Motion feature filtering for event detection in crowded scenes

We describe a spatio-temporal feature filtering approach that is appropriate for detecting video events in public scenes containing from many to few people. This non-discrete tracking – or pattern flow analysis – is distinguished by the fact that the usual video processing step of object segmentation is omitted; instead motion features alone are used to detect, follow, and separate activity. Motion features include location, scale, score (magnitude), direction, and velocity. The method entails gradient-based motion detection and multiscale motion feature calculation to obtain a scene activity vector. We focus on the motion features and their filtering, and distinguish our approach from the more common use of optical flow determined direction, and use of this feature alone for analysis. The end goal is event detection, classification and anomaly detection. We demonstrate the approach on 3 video datasets: hallway, emergency event, and subway platform.