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

By Yongxin Wang, Kris M. Kitani, Xinshuo Weng. IEEE International Conference on Robotics and Automation, 2021

298 citations recorded by the source corpus.

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 works often design detection and data association modules separately which are trained with separate objectives. As a result, one cannot back-propagate the gradients and optimize the entire MOT system, which leads to sub-optimal performance. To address this issue, recent works simultaneously optimize 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 variablesized 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.

Subfields: Computer Vision and Pattern Recognition, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/e243c89ac61aae7330792c6c3f8791f07f40d031

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

StrongSORT: Make DeepSORT Great Again (2022, background): “Recently, several joint trackers [30,32,38,57,59,65,68] have been proposed to train detection and some other components jointly, e.”
Track to Detect and Segment: An Online Multi-Object Tracker (2021, methodology): “Advanced online multi-object tracking methods follow two major paradigms: tracking-by-detection [5, 38, 27, 52, 30, 49] and joint detection and tracking [26, 63, 1, 29, 45, 25, 43, 44].”
TrackFormer: Multi-Object Tracking with Transformers (2021, methodology): “However, we surpass or perform on-par with several modern methods [55,66,68] that were trained on significantly more data, i.”