A statistical approach for trajectory analysis and motion segmentation for freely moving cameras

This paper examines the problem of motion segmentation by analyzing trajectories with statistical approach. We propose a statistical framework for motion segmentation, which makes no assumption on camera motion, camera model, number of moving objects and scene complexity. Long range trajectories are traced across frames and clustered by DTW metric. Various descriptors can be used to construct a weighted neighbor graph for the resulted clusters, following by spectral clustering to retrieve trajectories associated with motion. This framework is highly extensive because different descriptors can be combined into the bag-of-features, to build a more accurate neighbor graph to achieve better result. The algorithm is evaluated mainly with the Hopkins 155 database.