Object tracking based on an online learning network with total error rate minimization

• An online learning network is integrated into particle filtering.
• The number of particles and its spread range are automatically adjusted.
• A sampling technique is proposed using discriminative and generative confidence.
• An automatic updating scheme is proposed for self-adaptation.
• An extensive comparison with state-of-art methods.

This paper presents a visual object tracking system which is tolerant to external imaging factors such as illumination, scale, rotation, occlusion and background changes. Specifically, an integration of an online version of total-error-rate minimization based projection network with an observation model of particle filter is proposed to effectively distinguish between the target object and the background. A re-weighting technique is proposed to stabilize the sampling of particle filter for stochastic propagation. For self-adaptation, an automatic updating scheme and extraction of training samples are proposed to adjust to system changes online. Our qualitative and quantitative experiments on 16 public video sequences show convincing performances in terms of tracking accuracy and computational efficiency over competing state-of-the-art algorithms.