Image Segmentation for Maize Leaf Disease Based on U-Net

doi:10.11924/j.issn.1000-6850.casb2020-0051

Abstract

Abstract:

In this paper, a grading method of maize disease course based on U-Net algorithm model is proposed, which can quickly, accurately and objectively classify the degree of four kinds of common maize leaf diseases. In this method, the semantic segmentation of corn leaf disease spot image is realized by parallel operation of two groups of U-Net models. In the test image segmentation experiment, the MIoU value of disease spot segmentation is 93.63%, and the MIoU value of leaf segmentation is 96.33%, and the operation speed is completed in 1 second. The experimental results show that this study collects data sources by means of mobile phone photos, can achieve rapid grading of maize diseases without relying on professional instruments and equipment, and replace the previous method of disease identification by manual visual inspection. The accuracy and objectivity of disease grading are improved. Combined with the Internet of Things equipment, the model can achieve the goal of early warning of maize diseases, reducing the impact of diseases, increasing both production and income by science and technology benefiting farmers.

Key words: maize diseases, image processing, FCN, U-Net, course grading

CLC Number:

Liu Yongbo, Hu Liang, Cao Yan, Tang Jiangyun, Lei Bo. Image Segmentation for Maize Leaf Disease Based on U-Net[J]. Chinese Agricultural Science Bulletin, 2021, 37(5): 88-95.

Figures/Tables 14

References 30

[1]	武鹏鸣. 我国玉米育种问题及对策分析[J]. 粮食科技与经济, 2019,44(6):90-92.
[2]	沈冰冰. 玉米茎腐病和大斑病生防菌的筛选及其促生作用的研究[D]. 哈尔滨:东北农业大学, 2019.
[3]	李新疆, 王赏贵, 王丹, 等. 基于HSV色彩空间的红枣叶片病斑分割方法[J]. 安徽农学通报, 2020,26(4):85-87.
[4]	马浚诚, 温皓杰, 李鑫星, 等. 基于图像处理的温室黄瓜霜霉病诊断系统[J]. 农业机械学报, 2017,48(2):195-202.
[5]	蒲一鸣. 基于机器学习的水稻病害识别和叶龄检测算法研究[D]. 哈尔滨:哈尔滨工业大学, 2019.
[6]	吴韵清, 吴鹏, 陈北京, 等. 基于残差全卷积网络的图像拼接定位算法[J]. 应用科学学报, 2019,37(5):651-662.
[7]	段杰, 崔志明, 沈艺, 等. 一种改进FCN的肝脏肿瘤CT图像分割方法[J]. 图学学报, 2020,41(1):100-107.
[8]	刘永波, 雷波, 曹艳, 等. 基于深度卷积神经网络的玉米病害识别[J]. 中国农学通报, 2018,34(36):159-164.
[9]	刁智华, 袁万宾, 罗雅雯, 等. 基于图像处理的小麦白粉病病斑生长模型构建[J]. 中国农机化学报, 2019,40(6):158-161.
[10]	Long J, Shelhamer E, Darrell T. Fully Convolutional Networks for Semantic Segmentation[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2014,39(4):640-651. doi: 10.1109/TPAMI.2016.2572683 URL pmid: 27244717
[11]	Evan Shelhamer, Jonathan Long, Trevor Darrell. Fully Convolutional Networks for Semantic Segmentation[M]. IEEE Computer Society, 2017.
[12]	Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[J]. 2015.
[13]	臧睦君. 图像场景识别的特征研究[D]. 长春:吉林大学, 2015.
[14]	钟成. 基于机器学习的水果图像自动识别与分割算法研究[D]. 衡阳:南华大学, 2018.
[15]	王俊强, 李建胜, 丁波. 深度学习语义分割方法在遥感影像分割中的性能分析[J]. 计算机测量与控制, 2019,27(7):231-235.
[16]	魏芳. 基于语义分割的车载路面裂缝自动识别技术研究[D]. 西安:长安大学, 2019.
[17]	王爽. 深度学习在图像分类中的应用研究[D]. 济南:山东师范大学, 2016.
[18]	张永宏, 蔡朋艳, 陶润喆, 等. 基于改进U-Net网络的遥感图像云检测[J]. 测绘通报, 2020(3):17-20,34.
[19]	Mohamed Kerkech, Adel Hafiane, Raphael Canals. Vine disease detection in UAV multispectral images using optimized image registration and deep learning segmentation approach[J]. Elsevier B.V., 2020,174.
[20]	景庄伟, 管海燕, 彭代峰, 等. 基于深度神经网络的图像语义分割研究综述[J]. 计算机工程, 2020,46(10) 1-17.
[21]	任守纲, 贾馥玮, 顾兴健, 等. 反卷积引导的番茄叶部病害识别及病斑分割模型[J]. 农业工程学报, 2020,36(12):186-195.
[22]	王振, 张善文, 王献锋. 基于改进全卷积神经网络的黄瓜叶部病斑分割方法[J]. 江苏农业学报, 2019,35(5):1054-1060.
[23]	Ajeet Ram Pathak, Manjusha Pandey, Siddharth Rautaray. Application of Deep Learning for Object Detection[J]. Elsevier B.V., 2018,132.
[24]	Deng J, Dong W, Socher R, et al. ImageNet: A large-scale hierarchical image database[C] // IEEE Conference on Computer Vision & Pattern Recognition. IEEE, 2009.
[25]	赵建敏, 李艳, 李琦, 等. 基于卷积神经网络的马铃薯叶片病害识别系统[J]. 江苏农业科学, 2018,46(24):251-255.
[26]	Oriol J. Bosch, Melanie Revilla, Ezequiel Paura. Answering Mobile Surveys With Images: An Exploration Using a Computer Vision API[J]. Social Science Computer Review, 2019,37(5).
[27]	冯立萍. 玉米病虫害防治及高产栽培技术的推广[J]. 黑龙江科学, 2020,11(8):100-101.
[28]	王振, 师韵, 李玉彬. 基于改进全卷积神经网络的玉米叶片病斑分割[J]. 计算机工程与应用, 2019,55(22):127-132.
[29]	陈晓娟, 文成敬. 四川省玉米穗腐病研究初报[J]. 西南农业大学学报, 2002(1):21-23,25.
[30]	Miao S, Liao R . Agent-Based Methods for Medical Image Registration[M] // Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics. 2019.

CPU型号	Intel(R) Xeon(R) CPU E5-2678 v3 @2.50GHz
CPU个数	2
内存	4x32GB
硬盘	1.8TB
操作系统	Ubuntu 16
GPU型号	GeForce RTX2080
GPU数	1
GPU显存	8GB

CPU型号	Intel(R) Xeon(R) CPU E5-2678 v3 @2.50GHz
CPU个数	2
内存	4x32GB
硬盘	1.8TB
操作系统	Ubuntu 16
GPU型号	GeForce RTX2080
GPU数	1
GPU显存	8GB

Input_size	（256,256）
Batch_size	8
Epoch	100
Learning_rate	0.001
Gamma	0.1
Learning_rate_decay(epoch)	20
GPU_Num	1
GPU_Memory	8G
Training time	25h18m*

Input_size	（256,256）
Batch_size	8
Epoch	100
Learning_rate	0.001
Gamma	0.1
Learning_rate_decay(epoch)	20
GPU_Num	1
GPU_Memory	8G
Training time	25h18m*

Input_size (n)	Change brightness	Mean IOU	GPU time	CPU time
128	N	0.9270	32ms	78ms
128	Y	0.9174	32ms	78ms
256	N	0.9295	84ms	143ms
256	Y	0.9363	84ms	143ms