Real-time Multi-Object Tracking Based on Bi-directional Matching

TL;DR

This paper introduces a bi-directional matching algorithm for real-time multi-object tracking that effectively handles occlusions and improves trajectory continuity, achieving high accuracy and speed on standard benchmarks.

Contribution

It proposes a novel bi-directional matching method with stranded area management and an attentional up-sampling module for enhanced occlusion handling and faster training.

Findings

Achieves 63.4% MOTA on MOT17

Attains 55.3% IDF1 score

Runs at 20.1 FPS in real-time

Abstract

In recent years, anchor-free object detection models combined with matching algorithms are used to achieve real-time muti-object tracking and also ensure high tracking accuracy. However, there are still great challenges in multi-object tracking. For example, when most part of a target is occluded or the target just disappears from images temporarily, it often leads to tracking interruptions for most of the existing tracking algorithms. Therefore, this study offers a bi-directional matching algorithm for multi-object tracking that makes advantage of bi-directional motion prediction information to improve occlusion handling. A stranded area is used in the matching algorithm to temporarily store the objects that fail to be tracked. When objects recover from occlusions, our method will first try to match them with objects in the stranded area to avoid erroneously generating new identities, thus forming a more continuous trajectory. Experiments show that our approach can improve the multi-object tracking performance in the presence of occlusions. In addition, this study provides an attentional up-sampling module that not only assures tracking accuracy but also accelerates training speed. In the MOT17 challenge, the proposed algorithm achieves 63.4% MOTA, 55.3% IDF1, and 20.1 FPS tracking speed.