Robust Registration-Based Tracking by Sparse Representation with Model Update
Object tracking by image registration based on the Lucas-Kanade method has been studied over decades. The classical method is known to be sensitive to illumination changes, pose variation and occlusion. A great number of papers have been presented to address this problem. Despite great advances achieved thus far, robust registration-based tracking in challenging conditions remains unsolved. This paper presents a novel method which extends the Lucas-Kanade using the sparse representation. Our objective function involves joint optimization of the warp function and the optimal linear combination of the test image with a set of basis vectors in a dictionary. The objective function is regularized by ℓ1 norm of the linear combination coefficients. It is a non-linear and non-convex problem and we minimize it by alternating between the warp function and coefficients. We thus achieve an efficient algorithm which iteratively solves the LASSO and classical Lucas-Kanade by optimizing one while keeping another fixed. Unlike existing sparsity-based work that uses exemplar templates as the object model, we explore the low-dimensional linear subspace of the object appearances for object representation. For adaptation to dynamical scenarios, the mean vector and basis vectors of the appearance subspace are updated online by incremental SVD. Experiments demonstrate the promising performance of the proposed method in challenging image sequences.
KeywordsSparse Representation Object Tracking Object Representation Illumination Change Warp Function
Unable to display preview. Download preview PDF.
- 1.Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: Proc. of the 7th Int. Joint Conference on Artificial Intelligence, IJCAI 1981, pp. 674–679 (1981)Google Scholar
- 8.Shi, J., Tomasi, C.: Good features to track. In: Int. Conf. on Computer Vision and Pattern Recognition, pp. 593–600 (1994)Google Scholar
- 9.Birchfield, S., Pundlik, S.: Joint tracking of features and edges. In: Int. Conf. on Computer Vision and Pattern Recognition, pp. 1–6 (2008)Google Scholar
- 10.Kim, S.J., Frahm, J.M., Pollefeys, M.: Joint feature tracking and radiometric calibration from auto-exposure video. In: Int. Conf. on Computer Vision, pp. 1–8 (2007)Google Scholar
- 13.Jia, X., Lu, H., Yang, M.: Tracking via adaptive structural local sparse appearance model. In: Int. Conf. on Computer Vision and Pattern Recognition (2012)Google Scholar
- 14.Zhong, W., Lu, H., Yang, M.: Robust object tracking via sparsity-based collaborative model. In: Int. Conf. on Computer Vision and Pattern Recognition (2012)Google Scholar
- 15.Wu, Y., Shen, B., Ling, H.: Online robust image alignment via iterative convex optimization. In: Int. Conf. on Computer Vision and Pattern Recognition, pp. 1808–1814 (2012)Google Scholar
- 16.Huang, J., Huang, X., Metaxas, D.: Simultaneous image transformation and sparse representation recovery. In: Int. Conf. on Computer Vision and Pattern Recognition, pp. 1–8 (2008)Google Scholar
- 19.Mairal, J., Bach, F., Ponce, J., Sapiro, G.: Online dictionary learning for sparse coding. In: Proc. of the 26th Annual Int. Conf. on Machine Learning, ICML 2009, pp. 689–696. ACM, New York (2009)Google Scholar