Joint Registration and Active Contour Segmentation for Object Tracking

 

By Jifeng Ning, Lei Zhang, David Zhang and Wei Yu

 

IEEE Transactions on Circuits and Systems for Video Technology, vol. 23, no. 9, pp. 1589 -1597, Sept. 2013.

 

 

The proposed JRACS algorithm is compared with EM-shift algorithm [1], SOAMST algorithm [2], Combination flow algorithm [3], and Chiverton et al.¡¯s algorithm [4].

 

Experiment 1:  Car sequence

Chiverton et al.

download video

EM-shift

download video

SOAMST

download video

Combination flow

download video

JRACS

download video

 

Experiment 2:  Indoor face sequence

Chiverton et al.

download video

EM-shift

download video

SOAMST

download video

Combination flow

download video

JRACS

download video

 

Experiment 3:  Hand sequence

Chiverton et al.

download video

EM-shift

download video

SOAMST

download video

Combination flow

download video

JRACS

download video

 

Experiment 4:  Fish sequence 1

EM-shift

download video

SOAMST

download video

Combination flow

download video

JRACS

download video

 

Experiment 5:  Fish sequence 2

Chiverton et al.

download video

EM-shift

download video

SOAMST

download video

Combination flow

download video

JRACS

download video

 

Experiment 6:  Outdoor face sequence

Chiverton et al.

download video

EM-shift

download video

SOAMST

download video

Combination flow

download video

JRACS

download video

 

Experiment 7:  Multiple targets

Combination flow

download video

JRACS

download video

 

Experiment 8:  Micky mouse

Combination flow

download video

JRACS

download video

 

 

Reference

 

  [1]        Z. Zivkovic and B. Kröse, ¡°An EM-like Algorithm for Color-Histogram-Based Object Tracking,¡± In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Washington, D.C., USA, vol. I, pp. 798-803, 2004.

  [2]        J. Ning, L. Zhang, D. Zhang, and C. Wu, ¡°Scale and Orientation Adaptive Mean Shift Tracking,¡± IET Computer Vision, 2011. http://www4.comp.polyu.edu.hk/~cslzhang/SOAMST.htm

  [3]        T. Zhang, D. Freedman, ¡°Improving performance of distribution tracking through background matching,¡± IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 2, pp. 282¨C287, 2005.

  [4]        J. Chiverton, X. Xie, and M. Mirmehdi. ¡°Automatic Bootstrapping and Tracking of Object Contours,¡± IEEE Trans. on Image Processing, vol. 21, no. 3, pp, 1231-1245, 2012.