Design of a System for Obtaining the Diameter of Tree Trunks Using Depth Vision

DOI: https://doi.org/10.62517/jes.202502114

Author(s)

Ma Ruiting, Chen Qilin, Li Ming*, Zhu Wenjia, Chen Lina, Wang Runtao, Ma Tao, Wu Jiansheng, Xuan Zijian

Affiliation(s)

School of Electronic and Electrical Engineering, Lingnan Normal University, Zhanjiang, Guangdong, China *Corresponding author

Abstract

In order to improve the autonomous navigation and operation efficiency of orchard robots, this study proposes an improved YOLOv5 algorithm to identify the trunk of the fruit tree, and combines with the depth camera for accurate positioning. By combining the SENet attention mechanism module with the residual module in the network, we obtain the improved SE-Res module, which can enhance the extraction of useful feature information and compress useless feature information. After experimental verification, the accuracy of the improved YOLOv5 model is increased by 2.38 percentage points, the recall rate is increased by 0.84 percentage points, the frame rate is reduced by 0.99 frames/s, and the mAP is increased by 0.05 percentage points. Experimental results show that the method can accurately identify and locate fruit trees in the autonomous navigation and fertilization of orchard robots, so as to improve operation efficiency and ensure operation quality, and realize the intellectualization and rationalization of fruit tree fertilization in the orchard environment.

Keywords

YOLOv5 Algorithm; Attention Mechanism; Depth Image; Target Detection; Fruit Tree Trunk; Accuracy

References

[1] MEI Nan. Research on development countermeasures of Chinese style family farm [D]. Jilin University,2015. [2] Zhang Jicheng. Research on key technologies of variable fertilization system based on prescription map [D]. Northeast Agricultural University,2013. [3]GilesDK,SlaughterDC. Precision band spraying with machine vision guidance and adjustable yaw nozzles[J]. Transactions of theAsae, 1997, 40 (1) : 29-36. [4] NIU Runxin, Zhang Xiangyang, Wang Jie, Zhu Hui, Huang Jian, Chen Zhengwei. Tree-trunk detection algorithm of agricultural robot orchard based on LiDAR [J]. Transactions of the Chinese Society for Agricultural Machinery, 2019,51(11):21-27. [5] Zhang Yingying, Zhou Jun. Orchard trunk detection based on LiDAR [J]. Journal of China Agricultural University, 2015, 20(05): 249-255. (in Chinese) [6] LIU Weihong, HE Xiongkui, LIU Yajia, Wu Zhiming, YUAN Changjian, LIU Limin, QI Peng, LI Tian. 3DLiDAR navigation method for orchard rows [J]. Transactions of the Chinese Society of Agricultural Engineering, 201,37(09):165-174. [7] HAN Zhenhao, Li Jia, Yuan Yanwei, Fang Zhengjing, Zhao Bo, ZHU Licheng. Orchard visual navigation path recognition method based on U-Net network [J]. Transactions of the Chinese Society for Agricultural Machinery, 201,52(01):30-39. [8] Li Shiwei. Object Detection and License Plate Recognition System based on YOLOv5 algorithm [J]. Electronic Technology and Software Engineering,2022(01):138-141. [9] GU Baoxing, Liu Qin, Tian Guangzhao, Wang Haiqing, Li He, Xie Shangjie. Tree trunk recognition and localization based on improved YOLOv3 [J]. Transactions of the Chinese Society of Agricultural Engineering,202,38(06):122-129. (in Chinese) [10] SHEN Yue, Zhuang Zhenzhen, Liu Hui, Jiang Jianbin, OU Mingxiong. Multi-feature tree trunk recognition method based on RealSense depth camera [J]. Transactions of the Chinese Society for Agricultural Machinery, 2002,53(04):304-312. [11] Wang Han, Liu Haiming, Shao Yuhong. Research on Metal surface defect detection based on improved YOLOv5 algorithm [J/OL]. Mechanical science and technology: 1-6 [2023-10-21]. https://doi.org/10.13433/j.cnki.1003-8728.20230315. [12] Lu Bibo, Zhou Yun, Li Xiaojun et al. YOLOv5 Personnel Detection Algorithm in Light Coal Mine with Attention mechanism [J]. And coal technology, 2023 (10) : 200-203. The DOI: 10.13301 / j.carol carroll nki. Ct. 2023.10.045.