Abstract: The present disclosure relates to a target tracking method and apparatus, a device, and a medium. The method includes: acquiring a target video frame; determining, based on the target video frame, position information of a target area in the target video frame; in a case that a determination of the position information of the target area in the target video frame is failed, determining target photographing position information, and determining again, according to the target photographing position information and a camera projection algorithm, the position information of the target area in the target video frame.

Abstract: A method for estimating at least a length of a vessel comprises monitoring of a scene by a camera, wherein the camera provides a first plurality of two-dimensional images of the scene At least one reference object is detected in at least one two-dimensional image of the first plurality of two-dimensional images and a pixel position and at least a pixel width of each of the reference objects are determined. Further, at least a width scaling model is created. Further, the camera provides a second plurality of two-dimensional images of the scene and at least one vessel is detected in at least one two-dimensional image of the second plurality of two-dimensional images. A pixel position and at least a pixel width of the vessel are determined in the respective two-dimensional image and a vessel length estimation for the vessel is derived from the width scaling model.

Abstract: Systems and methods for automated eye tracking assessment for skill development. In some examples, a system includes an eye tracking device; a third-person tracking system comprising at least one external camera; and a computer system comprising one or more processors. The computer system is configured for receiving, while a user is performing a task, eye gaze data from the eye tracking device, a user-view video from the user-view camera or screen capture technology, and, in some examples, an external video of the user from the external camera. The computer system is configured for determining whether or not the user's gaze is fixated on or tracking a specific location or object in a performance space for a threshold amount of time prior to the onset of a movement or a performance action. The computer system is configured for determining a task performance outcome.

Abstract: A video analysis system is a system in which a video is analyzed through an edge device installed in each site to generate a security event, and when the edge device continuously generates erroneous security events, the video is analyzed through another edge device or a cloud server in parallel, and then a deep learning model enabling the edge device not to generate an erroneous security event is found to change the edge device, thereby maintaining high video analysis quality.

Abstract: Systems, tools and methods to allow for control and management of a free flowing parking facility. Accurate recognition of vehicles may be achieved by identifying a target time and location for capturing an image of the vehicle based on a predicted path of the vehicle. The predicted path may be calculated based on sensor readings that detect the presence of a vehicle as well as the speed at which it is traveling.

Abstract: A method, and a system for training super-resolution deep neural network to classify coastal area in Remote Sensing (RS) image includes retrieving RS image having first resolution. Further, the method includes processing RS image through multi-block residual attention based Very Deep Super Resolution (VDSR) network to obtain residual image. The method includes generating high-resolution output image by adding residual image to RS image. Further, the method includes generating color feature map using high-resolution output image. The method includes generating resultant feature map by processing high-resolution output image through multimodal inception attention network (M2IAN) including plurality of inception attention processes. Further, the method includes combining the color feature map and resultant feature map. The method further includes learning to classify composite feature image into plurality of coastal area categories.

Abstract: An optically variable surface pattern which is designed to provide a multi-color representation when viewed from at least one predefined viewing angle and includes a multiplicity of surface elements which are provided with relief structures, at least one of the relief structures having nanostructures that act as color filters. The relief structures are selected from a set of at least four relief structures that differ from one another, each of which generating a color impression corresponding to a predefined monochromatic color when viewed from the predefined viewing angle, and each of the monochromatic colors corresponding to a different basic color. The surface elements are dimensioned such that, in at least one subregion of the surface pattern, when viewed from the at least one predefined viewing angle, a color impression corresponding to a mixed color that differs from the predefined basic colors can be generated.

Abstract: A first Vision-Language Model (VLM) in a first branch identifies a first set of fields in input data using a visualized first set of bounding boxes (BB). The first VLM labels and outputs a labeled first set of fields. A first agentic AI in the first branch localizes and outputs an identified field as a desired type of field using a visualized identified BB. A second VLM in a second branch identifies a second set of fields in the input data using a visualized second set of BBs. An MLLM uses the input data with the second set of BBs to output a set of recognizing field from the second set of BBs. A second agentic AI in the second branch and labels a target field. A training data set is formed by combining the input data, labeled identified field, and the labeled target field.

Abstract: Various embodiments of the present technology relate to solutions for gas leak detection in natural gas extraction and storage environments. In some examples, a machine learning interface generates feature vectors based on video data that depicts a natural gas storage facility and feeds the feature vectors to a machine learning engine. The machine learning engine ingests the feature vectors and generates a machine learning output that indicates the presence of the gas leak in the natural gas storage facility. The machine learning interface receives the machine learning output that indicates the presence of a gas leak in the natural gas storage facility. The machine learning interface generates and transfers an alert based on the machine learning output.

Abstract: The present disclosure provides an image processing method and apparatus, and an electronic device and a storage medium. The image processing method includes: inputting an initial depth map, a first confidence level of the initial depth map, an initial normal vector map and a second confidence level of the initial normal vector map into an optimizer; performing joint optimization on a depth map and a normal vector map, with an objective of minimizing a difference between an optimized depth map and the depth map before being optimized and a difference between an optimized normal vector map and the normal vector map before being optimized, and an objective of minimizing an error between local planes determined on the basis of a same region in the optimized depth map and the optimized normal vector map; and outputting the optimized depth map and the optimized normal vector map.

Abstract: The disclosure provides a method, device and storage medium for back-end optimization of simultaneous localization and mapping. In the method, a target three-dimensional space point is determined in three-dimensional space points of a plurality of key frames located by a simultaneous localization and mapping system. In addition, a reprojection error is determined based on the target three-dimensional space point, and a weight is provided for the reprojection error by preprocessing the maximum parallax corresponding to the target three-dimensional space point, to obtain the relative reprojection error.

Abstract: A computer-implemented method of tracking objects in a video sequence of a scene comprises determining a location of a sink in the scene where objects exit the scene and a location of a source where objects enter the scene; tracking a first object moving in the scene using a re-identification algorithm, wherein the first object is associated with a re-identification threshold of the re-identification algorithm; detecting that the first object has exited the scene at the sink; and responsive to detecting that the first object has exited the scene at the sink, adjusting the re-identification threshold associated with the first object such that a probability that the re-identification algorithm re-identifies a second object, entering the scene at the source after the first object has exited the scene at the sink, as the first object is reduced.

Abstract: A two-stage learning framework provides image-based complementary item recommendations. After receiving an image of a real-world scene depicting at least one object, the first stage generates feature embeddings for the real-world scene and the at least one object. The second stage generates a predicted feature embedding for at least one predicted object from the feature embeddings obtained from the first stage, generates a category embedding for the at least one predicted object from the predicted feature embedding, generates a recommended feature embedding for at least one recommended object from the predicted feature embedding and the category embedding, and outputs an identifier of the at least one recommended object, wherein the at least one recommended object is complementary to the at least one object.

Abstract: Systems and methods for improved volumetric additive manufacturing (VAM) are described herein. In some aspects of the present disclosure, approaches to VAM image-computation are provided that algebraically optimizes directly on the structure to be printed, instead of on the set of external projection images. These approaches provide multiple advantages including improved reconstruction fidelity, simplicity, flexibility, and robust convergence to a desirable reconstruction, regardless of initial image-set guess.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: Techniques are described for improving computer-assisted surgical (CAS) systems, particularly, to recognize surgical phases in a video of a surgical procedure. A CAS system includes cameras that provide video stream of a surgical procedure. According to one or more aspects the surgical phases are automatically detected in the video stream using a machine learning model. Particularly, the machine learning model includes a boundary aware cascade stage network to perform surgical phase recognition.

Abstract: License plate recognition (“LPR”) systems may encounter degradation in quality and obstructions that negatively impact performance of the LPR systems. A LPR system is configured to apply image processing algorithms to output information describing performance of the system and to monitor the performance of the system over time. Based on the performance of the system over time, the LPR system determines when one or more entities of the system require action to maintain or improve performance and transmits information describing the required action.

Abstract: 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.