Computer Vision and Image Understanding
A Lattice-Based MRF Model for Dynamic Near-Regular Texture Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
The theory of trackability with applications to sensor networks
ACM Transactions on Sensor Networks (TOSN)
Tracking by parts: a Bayesian approach with component collaboration
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Tracking a group of highly correlated targets
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Robust visual tracking combining global and local appearance models
ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
Multi-target tracking by learning class-specific and instance-specific cues
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part II
SAMT'10 Proceedings of the 5th international conference on Semantic and digital media technologies
Editors Choice Article: Tracking highly correlated targets through statistical multiplexing
Image and Vision Computing
Tracking dynamic near-regular texture under occlusion and rapid movements
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Hierarchical model for joint detection and tracking of multi-target
ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
ACM Transactions on Intelligent Systems and Technology (TIST) - Special section on twitter and microblogging services, social recommender systems, and CAMRa2010: Movie recommendation in context
Hi-index | 0.00 |
This paper presents a decentralized approach to multiple target tracking. The novelty of this approach lies in the use of a set of autonomous while collaborative trackers to overcome the tracker coalescence problem with linear complexity. In this approach, the individual trackers are autonomous in the sense that they can select targets to track and evaluate themselves, and they are also collaborative since they need to compete for the targets against those trackers that are close to them through communication. The theoretical foundation of this new approach is based on the variational analysis of a Markov network that reveals the collaborative mechanism through a fixed point iteration among these trackers and the existence of the equilibriums. In addition, a trained object detector is incorporated to help sense the potential newly appearing targets in the dynamic scene. Experimental results on challenging video sequences demonstrate the effectiveness and efficiency of the proposed method.