ENHANCING LINEAR PROGRAMMING WITH MOTION MODELING FOR MULTI-TARGET TRACKING

Abstract

In this paper we extend the minimum-cost network flow approach to multi-target tracking, by incorporating a motion model, allowing the tracker to better cope with longterm occlusions and missed detections. In our new method, the tracking problem is solved iteratively: Firstly, an initial tracking solution is found without the help of motion information. Given this initial set of tracklets, the motion at each detection is estimated, and used to refine the tracking solution. Finally, special edges are added to the tracking graph, allowing a further revised tracking solution to be found, where distant tracklets may be linked based on motion similarity. Our system has been tested on the PETS S2.L1 and Oxford town-center sequences, outperforming the baseline system, and achieving results comparable with the current state of the art.

Graph used to represent the tracking problem. Every green edge represents a detection. Black edges are standard links between detections. The blue edge represents our proposed link between widely separated detections.

 

Results

The results of our tracker (ELP) on the indepenent Multiple Object Tracking Becnhmark, and its comparison against other state-of-art techniques can be found here:

https://motchallenge.net/results/2D_MOT_2015/

 

Citation

Enhancing Linear Programming with Motion Modeling for Multi-target Tracking

N McLaughlin, J Martinez Del Rincon, P Miller

IEEE WACV, 2015

  

bibtex
@inproceedings{McLaughlin2015,
	Author = {McLaughlin, N. and Martinez Del Rincon, J. and Miller, P.},
	Booktitle = {Applications of Computer Vision (WACV), 2015 IEEE Winter Conference on},
	Title = {Enhancing Linear Programming with Motion Modeling for Multi-target Tracking},
	Year = {2015},
        Month={Jan},
        Pages={71-77},
}

Videos