On Pairwise Costs for Network Flow Multi-Object Tracking

TL;DR

This paper enhances multi-object tracking by integrating pairwise costs into the min-cost network flow framework, improving robustness against occlusions and clutter with an efficient convex relaxation approach.

Contribution

It introduces a novel pairwise cost extension to network flow tracking, along with a convex relaxation and heuristic, addressing NP-hardness and improving tracking accuracy.

Findings

Improved tracking accuracy over recent methods.

Effective handling of occlusions and clutter.

Empirical validation on real-world videos.

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.