Opto-Electronic Engineering, Volume. 50, Issue 6, 230009(2023)
Multiple object tracking with aligned spatial-temporal feature
Figures & Tables(10)
Fig. 4. The visualization results comparison between baseline and our method on validation set. (a) ID switch; (b) FP and FN; (c) special FP
Fig. 5. Visualization results of this method on the KITTI test set. The video number is in the left side of the figure. The frame number is in the upper left of the figure
Table 1. The tracking performance comparision between our method and other advanced methods on MOT17 data set
View tableView in ArticleTable 1. The tracking performance comparision between our method and other advanced methods on MOT17 data set
Method Year MOTA↑ IDF1↑ HOTA↑ FP↓ FN↓ MT↑ ML↓ IDS↓ FPS↑ TubeTK[ 39 ]CVPR2020 63.0 58.6 48.0 27060 177483 31.2 19.9 5529 3.0 CTracker[ 26 ]ECCV2020 66.6 57.4 49.0 22284 160491 32.2 24.2 5529 6.8 CenterTrack[ 12 ]ECCV2020 67.8 64.7 52.2 18489 160332 34.6 24.6 3309 22.0 TraDes[ 40 ]CVPR2021 69.1 63.9 52.7 20892 150060 36.4 21.5 3555 3.4 FairMOT[ 10 ]IJCV2021 73.7 72.3 59.3 27507 117477 43.2 17.3 3303 18.9 TrackFormer[ 15 ]CVPR2022 65.0 63.9 - 70443 123552 - - 3528 - MOTR[ 16 ]ECCV2022 67.4 67.0 - 32355 149400 34.6 24.5 1992 - CSTrack[ 20 ]TIP2022 74.9 72.3 - 23847 114303 41.5 17.5 3567 16.4 Ours 74.2 73.9 60.1 27129 116337 43.8 19.1 2367 10.9
Table 2. The tracking performance comparision between our method and other advanced methods on MOT20 data set
View tableView in ArticleTable 2. The tracking performance comparision between our method and other advanced methods on MOT20 data set
Method Year MOTA↑ IDF1↑ HOTA↑ FP↓ FN↓ MT↑ ML↓ IDS↓ FPS↑ FairMOT[ 10 ]IJCV2021 61.8 67.3 54.6 103440 88901 68.8 7.6 5243 8.9 TransTrack[ 14 ]arXiv2021 64.5 59.2 - 28566 151377 49.1 13.6 3565 - CorrTracker[ 22 ]CVPR2021 65.2 73.6 - 29808 99510 47.6 12.7 3369 - CSTrack[ 20 ]TIP2022 66.6 68.6 54.0 25404 144358 50.4 15.5 3196 4.5 Ours 67.4 70.6 55.6 49358 117370 59.6 12.3 2066 4.8
Table 3. The impact of different components on the overall tracking performance
View tableView in ArticleTable 3. The impact of different components on the overall tracking performance
Method MOTA↑ IDF1↑ FP↓ FN↓ MT↑ ML↓ IDS↓ Baseline 69.1 72.8 1976 14443 143 53 299 Baseline+ConvGRU 69.6 73.4 2434 13729 150 50 321 Baseline+ConvGRU+Alignment Module 70.0 74.8 2201 13715 153 51 320
Table 4. The impact of video sequence input length on the overall tracking performance
View tableView in ArticleTable 4. The impact of video sequence input length on the overall tracking performance
Input length MOTA↑ IDF1↑ FP↓ FN↓ MT↑ ML↓ IDS↓ 2 68.9 73.5 2412 14092 143 52 311 3 69.6 74.1 2108 13990 144 51 319 4 69.6 73.9 2156 13949 152 52 293 5 69.5 74.1 2221 13947 151 52 313 8 70.0 74.8 2201 13715 153 51 320
Table 5. The tracking performance comparision between our method and other advanced methods on KITTI vehicle class test set
View tableView in ArticleTable 5. The tracking performance comparision between our method and other advanced methods on KITTI vehicle class test set
Method Year HOTA↑ MOTA↑ FP↓ FN↓ MT↑ ML↓ IDS↓ CenterTrack[ 12 ]ECCV2020 73.0 88.8 2703 886 82.2 15.4 254 QDTrack[ 41 ]CVPR2021 68.5 84.9 4320 549 69.5 3.8 313 Ours 69.6 82.2 5403 433 58.6 8.3 274
Tools
Get Citation
Copy Citation Text
Wen Cheng, Zhongbi Chen, Qingqing Li, Meihui Li, Jianlin Zhang, Yuxing Wei. Multiple object tracking with aligned spatial-temporal feature[J]. Opto-Electronic Engineering, 2023, 50(6): 230009
Paper Information
Category: Article
Received: Jan. 12, 2023
Accepted: Apr. 3, 2023
Published Online: Aug. 9, 2023
The Author Email:
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20