CONDENSATION—Conditional Density Propagation forVisual Tracking
International Journal of Computer Vision
Color-Based Probabilistic Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time tracking of image regions with changes in geometry and illumination
CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
Lucas-Kanade 20 Years On: A Unifying Framework
International Journal of Computer Vision
A Riemannian Framework for Tensor Computing
International Journal of Computer Vision
Covariance Tracking using Model Update Based on Lie Algebra
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
ACM Computing Surveys (CSUR)
Robust Face Recognition via Sparse Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Bayesian tracking on Riemannian manifolds via fragments-based representation
ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
Online Learning for Matrix Factorization and Sparse Coding
The Journal of Machine Learning Research
Multi-class classification on Riemannian manifolds for video surveillance
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Robust and fast collaborative tracking with two stage sparse optimization
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Region covariance: a fast descriptor for detection and classification
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
IEEE Transactions on Information Theory
Visual tracking and recognition using appearance-adaptive models in particle filters
IEEE Transactions on Image Processing
Gabor-Based Region Covariance Matrices for Face Recognition
IEEE Transactions on Circuits and Systems for Video Technology
Fast Pedestrian Detection Using a Cascade of Boosted Covariance Features
IEEE Transactions on Circuits and Systems for Video Technology
Sparse coding based visual tracking: Review and experimental comparison
Pattern Recognition
Hi-index | 0.00 |
Recently, sparse representation has been utilized in many computer vision tasks and adapted for visual tracking. Sparsity-based visual tracking is formulated as searching candidates with minimal reconstruction errors from a template subspace with sparsity constraints in the approximation coefficients. However, an intensity template is easily corrupted by noise and not robust for target tracking under a dynamic environment. The recently proposed covariance region descriptor has been proven robust and versatile for a modest computational cost. Further, the covariance matrix enables efficient fusion of different types of features, where the spatial and statistical properties as well as their correlation are characterized, and its dimension is small. Although the covariance matrix lies on Riemannian manifolds, its log-transformation can be measured on a Euclidean subspace. Based on the covariance region descriptor and using the sparse representation, we propose a novel tracking approach on the Log-Euclidean Riemannian subspace. Specifically, the target region is characterized by a covariance matrix which is then log-transformed from the Riemannian manifold to the Euclidean subspace. After that, the target tracking problem is integrated under a sparse approximation framework, where the sparsity is achieved by solving an l1-regularization problem. Then the candidate with the smallest approximation is taken as the tracked target. For target propagation, we use the Bayesian state inference framework, which propagates sample distributions over time using the particle filter algorithm. To evaluate our method, we have collected several video sequences and the experimental results show that our tracker can achieve robustly and reliably target tracking.