An efficient implementation of a scaling minimum-cost flow algorithm
Journal of Algorithms
Resolving Motion Correspondence for Densely Moving Points
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Noniterative Greedy Algorithm for Multiframe Point Correspondence
IEEE Transactions on Pattern Analysis and Machine Intelligence
MCMC-Based Particle Filtering for Tracking a Variable Number of Interacting Targets
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Spectral Technique for Correspondence Problems Using Pairwise Constraints
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
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
Evaluating multiple object tracking performance: the CLEAR MOT metrics
Journal on Image and Video Processing - Regular
Object Detection with Discriminatively Trained Part-Based Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
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
Multiobject tracking as maximum weight independent set
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Learning affinities and dependencies for multi-target tracking using a CRF model
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Multitarget data association with higher-order motion models
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Hi-index | 0.00 |
This paper addresses the problem of multi-frame, multi-target video tracking. Unlike recent approaches that use only unary and pairwise costs, we propose a solution based on three-frame tracklets to leverage constant-velocity motion constraints while keeping computation time low. Tracklets are solved for within a sliding window of frame triplets, each having a two frame overlap with neighboring triplets. Any inconsistencies in these local tracklet solutions are resolved by considering a larger temporal window, and the remaining tracklets are then merged globally using a min-cost network flow formulation. The result is a set of high-quality trajectories capable of spanning gaps caused by missed detections and long-term occlusions. Our experimental results show good performance in complex scenes.