Real-time head tracking by saccadic exploration and Gabor decomposition

The Gabor decomposition is a ubiquitous tool in computer vision. Nevertheless, it is generally considered computationally demanding for active vision applications. We suggest an attention-driven approach to head detection and tracking inspired by the human saccadic system. A dramatic speedup is achieved by computing the Gabor decomposition only on the points of a sparse retinotopic grid. The real-time head localisation and tracking system presented features a novel eyeball-mounted camera designed to simulate the mechanical performance of the human eye. It is, to the best of our knowledge, the first example of active vision system based on the Gabor decomposition.