Bibliographic Details
| Title: |
Research on Cattle Behavior Recognition and Multi-Object Tracking Algorithm Based on YOLO-BoT. |
| Authors: |
Tong, Lei1,2,3 (AUTHOR) tonglei1235@163.com, Fang, Jiandong1,2,3 (AUTHOR) fangjd@imut.edu.cn, Wang, Xiuling1,2,3 (AUTHOR), Zhao, Yudong2,3 (AUTHOR) |
| Source: |
Animals (2076-2615). Oct2024, Vol. 14 Issue 20, p2993. 31p. |
| Subject Terms: |
*BEHAVIORAL assessment, *ANIMAL welfare, *TRACKING algorithms, *FEATURE extraction, *AGRICULTURE, *OBJECT tracking (Computer vision) |
| Abstract: |
Simple Summary: This study presents a deep learning-based multi-object tracking method to enhance the accuracy of cattle detection and tracking, thereby improving farming efficiency and health management. The proposed method mitigates detection errors and omissions in complex environments while reducing identity switching and trajectory prediction errors through algorithmic enhancements. Experimental results show that the method achieves superior accuracy in cattle detection and behavioral tracking, operating in real time at 31.2 frames per second. This approach provides strong technical support for long-term monitoring and contactless cattle management, offering considerable practical value. In smart ranch management, cattle behavior recognition and tracking play a crucial role in evaluating animal welfare. To address the issues of missed and false detections caused by inter-cow occlusions and infrastructure obstructions in the barn environment, this paper proposes a multi-object tracking method called YOLO-BoT. Built upon YOLOv8, the method first integrates dynamic convolution (DyConv) to enable adaptive weight adjustments, enhancing detection accuracy in complex environments. The C2f-iRMB structure is then employed to improve feature extraction efficiency, ensuring the capture of essential features even under occlusions or lighting variations. Additionally, the Adown downsampling module is incorporated to strengthen multi-scale information fusion, and a dynamic head (DyHead) is used to improve the robustness of detection boxes, ensuring precise identification of rapidly changing target positions. To further enhance tracking performance, DIoU distance calculation, confidence-based bounding box reclassification, and a virtual trajectory update mechanism are introduced, ensuring accurate matching under occlusion and minimizing identity switches. Experimental results demonstrate that YOLO-BoT achieves a mean average precision (mAP) of 91.7% in cattle detection, with precision and recall increased by 4.4% and 1%, respectively. Moreover, the proposed method improves higher order tracking accuracy (HOTA), multi-object tracking accuracy (MOTA), multi-object tracking precision (MOTP), and IDF1 by 4.4%, 7%, 1.7%, and 4.3%, respectively, while reducing the identity switch rate (IDS) by 30.9%. The tracker operates in real-time at an average speed of 31.2 fps, significantly enhancing multi-object tracking performance in complex scenarios and providing strong support for long-term behavior analysis and contactless automated monitoring. [ABSTRACT FROM AUTHOR] |
|
Copyright of Animals (2076-2615) is the property of MDPI and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| Database: |
Academic Search Complete |
|
Full text is not displayed to guests. |
Login for full access.
|
