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
  • [31] Recurrent Autoregressive Networks for Online Multi-Object Tracking
    Fang, Kuan
    Xiang, Yu
    Li, Xiaocheng
    Savarese, Silvio
    2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 466 - 475
  • [32] Online Multi-Object Tracking With Visual and Radar Features
    Bae, Seung-Hwan
    IEEE ACCESS, 2020, 8 (08): : 90324 - 90339
  • [33] ONLINE MULTI-OBJECT TRACKING WITH CONVOLUTIONAL NEURAL NETWORKS
    Chen, Long
    Ai, Haizhou
    Shang, Chong
    Zhuang, Zijie
    Bai, Bo
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 645 - 649
  • [34] A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
    Yin, Junbo
    Wang, Wenguan
    Meng, Qinghao
    Yang, Ruigang
    Shen, Jianbing
    2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, : 6767 - 6776
  • [35] AETrack: An Efficient Approach for Online Multi-Object Tracking
    Wang, Xurui
    Han, Yuxuan
    Liu, Qingxiao
    Li, Ji
    Wang, Boyang
    Liu, Haiou
    Chen, Huiyan
    2024 35TH IEEE INTELLIGENT VEHICLES SYMPOSIUM, IEEE IV 2024, 2024, : 977 - 983
  • [36] Online Multi-object Tracking Based on Deep Learning
    Sun, Zheming
    Bo, Chunjuan
    Wang, Dong
    COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, VOL. 1, 2022, 878 : 33 - 40
  • [37] Attention mechanics for improving online Multi-Object Tracking
    Minh Chuong Dang
    Duc Dung Nguyen
    2022 ASIA CONFERENCE ON ALGORITHMS, COMPUTING AND MACHINE LEARNING (CACML 2022), 2022, : 200 - 205
  • [38] GNN-PMB: A Simple but Effective Online 3D Multi-Object Tracker Without Bells and Whistles
    Liu, Jianan
    Bai, Liping
    Xia, Yuxuan
    Huang, Tao
    Zhu, Bing
    Han, Qing-Long
    IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2023, 8 (02): : 1176 - 1189
  • [39] Detector-tracker integration framework and attention mechanism for multi-object tracking
    Li, Chunjiang
    Chen, Guangzhu
    Gou, Rongsong
    Tang, Zaizuo
    NEUROCOMPUTING, 2021, 464 : 450 - 461
  • [40] Learning from Outputs: Improving Multi-Object Tracking Performance by Tracker Fusion
    Scarrica, Vincenzo M.
    Staiano, Antonino
    TECHNOLOGIES, 2024, 12 (12)
12345