Abstract: A method and related system operations include obtaining a video stream with an image sensor of a camera device, detecting a plurality of target objects by executing a neural network model based on the video stream with a vision processor unit of the camera device. The method also includes generating a plurality of bounding boxes, determining a plurality of character sequences by, for each respective bounding box of the plurality of bounding boxes, performing a set of optical character recognition (OCR) operations to determine a respective character sequence of the plurality of character sequences. The method also includes updating a plurality of tracklets to indicate the plurality of bounding boxes and storing the plurality of tracklets in association with the plurality of character sequences in a memory of the camera device.

Abstract: An automatic bio-specimen inspection system includes an inspection device, an image processing module, a spatial learning module, a path generation module and a motion device. The inspection device is used to approach an inspection site for performing a bio-specimens collection and/or inspection. The image processing module is used to capture and process a plurality of 2D images of the inspection site. The spatial learning module is used to generate a 3D spatial information of the inspection site according to the 2D images. The path generation module is used to generate an inspection path information based on the 3D spatial information. The motion device is used to move the inspection device to the inspection site according to the inspection path information for performing the inspection operation.

Abstract: The method includes receiving data representing a first frame of video content including a plurality of frames and determining, for at least one object in a first frame, an object type and position in the first frame. The method further includes determining a number of frames N to skip over based on the type and position of the object in the first frame and the type and position of one or more objects in one or more prior frames, and for providing the N+1 frame, and not the skipped-over frames.

Abstract: Automatic license plate recognition occurs when a light sensor that continually captures video detects motion as a vehicle is driven through a gate. The light sensor detects the vehicle and license plate in the video stream captured by the light sensor. An algorithm associated with the video stream of the light sensor is trained to detect license plates. The light sensor starts executing the recognition algorithm when it detects motion. Recognition of characters in the license plate is based upon an aggregation of several captured video frames in which a license plate is detected.

Abstract: A method for generating training data for a recognition model for recognizing objects in sensor data of a sensor. Objects and object attributes are recognized in auxiliary sensor data of an auxiliary sensor mapping at least one overlapping area using a trained auxiliary recognition model, and the object attributes of the objects recognized in the overlapping area being transferred to the sensor data mapping at least the overlapping area in order to generate training data.

Abstract: To improve accuracy of search, a learner (L) of a search system calculates a feature quantity of information that is input and outputs a first analysis result of the information in a first viewpoint and a second analysis result of the information in a second viewpoint based on the feature quantity. Storing means stores a feature quantity of information to be searched, which has been input in the learner (L), in a database. Input means inputs input information in the learner (L). Search means searches for information to be searched that is similar to the input information in the feature quantity based on the database.

Abstract: Method and computing device using a neural network to determine whether or not to process images of an image flow. A predictive model of the neural network is generated and stored at a computing device. The computing device receives (b) an image of the image flow and executes (c) the neural network, using the predictive model for generating an indication of whether or not to process the image based on input(s) of the neural network, the input(s) comprising the image. The computing device determines (d) whether or not to process the image by an image processing module, based on the indication of whether or not to process the image. The image is processed by the image processing module if the determination is positive and not processed if the determination is negative. Steps (b), (c), (d) are repeated for consecutive images of the image flow.

Abstract: Methods and apparatus for computer-aided prostate condition diagnosis are disclosed. An example computer-aided prostate condition diagnosis apparatus includes memory to store instructions and a processor. The example processor can detect a lesion from an image of a prostate gland and generate a mapping of the lesion from the image to a sector map, the generating the mapping of the lesion comprising identifying a depth region of the lesion, wherein the depth region indicates a location of the lesion along a depth axis. The processor can also provide the sector map comprising a representation of the lesion within the prostate gland mapped from the image to the sector map.

Abstract: Aspects of the disclosure relate to using machine learning for foreground mask estimation. A computing platform may receive a set of images and corresponding ground truth foreground masks. Using the set of images and the corresponding ground truth foreground masks, the computing platform may train the first neural network to distinguish between image foregrounds and backgrounds, which may result in a first set of foreground masks. For each image and based on a corresponding foreground mask, the computing platform may estimate a first background clean plate. Using the set of images, the first background clean plates, and a set of corresponding ground truth mask images, the computing platform may train a second neural network, which may configure the second neural network to output foreground masks based on video input information. The computing platform may deploy, to an implementation computing device, the second neural network.

Abstract: An example method for training a neural network includes generating a training data set of point clouds. The training data set includes pairs of closed surfaces point clouds and non-closed surfaces point clouds. The method further includes, for each of the closed surface point clouds and the non-closed surface point clouds, generating a two-dimensional (2D) image by rendering a three-dimensional scene. The 2D image for the non-closed surfaces point clouds includes a gap in a surface, and the 2D image for the closed surfaces point clouds are free of gaps. The method further includes training the neural network to generate a trained neural network. The method further includes filling, using the trained neural network, gaps between scan points of the 2D image, and de-noising, using the trained neural network, scan point cloud data to generate a closed surface image of the scan point cloud data.

Abstract: A method may include: receiving a first image captured by a camera at a first time instance, wherein the first image includes at least a portion of an observed vehicle; determining a first ray angle based on a coordinate system of an ego-vehicle and a coordinate system of the observed vehicle corresponding to the first image; receiving a second image captured by the camera at a second time instance, wherein the second image includes at least a portion of the observed vehicle oriented at a different viewpoint; determining a second ray angle based on a coordinate system of the ego-vehicle and the coordinate system of the observed vehicle corresponding to the second image; determining a local angle difference based on the first ray angle and the second ray angle; and training a deep neural network using the local angle difference, the first image, and the second image.

Abstract: A computer-implemented method for classification of data by a machine learning system using a logic constraint for reducing a data labeling requirement. The computer-implemented method includes: generating a first embedding space from a first partially labeled training data set, wherein in the first embedding space, content-wise related training data of the first partially labeled training data are clustered together, determining at least two clusters in the first embedding space formed from the first partially labeled training data, and training a machine learning model based, at least in part, on a second partially labeled training data set and the at least two clusters, wherein the at least two clusters are used as training constraints.

Abstract: There is provided a computed implemented method of automatically generating an adapted presentation of at least one candidate anomalous object detected from anatomical imaging data of a target individual, comprising: providing anatomical imaging data of the target individual acquired by an anatomical imaging device, analyzing the anatomical imaging data by a detection classifier for detecting at least one candidate anomalous object of the anatomical imaging data and computed associated location thereof, computing, by a presentation parameter classifier, at least one presentation parameter for adapting a presentation of a sub-set of the anatomical imaging data including the at least one candidate anomalous object according to at least the location of the candidate anomalous object, and generating according to the at least one presentation parameter, an adapted presentation of the sub-set of the anatomical imaging data including the at least one candidate anomalous object.

Abstract: A mobile device that includes a camera and an extended reality software application program is employed by a user in an operating environment, such as an industrial environment. One or more objects within a geofence may be identified. A device crosses within the geofence and acquires sensor data associated with an object within the geofence. The sensor data may include image data and/or audio data. The device or a server system may then determine an object identifier associated with the object based on a comparison of the sensor data with data associated with object identifiers corresponding to objects within the geofence. Based on the object identifier, data associated with the object are obtained. The data associated with the object may be presented via the device, such as an extended reality overlay over a view of the object in the device.

Abstract: A method and apparatus for promoting a motion, an electronic device and a storage medium, relating to the field of image recognition technology are provided. An embodiment of the method may include: acquiring a user motion image, and acquiring three-dimensional recognition coordinates of body key points recognized in the user motion image; determining, based on the three-dimensional recognition coordinates, a user motion matching the user motion image; screening, according to a mapping relationship between user motion and body key points, a target body key point among all of the recognized body key points; acquiring three-dimensional standard coordinates of the target body key point corresponding to the user motion; and prompting a motion based on values of differences between the three-dimensional standard coordinates of the target body key point and the three-dimensional recognition coordinates of the target body key point.

Abstract: A computing system automatically extracting, from a digital video frame, scoreboard information including a first team name, a second team name, a first score, and a second score. The computing system (a) detects, within the digital video frame, a plurality of frame regions based on each detected frame region depicting text; (b) selects, from the detected frame regions, a set of frame regions based on the frame regions of the selected set cooperatively having a geometric arrangement that corresponds with a candidate geometric arrangement of the scoreboard information; (c) recognizes characters respectively within each of the frame regions of the selected set of frame regions; (d) based at least on the recognized characters in the frame regions of the selected set, detects the scoreboard information; and (e) records the detected scoreboard information.

Abstract: Methods and systems are disclosed for improvements in aquaculture that allow for increasing the number and harvesting efficiency of fish in an aquaculture setting by identifying and predicting internal conditions of the juvenile fish based on external characteristics that are imaged through non-invasive means.

Abstract: Methods and systems are provided for transforming sketches into stylized electronic paintings. A neural network system is trained where the training includes training a first neural network that converts input sketches into output images and training a second neural network that converts images into output paintings. Similarity for the first neural network is evaluated between the output image and a reference image and similarity for the second neural network is evaluated between the output painting, the output image, and a reference painting. The neural network system is modified based on the evaluated similarity. The trained neural network is used to generate an output painting from an input sketch where the output painting maintains features from the input sketch utilizing an extrapolated intermediate image and reflects a designated style from the reference painting.

Abstract: The present disclosure provides a material identification method and a device based on laser speckle and modal fusion, an electronic device and a non-transitory computer readable storage medium. The method includes: performing data acquisition on an object by using a structured light camera to obtain a color modal image, a depth modal image and an infrared modal image; preprocessing the color modal image, the depth modal image and the infrared modal image; and inputting the color modal image, the depth modal image and the infrared modal image preprocessed into a preset depth neural network for training, to learn a material characteristic from a speckle structure and a coupling relation between color modal and depth modal, to generate a material classification model for classifying materials, and to generate a material prediction result in testing by the material classification model of the object.

Abstract: Disclosed herein is a color restoration method and apparatus. The color restoration method may include pre-processing an input image, determining whether color is distorted, and restoring the color of the input image in an RGB scale or a grayscale according to whether the color is distorted. According to the present disclosure, color of a low light image may be restored using a deep neural network model trained through deep learning of a 5G network and color restoration.