SCALABLE AND OCCLUSION-AWARE MULTI-CUES CORRELATION FILTER FOR ROBUST STEREO VISUAL TRACKING

Zheng Zhu, Wei Zou, and Feng Zhang

Keywords

Depth information, Stereo tracking, Visual tracking

Abstract

Depth provided by binocular vision systems is extra information for stereo visual tracking, which has less distance limitation and can work well in outdoor environment compared to RGB-D cameras. By fusing depth with edge and color features, a stereo tracking algorithm named Scalable and Occlusion-aware Multi-cues Correlation Filter Tracker (SOMCFT) is proposed in this paper, which consists of by multi-cue correlation filter tracker (MCFT), scale handling and occlusion-aware strategy. In MCFT, the confidence maps drawn from all the features are filtered by each other, and then an optimal confidence map is determined by minimizing the sum of Kullback-Leibler (KL) divergence. In scale handling, the target is segmented by 2D gray-depth histograms and then a quantized set is used to guide the scale variants of bounding boxes. In occlusion-aware strategy, the start and end of occlusion is detected by combining the changes of depth and the results of MCFT, meanwhile a reasonable candidate region is determined during occlusion. Both qualitative and quantitative evaluations on the Stereo Tracking Dataset (STD) demonstrate that the proposed SOMCFT algorithm performs favorably when compared against other methods. Our algorithm outperforms the second ranked method by 5.4% in success score and 14.59% in precision score.

Important Links:



Go Back