Chen Dong-Yue
College of Information Science and Engineering, Northeastern University, China
Qi Yuan-Chen
College of Information Science and Engineering, Northeastern University, China
ABSTRACT
In order to solve the video-based object tracking problem in complex dynamic scenes, a robust tracking algorithm based on adaptive feature selection was proposed in this paper. To address the poor robustness of candidates in the feature pool in the online Adaboost algorithm and the drift problem caused by the template updating, a new feature pool was built based on both color features and histogram of pyramidal gradient features. An occlusion detector is added after the tracking in the current frame to improve the reliability of the realtime updated template. Experimental results showed that the proposed algorithm has better performance against object deformation, pose transformation, illumination variance and occlusion.
PDF References Citation
How to cite this article
Chen Dong-Yue and Qi Yuan-Chen, 2013. Robust Object Tracking Based on Adaptive Feature Selection. Information Technology Journal, 12: 7325-7330.
DOI: 10.3923/itj.2013.7325.7330
URL: https://scialert.net/abstract/?doi=itj.2013.7325.7330
DOI: 10.3923/itj.2013.7325.7330
URL: https://scialert.net/abstract/?doi=itj.2013.7325.7330
REFERENCES
- Bosch, A., A. Zisserman and X. Munoz, 2007. Representing shape with a spatial pyramid kernel. Proceedings of the 6th ACM International Conference on Image and Video Retrieval, July 9-11, 2007, Amsterdam, The Netherlands, pp: 401-408.
Direct Link - Babenko, B., Y. Ming-Hsuan and S. Belongie, 2011. Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell., 33: 1619-1632.
CrossRef - Cheng, C., R. Ansari and A. Khokhar, 2005. Multiple object tracking with kernel particle filter. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June 20-25, 2005, San Diego, California, USA., pp: 566-573.
CrossRef - Grabner, H., M. Grabner and H. Bischof, 2006. Real-time tracking via on-line boosting. Proceedings of the British Machine Vision Conference, September 4-7, 2006, Edinburgh, UK., pp: 47-56.
CrossRef - Kwak, S., W. Nam, B. Han and J.H. Han, 2011. Learning occlusion with likelihoods for visual tracking. Proceedings of the IEEE International Conference on Computer Vision, November 6-13, 2011, Barcelona, Spain, pp: 1551-1558.
CrossRef - Lei, F., Y. Lu, W. Huang, L. Yu and L. Jia, 2012. Fast static particle swarm optimization based feature selection for face detection. Proceedings of the 8th International Conference on Computational Intelligence and Security, November 17-18, 2012, Guangzhou, pp: 401-405.
CrossRef - Matthews, L., T. Ishikawa and S. Baker, 2004. The template update problem. IEEE Trans. Pattern Anal. Mach. Intell., 26: 810-815.
CrossRef - Xue, M. and H.B. Ling, 2009. Robust visual tracking using L1 minimization. Proceedings of the 12th International Conference on Computer Vision, September 29-October 2, 2009, Kyoto, pp: 1436-1443.
CrossRef - Xue, M. and H.B. Ling, 2011. Robust visual tracking and vehicle classification via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell., 33: 2259-2272.
CrossRef