Tracking Human Position and Lower Body Parts Using Kalman and Particle Filters Constrained by Human Biomechanics

Featured Image

Why is it important?

This paper tackles the problem of tracking human body parts from a single video. Its main novelty is that it only relies on a 2D model that is constrained by biomechanical knowledge about human bipedal motion, instead of constraints linked to a specific activity or camera. The relevance of this framework to visual surveillance scenarios where data are usually captured by a single CCTV camera has been confirmed by a high citation count, in addition to that of the preliminary results published at the BMVC’08 conference.