Tracking of Multiple, Partially Occluded Humans based on Static Body Part Detection
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Robust Object Tracking by Hierarchical Association of Detection Responses
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Cascaded confidence filtering for improved tracking-by-detection
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
Multiple Object Tracking Using K-Shortest Paths Optimization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Globally-optimal greedy algorithms for tracking a variable number of objects
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
How does person identity recognition help multi-person tracking?
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Multi-target tracking by continuous energy minimization
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
GraphTrack: Fast and globally optimal tracking in videos
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Hi-index | 0.00 |
The occlusion in dynamic or clutter scene is a critical issue in multi-object tracking. Using latent variable to formulate this problem, some methods achieved state-of-the-art performance, while making an exact solution computationally intractable. In this paper, we present a hierarchical association framework to address the problem of occlusion in a complex scene taken by a single camera. At the first stage, reliable tracklets are obtained by frame-to-frame association of detection responses in a flow network. After that, we propose to formulate tracklets association problem in a spatio-temporal clustering model which presents the problem as faithfully as possible. Due to the important role that affinity model plays in our formulation, we then construct a sparsity induced affinity model under the assumption that a detection sample in a tracklet can be efficiently represented by another tracklet belonging to the same object. Furthermore, we give a near-optimal algorithm based on globally greedy strategy to deal with spatio-temporal clustering, which runs linearly with the number of tracklets. We quantitatively evaluate the performance of our method on three challenging data sets and achieve a significant improvement compared to state-of-the-art tracking systems.