Track to Detect and Segment: An Online Multi-Object Tracker

被引：212
|
作者：
Wu, Jialian [1 ]
Cao, Jiale [2 ]
Song, Liangchen [1 ]
Wang, Yu [3 ]
Yang, Ming [3 ]
Yuan, Junsong [1 ]
机构：
[1] SUNY Buffalo, Buffalo, NY 14260 USA
[2] TJU, Tianjin, Peoples R China
[3] Horizon Robot, Beijing, Peoples R China
来源：
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 | 2021年
基金：
美国国家科学基金会;
关键词：
D O I：
10.1109/CVPR46437.2021.01217
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking).
引用
收藏
页码：12347 / 12356
页数：10
相关论文
共 50 条
  • [1] Online Multi-object Tracking Using Single Object Tracker and Markov Clustering
    Zhu, Jiao
    Zhang, Shanshan
    Yang, Jian
    IMAGE AND GRAPHICS, ICIG 2019, PT III, 2019, 11903 : 555 - 567
  • [2] Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker
    Hyun, Jeongseok
    Kang, Myunggu
    Wee, Dongyoon
    Yeung, Dit-Yan
    2023 IEEE/CVF WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2023, : 4839 - 4848
  • [3] On the detection-to-track association for online multi-object tracking
    Lin, Xufeng
    Li, Chang-Tsun
    Sanchez, Victor
    Maple, Carsten
    PATTERN RECOGNITION LETTERS, 2021, 146 : 200 - 207
  • [4] Learning to Track: Online Multi-Object Tracking by Decision Making
    Xiang, Yu
    Alahi, Alexandre
    Savarese, Silvio
    2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 4705 - 4713
  • [5] A labeled random finite set online multi-object tracker for video data
    Kim, Du Yong
    Ba-Ngu Vo
    Ba-Tuong Vo
    Jeon, Moongu
    PATTERN RECOGNITION, 2019, 90 : 377 - 389
  • [6] Track Everything: Limiting Prior Knowledge in Online Multi-Object Recognition
    Wong, Sebastien C.
    Stamatescu, Victor
    Gatt, Adam
    Kearney, David
    Lee, Ivan
    McDonnell, Mark D.
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (10) : 4669 - 4683
  • [7] Online multi-object tracking with efficient track drift and fragmentation handling
    Ju, Jaeyong
    Kim, Daehun
    Ku, Bonhwa
    Han, David K.
    Ko, Hanseok
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2017, 34 (02) : 280 - 293
  • [8] Segment as Points for Efficient and Effective Online Multi-Object Tracking and Segmentation
    Xu, Zhenbo
    Yang, Wei
    Zhang, Wei
    Tan, Xiao
    Huang, Huan
    Huang, Liusheng
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (10) : 6424 - 6437
  • [9] Compensation Tracker: Reprocessing Lost Object for Multi-Object Tracking
    Zou, Zhibo
    Huang, Junjie
    Luo, Ping
    2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022), 2022, : 2673 - 2683
  • [10] Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshment
    Chu, Peng
    Fan, Heng
    Tan, Chiu C.
    Ling, Haibin
    2019 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV), 2019, : 161 - 170
12345