Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG
Rubber tire gantry (RTG) plays a pivotal role in facilitating efficient container handling within port operations. Conventional RTG, highly depending on human operations, is inefficient, labor-intensive, and also poses safety issues in adverse environments. This article introduces a multitarget dete...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of the Industrial Electronics Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10499882/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841526345421553664 |
|---|---|
| author | ZHENGTAO YU XUEQIN ZHENG JUN YANG JINYA SU |
| author_facet | ZHENGTAO YU XUEQIN ZHENG JUN YANG JINYA SU |
| author_sort | ZHENGTAO YU |
| collection | DOAJ |
| description | Rubber tire gantry (RTG) plays a pivotal role in facilitating efficient container handling within port operations. Conventional RTG, highly depending on human operations, is inefficient, labor-intensive, and also poses safety issues in adverse environments. This article introduces a multitarget detection and tracking (MTDT) algorithm specifically tailored for automated port RTG operations. The approach seamlessly integrates enhanced YOLOX for object detection and improved DeepSORT for object tracking to enhance the MTDT performance in the complex port settings. In particular, Light-YOLOX, an upgraded version of YOLOX incorporating separable convolution and attention mechanism, is introduced to improve real-time capability and small target detection. Subsequently, OSNet-DeepSORT, an enhanced version of DeepSORT, is proposed to mitigate ID switching challenges arising from unreliable data communication or occlusion in real port scenarios. The effectiveness of the proposed method is validated in various real-life port operations. Ablation studies and comparative experiments against typical MTDT algorithms demonstrate noteworthy enhancements in key performance metrics, encompassing small target detection, tracking accuracy, ID switching frequency, and real-time performance. |
| format | Article |
| id | doaj-art-5ceb94df9f8145c9bd3a456faab60c64 |
| institution | Kabale University |
| issn | 2644-1284 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Industrial Electronics Society |
| spelling | doaj-art-5ceb94df9f8145c9bd3a456faab60c642025-01-17T00:00:41ZengIEEEIEEE Open Journal of the Industrial Electronics Society2644-12842024-01-01531732510.1109/OJIES.2024.338863210499882Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTGZHENGTAO YU0https://orcid.org/0009-0006-0123-955XXUEQIN ZHENG1https://orcid.org/0009-0005-4601-5704JUN YANG2https://orcid.org/0000-0002-4290-9568JINYA SU3https://orcid.org/0000-0002-3121-7208School of Automation, Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, ChinaMeituan, Beijing, ChinaDepartment of Aeronautical and Automotive Engineering, Loughborough University, Loughborough, U.K.School of Automation, Key Laboratory of Measurement and Control of Complex Systems of Engineering, Ministry of Education, Southeast University, Nanjing, ChinaRubber tire gantry (RTG) plays a pivotal role in facilitating efficient container handling within port operations. Conventional RTG, highly depending on human operations, is inefficient, labor-intensive, and also poses safety issues in adverse environments. This article introduces a multitarget detection and tracking (MTDT) algorithm specifically tailored for automated port RTG operations. The approach seamlessly integrates enhanced YOLOX for object detection and improved DeepSORT for object tracking to enhance the MTDT performance in the complex port settings. In particular, Light-YOLOX, an upgraded version of YOLOX incorporating separable convolution and attention mechanism, is introduced to improve real-time capability and small target detection. Subsequently, OSNet-DeepSORT, an enhanced version of DeepSORT, is proposed to mitigate ID switching challenges arising from unreliable data communication or occlusion in real port scenarios. The effectiveness of the proposed method is validated in various real-life port operations. Ablation studies and comparative experiments against typical MTDT algorithms demonstrate noteworthy enhancements in key performance metrics, encompassing small target detection, tracking accuracy, ID switching frequency, and real-time performance.https://ieeexplore.ieee.org/document/10499882/DeepSORTmultitarget trackingrubber tire gantry (RTG)target detectionYOLOX |
| spellingShingle | ZHENGTAO YU XUEQIN ZHENG JUN YANG JINYA SU Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG IEEE Open Journal of the Industrial Electronics Society DeepSORT multitarget tracking rubber tire gantry (RTG) target detection YOLOX |
| title | Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG |
| title_full | Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG |
| title_fullStr | Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG |
| title_full_unstemmed | Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG |
| title_short | Improved YOLOX-DeepSORT for Multitarget Detection and Tracking of Automated Port RTG |
| title_sort | improved yolox deepsort for multitarget detection and tracking of automated port rtg |
| topic | DeepSORT multitarget tracking rubber tire gantry (RTG) target detection YOLOX |
| url | https://ieeexplore.ieee.org/document/10499882/ |
| work_keys_str_mv | AT zhengtaoyu improvedyoloxdeepsortformultitargetdetectionandtrackingofautomatedportrtg AT xueqinzheng improvedyoloxdeepsortformultitargetdetectionandtrackingofautomatedportrtg AT junyang improvedyoloxdeepsortformultitargetdetectionandtrackingofautomatedportrtg AT jinyasu improvedyoloxdeepsortformultitargetdetectionandtrackingofautomatedportrtg |