English

Depth Perspective-aware Multiple Object Tracking

Computer Vision and Pattern Recognition 2023-02-28 v2

Abstract

This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware Multiple Object Tracking (DP-MOT) approach to tackle the occlusion problem in MOT. A simple yet efficient Subject-Ordered Depth Estimation (SODE) is first proposed to automatically order the depth positions of detected subjects in a 2D scene in an unsupervised manner. Using the output from SODE, a new Active pseudo-3D Kalman filter, a simple but effective extension of Kalman filter with dynamic control variables, is then proposed to dynamically update the movement of objects. In addition, a new high-order association approach is presented in the data association step to incorporate first-order and second-order relationships between the detected objects. The proposed approach consistently achieves state-of-the-art performance compared to recent MOT methods on standard MOT benchmarks.

Keywords

Cite

@article{arxiv.2207.04551,
  title  = {Depth Perspective-aware Multiple Object Tracking},
  author = {Kha Gia Quach and Huu Le and Pha Nguyen and Chi Nhan Duong and Tien Dai Bui and Khoa Luu},
  journal= {arXiv preprint arXiv:2207.04551},
  year   = {2023}
}

Comments

In review PR journal