Abstract: To present a region which is not fully monitored, provided is a monitoring device comprising a detection means, an estimation means, a determination means, and a presentation means. The detection means detects a person from an image. The estimation means estimates a region which is being viewed by the person who is detected by the detection means. On the basis of the region estimated by the estimation means, the determination means determines a region which requires special attention within a monitoring area. The presentation means presents information indicating the region which requires special attention determined by the determination means.

Abstract: To present a region which is not fully monitored, provided is a monitoring device comprising a detection means, an estimation means, a determination means, and a presentation means. The detection means detects a person from an image. The estimation means estimates a region which is being viewed by the person who is detected by the detection means. On the basis of the region estimated by the estimation means, the determination means determines a region which requires special attention within a monitoring area. The presentation means presents information indicating the region which requires special attention determined by the determination means.

Abstract: A computing apparatus to classify anomalies in images, by unsupervised anomaly detection on an input dataset of the images to detect anomaly portions from said images to generate, for an image in the dataset, a corresponding mask image transmitting a detected anomaly portion in the image and blocking anomaly-free portions; train a classifier ANN, including, in a first epoch process processing a masked version of the input dataset with the classifier ANN, the masked version including the image of the input dataset masked by the corresponding mask image, and training the classifier ANN to classify anomaly portions into one of plural classes by minimising a cross entropy loss function using generated labels as ground truths; extracting, from the classifier ANN, a latent feature representation of the image of the masked version in the input dataset; and in a second epoch process generating a set of pseudo labels corresponding to the masked version of the input dataset by applying an unsupervised clustering algori

Abstract: Embodiments include receiving image data comprising contours of teeth of an individual and generating a new image based on the image data and one or more parametric functions associated with tooth color that comprise a first variable for a first image axis and a second variable for a second image axis, wherein a shape of the teeth in the new image is based on the image data and a color of the teeth in the new image is based on applying the one or more parametric functions to at least a portion of the image data.

Abstract: A real-time measurement system for mechanical parameters of rock slag during excavation includes a rock slag conveyor belt configured to convey rock slag; cleaning device, located on both sides of the rock slag conveyor belt, configured to clean the rock slag; an image acquisition device, located behind the cleaning device and on both sides and above the rock slag conveyor belt, configured to collect images of rock slag; an on-site loading device, for conducting on-site mechanical loading procedure on the rock slag to obtain on-site mechanical parameters. The on-site loading device includes a loading bottom plate, a push plate and a pressure head. The loading bottom plate is provided with a loading area. The push plate is located on the loading bottom plate and pushed by a pushing mechanism to push the rock slag.

Abstract: The present disclosure involves systems, software, and computer implemented methods for automatically identifying table locations and table cell types of located tables. One example method includes receiving a request to detect tables. Features are extracted from an input spreadsheet and provided to a trained table detection model trained to predict whether worksheet cells are table cells or background cells and to a cell classification model that is trained to classify worksheet cells by cell structure type. The table detection model generates binary classifications that indicate whether cells are table cells or background cells. A contour detection process is performed on the binary classifications to generate table location information that describes at least one table boundary in the spreadsheet. The trained cell classification model generates a cell structure type classification for each cell that is included in a table boundary generated by the contour detection process.

Abstract: A method of compressing image data comprising a set of image values each representing a position in image-value space so as to define an occupied region thereof. The method comprises selectively applying a series of compression transforms to subsets of the image data items to generate a transformed set of image data items occupying a compacted region of value space. The method further comprises identifying a set of one or more reference data items that quantizes the compacted region in value space. For each image data item in the set of image data items, a sequence of decompression transforms from a fixed set of decompression transforms is identified that generates an approximation of that image data item when applied to a selected one of the one or more reference data items. Each image data item in the set of image data items is encoded as a representation of the identified sequence of decompression transforms for that image data item.

Abstract: In various examples, sensor data—such as masked sensor data—may be used as input to a machine learning model to determine a confidence for object to person associations. The masked sensor data may focus the machine learning model on particular regions of the image that correspond to persons, objects, or some combination thereof. In some embodiments, coordinates corresponding to persons, objects, or combinations thereof, in addition to area ratios between various regions of the image corresponding to the persons, objects, or combinations thereof, may be used to further aid the machine learning model in focusing on important regions of the image for determining the object to person associations.

Abstract: Systems, methods, and computer-readable storage media for digital fingerprinting of media content. The system does this by normalizing and pre-processing the media content into a standard format, then generating fingerprints for image, audio, and/or video aspects of the media. These fingerprints are mathematical vectors generated using one or more techniques, such as perceptual hashes coupled with machine learning. Once the fingerprints for new content is generated, the system can compare those fingerprints to fingerprints of known content to determine if the new content contains prohibited content.

Abstract: A deep neural network(s) (DNN) may be used to detect objects from sensor data of a three dimensional (3D) environment. For example, a multi-view perception DNN may include multiple constituent DNNs or stages chained together that sequentially process different views of the 3D environment. An example DNN may include a first stage that performs class segmentation in a first view (e.g., perspective view) and a second stage that performs class segmentation and/or regresses instance geometry in a second view (e.g., top-down). The DNN outputs may be processed to generate 2D and/or 3D bounding boxes and class labels for detected objects in the 3D environment. As such, the techniques described herein may be used to detect and classify animate objects and/or parts of an environment, and these detections and classifications may be provided to an autonomous vehicle drive stack to enable safe planning and control of the autonomous vehicle.

Abstract: Techniques for determining unified futures of objects in an environment are discussed herein. Techniques may include determining a first feature associated with an object in an environment and a second feature associated with the environment and based on a position of the object in the environment, updating a graph neural network (GNN) to encode the first feature and second feature into a graph node representing the object and encode relative positions of additional objects in the environment into one or more edges attached to the node. The GNN may be decoded to determine a distribution of predicted positions for the object in the future. A predicted position of the object at a subsequent timestep may be determined by sampling from the distribution of predicted positions according to various sampling strategies. Alternatively, the predicted position of the object may be overwritten using a candidate position of the object.

Abstract: A system and method for determining car to lane distance is provided. In one aspect, the system includes a camera configured to generate an image, a processor, and a computer-readable memory. The processor is configured to receive the image from the camera, generate a wheel segmentation map representative of one or more wheels detected in the image, and generate a lane segmentation map representative of one or more lanes detected in the image. For at least one of the wheels in the wheel segmentation map, the processor is also configured to determine a distance between the wheel and at least one nearby lane in the lane segmentation map. The processor is further configured to determine a distance between a vehicle in the image and the lane based on the distance between the wheel and the lane.

Abstract: A surveillance information generation apparatus (2000) includes a first surveillance image acquisition unit (2020), a second surveillance image acquisition unit (2040), and a generation unit (2060). The first surveillance image acquisition unit (2020) acquires a first surveillance image (12) generated by a fixed camera (10). The second surveillance image acquisition unit (2040) acquires a second surveillance image (22) generated by a moving camera (20). The generation unit (2060) generates surveillance information (30) relating to object surveillance, using the first surveillance image (12) and first surveillance information (14).

Abstract: A method for performing detection-based object searches includes receiving a user request indicating a region of interest, a timeframe of interest, or an object of interest. A signal is sent to cause execution of a query to identify object detections based on the user request. A signal representing at least one event identified in response to the query is received. For each event from the at least one event, a thumbnail image is identified based on the user request and using a ranking algorithm. A video frame identified based on the thumbnail image is received, and a video segment associated with the video frame is retrieved, A preview image clip that includes the video frame and the video segment is generated and displayed to a user associated with the user request.

Abstract: Computer vision systems and methods for object detection with reinforcement learning are provided. The system includes a reinforcement learning agent configured to detect an object pertaining to a target object class and a plurality of objects pertaining to different target object classes, such that the reinforcement learning agent determines a bounding box for each of the detected of objects. The system first sets parameters of the reinforcement learning agent. The system then detects an object and/or objects in an image based on the set parameters. Finally, the system determines a bounding box and/or bounding boxes for each of the detected objects.

Abstract: A method of block-wise neural image compression with post filtering is performed by at least one processor of an encoder and includes encoding a block of an input image, using a first neural network, wherein the encoded block is decoded by a decoder using a second neural network to generate a reconstructed block, and performing intra-prediction on the reconstructed block, using a third neural network, to generate a predicted block. The method further includes determining a difference between the block of the input image and the generated predicted block, to generate a prediction residual, encoding the generated prediction residual, using a fourth neural network, wherein the encoded prediction residual is decoded by the decoder using a fifth neural network, and adding the decoded prediction residual to the generated predicted block, to generate a recovered predicted block.

Abstract: An information processing device of the present invention includes a detection means that detects the content of an image, a determination means that determines a processing mode for the image based on the result of detection of the content of the image, and an execution means that executes processing for a captured image corresponding to the processing mode.

Abstract: Systems, devices, and methods are provided to provide serial monitoring for a patient. An ultrasound system is provided which may include subdividing a portion of the anatomy of a patient into a number of zones. Imaging data may be received by an imaging device. This imaging data may be used to generate a severity score for each zone based on imaging parameters within the imaging data. Changes in the severity score for each zone may be displayed over time, such that a medical professional may monitor each zone in a serial manner.

Abstract: A method performed by a computing system includes receiving, by a document data extraction system (DDES), image data associated with a document. The DDES extracts, via optical character recognition (OCR) logic of the DDES, metadata from the image data. The metadata specifies sequences of text content items and text content item features associated with each text content item of the sequences of text content items. A machine learning logic (MLL) module of the DDES determines, based on the sequences of text content items and the text content item features, one or more text content items associated with a key. The DDES communicates information that specifies the key and a corresponding value that is associated with the one or more text content items that are associated with the key to a terminal.

Abstract: The operation sequence identification device identifies an operation sequence including a series of individual operations. The operation sequence identification device includes an communication circuit that acquires first sensing information indicating the position of a moving object in an operation area in chronological order and plural pieces of second sensing information indicating surrounding environment states at different positions in the operation area in chronological order, and a control circuit that specifies the order of the series of individual operations based on the first sensing information and that identifies the operation content of each of the series of individual operations based on the second sensing information.