基于改进YOLOv3的玉米病害识别方法

doi:10.13733/j.jcam.issn.2095-5553.2024.07.040

摘要/Abstract

摘要： 为提高玉米作物病害叶片识别模型的准确性，提出改进YOLOv3的玉米病害识别方法。首先，为获得更深的玉米疾病特征，通过更改浅特征图比例和添加第四个检测层，分别修改YOLOv3网络体系结构为YOLOv3-M1和YOLOv3-M2。然后，采用改进的K-means算法进行聚类，获得的锚框倾向于数据集的真实边界框。最后，为每个类别添加一个平衡因子，并对不同类别中样本的难度进行加权来修改损失函数，使得模型能够找到边界盒预测与类别预测之间的最佳点，使算法获得最佳检测效果。结果表明，改进的YOLOv3-M1和YOLOv3-M2模型在测试集上的准确率分别高达95.63%和97.59%，相比YOLOv3模型，识别准确率分别提高4.15%和6.28%，识别准确率在玉米数据集上得到大幅度提高。

关键词: 玉米, 深度学习, 病害识别, YOLOv3模型, 损失函数

Abstract: In order to improve the accuracy of maize disease leaf recognition model, an improved YOLOv3 maize disease recognition method was proposed. First of all, in order to obtain deeper maize disease characteristics, the YOLOv3 network architecture was modified to YOLOv3-M1 and YOLOv3-M2 by changing the proportion of shallow feature map and adding a fourth detection layer. Then, the improved K-means algorithm was used for clustering, and the obtained anchor frame tended to be the true boundary frame of the data set. Finally, a balance factor was added for each category, and the difficulty of samples in different categories was weighted to modify the loss function, so that the model could find the best point between the boundary box prediction and the category prediction, so that the algorithm could obtain the best detection effect. The test results show that the accuracy of the improved YOLOv3-M1 and YOLOv3-M2 models in the test set is as high as 95.63% and 97.59%, respectively. Compared with the YOLOv3 model, the recognition accuracy is increased by 4.15% and 6.28%, respectively, and the recognition accuracy is greatly improved in the corn data set.

Key words: maize, deep learning, disease recognition, YOLOv3 model, loss function

中图分类号:

S24
TP391.4

张继成, 黄向党. 基于改进YOLOv3的玉米病害识别方法[J]. 中国农机化学报, 2024, 45(7): 269-275.

Zhang Jicheng, Huang Xiangdang. Maize disease identification method based on improved YOLOv3[J]. Journal of Chinese Agricultural Mechanization, 2024, 45(7): 269-275.

参考文献

［1］　Zhang X, Qiao Y, Meng F, et al. Identification of maize leaf diseases using improved deep convolutional neural networks ［J］. IEEE Access, 2018, 6: 30370-30377.
［2］　Bai, Xiaodong, Cao, et al. Rice heading stage automatic observation by multiclassifier cascade based rice spike detection method ［J］. Agricultural & Forest Meteorology, 2018, 259: 260-270.
［3］　Pattnaik G, Shrivastava V K, Parvathi K. Transfer learningbased framework for classification of pest in tomato plants ［J］. Applied Artificial Intelligence, 2020, 34(13): 981-993.
［4］　Xiong Y, Liang L, Wang L, et al. Identification of cash crop diseases using automatic image segmentation algorithm and deep learning with expanded dataset ［J］. Computers and Electronics in Agriculture, 2020, 177: 105712.
［5］　Sujatha R, Chatterjee J M, Jhanjhi N Z, et al. Performance of deep learning vs machine learning in plant leaf disease detection ［J］. Microprocessors and Microsystems, 2021, 80: 103615.
［6］　Chen X, Zhou G, Chen A, et al. Identification of tomato leaf diseases based on combination of ABCK-BWTR and B-ARNet ［J］. Computers and Electronics in Agriculture, 2020, 178: 105730.
［7］　Zhang Y, Song C, Zhang D. Deep learningbased object detection improvement for tomato disease ［J］. IEEE Access, 2020, 8: 56607-56614.
［8］　Zhong Y, Zhao M. Research on deep learning in apple leaf disease recognition ［J］. Computers and Electronics in Agriculture, 2020, 168: 105146.
［9］　Waheed A, Goyal M, Gupta D, et al. An optimized dense convolutional neural network model for disease recognition and classification in corn leaf ［J］. Computers and Electronics in Agriculture, 2020, 175: 105456.
［10］　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］. 中国农机化学报, 2021, 42(2): 139-145.
Wang Guowei, Liu Jiaxin. Research on corn disease recognition method based on convolutional neural network ［J］. Journal of Chinese Agricultural Mechanization, 2021, 42(2): 139-145.
［11］　许景辉, 邵明烨, 王一琛, 等. 基于迁移学习的卷积神经网络玉米病害图像识别［J］. 农业机械学报, 2020, 51(2): 230-236, 253.
Xu Jinghui, Shao Mingye, Wang Yichen, et al. Recognition of corn leaf spot and rust based on transfer learning with convolutional neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(2): 230-236, 253.
［12］　樊湘鹏, 周建平, 许燕, 等. 基于改进卷积神经网络的复杂背景下玉米病害识别［J］. 农业机械学报, 2021, 52(3): 210-217.
Fan Xiangpeng, Zhou Jianping, Xu Yan, et al. Corn disease recognition under complicated background based on improved convolutional neural network ［J］. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(3): 210-217.
［13］　董萍, 卫梦华, 时雷, 等. 迁移学习在玉米叶片病害识别中的研究与应用［J］. 中国农机化学报, 2022, 43(3): 146-152.
Dong Ping, Wei Menghua, Shi Lei, et al. Research and application of transfer learning in identification of maize leaf diseases ［J］. Journal of Chinese Agricultural Mechanization, 2022, 43(3): 146-152.
［14］　张开兴, 吕高龙, 贾浩, 等. 基于图像处理和BP神经网络的玉米叶部病害识别［J］. 中国农机化学报, 2019, 40(8): 122-126.
Zhang Kaixing, Lü Gaolong, Jia Hao, et al. Identification of corn leaf disease based on image processing and BP neural network ［J］. Journal of Chinese Agricultural Mechanization, 2019, 40(8): 122-126.
［15］　Rezatofighi H, Tsoi N, Gwak J Y, et al. Generalized intersection over union: A metric and a loss for bounding box regression ［C］. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 658-666.
［16］　Redmon J, Farhadi A. YOLOv3: An incremental improvement ［J］. Arxiv Preprint Arxiv: 1804.02767, 2018.

[1]	娄秀华, 李茂峰, 杜岳峰, 毛恩荣, 付磊. 玉米联合收获机清选控制系统设计与试验[J]. 中国农机化学报, 2024, 45(7): 1-8.
[2]	李向阳, 李晓康, , 张锋伟, 宋学锋, 潘伟阳, 侯晶涛. 青贮玉米收获机喂入切碎试验台设计与试验[J]. 中国农机化学报, 2024, 45(7): 41-47.
[3]	王宝梁, 王政, 孟为国, 陆凯, 贾寿良, 薛金林. 基于大豆玉米带状复合种植下的分带式喷杆喷药机设计与试验[J]. 中国农机化学报, 2024, 45(7): 60-67.
[4]	唐可记, 孙文磊, 杨炀, 孔德龙. 玉米收获机发动机服役状态趋势分析与预警[J]. 中国农机化学报, 2024, 45(7): 160-165.
[5]	吴利刚, 吕媛媛, 周倩, 陈乐, 张梁, 史建华. 基于改进YOLOv5的轻量级黄花成熟检测方法[J]. 中国农机化学报, 2024, 45(7): 235-242.
[6]	单海勇, 严旖旎, 张晋, 刘旭杰, 韩笑, 刘建. 大豆—玉米带状复合种植耕种机械化研究进展[J]. 中国农机化学报, 2024, 45(6): 42-52.
[7]	李鑫, 王占滨, 张银平, 张雨滋, 陈美舟, 周华. 不同品种玉米机收适宜性试验[J]. 中国农机化学报, 2024, 45(6): 58-62.
[8]	雷浩, 苑迎春, 何振学. 基于多尺度卷积和注意力机制的枣品种识别[J]. 中国农机化学报, 2024, 45(6): 135-141.
[9]	王宏轩, 于珍珍, 李海亮, 汪春, 严晓丽, 邹华芬. 基于GA-BP神经网络的鲜食玉米产量预测[J]. 中国农机化学报, 2024, 45(6): 156-162.
[10]	崔海朋, 秦朝旭, 马志宇. 基于深度学习的鱼类特征点检测与体征识别方法[J]. 中国农机化学报, 2024, 45(6): 201-207.
[11]	黄尧, 何敬, 付饶, 刘刚, , 林远杨. YOLOv5s-CBAM算法在福寿螺虫卵识别中的应用分析[J]. 中国农机化学报, 2024, 45(6): 223-228.
[12]	周康乔, 刘向阳, 郑特驹. 改进YOLOv5的小目标多类别农田害虫检测算法研究[J]. 中国农机化学报, 2024, 45(6): 235-241.
[13]	张红梅, 张晨明, 朱晨辉, 祝英豪, 李志杰, 李鹏昌. 玉米免耕播种机振动特性及对排种器排种性能的影响[J]. 中国农机化学报, 2024, 45(5): 1-8.
[14]	陶旭, , 余富强, , 蔡金金, 么炜, , 刘博, . 面向激光雷达点云数据的多结构树种识别[J]. 中国农机化学报, 2024, 45(5): 168-175.
[15]	漆海霞, , , 李承杰, 黄桂珍. 基于轻量化YOLOv4的死淘鸡目标检测算法[J]. 中国农机化学报, 2024, 45(5): 195-201.