Heuristic Search for Structural Constraints in Data Association

TL;DR

This paper introduces a heuristic search method to utilize structural constraints among multiple targets, improving data association in online multi-object tracking by reducing ambiguities caused by similar appearances and camera motion.

Contribution

The paper proposes a novel heuristic approach to incorporate structural constraints into data association, enhancing the discriminative power of matching in multi-object tracking.

Findings

Achieved MOTA of 25.0 on 2DMOT2015 dataset.

Effectively reduces match ambiguities caused by camera motion.

Improves data association accuracy by integrating structural constraints.

Abstract

The research on multi-object tracking (MOT) is essentially to solve for the data association assignment, the core of which is to design the association cost as discriminative as possible. Generally speaking, the match ambiguities caused by similar appearances of objects and the moving cameras make the data association perplexing and challenging. In this paper, we propose a new heuristic method to search for structural constraints (HSSC) of multiple targets when solving the problem of online multi-object tracking. We believe that the internal structure among multiple targets in the adjacent frames could remain constant and stable even though the video sequences are captured by a moving camera. As a result, the structural constraints are able to cut down the match ambiguities caused by the moving cameras as well as similar appearances of the tracked objects. The proposed heuristic method aims to obtain a maximum match set under the minimum structural cost for each available match pair, which can be integrated with the raw association costs and make them more elaborate and discriminative compared with other approaches. In addition, this paper presents a new method to recover missing targets by minimizing the cost function generated from both motion and structure cues. Our online multi-object tracking (MOT) algorithm based on HSSC has achieved the multi-object tracking accuracy (MOTA) of 25.0 on the public dataset 2DMOT2015[1].