Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments
Aiming at the problems of poor detection effect and low tracking stability of multi-type vehicles in complex mining environment due to the similarity of operating vehicles and background images, this paper proposes a multi-category and multi-target real-time detection and tracking algorithm for oper...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Control and Information Technology
2022-10-01
|
| Series: | Kongzhi Yu Xinxi Jishu |
| Subjects: | |
| Online Access: | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2022.05.300 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849224976549281792 |
|---|---|
| author | KANG Gaoqiang LIN Jun LIU Shiwang YUE Wei XIONG Qunfang TONG Hao |
| author_facet | KANG Gaoqiang LIN Jun LIU Shiwang YUE Wei XIONG Qunfang TONG Hao |
| author_sort | KANG Gaoqiang |
| collection | DOAJ |
| description | Aiming at the problems of poor detection effect and low tracking stability of multi-type vehicles in complex mining environment due to the similarity of operating vehicles and background images, this paper proposes a multi-category and multi-target real-time detection and tracking algorithm for operating vehicles in complex mining environments. The model framework is constructed based on the lightweight backbone network YOLO combined with the multi-scale feature fusion module. The model uses DIoU as loss function, uses <italic>K</italic>-means clustering to regress the size of candidate frame, and learns image features through the lightweight backbone network. On this basis, the features of multi-category work vehicle targets are used as similarity metric, combined with Mahalanobis distance metric and cosine metric that characterize motion information for cascading matching, and IoU matching and Kalman filtering are connected in series to confirm the trajectory and the real-time tracking of multiple work vehicles. Experimental results show that the average vehicle detection accuracy of the algorithm mAP@ 0.5-0.95 is 58.40%, the multi-target tracking accuracy reaches 82.60%, and the image processing time per frame is 26.5 ms, which can effectively perform real-time detection and tracking of working vehicles. |
| format | Article |
| id | doaj-art-b85ef2cc8d904bd381da7e3464fc4dac |
| institution | Kabale University |
| issn | 2096-5427 |
| language | zho |
| publishDate | 2022-10-01 |
| publisher | Editorial Office of Control and Information Technology |
| record_format | Article |
| series | Kongzhi Yu Xinxi Jishu |
| spelling | doaj-art-b85ef2cc8d904bd381da7e3464fc4dac2025-08-25T06:47:57ZzhoEditorial Office of Control and Information TechnologyKongzhi Yu Xinxi Jishu2096-54272022-10-01687431013876Real-time Detection and Tracking for Operating Vehicles in Complex Mining EnvironmentsKANG GaoqiangLIN JunLIU ShiwangYUE WeiXIONG QunfangTONG HaoAiming at the problems of poor detection effect and low tracking stability of multi-type vehicles in complex mining environment due to the similarity of operating vehicles and background images, this paper proposes a multi-category and multi-target real-time detection and tracking algorithm for operating vehicles in complex mining environments. The model framework is constructed based on the lightweight backbone network YOLO combined with the multi-scale feature fusion module. The model uses DIoU as loss function, uses <italic>K</italic>-means clustering to regress the size of candidate frame, and learns image features through the lightweight backbone network. On this basis, the features of multi-category work vehicle targets are used as similarity metric, combined with Mahalanobis distance metric and cosine metric that characterize motion information for cascading matching, and IoU matching and Kalman filtering are connected in series to confirm the trajectory and the real-time tracking of multiple work vehicles. Experimental results show that the average vehicle detection accuracy of the algorithm mAP@ 0.5-0.95 is 58.40%, the multi-target tracking accuracy reaches 82.60%, and the image processing time per frame is 26.5 ms, which can effectively perform real-time detection and tracking of working vehicles.http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2022.05.300unmanned drivingmulti-operation vehicle trackingvehicle detectioncascade matchingYOLO algorithmKalman filteringmine truck |
| spellingShingle | KANG Gaoqiang LIN Jun LIU Shiwang YUE Wei XIONG Qunfang TONG Hao Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments Kongzhi Yu Xinxi Jishu unmanned driving multi-operation vehicle tracking vehicle detection cascade matching YOLO algorithm Kalman filtering mine truck |
| title | Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments |
| title_full | Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments |
| title_fullStr | Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments |
| title_full_unstemmed | Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments |
| title_short | Real-time Detection and Tracking for Operating Vehicles in Complex Mining Environments |
| title_sort | real time detection and tracking for operating vehicles in complex mining environments |
| topic | unmanned driving multi-operation vehicle tracking vehicle detection cascade matching YOLO algorithm Kalman filtering mine truck |
| url | http://ctet.csrzic.com/thesisDetails#10.13889/j.issn.2096-5427.2022.05.300 |
| work_keys_str_mv | AT kanggaoqiang realtimedetectionandtrackingforoperatingvehiclesincomplexminingenvironments AT linjun realtimedetectionandtrackingforoperatingvehiclesincomplexminingenvironments AT liushiwang realtimedetectionandtrackingforoperatingvehiclesincomplexminingenvironments AT yuewei realtimedetectionandtrackingforoperatingvehiclesincomplexminingenvironments AT xiongqunfang realtimedetectionandtrackingforoperatingvehiclesincomplexminingenvironments AT tonghao realtimedetectionandtrackingforoperatingvehiclesincomplexminingenvironments |