EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
International Journal of Computer Vision
IEEE Transactions on Pattern Analysis and Machine Intelligence
Online Selection of Discriminative Tracking Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM Computing Surveys (CSUR)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Incremental Learning for Robust Visual Tracking
International Journal of Computer Vision
Semi-supervised On-Line Boosting for Robust Tracking
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Robust Object Tracking with Online Multiple Instance Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Visual Tracking and Vehicle Classification via Sparse Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Decoding by linear programming
IEEE Transactions on Information Theory
IEEE Transactions on Information Theory
Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?
IEEE Transactions on Information Theory
Real-time compressive tracking
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Hi-index | 0.00 |
A small number of randomly generated linear measurements can preserve most of the salient information of one compressible image according to compress sensing theory. Using these measurements as features can greatly improve the speed of detection based tracking methods, and deal with the problems caused by occlusion, illumination change, pose variation and motion blur to some extent. This paper addressed to improve the state-of-the-art real-time compressive object tracking algorithm, which extracted low-dimensional multistate features of object and background, then used naïve Bayesian classifier combined with online updating mechanism to track object in real-time under the compressed domain. On the basis of its tracking results, we rematch the first 30 candidate targets with online appearance model to search for the optimum tracking position. The experimental results in lot of challenging test sequences show that the proposed algorithm has promising potential.