Provided is a method for detecting a violent incident in a video based on a hypergraph transition model, comprising a procedure of extracting a foreground target track, a procedure of establishing a hypergraph and a similarity measure, and a procedure of constructing a hypergraph transition descriptor; using the hypergraph to describe a spatial relationship of feature points, in order to reflect attitude information about a movement; and modelling the transition of correlative hypergraphs in a time sequence and extracting a feature descriptor HVC, wherein same can effectively reflect the intensity and stability of the movement. The method firstly analyses the spatial relationship of the feature points and a transition condition of a feature point group, and then performs conjoint analysis on same. The method of the present invention is sensitive to disorderly and irregular behaviours in a video, wherein same is applicable to the detection of violent incidents.

A method and system of graph feature extraction and graph classification based on adjacency matrix is provided. The invention first concentrates the connection information elements in the adjacency matrix into a specific diagonal region of the adjacency matrix which reduces the non-connection information elements in advance. Then the subgraph structure of the graph is further extracted along the diagonal direction using the filter matrix. Further, it uses a stacked convolutional neural network to extract a larger subgraph structure. On one hand, it greatly reduces the amount of computation and complexity, getting rid of the limitations caused by computational complexity and window size. On the other hand, it can capture large subgraph structure through a small window, as well as deep features from the implicit correlation structures at both vertex and edge level, which improves speed and accuracy of graph classification.

A relative atlas may be used to lay out elements in a digital map used in the control of an autonomous vehicle. A vehicle pose for the autonomous vehicle within a geographical area may be determined, and the relative atlas may be accessed to identify elements in the geographical area and to determine relative poses between those elements. The elements may then be laid out within the digital map using the determined relative poses, e.g., for use in planning vehicle trajectories, for estimating the states of traffic controls, or for tracking and/or identifying dynamic objects, among other purposes.

Described is a system for extracting multi-scale hierarchical clustering on customer observables (COs) data in a vehicle. The system selects a parameter for a set of incident data of COs data. Simplicial complexes are generated from the COs data based on the selected parameter. Face networks are generated from the simplicial complexes. For each face network, a set of connected components is extracted. Each connected component is transformed to a cluster of related COs, resulting in a first extracted relation between COs. The first extracted relation is used to automatically generate an alert at a client device when a second extracted relation different from the first extracted relation results from the transformation.

Embodiments provide for perceptual data association received from at least a first and a second sensor disposed at different positions in an environment, in respective time series of local scene graphs that identify several characteristics of at least one object in the environment that are updated different rates; merging, at an output rate, characteristics for each given object from the several time series of local scene graphs that are updated at the output rate; merging, at the output rate, characteristics for each given object from the time series of local scene graphs that are updated at rates other than the output rate; and outputting, at the output rate, a time series of global scene graphs including the merged characteristics.

A computer-implemented method for representing environmental elements includes receiving scan data comprising at least a point cloud representing at least an environmental element from a sensor, segmenting the point cloud into point clusters, and partitioning the point clusters into hierarchical grids. The method also includes establishing a Gaussian distribution for points in each cell of each of the hierarchical grids, and constructing a Gaussian Mixture Model based on the Gaussian distribution for representing the environmental element.

A method of deep graph representation learning includes: deriving a set of base features; and automatically developing, by a processing device, a multi-layered hierarchical graph representation based on the set of base features, wherein each successive layer of the multi-layered hierarchical graph representation leverages an output from a previous layer to learn features of a higher-order.

An activity recognition system is disclosed. A plurality of temporal features is generated from a digital representation of an observed activity using a feature detection algorithm. An observed activity graph comprising one or more clusters of temporal features generated from the digital representation is established, wherein each one of the one or more clusters of temporal features defines a node of the observed activity graph. At least one contextually relevant scoring technique is selected from similarity scoring techniques for known activity graphs, the at least one contextually relevant scoring technique being associated with activity ingestion metadata that satisfies device context criteria defined based on device contextual attributes of the digital representation, and a similarity activity score is calculated for the observed activity graph as a function of the at least one contextually relevant scoring technique, the similarity activity score being relative to at least one known activity graph.

System, methods, and other embodiments described herein relate to improving persistent simulation of an environment. In one embodiment, a method includes capturing, using at least one sensor, state information about the environment that is proximate to a robotic device. The state information includes data about at least one object that is in the environment. The method includes generating a simulation of the environment according to at least a simulation model and characteristics of the at least one object identified from the state information. The simulation is a virtualization of the environment that characterizes the at least one object in relation to an inertial frame of the environment around the observing robotic device. The method includes predicting a subsequent state for the at least one object within the simulation based, at least in part, on the simulation model. The method includes providing the subsequent state as an electronic output.

Embodiments of an automated method of processing fingerprint images, identity information is extracted from prints typically classified as having no identification value because of sparse or missing minutiae by capturing ridge contour information. Bezier approximations of ridge curvature are used as Ridge Specific Markers. Control points arising from Bezier curves generate unique polygons that represent the actual curve in the fingerprint. The Bezier-based descriptors are then grouped together and compared to corresponding reference print Ridge Specific Marker data. The method makes it possible to fuse a plurality of individual latent print portions into a single descriptor of identity and use the resulting data for comparison and identification. Processing of poor quality reference prints according to the methods disclosed renders these prints useable for reference purposes.