Item

Abstract

This paper presents an approach for motion-based anomaly detection, where a prototype pattern is detected and elastically registered against a test sample to detect anomalies in the test sample. The prototype model is learned from multiple sequences to define accepted variations. “Supertrajectories” based on hierarchical clustering of dense point trajectories serve as an efficient and robust representation of motion patterns. An efficient hashing approach provides transformation hypotheses that are refined by a spatiotemporal elastic registration. We propose a new method for elastic registration of 3D+time trajectory patterns that induces spatial elasticity from trajectory affinities. The method is evaluated on a new motion anomaly dataset of juggling patterns and performs well in detecting subtle anomalies. Moreover, we demonstrate the applicability to biological motion patterns.