圣女果温室巡检机器人系统设计与试验

doi:10.13733/j.jcam.issn.2095-5553.2024.01.039

摘要/Abstract

摘要： 为解决传统农业生产方式中人工巡检成本高、劳动强度大、速度慢等问题，设计一种圣女果温室巡检机器人系统，融合自动控制技术、机器视觉技术和深度学习技术，实现对圣女果的准确识别和计数。通过机器视觉提取工作路径和红外传感器避障实现机器人自动导航功能；并提出一种改进型YOLOv4-tiny模型对圣女果进行检测，该模型在YOLOv4-tiny的基础上增加52×52的特征层和注意力机制，提高小目标检测的识别精度。试验结果表明，该巡检机器人以0.2m/s的速度行进时可以准确沿着预定路径工作，改进的YOLOv4-tiny-Tomato模型在温室环境中对成熟和未成熟圣女果的平均识别精度分别为98.7%和98.0%，F1值分别达到96.71%和95.8%，实时帧率达到36帧/s。本研究可为农业领域的智能化巡检和精细管理提供新的思路和技术支持。

关键词: 温室大棚, 巡检机器人, 自动导航, 深度学习, 目标检测, YOLOv4-tiny

Abstract: In order to solve the problems of high cost, high labor intensity and slow speed of manual inspection in traditional agricultural production mode, a cherry tomatoes greenhouse inspection robot system was designed, which integrated automatic control technology, machine vision technology and deep learning technology to achieve accurate identification and counting of cherry tomatoes. The robots automatic navigation function is realized by extracting the working path through machine vision and avoiding the obstacle by infrared sensor. An improved YOLOv4-tiny model was proposed to detect cherry tomatoes. The model added 52×52 feature layer and attention mechanism on the basis of YOLOv4-tiny to improve the recognition accuracy of small target detection. The test results show that the inspection robot can accurately work along the predetermined path when traveling at a speed of 0.2m/s. The average recognition accuracy of the improved YOLOv4-tiny-Tomato model for mature and immature cherry tomatoes in the greenhouse environment is 98.7% and 98.0%, and the F1 value reaches 96.71% and 95.8%, respectively. The realtime frame rate reaches 36 frames/s. This research can provide new ideas and technical support for intelligent inspection and fine management in agricultural field.

Key words: greenhouse, inspection robot, automatic navigation, deep learning, object detection, YOLOv4-tiny

中图分类号:

S24: TP391

侯炳法, 李小敏, 牟向伟, 姚华平. 圣女果温室巡检机器人系统设计与试验[J]. 中国农机化学报, 2024, 45(1): 285-294.

Hou Bingfa, Li Xiaomin, Mou Xiangwei, Yao Huaping. Design and experiment of inspection robot system in cherry tomato greenhouse[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(1): 285-294.

参考文献

［1］吕亚荣, 周诚. 论农业是国民经济的基础［J］. 学理论, 2009(17): 64-67.
［2］本刊综合报道. 小小圣女果红火振兴路［J］. 农村新技术, 2022(4): 60-61.
［3］王柯, 付怡然, 彭向阳, 等. 无人机低空遥感技术进展及典型行业应用综述［J］. 测绘通报, 2017(S1): 79-83.
Wang Ke, Fu Yiran, Peng Xiangyang, et al. Overview of UAV low altitude remote sensing technology and application in typical industries ［J］. Bulletin of Surveying and Mapping, 2017(S1): 79-83.
［4］黄山, 吴振升, 任志刚, 等. 电力智能巡检机器人研究综述［J］. 电测与仪表, 2020, 57(2): 26-38.
Huang Shan, Wu Zhensheng, Ren Zhigang, et al. Review of electric power intelligent inspection robot ［J］. Electrical Measurement and Instrumentation, 2020, 57(2): 26-38.
［5］杨剑超, 姜学玲, 王德涛, 等. 农业物联网巡检系统在设施温棚的应用与效益分析［J］. 农业工程技术, 2017, 37(24): 55-57.
［6］张世昂, 付根平. 农业智能巡检小车的设计［J］. 中国农机化学报, 2018, 39(4): 82-89.
Zhang Shiang, Fu Genping. Design of intelligent routing inspection car for agriculture ［J］. Journal of Chinese Agricultural Mechanization, 2018, 39(4): 82-89.
［7］赵杰文, 刘木华, 杨国彬. 基于HIS颜色特征的田间成熟番茄识别技术［J］. 农业机械学报, 2004(5): 122-124.
Zhao Jiewen, Liu Muhua, Yang Guobin. Discrimination of mature tomato based on HIS color space in natural outdoor scenes ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2004(5): 122-124.
［8］蒋焕煜, 彭永石, 申川, 等. 基于双目立体视觉技术的成熟番茄识别与定位［J］. 农业工程学报, 2008(8): 279-283.
Jiang Huanyu, Peng Yongshi, Shen Chuan, et al. Recognizing and locating ripe tomatoes based on binocular stereovision technology ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2008(8): 279-283.
［9］陶彦辉, 尹君驰, 方菲. 基于RGB颜色模型的番茄识别系统设计［J］. 机械研究与应用, 2015, 28(1): 159-160.
Tao Yanhui, Yin Junchi, Fang Fei. Design of tomato identification system based on RGB color model ［J］. Mechanical Research & Application, 2015, 28(1): 159-160.
［10］周惠汝, 吴波明. 深度学习在作物病害图像识别方面应用的研究进展［J］. 中国农业科技导报, 2021, 23(5): 61-68.
Zhou Huiru, Wu Boming. Advances in research on deep learning for crop disease lmage recognition ［J］. Journal of Agricultural Science and Technology, 2021, 23(5): 61-68.
［11］李小敏, 张日红, 陈天赐, 等. 基于深度学习的林下落果识别方法与试验［J］. 中国农机化学报, 2021, 42(9): 202-208.
Li Xiaomin, Zhang Rihong, Chen Tianci, et al. Identification method and experiment of fallen fruit based on deep learning ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(9): 202-208.
［12］傅隆生, 冯亚利, Tola Elkamil, 等. 基于卷积神经网络的田间多簇猕猴桃图像识别方法［J］. 农业工程学报, 2018, 34(2): 205-211.
Fu Longsheng, Feng Yali, Tola Elkamil, et al. lmage recognition method of multicluster kiwifruit in field based on convolutional neural networks ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(2): 205-211.
［13］赵德安, 吴任迪, 刘晓洋, 等. 基于YOLO深度卷积神经网络的复杂背景下机器人采摘苹果定位［J］. 农业工程学报, 2019, 35(3): 164-173.
Zhao Dean, Wu Rendi, Liu Xiaoyang, et al. Apple positioning based on YOLO deep convolutional neural network for picking robot in complex background ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(3): 164-173.
［14］刘芳, 刘玉坤, 林森, 等. 基于改进型YOLO的复杂环境下番茄果实快速识别方法［J］. 农业机械学报, 2020, 51(6): 229-237.
Liu Fang, Liu Yukun, Lin Sen, et al. Fast recognition method for tomatoes under complex environments based on improved YOLO ［J］. Transactions of the Chinese Society of Agricultural Machinery, 2020, 51(6): 229-237.
［15］苏斐, 张泽旭, 赵妍平, 等. 基于轻量化YOLO-v3的绿熟期番茄检测方法［J］. 中国农机化学报, 2022, 43(3): 132-137.
Su Fei, Zhang Zexu, Zhao Yanping, et al. Detection of mature green tomato based on lightweight YOLO-v3 ［J］.Journal of Chinese Agricultural Mechanization, 2022, 43(3): 132-137.
［16］张伏, 陈自均, 鲍若飞, 等. 基于改进型YOLOv4-LITE轻量级神经网络的密集圣女果识别［J］. 农业工程学报, 2021, 37(16): 270-278.
Zhang Fu, Chen Zijun, Bao Ruofei, et al. Recognition of dense cherry tomatoes based on improved YOLOv4-LITE lightweight neural network ［J］. Transactions of the Chinese Society of Agricultural Engineering, 2021, 37(16): 270-278.
［17］王树文, 闫成新, 张天序, 等. 数学形态学在图像处理中的应用［J］. 计算机工程与应用, 2004(32): 89-92.
Wang Shuwen, Yan Chengxin, Zhang Tianxu, et al. Application of mathematical morphology in image processing ［J］. Computer Engineering and Applications, 2004(32): 89-92.
［18］周晓彦, 王珂, 李凌燕. 基于深度学习的目标检测算法综述［J］. 电子测量技术, 2017, 40(11): 89-93.
Zhou Xiaoyan, Wang Ke, Li Lingyan. Review of object detection based on deep learning ［J］. Electronic Measurement Technology, 2017, 40(11): 89-93.
［19］ Li Xu, Pan Jiandong, Xie Fangping, et al. Fast and accurate green pepper detection in complex backgrounds via an improved Yolov4-tiny model ［J］. Computers and Electronics in Agriculture, 2021,191: 106503.
［20］ Guo Menghao, Xu Tianxing, Liu Jiangjiang, et al. Attention mechanisms in computer vision: A survey ［J］. Computational Visual Media, 2022, 8(3): 331-368.
（上接第243页）
［17］邵超, 赵帅, 赵有信, 等. 太阳能光伏直流蓄冷冷库温度场模拟和实验研究［J］. 现代信息科技, 2020, 4(7): 29-32.
Shao Chao, Zhao Shuai, Zhao Youxin, et al. Simulation and experimental study on temperature field of solar photovoltaic DC cold storage ［J］. Modern Information Technology, 2020, 4(7): 29-32.
［18］孙锦涛, 游辉, 谢晶. 蓄冷板对冷库保温的影响实验［J］. 包装工程, 2022, 43(13): 107-116.
Sun Jintao, You Hui, Xie Jing. Experimental research on influence of cold storage plate on insulation of cold storage ［J］. Packaging Engineering, 2022, 43(13): 107-116.
［19］李振华, 李征涛, 王芳, 等. 冷库热气融霜与电热融霜的对比分析［J］. 制冷与空调(四川), 2011, 25(6): 577-579.
Li Zhenhua, Li Zhengtao, Wang Fang, et al. The comparative analysis of hot gas defrost and electricity defrost in cold storage ［J］.Refrigeration and Air Conditioning, 2011, 25(6): 577-579.
［20］赵松松, 杨昭, 陈爱强, 等. 微型冷库复合加热循环除霜系统的研制与试验［J］. 农业工程学报, 2015, 31(2): 306-311.
Zhao Songsong, Yang Zhao, Chen Aiqiang, et al. Development and experiment about recombination heating circulation defrosting system of mini cold storage house ［J］.Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(2): 306-311.

[1]	叶荣, 马自飞, 高泉, 李彤, 邵郭奇, 王白娟. 基于改进YOLOv5sECAASFF算法的茶叶病害目标检测[J]. 中国农机化学报, 2024, 45(1): 244-251.
[2]	方俊泽, 郭正, 李歌, 邢素霞, 王瑜. 基于改进Swin-Transformer的柑橘病叶分类模型[J]. 中国农机化学报, 2024, 45(1): 252-258.
[3]	王瑞彬, 杨世忠, 高升. 融合残差网络与注意力机制的草莓检测[J]. 中国农机化学报, 2024, 45(1): 266-273.
[4]	林森, , 许童羽, 葛禹豪, 马璟, 孙添龙, 赵春江. 基于改进YOLOv5l的设施番茄3D信息检测方法[J]. 中国农机化学报, 2024, 45(1): 274-284.
[5]	吴潇, 杨颖, 刘刚, 张倩, 宁远霖. 基于迁移学习和改进ResNet34的猪个体识别方法[J]. 中国农机化学报, 2023, 44(9): 214-221.
[6]	孙松丽, 温宏愿, 刘宾龄, 钟锦扬, 毛政兴. 基于ROS和深度学习的杏鲍菇智能分选系统设计[J]. 中国农机化学报, 2023, 44(8): 95-102.
[7]	高芳征, 汤文俊, 陈光明, 黄家才. 基于改进YOLOv3的复杂环境下西红柿成熟果实快速识别[J]. 中国农机化学报, 2023, 44(8): 174-183.
[8]	李宗南, 蒋怡, 王思, 李源洪, 黄平, 魏鹏. 基于YOLOv5模型的飞蓬属入侵植物目标检测[J]. 中国农机化学报, 2023, 44(7): 200-206.
[9]	王春桃, , , , 梁炜健, 郭庆文, 钟浩, 甘雨, 肖德琴, , . 农业害虫智能视觉检测研究综述[J]. 中国农机化学报, 2023, 44(7): 207-213.
[10]	陈维美, 刘馨蔚, 王铁伟, 徐文凯, 李娟. 基于两级融合深度学习的松材线虫病识别[J]. 中国农机化学报, 2023, 44(7): 214-219.
[11]	李明, 丁智欢, 赵靖暄, 陈思铭, 李文勇, 杨信廷. 基于改进YOLOv5s的日光温室黄瓜霜霉病孢子囊检测计数方法[J]. 中国农机化学报, 2023, 44(5): 63-70.
[12]	杨承磊, 兰玉彬, 王庆雨, 别晓婷, 单常峰, 王国宾, . 神经网络在温室小气候预测中的应用[J]. 中国农机化学报, 2023, 44(5): 89-99.
[13]	付豪, , 赵学观, 翟长远, , 郑康, 郑申玉, 王秀. 基于深度学习的杂草识别方法研究进展[J]. 中国农机化学报, 2023, 44(5): 198-207.
[14]	段宇飞, 董庚, 孙记委, 王焱清, . 基于SE-ResNet网络的油茶果果壳与茶籽分选模型[J]. 中国农机化学报, 2023, 44(4): 89-95.
[15]	张俊峰, 张唐娟, 肖进, 王琢, 田满洲, 何雨霜. 池塘养殖船自动导航系统设计与试验[J]. 中国农机化学报, 2023, 44(3): 49-54.