On pairwise costs for network flow multi-object tracking
Authors:
- 1 June 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 5537-5545
Abstract
Multi-object tracking has been recently approached with the min-cost network flow optimization techniques. Such methods simultaneously resolve multiple object tracks in a video and enable modeling of dependencies among tracks. Min-cost network flow methods also fit well within the “tracking-by-detection” paradigm where object trajectories are obtained by connecting per-frame outputs of an object detector. Object detectors, however, often fail due to occlusions and clutter in the video. To cope with such situations, we propose to add pairwise costs to the min-cost network flow framework. While integer solutions to such a problem become NP-hard, we design a convex relaxation solution with an efficient rounding heuristic which empirically gives certificates of small suboptimality. We evaluate two particular types of pairwise costs and demonstrate improvements over recent tracking methods in real-world video sequences.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Multi-target Tracking by Lagrangian Relaxation to Min-cost Network Flow2013
- Detection- and Trajectory-Level Exclusion in Multiple Object Tracking2013
- Continuous Energy Minimization for Multitarget TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Globally-optimal greedy algorithms for tracking a variable number of objects2011
- Multiobject tracking as maximum weight independent set2011
- The Pascal Visual Object Classes (VOC) ChallengeInternational Journal of Computer Vision, 2009
- A Linear Programming Approach for Multiple Object Tracking2007
- A survey for the quadratic assignment problemEuropean Journal of Operational Research, 2007
- Object trackingACM Computing Surveys, 2006
- Word alignment via quadratic assignment2006