Visual event detection using orientation histograms with feature point trajectory information

Visual event detection in video streams allows easier access to, and better organization of large media collections. This paper presents an event detection framework with a novel feature that incorporates flow, appearance and trajectory information jointly. While previous event detection methods have been designed for understanding human behaviours where the camera is either static or with minimal motion, a more general approach is needed as real-life events are always subjected to fast camera motion and involve non-human dynamic objects. Inspired by the success of dense and overlapping orientation histograms in human detection, we build an event descriptor using orientation histograms augmented with feature point trajectory information. We put our system to test on tennis videos which have significant camera motion and multiple dynamic objects, and achieved good classification performance under a comparable setting.