Multi-Person Tracking by Multicut and Deep Matching

TL;DR

This paper enhances multi-person tracking by introducing a robust local appearance feature, optimizing the multicut problem for efficiency, and demonstrating state-of-the-art results on the MOT16 benchmark.

Contribution

It proposes a novel local appearance feature for tracking, simplifies the multicut formulation, and employs an efficient optimization algorithm for long videos.

Findings

Achieved state-of-the-art performance on MOT16 benchmark.

Demonstrated robustness to occlusion and camera motion.

Validated the effectiveness of the new local appearance feature.

Abstract

In [1], we proposed a graph-based formulation that links and clusters person hypotheses over time by solving a minimum cost subgraph multicut problem. In this paper, we modify and extend [1] in three ways: 1) We introduce a novel local pairwise feature based on local appearance matching that is robust to partial occlusion and camera motion. 2) We perform extensive experiments to compare different pairwise potentials and to analyze the robustness of the tracking formulation. 3) We consider a plain multicut problem and remove outlying clusters from its solution. This allows us to employ an efficient primal feasible optimization algorithm that is not applicable to the subgraph multicut problem of [1]. Unlike the branch-and-cut algorithm used there, this efficient algorithm used here is applicable to long videos and many detections. Together with the novel feature, it eliminates the need for the intermediate tracklet representation of [1]. We demonstrate the effectiveness of our overall approach on the MOT16 benchmark [2], achieving state-of-art performance.