Real-time visual tracking using compressive sensing

  • Authors:

  • Hanxi Li; Chunhua Shen; Qinfeng Shi

  • Affiliations:

  • NICTA, Canberra Res. Lab., Canberra, ACT, Australia;Australian Center for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia;Australian Center for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia

  • Venue:
  • CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The $/ell _1$ tracker obtains robustness by seeking a sparse representation of the tracking object via $/ell _1$ norm minimization. However, the high computational complexity involved in the $/ell _1$ tracker may hamper its applications in real-time processing scenarios. Here we propose Real-time Com-pressive Sensing Tracking (RTCST) by exploiting the signal recovery power of Compressive Sensing (CS). Dimensionality reduction and a customized Orthogonal Matching Pursuit (OMP) algorithm are adopted to accelerate the CS tracking. As a result, our algorithm achieves a realtime speed that is up to 5,000 times faster than that of the $/ell _1$ tracker. Meanwhile, RTCST still produces competitive (sometimes even superior) tracking accuracy compared to the $/ell _1$ tracker. Furthermore, for a stationary camera, a refined tracker is designed by integrating a CS-based background model (CSBM) into tracking. This CSBM-equipped tracker, termed RTCST-B, outperforms most state-of-the-art trackers in terms of both accuracy and robustness. Finally, our experimental results on various video sequences, which are verified by a new metric - Tracking Success Probability (TSP), demonstrate the excellence of the proposed algorithms.