Abstract

This paper proposes a novel approach to anomalous behaviour detec- tion in video. The approach is comprised of three key components. First, dis- tributions of spatiotemporal oriented energy are used to model behaviour. This representation can capture a wide range of naturally occurring visual spacetime patterns and has not previously been applied to anomaly detection. Second, a novel method is proposed for comparing an automatically acquired model of nor- mal behaviour with new observations. The method accounts for situations when only a subset of the model is present in the new observation, as when multiple activities are acceptable in a region yet only one is likely to be encountered at any given instant. Third, event driven processing is employed to automatically mark portions of the video stream that are most likely to contain deviations from the expected and thereby focus computational efforts. The approach has been imple- mented with real-time performance. Quantitative and qualitative empirical eval- uation on a challenging set of natural image videos demonstrates the approach’s superior performance relative to various alternatives.