Efficient Region Tracking With Parametric Models of Geometry and Illumination
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Lie algebra approach for tracking and 3D motion estimation using monocular vision
Image and Vision Computing
Incremental Learning for Robust Visual Tracking
International Journal of Computer Vision
Tracking by Affine Kernel Transformations Using Color and Boundary Cues
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Face Recognition via Sparse Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Online dictionary learning for sparse coding
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
An iterative image registration technique with an application to stereo vision
IJCAI'81 Proceedings of the 7th international joint conference on Artificial intelligence - Volume 2
Robust Visual Tracking and Vehicle Classification via Sparse Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Online robust image alignment via iterative convex optimization
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Visual tracking via adaptive structural local sparse appearance model
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Robust object tracking via sparsity-based collaborative model
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hi-index | 0.00 |
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.