Joint Object Detection and Multi-Object Tracking with Graph Neural Networks

Yongxin Wang, Kris Kitani, Xinshuo Weng

Robotics Institute, Carnegie Mellon University

Code


One-Sentence Summary

We proposed the first joint detection and tracking approach that utilizes Graph Neural Networks for object relation modeling, achieving S.O.T.A. performance on MOT Challenges.


Demo Video (3 minute short presentation)


Abstract

Object detection and data association are critical components in multi-object tracking (MOT) systems. Despite the fact that the two components are dependent on each other, prior work often designs detection and data association modules separately which are trained with different objectives. As a result, we cannot back-propagate the gradients and optimize the entire MOT system, which leads to sub-optimal performance. To address this issue, recent work simultaneously optimizes detection and data association modules under a joint MOT framework, which has shown improved performance in both modules. In this work, we propose a new instance of joint MOT approach based on Graph Neural Networks (GNNs). The key idea is that GNNs can model relations between variable-sized objects in both the spatial and temporal domains, which is essential for learning discriminative features for detection and data association. Through extensive experiments on the MOT15/16/17/20 datasets, we demonstrate the effectiveness of our GNN-based joint MOT approach and show state-of-the-art performance for both detection and MOT tasks.


Approach




Quantitative Performance on MOT Challenges



Our results on the MOT Leaderboard are referred to as GSDT (GNNs for Simultaneous Detection and Tracking)


BibTex

@article{Wang2020_GNNDetTrk, 
author = {Wang, Yongxin and Kitani, Kris and Weng, Xinshuo}, 
journal = {arXiv:2006.13164}, 
title = {{Joint Object Detection and Multi-Object Tracking with Graph Neural Networks}}, 
year = {2020} 
}

Page Views since 08/18/2020