A non-transitory computer-readable storage medium storing a determination program that causes at least one computer to execute a process, the process includes obtaining a plurality of pair images of a person obtained from a overlapping region of images captured by each of a plurality of cameras; generating a directed graph including nodes corresponding to person features obtained from each of a plurality of person images included in the plurality of obtained pair images; acquiring weights of links between the nodes in the generated directed graph based on a number of person images with similar person features between the nodes; and determining a combination of the person features in which a number of the person images with the similar person features in the plurality of pair images is maximized based on the acquired weights of the links.

Examples disclosed herein may generate a refined and denoised body pose data from a video feed of a sporting event. Tracking data containing player locations may be used to determine correspondence between a location and a body pose. For example, body pose with middle of key footpoints with shortest distance from the location may be selected as a likely body pose for the location. The body pose data may be refined to estimate the length of missing limbs or limbs with unusual length ratios. The body pose data may further be filtered to filter out unwanted body poses such as body poses of spectators or noisy body poses. The refined and filtered body pose data may be used for other downstream processing such as projecting the body poses to a three dimensional play surface.

A method for training a first machine learning system for generating a graph representation of objects and their relationships in a 3D environment scene from 3D point cloud input data. For each object and each pair of objects and in the scene initial node feature vectors and initial edge feature vectors are determined from the point cloud input data and are arranged in an initial graph structure. A refined graph structure is determined by a graph neural network. From 2-dimensional image sensor data of the environment scene, feature vectors of the objects are determined by a second machine learning system and feature vectors of the object pairs are determined by a third machine learning system. Parameters of the first machine learning system are adjusted.

A method for training a first machine learning system for generating a graph representation of objects and their relationships in a 3D environment scene from 3D point cloud input data. For each object and each pair of objects and in the scene initial node feature vectors and initial edge feature vectors are determined from the point cloud input data and are arranged in an initial graph structure. A refined graph structure is determined by a graph neural network. From 2-dimensional image sensor data of the environment scene, feature vectors of the objects are determined by a second machine learning system and feature vectors of the object pairs are determined by a third machine learning system. Parameters of the first machine learning system are adjusted.

The present disclosure discloses a multi-modal brain network calculation method, apparatus, device, and storage medium. The method is configured to train a brain disease prediction model. After the brain region structural feature and the brain region functional feature are separately extracted from magnetic resonance diffusion tensor imaging data and brain functional magnetic resonance data, a graph representation diffusion learning network is used to separate the universal feature and the unique feature in the brain region structural feature and the brain region functional feature. And then, multi-modal universal and unique feature fusion is implemented based on an alignment algorithm and adaptive weighting technology. Thus, complementary information between the multi-modal data is fully mining. The model can learn an effective feature of a related disease in a training process, and a finally obtained brain region disease prediction model has higher precision and better prediction effect.

The present disclosure discloses a multi-modal brain network calculation method, apparatus, device, and storage medium. The method is configured to train a brain disease prediction model. After the brain region structural feature and the brain region functional feature are separately extracted from magnetic resonance diffusion tensor imaging data and brain functional magnetic resonance data, a graph representation diffusion learning network is used to separate the universal feature and the unique feature in the brain region structural feature and the brain region functional feature. And then, multi-modal universal and unique feature fusion is implemented based on an alignment algorithm and adaptive weighting technology. Thus, complementary information between the multi-modal data is fully mining. The model can learn an effective feature of a related disease in a training process, and a finally obtained brain region disease prediction model has higher precision and better prediction effect.

A system and method of autonomously navigating an autonomous robot is described. The described method involves creating a topological mapping of an area of environment around a location of the mobile robot; identifying at least one pathway around the location; and locally constraining a motion of the mobile robot based on the topological mapping and the identified at least pathway. The method expects inaccuracies in the localization to happen within an acceptable range and mitigates these errors by locally constraining the motion of the robot or vehicle to what is defined safe upon an analysis of data perceived through one or more robot sensors.

A system and method of autonomously navigating an autonomous robot is described. The described method involves creating a topological mapping of an area of environment around a location of the mobile robot; identifying at least one pathway around the location; and locally constraining a motion of the mobile robot based on the topological mapping and the identified at least pathway. The method expects inaccuracies in the localization to happen within an acceptable range and mitigates these errors by locally constraining the motion of the robot or vehicle to what is defined safe upon an analysis of data perceived through one or more robot sensors.

Methods and systems for automated video segmentation are disclosed. A sequence of video frames having video segments of contextually-related sub-sequences may be received. Each frame may be labeled according to segment and segment class. A video graph may be constructed in which each node corresponds to a different frame, and each edge connects a different pair of nodes, and is associated with a time between video frames and a similarity metric of the connected frames. An artificial neural network (ANN) may be trained to predict both labels for the nodes and clusters of the nodes corresponding to predicted membership among the segments, using the video graph as input to the ANN, and ground-truth clusters of ground-truth labeled nodes. The ANN may be further trained to predict segment classes of the predicted clusters, using the segment classes as ground truths. The trained ANN may be configured for application runtime video sequences.

Methods and systems for automated video segmentation are disclosed. A sequence of video frames having video segments of contextually-related sub-sequences may be received. Each frame may be labeled according to segment and segment class. A video graph may be constructed in which each node corresponds to a different frame, and each edge connects a different pair of nodes, and is associated with a time between video frames and a similarity metric of the connected frames. An artificial neural network (ANN) may be trained to predict both labels for the nodes and clusters of the nodes corresponding to predicted membership among the segments, using the video graph as input to the ANN, and ground-truth clusters of ground-truth labeled nodes. The ANN may be further trained to predict segment classes of the predicted clusters, using the segment classes as ground truths. The trained ANN may be configured for application runtime video sequences.