On Pairwise Costs for Network Flow Multi-Object Tracking
This work addresses tracking failures in video analysis for applications like surveillance and autonomous driving, representing an incremental improvement.
The paper tackles the problem of multi-object tracking in videos by enhancing min-cost network flow methods with pairwise costs to handle occlusions and clutter, resulting in improved performance over recent tracking methods in real-world sequences.
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.