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
  • [21] Adaptive Neuro-Fuzzy Controller for Multi-object Tracker
    Chau, Duc Phu
    Subramanian, K.
    Bremond, Francois
    COMPUTER VISION SYSTEMS (ICVS 2015), 2015, 9163 : 466 - 476
  • [22] Context Enhanced Multi-Object Tracker for Human Robot Collaboration
    Chandra, Akkaladevi Sharath
    Plasch, Matthias
    Eitzinger, Christian
    Rinner, Bernhard
    COMPANION OF THE 2017 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI'17), 2017, : 61 - 62
  • [23] New results from the multi-object Keck Exoplanet Tracker
    van Eyken, J. C.
    Ge, J.
    Wan, X.
    Zhao, B.
    Hariharan, A.
    Mahadevan, S.
    DeWitt, C.
    Guo, P.
    Cohen, R.
    Fleming, S. W.
    McDavitt, D.
    Crepp, J.
    Warner, C.
    Kane, S.
    Leger, F.
    Pan, K.
    FIRST LIGHT SCIENCE WITH THE GTC, 2007, 29 : 151 - 151
  • [24] TdmTracker: Multi-Object Tracker Guided by Trajectory Distribution Map
    Gao, Yuxuan
    Gu, Xiaohui
    Gao, Qiang
    Hou, Runmin
    Hou, Yuanlong
    ELECTRONICS, 2022, 11 (07)
  • [25] Joint detection and online multi-object tracking
    Kieritz, Hilke
    Huebner, Wolfgang
    Arens, Michael
    PROCEEDINGS 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW), 2018, : 1540 - 1548
  • [26] Online Multi-Object Tracking Using CNN-based Single Object Tracker with Spatial-Temporal Attention Mechanism
    Chu, Qi
    Ouyang, Wanli
    Li, Hongsheng
    Wang, Xiaogang
    Liu, Bin
    Yu, Nenghai
    2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2017, : 4846 - 4855
  • [27] Occlusion Geodesics for Online Multi-Object Tracking
    Possegger, Horst
    Mauthner, Thomas
    Roth, Peter M.
    Bischof, Horst
    2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2014, : 1306 - 1313
  • [28] SynDHN: Multi-Object Fish Tracker Trained on Synthetic Underwater Videos
    Martija, Mygel Andrei M.
    Naval, Prospero C., Jr.
    2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2021, : 8841 - 8848
  • [29] Multitarget Track-before-detect from Image Observations Based on Multi-object Particle PHD Filter
    Zhu, Ran
    Long, Yunli
    Sha, Zhichao
    An, Wei
    2017 PROGRESS IN ELECTROMAGNETICS RESEARCH SYMPOSIUM - SPRING (PIERS), 2017, : 3062 - 3066
  • [30] Learn-select-track: An approach to multi-object tracking
    Makhura, Onalenna J.
    Woods, John C.
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2019, 74 : 153 - 161
12345