of data by near-field communications between the microcircuit card and a near-field communication device. A mechanical positioning system associated with the near-field communication device is configured to retain the microcircuit card such that the fingerprint sensor is accessible and near-field communication between the microcircuit card and the near-field communication device is assured. The mechanical positioning system may, in an example where the near-field communication device is a cell phone, be formed by a slot of a protective case for the cell phone. | 2022-03-10 |
20220076090 | Memory Card Identification Method and Mobile Device - A memory card identification method and a mobile device are provided. The memory card identification method includes: sending an initialization command of a first-type memory card communications protocol to a to-be-identified memory card; detecting whether there is a response in a command pin of the memory card; and identifying the memory card as a first-type memory card or a second-type memory card based on a response status of the command pin. | 2022-03-10 |