Saved in:
Bibliographic Details
Main Authors: Jing, Longlong, Yu, Ruichi, Chen, Xu, Zhao, Zhengli, Sheng, Shiwei, Graber, Colin, Chen, Qi, Li, Qinru, Wu, Shangxuan, Deng, Han, Lee, Sangjin, Sweeney, Chris, He, Qiurui, Hung, Wei-Chih, He, Tong, Zhou, Xingyi, Moussavi, Farshid, Guo, Zijian, Zhou, Yin, Tan, Mingxing, Yang, Weilong, Li, Congcong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.00236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909186244214784
author Jing, Longlong
Yu, Ruichi
Chen, Xu
Zhao, Zhengli
Sheng, Shiwei
Graber, Colin
Chen, Qi
Li, Qinru
Wu, Shangxuan
Deng, Han
Lee, Sangjin
Sweeney, Chris
He, Qiurui
Hung, Wei-Chih
He, Tong
Zhou, Xingyi
Moussavi, Farshid
Guo, Zijian
Zhou, Yin
Tan, Mingxing
Yang, Weilong
Li, Congcong
author_facet Jing, Longlong
Yu, Ruichi
Chen, Xu
Zhao, Zhengli
Sheng, Shiwei
Graber, Colin
Chen, Qi
Li, Qinru
Wu, Shangxuan
Deng, Han
Lee, Sangjin
Sweeney, Chris
He, Qiurui
Hung, Wei-Chih
He, Tong
Zhou, Xingyi
Moussavi, Farshid
Guo, Zijian
Zhou, Yin
Tan, Mingxing
Yang, Weilong
Li, Congcong
contents Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. Existing works frequently focus on the association task while either neglecting the model performance on state estimation or deploying complex heuristics to predict the states. In this paper, we propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately. STT consumes rich appearance, geometry, and motion signals through long term history of detections and is jointly optimized for both data association and state estimation tasks. Since the standard tracking metrics like MOTA and MOTP do not capture the combined performance of the two tasks in the wider spectrum of object states, we extend them with new metrics called S-MOTA and MOTPS that address this limitation. STT achieves competitive real-time performance on the Waymo Open Dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2405_00236
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle STT: Stateful Tracking with Transformers for Autonomous Driving
Jing, Longlong
Yu, Ruichi
Chen, Xu
Zhao, Zhengli
Sheng, Shiwei
Graber, Colin
Chen, Qi
Li, Qinru
Wu, Shangxuan
Deng, Han
Lee, Sangjin
Sweeney, Chris
He, Qiurui
Hung, Wei-Chih
He, Tong
Zhou, Xingyi
Moussavi, Farshid
Guo, Zijian
Zhou, Yin
Tan, Mingxing
Yang, Weilong
Li, Congcong
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Tracking objects in three-dimensional space is critical for autonomous driving. To ensure safety while driving, the tracker must be able to reliably track objects across frames and accurately estimate their states such as velocity and acceleration in the present. Existing works frequently focus on the association task while either neglecting the model performance on state estimation or deploying complex heuristics to predict the states. In this paper, we propose STT, a Stateful Tracking model built with Transformers, that can consistently track objects in the scenes while also predicting their states accurately. STT consumes rich appearance, geometry, and motion signals through long term history of detections and is jointly optimized for both data association and state estimation tasks. Since the standard tracking metrics like MOTA and MOTP do not capture the combined performance of the two tasks in the wider spectrum of object states, we extend them with new metrics called S-MOTA and MOTPS that address this limitation. STT achieves competitive real-time performance on the Waymo Open Dataset.
title STT: Stateful Tracking with Transformers for Autonomous Driving
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2405.00236