计算机科学
目标检测
判别式
人工智能
视频跟踪
联想(心理学)
接头(建筑物)
机器学习
图形
数据关联
对象(语法)
人工神经网络
数据挖掘
模式识别(心理学)
理论计算机科学
工程类
哲学
认识论
建筑工程
概率逻辑
作者
Yongxin Wang,Kris Kitani,Xinshuo Weng
出处
期刊:Proceedings
[Institute of Electrical and Electronics Engineers]
日期:2021-05-30
卷期号:: 13708-13715
被引量:372
标识
DOI:10.1109/icra48506.2021.9561110
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI