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

被引：238
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 66 条
[31]  
Liu S., 2019, LEARNING SPATIAL FUS
[32]   RetinaTrack: Online Single Stage Joint Detection and Tracking [J].
Lu, Zhichao ;
Rathod, Vivek ;
Votel, Ronny ;
Huang, Jonathan .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :14656-14666
[33]  
Meinhardt T., 2021, TrackFormer: Multi-Object Tracking with Transformers, P8844
[34]   TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Model [J].
Pang, Bo ;
Li, Yizhuo ;
Zhang, Yifan ;
Li, Muchen ;
Lu, Cewu .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :6307-6317
[35]   Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking [J].
Peng, Jinlong ;
Wang, Changan ;
Wan, Fangbin ;
Wu, Yang ;
Wang, Yabiao ;
Tai, Ying ;
Wang, Chengjie ;
Li, Jilin ;
Huang, Feiyue ;
Fu, Yanwei .
COMPUTER VISION - ECCV 2020, PT IV, 2020, 12349 :145-161
[36]   Learning Multi-Object Tracking and Segmentation from Automatic Annotations [J].
Porzi, Lorenzo ;
Hofinger, Markus ;
Ruiz, Idoia ;
Serrat, Joan ;
Bulo, Samuel Rota ;
Kontschieder, Peter .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :6845-6854
[37]   Turning Coders into Makers: The Promise of Embedded Design Generation [J].
Ramesh, Rohit ;
Lin, Richard ;
Iannopollo, Antonio ;
Sangiovanni-Vincentelli, Alberto ;
Hartmann, Bjorn ;
Dutta, Prabal .
PROCEEDINGS SCF 2017: ACM SYMPOSIUM ON COMPUTATIONAL FABRICATION, 2017,
[38]   Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks [J].
Ren, Shaoqing ;
He, Kaiming ;
Girshick, Ross ;
Sun, Jian .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) :1137-1149
[39]  
Schroff F, 2015, PROC CVPR IEEE, P815, DOI 10.1109/CVPR.2015.7298682
[40]   Deep Network Flow for Multi-Object Tracking [J].
Schulter, Samuel ;
Vernaza, Paul ;
Choi, Wongun ;
Chandraker, Manmohan .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2730-2739
1234567