Extended MHT algorithm for multiple object tracking
Proceedings of the 4th International Conference on Internet Multimedia Computing and Service
Combining per-frame and per-track cues for multi-person action recognition
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part I
GMCP-Tracker: global multi-object tracking using generalized minimum clique graphs
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part II
A discrete chain graph model for 3d+t cell tracking with high misdetection robustness
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Two-granularity tracking: mediating trajectory and detection graphs for tracking under occlusions
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Online multi-target tracking by large margin structured learning
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Multiple target tracking using frame triplets
ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part III
Iterative hypothesis testing for multi-object tracking with noisy/missing appearance features
ACCV'12 Proceedings of the 11th international conference on Computer Vision - Volume 2
Decomposing combinatorial auctions and set packing problems
Journal of the ACM (JACM)
Tracking with a mixed continuous-discrete Conditional Random Field
Computer Vision and Image Understanding
People reidentification in surveillance and forensics: A survey
ACM Computing Surveys (CSUR)
Hi-index | 0.00 |
This paper addresses the problem of simultaneous tracking of multiple targets in a video. We first apply object detectors to every video frame. Pairs of detection responses from every two consecutive frames are then used to build a graph of tracklets. The graph helps transitively link the best matching tracklets that do not violate hard and soft contextual constraints between the resulting tracks. We prove that this data association problem can be formulated as finding the maximum-weight independent set (MWIS) of the graph. We present a new, polynomial-time MWIS algorithm, and prove that it converges to an optimum. Similarity and contextual constraints between object detections, used for data association, are learned online from object appearance and motion properties. Long-term occlusions are addressed by iteratively repeating MWIS to hierarchically merge smaller tracks into longer ones. Our results demonstrate advantages of simultaneously accounting for soft and hard contextual constraints in multitarget tracking. We outperform the state of the art on the benchmark datasets.