Proceedings of the 2025 International Conference on Agriculture and Resource Economy (ICARE 2025)

<Previous Article In Volume
Next Article In Volume>

Tractor Road Detection Based on Improved YOLOv5m for Grain Truck

Authors
Qian Zhang1, *, Wenjie Xu1, Qingshan Chen1, Zhenghui Zhao2, Chunsong Du2, Xiangqian Xu3
1School of Agricultural Engineering, Jiangsu University, Zhenjiang, China
2School of Electrical & Information Engineering, Jiangsu University, Zhenjiang, China
3Shandong Golddafeng Machinery Co., Ltd., Jining, China
*Corresponding author. Email: zhangq_jsu@ujs.edu.cn
Corresponding Author
Qian Zhang
Available Online 27 May 2025.
DOI
10.2991/978-94-6463-746-5_12How to use a DOI?
Keywords
tractor road detection; grain truck; neural network; vehicle vision
Abstract

Rapid and accurate detection of tractor roads plays a vital role in the intelligent and autonomous driving of grain trucks. The tractor roads are unstructured, have a complex background and are covered by multiple obstacles. These factors result in low accuracy of tractor road detection based on the existing YOLOv5m. This paper improves YOLOv5m based on the Squeeze-and-Excitation (SE) attention mechanism. After the C3 module in the backbone, the SE attention module is added to optimize the weighting process of local features. This improves the ability of the model to focus on details such as blurred areas at the edge of the tractor roads and obstacles. At the same time, attention optimization of non-full-graph processes also reduces computational redundancy. Experimental verification was carried out on the intelligent grain truck developed by our research group. Experimental results show that compared with the existing YOLOv5m, Deeplabv3+, FCN, and UNet, the mAP50 of improved YOLOv5m for tractor road detection is improved by at least 2.7%, and the detection time is 52.1ms. Based on the method proposed in this paper, the onboard vision of intelligent grain truck can quickly and accurately predict the tractor roads, and it will help to further realize the intelligent unmanned operation of the grain truck.

Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the 2025 International Conference on Agriculture and Resource Economy (ICARE 2025)
Series
Advances in Biological Sciences Research
Publication Date
27 May 2025
ISBN
978-94-6463-746-5
ISSN
2468-5747
DOI
10.2991/978-94-6463-746-5_12How to use a DOI?
Copyright
© 2025 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Qian Zhang
AU  - Wenjie Xu
AU  - Qingshan Chen
AU  - Zhenghui Zhao
AU  - Chunsong Du
AU  - Xiangqian Xu
PY  - 2025
DA  - 2025/05/27
TI  - Tractor Road Detection Based on Improved YOLOv5m for Grain Truck
BT  - Proceedings of the 2025 International Conference on Agriculture and Resource Economy (ICARE 2025)
PB  - Atlantis Press
SP  - 112
EP  - 124
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-746-5_12
DO  - 10.2991/978-94-6463-746-5_12
ID  - Zhang2025
ER  -