Corpus ID: 220055599

# Lifted Disjoint Paths with Application in Multiple Object Tracking

@inproceedings{Hornkov2020LiftedDP,
title={Lifted Disjoint Paths with Application in Multiple Object Tracking},
author={Andrea Horn{\'a}kov{\'a} and Roberto Henschel and B. Rosenhahn and P. Swoboda},
booktitle={ICML},
year={2020}
}
We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors. We call the resulting optimization problem the lifted disjoint paths problem. We show that this problem is NP-hard by reduction from integer multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting… Expand

#### References

SHOWING 1-10 OF 65 REFERENCES
On pairwise costs for network flow multi-object tracking
• Computer Science, Mathematics
• 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• 2015
Multiple Object Tracking Using K-Shortest Paths Optimization
• Mathematics, Computer Science
• IEEE Transactions on Pattern Analysis and Machine Intelligence
• 2011
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications
Multiobject tracking as maximum weight independent set
• Mathematics, Computer Science
• CVPR 2011
• 2011
Multiple People Tracking by Lifted Multicut and Person Re-identification
• Mathematics, Computer Science
• 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• 2017
Multi-person Tracking by Multicut and Deep Matching
• Computer Science, Mathematics
• ECCV Workshops
• 2016
Subgraph decomposition for multi-target tracking
• Mathematics, Computer Science
• 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
• 2015