Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting
Tracking-by-detection is a popular paradigm for Multi-Object Tracking (MOT), but the problems of unstable tracking and frequent ID transitions still occur due to the low illumination, point light sources, and high dust in the underground coal mine space. In this respect, this paper proposes a Dark-S...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10348583/ |
| _version_ | 1827398941509943296 |
|---|---|
| author | Rui Wang Jingzhao Li Zhi Xu |
| author_facet | Rui Wang Jingzhao Li Zhi Xu |
| author_sort | Rui Wang |
| collection | DOAJ |
| description | Tracking-by-detection is a popular paradigm for Multi-Object Tracking (MOT), but the problems of unstable tracking and frequent ID transitions still occur due to the low illumination, point light sources, and high dust in the underground coal mine space. In this respect, this paper proposes a Dark-SORT personnel tracking algorithm for downhole environment characteristics. First, a video image enhancement method is designed to enhance the video image quality and improve the localization accuracy of the detector for the dim and unevenly distributed light environment in the well. Second, an Adaptive Discrete-weighted Attention Module (ADAM) is designed, which consists of an Enhanced Discrete Channel Attention (EDCA) module and an Adaptive Discrete Spatial Attention (ADSA) module. EDCA enables the network to capture richer information at different scales by adaptively processing different channels according to their importance and feature scales. The ADSA approach enhances the linkage between different locations within the same region, combines different pooling strategies to highlight important regions, and reduces the focus on overexposed regions. Finally, the OC-SORT tracking algorithm is introduced to solve the error accumulation problem based on the motion model and incorporate the appearance feature information to improve the stability of target tracking. We conducted a comparison test on the self-built dataset MINE-MOT, and the HOTA, MOTA, DetA, AssA, IDF1, AssRe, and FPS metrics of the Dark-SORT tracking algorithm based on the YOLOv7 target detection model were 67.4, 92.6, 80.3, 46.8, 61.7, 65.7, and 23, respectively, which was the best in terms of accuracy and stability of all the models involved in the test. |
| first_indexed | 2024-03-08T19:37:05Z |
| format | Article |
| id | doaj.art-2e237df6a2eb49ceb8a7d9a004e6e905 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-08T19:37:05Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-2e237df6a2eb49ceb8a7d9a004e6e9052023-12-26T00:08:29ZengIEEEIEEE Access2169-35362023-01-011113942213943810.1109/ACCESS.2023.334091410348583Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete WeightingRui Wang0https://orcid.org/0009-0004-3003-2713Jingzhao Li1Zhi Xu2https://orcid.org/0000-0001-6241-2578School of Artificial Intelligence, Anhui University of Science and Technology, Huainan, ChinaSchool of Artificial Intelligence, Anhui University of Science and Technology, Huainan, ChinaSchool of Electrical and Information Engineering, Anhui University of Science and Technology, Huainan, ChinaTracking-by-detection is a popular paradigm for Multi-Object Tracking (MOT), but the problems of unstable tracking and frequent ID transitions still occur due to the low illumination, point light sources, and high dust in the underground coal mine space. In this respect, this paper proposes a Dark-SORT personnel tracking algorithm for downhole environment characteristics. First, a video image enhancement method is designed to enhance the video image quality and improve the localization accuracy of the detector for the dim and unevenly distributed light environment in the well. Second, an Adaptive Discrete-weighted Attention Module (ADAM) is designed, which consists of an Enhanced Discrete Channel Attention (EDCA) module and an Adaptive Discrete Spatial Attention (ADSA) module. EDCA enables the network to capture richer information at different scales by adaptively processing different channels according to their importance and feature scales. The ADSA approach enhances the linkage between different locations within the same region, combines different pooling strategies to highlight important regions, and reduces the focus on overexposed regions. Finally, the OC-SORT tracking algorithm is introduced to solve the error accumulation problem based on the motion model and incorporate the appearance feature information to improve the stability of target tracking. We conducted a comparison test on the self-built dataset MINE-MOT, and the HOTA, MOTA, DetA, AssA, IDF1, AssRe, and FPS metrics of the Dark-SORT tracking algorithm based on the YOLOv7 target detection model were 67.4, 92.6, 80.3, 46.8, 61.7, 65.7, and 23, respectively, which was the best in terms of accuracy and stability of all the models involved in the test.https://ieeexplore.ieee.org/document/10348583/Attention mechanismcomputer visiontarget detectiontarget trackingimage enhancement |
| spellingShingle | Rui Wang Jingzhao Li Zhi Xu Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting IEEE Access Attention mechanism computer vision target detection target tracking image enhancement |
| title | Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting |
| title_full | Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting |
| title_fullStr | Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting |
| title_full_unstemmed | Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting |
| title_short | Dark-SORT: Multi-Person Tracking in Underground Coal Mines Using Adaptive Discrete Weighting |
| title_sort | dark sort multi person tracking in underground coal mines using adaptive discrete weighting |
| topic | Attention mechanism computer vision target detection target tracking image enhancement |
| url | https://ieeexplore.ieee.org/document/10348583/ |
| work_keys_str_mv | AT ruiwang darksortmultipersontrackinginundergroundcoalminesusingadaptivediscreteweighting AT jingzhaoli darksortmultipersontrackinginundergroundcoalminesusingadaptivediscreteweighting AT zhixu darksortmultipersontrackinginundergroundcoalminesusingadaptivediscreteweighting |