Region covariance based probabilistic tracking

Abstract

Region covariance descriptor recently proposed in has been approved robust and elegant to describe a region of interest which has been applied to visual tracking. By employing region covariance descriptor, the tracker efficiently fuses multiple features and modalities and has a capacity for comparing regions with different window sizes. Relying on the same principle of region covariance descriptor, but with a probabilistic framework, we introduce an elegant way to integrate covariance descriptor into Monte Carlo tracking technique for visual tracking. The advantages of particle filter and multiple features of region covariance descriptor entitle us better competence to handle object tracking within complex environment, as well as partial and completed occlusions of the tracked entity over a few frames. The experimental results show that region covariance based particle tracker outperforms CAMSHIFT tracker and color based particle tracker within complex environment. And our tracker also better handles occlusions when comparing with region covariance descriptor based local search tracker.