基于机器学习的中耕期甘蔗幼苗识别定位*

doi:10.13733/j.jcam.issn.20955553.2021.11.20

中国农机化学报 ›› 2021, Vol. 42 ›› Issue (11): 130-137.DOI: 10.13733/j.jcam.issn.20955553.2021.11.20

基于机器学习的中耕期甘蔗幼苗识别定位^*

李威¹, 李尚平¹, 潘家枫², 李凯华¹, 闫昱晓¹

1.广西民族大学人工智能学院,南宁市,530006;
2.广西大学机械工程学院,南宁市,530004

收稿日期:2021-03-15 修回日期:2021-09-26 出版日期:2021-11-15 发布日期:2021-11-15
通讯作者: 李尚平,男,1956年生,广西博白人,博士,教授,博导;研究方向为农业机械化工程。E-mail: spli501@vip.sina.com
作者简介:李威,男,1997年生,安徽淮南人,硕士研究生;研究方向为图像识别与智能系统、农业智能化。E-mail: 603727846@qq.com
基金资助:
*亚热带农业生物资源保护与利用国家重点实验室科教结合创新基地课题(SKLCUSA—a202007)

Recognition and location of sugarcane seedlings in intertillage period based on machine learning

Li Wei¹, Li Shangping¹, Pan Jiafeng¹, Li Kaihua¹, Yan Yuxiao¹

1. School of Artificial Intelligence, Guangxi University for Nationalities, Nanning, 530006, China;
2. School of Mechanical Engineering, Guangxi University, Nanning, 530004, China

Received:2021-03-15 Revised:2021-09-26 Online:2021-11-15 Published:2021-11-15

摘要/Abstract

摘要： 针对甘蔗中耕培土过程中,由于甘蔗植株种植垄间距的改变,导致中耕培土机难以兼顾左右两侧垄的甘蔗植株而引起甘蔗植株培土不到位、不充分的问题,即“火山口”现象,结合多功能甘蔗中耕培土机械的开发,提出一种基于机器学习的中耕期甘蔗幼苗识别定位和坐标分类计算方法。该方法通过YOLOv4网络建立识别网络模型,对中耕期甘蔗幼苗根部和土壤接触的局部区域进行识别定位和坐标获取,然后采用支持向量机将坐标数据分成两组,并分别对每组坐标数据进行实时计算处理,得到两组坐标数据的倾斜值,后续中耕设备将根据倾斜值的数值大小进行调整,改变供土量和供土方向。试验结果表明,采用基于YOLOv4识别网络模型对甘蔗幼苗的识别准确率可达95.50%,采用支持向量机对甘蔗幼苗坐标分类的准确率可达92.60%,实现了对中耕期甘蔗幼苗的实时动态识别及分类计算,为智能甘蔗中耕植保联合作业机械的开发提供数据基础。

关键词: 甘蔗中耕培土, YOLOv4网络, 识别定位, 分类计算, 支持向量机, 倾斜值

Abstract: Due to the change of the ridge spacing of sugarcane plants, it is difficult for the conventional cultivator to control the quality of soil cultivation on both sides of the ridge, which causes inadequate soil cultivation, i.e., the “crater”phenomenon. We thus developed a multi-functional sugarcane intertillage cultivator and proposed a machine learning-based method to locate and identify sugarcane seedlings and calculate the coordinate classification during the intertillage period. Based on the YOLOv4 network, the method established a recognition model, which identifies and locates the area between the roots and the soil and accesses the coordinates. Then, the Support Vector Machine divided the coordinate data into two groups and processed them separately in real-time to obtain the tilt value. Finally, the data were adjusted according to the tilt value to modify the quantity and direction of soil supply. The results of the present study indicate that in use of the YOLOv4 recognition model, the recognition accuracy can reach 95.50%, and the classification accuracy using the SVM is 92.60%, which realizes the real-time dynamic recognition and classification calculation of sugarcane seedlings in the intertillage period, and provided data foundation for the development of intelligent sugarcane protection and joint operation machinery.

Key words: soil cultivation for sugarcane seedlings, YOLOv4 network, recognition and location, classification calculation, Support Vector Machine, tilt value

中图分类号:

TP391.4

李威, 李尚平, 潘家枫, 李凯华, 闫昱晓. 基于机器学习的中耕期甘蔗幼苗识别定位^*[J]. 中国农机化学报, 2021, 42(11): 130-137.

Li Wei, Li Shangping, Pan Jiafeng, Li Kaihua, Yan Yuxiao. Recognition and location of sugarcane seedlings in intertillage period based on machine learning[J]. Journal of Chinese Agricultural Mechanization, 2021, 42(11): 130-137.

参考文献

[1] 廖平伟, 张华, 罗俊, 等. 我国甘蔗生产现状及竞争力分析[J]. 中国糖料, 2010(4): 44-45.
Liao Pingwei, Zhang Hua, Luo Jun, et al. Present status and potential competition of sugarcane production in China [J]. Sugar Crops of China, 2010(4): 44-45.
[2] 曾芳芳, 朱朝枝, 郑传芳. 产业融合视域下甘蔗产业发展研究——基于广西甘蔗主产区数据的分析[J]. 黑龙江八一农垦大学学报, 2020, 32(5): 121-128.
Zeng Fangfang, Zhu Chaozhi, Zheng Chuanfang. Study on sugarcane industry development from the perspective of industry convergence—based on the data of main sugarcane producing region in Guangxi [J]. Journal of Heilongjiang Bayi Agricultural University, 2020, 32(5): 121-128.
[3] 王丽娉. 甘蔗生产全程机械化作业农艺与农机配套规划方案[J]. 农机质量与监督, 2017(1): 32-34, 29.
[4] 农宏亮, 曾伯胜, 范雨杭. 甘蔗中耕施肥培土技术及发展趋势分析[J]. 广西农业机械化, 2017(3): 10-13.
[5] 杨云福, 王华准, 汤瑞学, 等. 3ZSP-2型甘蔗中耕施肥培土机的使用调整与维护保养[J]. 农机使用与维修, 2019(12): 8-10.
Yang Yunfu, Wang Huazhun, Tang Ruixue, et al. Adjustment and maintenance of 3ZSP-2 sugarcane cultivator-cum-fertilizer-applicator [J]. Agricultural Mechanization Using & Maintenance, 2019(12): 8-10.
[6] 吕美巧, 刘丽敏, 吴玉. V型深沟甘蔗中耕施肥起垄培土机的研究设计[J]. 浙江大学学报(农业与生命科学版), 2019, 45(2): 251-255.
Lü Meiqiao, Liu Limin, Wu Yu. Research and design of V-shaped deep trench sugarcane cultivating machine [J]. Journal of Zhejiang University(Agriculture and Life Sciences), 2019, 45(2): 251-255.
[7] 陈晓. 久菱牌3ZP-0.8型甘蔗中耕培土机的研发[J]. 广西农业机械化, 2010(4): 28-30.
[8] 黄敞, 刘海滨, 王迎, 等. 甘蔗中耕施肥机发展探讨[J]. 农业装备与车辆工程, 2014, 52(11): 14-17.
Huang Chang, Liu Haibin, Wang Ying, et al. Study on development of sugarcane intertillage fertilizing machine [J]. Agricultural Equipment & Vehicle Engineering, 2014, 52(11): 14-17.
[9] 农浩智, 农冠松. 不同甘蔗行距对产量的影响[J]. 广西蔗糖, 1998(1): 10-14.
Nong Haozhi, Nong Guansong. The effect of different row distance to sugarcane yield [J]. Guangxi Sugar Industry, 1998(1): 10-14.
[10] Shin H C, Roth H R, Gao M, et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning [J]. IEEE Transactions on Medical Imaging, 2016, 35(5): 1285-1298.
[11] Dhakal N, Zihan Z U A, Elseifi M A, et al. Surface identification of top-down, bottom-up, and cement-treated reflective cracks using convolutional neural network and artificial neural networks [J]. Journal of Transportation Engineering Part B Pavements, 2020, 147(1): 04020080.
[12] Li Q, Zhao J, Zhang Y, et al. Imaging reconstruction through strongly scattering media by using convolutional neural networks [J]. Optics Communications, 2020, 477(1): 126341.
[13] Ren X, Kai C, Yang X, et al. A new unsupervised convolutional neural network model for Chinese scene text detection [C]. 2015 IEEE China Summit and International Conference on Signal and Information Processing (China SIP). IEEE, 2015.
[14] Atsushi T, Tetsuya T, Yuka K, et al. Automated classification of lung cancer types from cytological images using deep convolutional neural networks [J]. BioMed Research International, 2017: 1-6.
[15] F Milletari, Navab N, Ahmadi S A. V-Net: Fully convolutional neural networks for volumetric medical image segmentation [C]. 2016 Fourth International Conference on 3D Vision (3DV). IEEE, 2016.
[16] Liu J, Zhang R, Han G, et al. Video action recognition with visual privacy protection based on compressed sensing [J]. Journal of Systems Architecture, 2020, 113(9): 101882.
[17] Caltagirone L, Scheidegger S, Svensson L, et al. Fast LIDAR-based road detection using fully convolutional neural networks [C]. 2017 IEEE Intelligent Vehicles Symposium (IV). IEEE, 2017.
[18] 杨文佳, 朱海龙, 刘靖宇. 基于卷积神经网络的天气现象识别方法研究[J]. 智能计算机与应用, 2019, 9(6): 214-216.
Yang Wenjia, Zhu Hailong, Liu Jingyu. Research of weather phenomena recognition method based on CNN [J]. Intelligent Computer and Applications, 2019, 9(6): 214-216.
[19] 张翠平, 苏光大. 人脸识别技术综述[J]. 中国图象图形学报, 2000(11): 7-16.
Zhang Cuiping, Su Guangda. Human face recognition: A survey [J]. Journal of Image and Graphics, 2000(11): 7-16.
[20] 阮有兵, 徐海黎, 万旭, 等. 适用于嵌入式平台的E-YOLO人脸检测网络研究[J]. 计算机应用与软件, 2020, 37(2): 147-151.
Ruan Youbing, Xu Haili, Wan Xu, et al. E-YOLO face detection network for embedded platform [J]. Computer Applications and Software, 2020, 37(2): 147-151.
[21] 王兵, 乐红霞, 李文璟, 等. 改进YOLO轻量化网络的口罩检测算法[J]. 计算机工程与应用, 2021, 57(8): 62-69.
Wang Bing, Le Hongxia, Li Wenjing, et al. Mask detection algorithm based on improved YOLO lightweight network [J]. Computer Engineering and Applications, 2021, 57(8): 62-69.
[22] 汪京京, 张武, 刘连忠, 等. 农作物病虫害图像识别技术的研究综述[J]. 计算机工程与科学, 2014, 36(7): 1363-1370.
Wang Jingjing, Zhang Wu, Liu Lianzhong, at al. Summary of crop diseases and pests image recognition technology [J]. Computer Engineering & Science, 2014, 36(7): 1363-1370.
[23] 陈旭君, 王承祥, 朱德泉, 等. 基于YOLO卷积神经网络的水稻秧苗行线检测[J]. 江苏农业学报, 2020, 36(4): 930-935.
[24] 朱永宁, 周望, 杨洋, 等. 基于Faster R-CNN的枸杞开花期与果实成熟期识别技术[J]. 中国农业气象, 2020, 41(10): 668-677.
Zhu Yongning, Zhou Wang, Yang Yang, et al. Automatic identification technology of lyceum barbarum flowering period and fruit ripening period based on faster R-CNN [J]. Chinese Journal of Agrometeorology, 2020, 41(10): 668-677.
[25] Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]. Computer Vision & Pattern Recognition. IEEE, 2016.
[26] Bochkovskiy A, Wang C Y, Liao H Y M. YOLOv4: Optimal speed and accuracy of object detection [J]. arXiv preprint, 2020.
[27] Redmon J. Farhadi A. YOLOv3: An incremental improvement [R]. arXiv, 2018.
[28] 张学工. 关于统计学习理论与支持向量机[J]. 自动化学报, 2000(1): 36-46.
Zhang Xuegong.Introduction to statistical learning theory and support vector machines [J]. Acta Automatica Sinica, 2000(1): 36-46.
[29] 奉国和. SVM分类核函数及参数选择比较[J]. 计算机工程与应用, 2011, 47(3): 123-124, 128.
Feng Guohe. Parameter optimizing for support vector machines classification [J].Computer Engineering and Applications, 2011, 47(3): 123-124, 128.

基于机器学习的中耕期甘蔗幼苗识别定位^*

Recognition and location of sugarcane seedlings in intertillage period based on machine learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	翁海勇;许金钗;陶铸;刘江洪;郑金贵;叶大鹏;. 高EGCG含量茶树品种光谱识别模型构建[J]. 中国农机化学报, 2021, 42(6): 111-117.
[2]	张亚军;. 基于改进支持向量机算法的农业害虫图像识别研究[J]. 中国农机化学报, 2021, 42(2): 146-152.
[3]	孔庆好, 吐尔逊·买买提, 赵梦佳. 基于卷积神经网络的拖拉机工况识别[J]. 中国农机化学报, 2021, 42(11): 144-150.