Systems, methods, and non-transitory media are provided for providing spatiotemporal recycling networks (e.g., for video segmentation). For example, a method can include obtaining video data including a current frame and one or more reference frames. The method can include determining, based on a comparison of the current frame and the one or more reference frames, a difference between the current frame and the one or more reference frames. Based on the difference being below a threshold, the method can include performing semantic segmentation of the current frame using a first neural network. The semantic segmentation can be performed based on higher-spatial resolution features extracted from the current frame by the first neural network and lower-resolution features extracted from the one or more reference frames by a second neural network. The first neural network has a smaller structure and/or a lower processing cost than the second neural network.

Example implementations include a method, apparatus and computer-readable medium for controlling a camera, comprising receiving a video sequence of a scene. The method includes determining one or more scene description metadata in the scene from the video sequence. The method includes identifying one or more scene object types in the scene based on the one or more scene description metadata. The method includes determining one or more rules based on one or both of the scene description metadata or the scene object types, each rule configured to generate an event based on a detected object following a rule-specific pattern of behavior. The method includes applying the one or more rules to operation of the camera.

A system and a method of tracking an input sign for an extended reality are provided, wherein the method including: obtaining an image; detecting for a handheld device and a hand in the image; in response to a first bounding box of the hand and a second bounding box of the handheld device being detected, detecting at least one joint of the hand from the image; performing a data fusion of the first bounding box and the second bounding box according to the at least one joint to obtain the input sign; and outputting a command corresponding to the input sign via the output device.

Methods, systems, and apparatus for receiving a request for a risk assessment for a parcel, receiving a set of images for the parcel, the set of images including two or more images, each image having an image scale and an image resolution that is different from other images in the set of images, providing a first-level feature embedding and a second-level feature embedding, the first-level feature embedding being provided by processing a first-level image through a first-level machine learning (ML) model, and the second-level feature embedding being provided by processing a second-level image through a second-level ML model, determining a risk assessment at least partially by processing each of the first-level feature embedding and a second-level feature embedding through a fusion network, and providing a representation of the risk assessment for display.

An image processing apparatus includes a generation unit that generates feature data based on an image, classification units that classify a predetermined pattern by referring to the feature data, and a control unit that controls operations of the classification units. The classification units include a first classification unit and a second classification unit, processing results of which do not depend on each other, and a third classification unit. The first and the second classification units are operated in parallel. When either of the first and the second classification units determines that a classification condition is not satisfied, the control unit stops operations of all of the classification units. When both the first and the second classification units determine the classification condition is satisfied, the control unit operates the third classification unit by using classification results of the first and the second classification units.

An image analysis apparatus including a processor configured to: acquire a first fluorescence image indicating an observation target including a plurality of types of cells, each of which has a first region stained by first staining, and a second fluorescence image indicating the observation target in which a second region of a specific cell among the plurality of types of cells is stained by second staining different from the first staining; determine whether or not the first region is included in the second region in a superimposed image obtained by superimposing the first fluorescence image and the second fluorescence image and acquire a first determination result for each of the first regions; and determine the type of cell included in the observation target on the basis of the first determination result.

A computer implemented method is proposed for classifying one or more embossed and/or engraved markings on a sidewall of a tyre into one or more classes comprising digital image data of the sidewall of the tyre. The method comprises generating a first image channel from a first portion of the digital image data relating to a corresponding first portion of the sidewall of the tyre. Generating the first image channel comprises performing histogram equalisation on the first portion of the digital image data to generate the first image channel. The method further comprises generating a first feature map using the first image channel and applying a first classifier to the first feature map to classify said embossed and/or engraved markings into one or more first classes.

This disclosure provides a moving object tracking method and apparatus. The method includes: obtaining a current frame captured by a camera; predicting a current state vector of the camera based on an inertial measurement unit IMU and the current frame, to obtain a predicted value of the current state vector of the camera; predicting a current state vector of a target object that is moving in the current frame, to obtain a predicted value of the current state vector of the target object; and updating a Kalman state vector based on a measurement result of an image feature in the current frame. According to technical solutions provided in this disclosure, a target object that is moving in a surrounding environment can be tracked and a pose of the target object can be estimated while a pose of a system can be estimated.

This application provides a semantic segmentation network structure generation method performed by an electronic device, and a non-transitory computer-readable storage medium. The method includes: generating a corresponding architectural parameter for cells that form a super cell in a semantic segmentation network structure; optimizing the semantic segmentation network structure based on image samples, and removing a redundant cell from a super cell to which a target cell pertains, to obtain an improved semantic segmentation network structure; performing, by an aggregation cell in the improved semantic segmentation network structure, feature fusion on an output of the super cell; performing recognition processing on a fused feature map, to determine positions corresponding to objects that are in the image samples; and training the improved semantic segmentation network structure based on the positions corresponding to the objects that are in the image samples and annotations corresponding to the image samples, to obtain a trained semantic segmentation network structure.

Embodiments of this application disclose a video classification method performed by a computer device and belong to the field of computer vision (CV) technologies. The method includes: obtaining a video; selecting n image frames from the video; extracting respective feature information of the n image frames according to a learned feature fusion policy by using a feature extraction network, the learned feature fusion policy being used for indicating proportions of the feature information of the other image frames that have been fused with feature information of a first image frame in the n image frames; and determining a classification result of the video according to the respective feature information of the n image frames. By replacing complex and repeated 3D convolution operations with simple feature information fusion between adjacent image frames, time for finally obtaining a classification result of the video is therefore reduced, thereby having high efficiency.