Design and test of intelligent spraying unmanned vehicle for greenhouse tomato based on YOLOv4-tiny

doi:10.12398/j.issn.2096-7217.2023.02.005

Abstract

Abstract: Unmanned vehicle for spraying is used in production of facility agriculture and smart agriculture. Tomato in greenhouse has characteristics of narrow planting spacing and many twisted lead wires, which required special vehicles. Therefore, it is necessary to design a miniaturized, variable, and intelligent spraying unmanned vehicle for greenhouse tomato. It is mainly composed of a disease detection and positioning module, a lifting platform, a steering gear rocker mechanism, and a fully automatic bearing chassis. This design innovatively combines deep learning technology to achieve automatic detection of disease targets. RGB image of greenhouse tomato collected by Kinect V2 was used as input for disease detection. Two-dimensional pixel coordinates of the disease detection results were converted into three-dimensional spatial coordinates for realizing disease location. Ball screw and stepping motor were used to adjust height of the lifting platform. Then, the steering gear rocker mechanism was employed to locate disease of the greenhouse tomato. Variable and intelligent spraying was thus completed. Results showed that target detection accuracy of fruit clusters and diseases in complex environment reached 75.15% with F1 score of 79.96 through testing the trained YOLOv4-tiny model. It detected 37.6 images per second, so it was able to be deployed on the embedded development board to detect disease targets of greenhouse tomato. Compared with the results of manual disease location, results showed that absolute error of disease location was within ±3.5cm. Through field test of the spraying unmanned vehicle, the success rate of the whole machine of the intelligent spraying unmanned vehicle for greenhouse tomato was above 75%, and the error rate of spraying pesticide was below 20%, which achieved accurate positioning of diseases of greenhouse tomato and variable intelligent spraying according to disease degree. This design can provide reference for the design of other spraying unmanned vehicle and has a good promotion and application prospect.

Key words: facility agriculture, intelligent spraying, greenhouse tomato, unmanned vehicle, object detection

CLC Number:

S223.2

LI Qianxi, SUN Xiaoming, JIANG Hanhui, WU Airu, FU Longsheng, LI Rui. Design and test of intelligent spraying unmanned vehicle for greenhouse tomato based on YOLOv4-tiny[J]. Journal of Intelligent Agricultural Mechanization, 2023, 4(2): 44-52.

References

［1］张瑞花, 兰超杰, 刘雯, 等. 生物炭对反季节露地樱桃番茄生长及产量品质的影响［J］. 分子植物育种, 2019, 17(14): 4831-4839.
ZHANG Ruihua, LAN Chaojie, LIU Wen, et al. Effect of biochar on growth, yield and quality of openfield cherry tomato in counter season ［J］. Molecular Plant Breeding, 2019, 17(14): 4831-4839.
［2］　张佼, 屈锋, 朱玉尧, 等. 增施有机肥和微生物菌剂对春季杨凌设施番茄产量和品质的影响［J］. 西北农业学报, 2019, 28(5): 767-773.
ZHANG Jiao, QU Feng, ZHU Yuyao, et al. Effects of more organic fertilizer and microbial agents on yield and quality of spring greenhouse tomato in Yangling ［J］. Acta Agriculturae Borealioccidentalis Sinica, 2019, 28(5): 767-773.
［3］　CARILLO P, KYRIACOU M C, ELNAKHEL C, et al. Sensory and functional quality characterization of protected designation of origin ‘Piennolo del Vesuvio cherry tomato landraces from CampaniaItaly ［J］. Food Chemistry, 2019, 292: 166-175.
［4］　李君明, 项朝阳, 王孝宣, 等. “十三五”我国番茄产业现状及展望［J］. 中国蔬菜, 2021(2): 13-20.
LI Junming, XIANG Chaoyang, WANG Xiaoxuan, et al. Current situation of tomato industry in China during ‘The Thirteenth Fiveyear Plan period and future prospect ［J］. China Vegetables, 2021(2): 13-20.
［5］　王作娟. 温室喷药机设计及其变量施药系统研究［D］. 青岛: 青岛理工大学, 2018.
WANG Zuojuan. Design of greenhouse spraying machine and study on variable spraying ［D］. Qingdao: Qingdao University of Technology, 2018.
［6］　姜振龙. 自动化技术在农业机械化生产中的应用与发展趋势［J］. 农机使用与维修, 2021(1): 121-122.
［7］　GAO C, QI L, WU Y, et al. Design and testing of a selfpropelled airblowing greenhouse sprayer ［C］∥ 2017 ASABE Annual International Meeting. American Society of Agricultural and Biological Engineers, 2017: 1.
［8］　赵云月, 刘明普, 王树林, 等. 一种小型互换式大棚自动喷药机构设计［J］. 佳木斯大学学报(自然科学版), 2020, 38(2): 81-84.
ZHAO Yunyue, LIU Mingpu, WANG Shulin, et al. Design of a small interchangeable greenhouse automatic spraying mechanism ［J］. Journal of Jiamusi University(Natural Science Edition), 2020, 38(2): 81-84.
［9］　张梅, Daniel K F, 马伟. 温室智能装备系列之九十六—新型背负式电动喷药机的设计［J］. 农业工程技术, 2017, 37(25): 41-42.
［10］　OBERTI R, MARCHI M, TIRELLI P, et al. Selective spraying of grapevines for disease control using a modular agricultural robot ［J］. Biosystems Engineering, 2016, 146: 203-215.
［11］　王国伟, 刘嘉欣. 基于卷积神经网络的玉米病害识别方法研究［J］. 智能化农业装备学报（中英文）, 2021, 2(1): 64-70.
WANG Guowei, LIU Jiaxin. Research on corn disease recognition method based on convolutional neural network ［J］. Journal of Intelligent Agricultural Mechanization (in Chinese and English), 2021, 2(1): 64-70.
［12］　CARILLO P, KYRIACOU M C, ELNAKHEL C, et al. Sensory and functional quality characterization of protected designation of origin ‘Piennolo del Vesuvio cherry tomato landraces from CampaniaItaly ［J］. Food Chemistry, 2019, 292: 166-175.
［13］　WANG C Y, BOCHKOVSKIY A, LIAO H Y M. Scaledyolov4: Scaling cross stage partial network ［C］∥ Proceedings of the IEEE/cvf conference on computer vision and pattern recognition. 2021: 13029-13038.
［14］　JIANG Z, ZHAO L, LI S, et al. Realtime object detection method based on improved YOLOv4tiny ［J］. arXiv preprint arXiv: 2011.04244, 2020.
［15］　孟志军, 颜丙新, 尹彦鑫, 等. 非结构农田环境机器视觉障碍物检测方法［J］. 智能化农业装备学报（中英文）, 2021, 2(2): 1-6.
MENG Zhijun, YAN Bingxin, YIN Yanxin, et al. Machine vision obstacle detection method in unstructured farmland environment ［J］. Journal of Intelligent Agricultural Mechanization(in Chinese and English), 2021, 2(2): 1-6.
［16］　SUN X, FANG W, GAO C, et al. Remote estimation of grafted apple tree trunk diameter in modern orchard with RGB and point cloud based on SOLOv2［J］. Computers and Electronics in Agriculture, 2022, 199: 197209.
［17］　FU L, GAO F, WU J, et al. Application of consumer RGB-D cameras for fruit detection and localization in field: A critical review［J］. Computers and Electronics in Agriculture, 2020, 177, 105687.
［18］　周俊, 何永强. 农业机械导航路径规划研究进展［J］. 农业机械学报, 2021, 52(9): 1-14.
ZHOU Jun, HE Yongqiang. Research progress on navigation path planning of agricultural machinery ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(9): 1-14.
［19］　贾全, 张小超, 苑严伟, 等. 拖拉机自动驾驶系统上线轨迹规划方法［J］. 农业机械学报, 2018, 49(4): 36-44.
JIA Quan, ZHANG Xiaochao, YUAN Yanwei, et al. Guided trajectory planning method for tractor autopilot system ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(4): 36-44.
［20］　毛婷婷, 董淑娴, 薛金林. 农业机器人车辆人机协作控制的动态功能分配研究［J］. 智能化农业装备学报（中英文）, 2020, 1(1): 24-31.
MAO Tingting, DONG Shuxian, XUE Jinlin. Dynamic function allocation of agricultural robot vehicle controlled by manmachine cooperation dynamic function allocation of agricultural robot vehicle controlled by manmachine cooperation ［J］. Journal of Intelligent Agricultural Mechanization (in Chinese and English), 2020, 1(1): 24-31.
［21］　HOSSEIN M, TAMER I, JACEK M Z. Radialbasis function interpolation and galerkin projection for direct trajectory optimization and costate estimation ［J］. IEEE/CAA Journal of AutomaticaSinica, 2021, 8(8): 1380-1388.
［22］　XI Z, XU A, KOU Y, et al. Target maneuver trajectory prediction based on RBF neural network optimized by hybrid algorithm［J］. Journal of Systems Engineering and Electronics, 2021, 32(2): 498-516.
［23］　吴爱国, 刘海亭, 董娜. 机械臂神经网络非奇异快速终端滑模控制［J］. 农业机械学报, 2018, 49(2): 395-404, 240.
WU Aiguo, LIU Haiting, DONG Na. Nonsingular fast terminal sliding mode control of robotic manipulators based on neural networks ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(2): 395-404, 240.

[1]	HUANG Chenglong, ZHANG Zhongfu, LU Zhihao, ZHANG Xiaojun, ZHU Longfu, YANG Wanneng. Leaf grading for cotton verticillium wilt based on VFNet-Improved and Deep Sort [J]. Journal of Intelligent Agricultural Mechanization, 2023, 4(2): 12-21.
[2]	XIAO Zhangna, LUO Lufeng, CHEN Mingyou, WANG Jinhai, LU Qinghua, LUO Shaoming. Detection of grapes in orchard environment based on improved YOLO-v4 [J]. Journal of Intelligent Agricultural Mechanization, 2023, 4(2): 35-43.