Gait Recognition using Dynamic Affine Invariants

We present a method for recognizing classes of human gaits from video sequences. We propose a novel image-based representation of human gaits. At any instant of time a gait is represented by a vector of affine invariant moments. These invariants are computed on the binary silhouettes corresponding to the moving body. We represent the time trajectories of the affine invariant moment vector as the output of a linear dynamical system driven by white noise. The problem of gait classification then boils down to formulating distances and performing recognition in the space of linear dynamical systems. Experimental results demonstrate the discriminative power of the proposed approach.