Anomalous object interaction detection and reporting
AssigneeOmni AI, Inc.
InventorsKishor Adinath SAITWAL, Dennis G. URECH, Wesley Kenneth COBB
Life of this patent
Estimating the term…
Loading patent…
AssigneeOmni AI, Inc.
InventorsKishor Adinath SAITWAL, Dennis G. URECH, Wesley Kenneth COBB
Estimating the term…
Techniques are disclosed for analyzing a scene depicted in an input stream of video frames captured by a video camera. The techniques include evaluating sequence pairs representing segments of object trajectories. Assuming the objects interact, each of the sequences of the sequence pair may be mapped to a sequence cluster of an adaptive resonance theory (ART) network. A rareness value for the pair of sequence clusters may be determined based on learned joint probabilities of sequence cluster pairs. A statistical anomaly model, which may be specific to an interaction type or general to a plurality of interaction types, is used to determine an anomaly temperature, and alerts are issued based at least on the anomaly temperature. In addition, the ART network and the statistical anomaly model are updated based on the current interaction.
A computer-implemented method for analyzing a scene depicted in an input stream of video frames captured by a video camera, the method comprising:
A non-transitory computer-readable storage medium storing instructions, which when executed by a computer system, perform operations for analyzing a scene depicted in an input stream of video frames captured by a video camera, the operations comprising:
A system, comprising:
Dependencies are inferred from the claim text.