Multi-object tracking driven event detection for evaluation

This paper describes a monocular object tracker, able to detect and track multiple object classes in non-controlled environments. Our tracking framework uses Bayesian per-pixel classification to segment an image into foreground and background objects, based on observations of object appearances and motions in real-time. Furthermore, semantically high level events are automatically extracted from the tracking data for performance evaluation. The reliability of the event detection is demonstrated by applying it to state-of-the-art methods and comparing the results to human annotated ground truth data for multiple public datasets.