On Pairwise Cost for Multi-Object Network Flow Tracking - Archive ouverte HAL Access content directly
Conference Papers Year :

On Pairwise Cost for Multi-Object Network Flow Tracking

(1, 2) , (2, 3, 4) , (2, 1) , (2, 1)
1
2
3
4

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.

Dates and versions

hal-01110678 , version 1 (28-01-2015)

Identifiers

Cite

Visesh Chari, Simon Lacoste-Julien, Ivan Laptev, Josef Sivic. On Pairwise Cost for Multi-Object Network Flow Tracking. CVPR 2015 - 28th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. ⟨hal-01110678⟩
287 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More