Online Long-Term Object Tracking Based on Compressed Haar-Like Features via Sparse Representation

Abstract:

Online long-term tracking is a challenging problem as data streams change over time. In this paper, sparse representation has been applied to visual tracking by finding the most correct sample with minimal reconstruction error using compressed Haar-like features. However, most sparse representation tracking algorithm introduce l₁ regularization into the PCA reconstruction using samples directly, which leads to complexity computation and can not adapt to occlusion, rotation and change in size. Our model updating not only uses the samples from the training set, but also generates the warped versions (include scale variation, rotation, occlusion and illumination changes) for the previous tracking result. Also, we do not use the samples in models for sparse representation directly, but the Haar-like features instead which are compressed in a very low-dimensional space. In addition, we use a robust and fast algorithm which exploits the spatio-temporal context for predicting the target location in the next frame. This step will lead to the reduction of the searching range by the detector. We demonstrate the proposed method is able to track objects well under pose and scale variation, rotation, occlusion and illumination with great real-time performance on challenging image sequences.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 1610-1614
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.1610
• Online since: July 2014
• Authors: Ming Zhao*, Lu Ping Wang, Lu Ping Zhang
• Keywords: Compressive Sensing, Context Learning, Haar-Like, l₁Minimizatio, Long-Term Tracking, Online Learning, Sparse Representation

References

[1] Mei X, Ling H, Yi W, et al. Minimum error bounded efficient tracker with occlusion detection[C]. Proceedings of the IEEE 12th International Conference on Computer Vision and Pattern Recognition. Colorado, USA: IEEE, 2011: 1257-1264.

[2] T. B. Dinh and G. G. Medioni, Co-trainning framework of generative and discriminative trackers with partial occlusion handling, in Proc. IEEE Workshop Appl. Computer Vision, Jan. 2011, PP. 642-649.

DOI: 10.1109/wacv.2011.5711565

[3] Wang D, Lu H-C, Yang M-H. Online object tracking with sparse prototypes[J]. IEEE Transactions on Image Processing, 2013, 22(1): 314-325.

DOI: 10.1109/tip.2012.2202677

[4] Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang, David Zhang. Fast Tracking via Spatio- Temporal Context Learning[J]. ECCV. 2013, 11.

[5] Zhang Kai-hua, Zhang Lei, Yang Ming-hsuan. Real-Time Compressive Tracking. ECCV (2012).

[6] Rigamonti R, Brown M A, Lepetit V. Are sparse representations really relevant for image classification?[C]. Proceedings of the IEEE 12th International Conference on Computer Vision and Pattern Recognition, Colorado, USA: IEEE, 2011: 1545-1552.

DOI: 10.1109/cvpr.2011.5995313

[7] Xiao Z-Y, Lu H-Ch, Wang D. Object tracking with L2-RLS[C]. Proceeding of the 21th International Conference on Pattern Recognition. Tsukuba, Japan: IEEE, 2012: 681-684.