Target tracking and localization of binocular mobile robot using camshift and SIFT

ABSTRACT

A real time dynamic target recognition and tracking method is presented for mobile robot in this paper. Firstly, the inter-frame difference method is applied to detect the moving target. And the proposed method computes the color histogram and extracts SIFT features in the target region. Then from the following frame, it extracts SIFT features, matches with SIFT features extracted from target, and calculates the center location of the matched features. Finally the Camshift algorithm, starting from the center location, is used to track the target. Experiments demonstrate that the proposed method can effectively recognize and track the moving target, and its performance is better than the classic Camshift algorithm

REFERENCES

• 1: Weiming, H., T. Tieniu. 2004. A Survey on Visual Surveillance of Object Motion and Behaviors {J}. IEEE Transactions on Systems, Man, and Cybernetics, Part C, 34 (3): 334--352.
• 2: Dorin Comaniciu , Visvanathan Ramesh , Peter Meer, Kernel-Based Object Tracking, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.25 n.5, p.564-575, May 2003 [doi>10.1109/TPAMI.2003.1195991]
• 3: Dorin Comaniciu, An Algorithm for Data-Driven Bandwidth Selection, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.25 n.2, p.281-288, February 2003 [doi>10.1109/TPAMI.2003.1177159]
• 4: Peng, N S,Yang J,Liu Z, et al. 2005. Automatic Selection of Kernel-Bandwidth for Mean-Shift Object Tracking, Journal of Software, 16(9): 1542--1550. (in Chinese)
• 5: Peng, N S,Yang J, Liu Z. 2005. Mean shift blob tracking with kernel histogram filtering and hypothesis testing {J}.Pattern Recognition Letters, 26(5): 605--614.
• 6: Robert T. Collins , Yanxi Liu , Marius Leordeanu, Online Selection of Discriminative Tracking Features, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.27 n.10, p.1631-1643, October 2005 [doi>10.1109/TPAMI.2005.205]
• 7: G. R. Bradski. 1998.Computer vision face tracking for use in a perceptual user interface {J}. Intel Technology Journal, 2(2): 12--21.
• 8: David G. Lowe, Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision, v.60 n.2, p.91-110, November 2004 [doi>10.1023/B:VISI.0000029664.99615.94]
• 9: Bradski, G.R., Pisarevsky, V., 2000. Intel's computer vision library: Application in calibration, stereo, segmentation, tracking, gesture, face and object recognition. IEEE Conference of Computation Vision Pattern Recognition, Vol. 2, pp. 796--797

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.7 COMPUTERS IN OTHER SYSTEMS
      Subjects: Command and control

Additional Classification:
  J. Computer Applications
  J.7 COMPUTERS IN OTHER SYSTEMS
      Subjects: Real time

General Terms:
Algorithms, Experimentation

Keywords:
SIFT, binocular mobile robot, camshift, target tracking