基于改进Faster R_CNN的苹果叶片病害检测模型

doi:10.19678/j.issn.1000-3428.0059290

摘要/Abstract

摘要： 在实际条件下，苹果叶片病害图像背景复杂且病斑较小，难以进行实时检测。针对该问题，提出一种改进的Faster R_CNN模型。通过特征金字塔网络将具有细节信息的浅层特征和具有语义信息的深层特征融合，以提取丰富的苹果叶片病害特征。同时采用精确感兴趣区域池化，避免感兴趣区域池化中2次量化操作对病斑较小的苹果叶片病害造成像素偏差。实验结果表明，该模型能对自然条件下5种苹果叶片病害进行有效检测，平均精度均值达82.48%，与Faster R_CNN、YOLOv3和Mask R_CNN模型相比，其平均精度均值分别提高了6.01、14.12和5.06个百分点。

关键词: 苹果叶片病害, 病害检测, Faster R_CNN模型, 特征金字塔网络, 精确感兴趣区域池化

Abstract: In practice,it is difficult to detect apple leaf diseases in real time due to the complex background of apple leaf disease images and the small disease spots.To address the problem,an improved Faster R_CNN model is proposed for apple leaf disease detection.Through the Feature Pyramid Networks(FPN),the shallow features with detailed information and the deep features with semantic information are fused to extract the rich features of apple leaf disease. At the same time,the Precise Region Of Interest Pooling(PrROI Pooling) is adopted to avoid the pixel deviation caused by the two quantization operations in the Region Of Interest Pooling(ROI Pooling) to the small disease spots of apple leaf diseases.The experimental results show that the model can effectively detect five kinds of apple leaf diseases under natural conditions at an average precision of 82.48%.Compared with Faster R_CNN,YOLOv3 and Mask R_CNN,the proposed model increases the average accuracy by 6.01,14.12 and 5.06 percentage points respectively.

Key words: apple leaf disease, disease detection, Faster R_CNN model, feature pyramid networks, precise regions of interest pooling

中图分类号:

TP753

李鑫然, 李书琴, 刘斌. 基于改进Faster R_CNN的苹果叶片病害检测模型[J]. 计算机工程, 2021, 47(11): 298-304.

LI Xinran, LI Shuqin, LIU Bin. Apple Leaf Diseases Detection Model Based on Improved Faster R_CNN[J]. Computer Engineering, 2021, 47(11): 298-304.

http://www.ecice06.com/CN/Y2021/V47/I11/298

图/表 10

20211113145843

20211113145847

20211113145852

20211113145855

20211113145859

20211113145902

20211113145905

20211113145908

20211113145911

20211113145914

参考文献

[1] 陶源,史建民.全国苹果种植收益波动特征及其影响因素分析——基于1991-2014年苹果种植收益数据的实证分析[J].中国农业资源与区划,2017,9(38):167-173. TAO Y,SHI J M.Analysis on the fluctuation characteristics and influencing factors of apple planting income in China——an empirical analysis based on the data of apple planting income from 1991 to 2014[J].Journal of China Agricultural Resources and Regional Planning,2017,9(38):167-173.(in Chinese)
[2] LIU B,ZHANG Y,HE D,et al.Identification of apple leaf diseases based on deep convolutional neural networks[J].Symmetry,2018,10(1):11-21.
[3] 霍迎秋,唐晶磊,尹秀珍,等.基于压缩感知理论的苹果病害识别方法[J].农业机械学报,2013,44(10):227-232. HUO Y Q,TANG J L,YIN X Z,et al.Apple disease recognition based on compressive sensing[J].Transactions of the Chinese Society of Agricultural Engineering,2013,44(10):227-232.(in Chinese)
[4] 刘洋,冯全,王书志.基于轻量级CNN的植物病害识别方法及移动端应用[J].农业工程学报,2019,35(17):194-204. LIU Y,FENG Q,WANG S Z.Plant disease identification method based on lightweight CNN and mobile application[J].Transactions of the Chinese Society of Agricultural Engineering,2019,35(17):194-204.(in Chinese)
[5] 王聃,柴秀娟.机器学习在植物病害识别研究中的应用[J].中国农机化学报,2019,40(9):171-180. WANG D,CHAI X J.Application of machine learning in plant diseases recognition[J].Journal of Chinese Agricultural Mechanization,2019,40(9):171-180.(in Chinese)
[6] 李鑫星,朱晨光,白雪冰,等.基于可见光谱和支持向量机的黄瓜叶部病害识别方法研究[J].光谱学与光谱分析,2019,39(7):2250-2256. LI X X,ZHU C G,BAI X B,et al.Recognition method of cucumber leaves based on visual spectrum and support vector machine[J].Spectroscopy and Spectral Analysis,2019,39(7):2250-2256.(in Chinese)
[7] LIU B,TAN C,LI S,et al.A data augmentation method based on generative adversarial networks for grape leaf disease identification[J].IEEE Access,2020,8:102188-102198.
[8] 孙俊,谭文军,毛罕平,等.基于改进卷积神经网络的多种植物叶片病害识别[J].农业工程学报,2017,33(19):209-215. SUN J,TAN W J,MAO H P,et al.Recognition of multiple plant diseases based on improved convolutional neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(19):209-215.(in Chinese)
[9] 黄双萍,孙超,齐龙,等.基于深度卷积神经网络的水稻穗瘟病检测方法[J].农业工程学报,2017,33(20):169-176. HUANG S P,SUN C,QI L,et al.Rice panicle blasr identification method based on deep convolution neural network[J].Transactions of the Chinese Society of Agricultural Engineering,2017,33(20):169-176.(in Chinese)
[10] 张敏,刘杰,蔡高勇.基于卷积神经网络的柑橘溃疡病识别方法[J].计算机应用,2018,38(S1):48-52,76. ZHANG M,LIU J,CAI G Y.Recognition method of citrus canker disease based on convolution neural network[J].Journal of Computer Applications,2018,38(S1):48-52,76.
[11] XIE X,MA Y,LIU B,et al.A deep-learning-based real-time detector for grape leaf diseases using improved convolutional neural networks[J].Frontiers in Plant Science,2020,11(751):1-13.
[12] 张云龙,袁浩,张晴晴,等.基于颜色特征和差直方图的苹果叶部病害识别方法[J].江苏农业科学,2017,45(14):171-174. ZHANG Y L,YUAN H,ZHANG Q Q,et al.Recognition method of apple leaves disease based on color feature and difference histogram[J].Jiangsu Agricultural Sciences,2017,45(14):171-174.(in Chinese)
[13] 师韵,黄文准,张善文.基于二维子空间的苹果病害识别方法[J].计算机工程与应用,2017,53(22):180-184. SHI Y,HUANG W Z,ZHANG S W.Apple disease recognition based on two-dimensionality subspace learning[J].Computer Engineering and Applications,2017,53(22):180-184.(in Chinese)
[14] ZHANG C,ZHANG S,YANG J,et al.Apple leaf identification using genetic algorithm and correlation based feature selection method[J].International Journal of Agricultural and Biological Engineering,2017,10(2):74-83.
[15] BARANWAL S,KHANDELWAL S,ARORA A.Deep learning convolutional neural network for apple leaves disease detection[J].Social Science Electronic Publishing,2019,1:260-267.
[16] REN S,HE K,GIRSHICK R,et al.Faster R-CNN:towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2017,39(6):1137-1149.
[17] LIN T,PIOTR D,ROSS G,et al.Feature pyramid networks for object detection[C]//Proceedings of the 37th International Conference on Distributed Computing Systems Workshops.Washington D.C.,USA:IEEE Press,2017:2117-2125.
[18] JIANG B,LUO R,MAO J,et al.Acquisition of localization confidence for accurate object detection[C]///Proceedings of European Conference on Computer Vision.Berlin,Germang:Springer,2018:784-799.
[19] 李东洁,李若昊.基于改进Faster RCNN的马克杯缺陷检测方法[J].激光与光电子学进展,2020,57(4):1-8. LI D J,LI R H.Mug defect detection method based on improved Faster RCNN[J].Laser and Optoelectronics Progress,2020,57(4):1-8.(in Chinese)
[20] 谢金衡,张炎生.基于深度残差和特征金字塔网络的实时多人脸关键点定位算法[J].计算机应用,2019,39(12):3659-3664. XIE J H,ZHANG Y S.Real-time multi-face landmark localization algorithm based on deep residual and feature pyramid neural network[J].Journal of Computer Applications,2019,39(12):3659-3664.(in Chinese)
[21] 乔婷,苏寒松,刘高华,等.基于改进的特征提取网络的目标检测算法[J].激光与光电子学进展,2019,56(23):1-6. QIAO T,SU H S,LIU G H,et al.Object detection algorithm based on improved feature extraction network[J].Laser and Optoelectronics Progress,2019,56(23):1-6.(in Chinese)
[22] HUGO L,YOSHUA B,PASCAL L,et al.Exploring strategies for training deep neural networks[J].Journal of Machine Learning Research,2019,1:1-40.
[23] CHAO P,TETE X,ZEMING L,et al.MegDet:a large mini-batch object detector[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:6181-6189.
[24] MOLCHANOV P,TYREE S,KARRAS T,et al.Pruning convolutional neural networks for resource efficient inference[C]//Proceedings of International Conference on Learning Representation.Washington D.C.,USA:IEEE Press,2017:1-17.
[25] 王艺皓,丁洪伟,李波,等.复杂场景下基于改进YOLOv3的口罩佩戴检测算法[J].计算机工程,2020,46(11):12-22. WANG Y H,DING H W,LI B,et al.Mask wearing detection algorithm based on improved YOLOv3 in complex scenes[J].Computer Engineering,2020,46(11):12-22.(in Chinese)
[26] HE K,GKIOXARI G,DOLLAR P,et al.Mask R-CNN[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2017:2961-2969.
[27] 彭明霞,夏俊芳,彭辉.融合FPN的Faster R-CNN复杂背景下棉田杂草高效识别方法[J].农业工程学报,2019,35(20):202-209. PENG M X,XIA J F,PENG H.Efficient recognition of cotton and weed in field based on Faster R-CNN by integrating FPN[J].Transactions of the Chinese Society of Agricultural Engineering,2019,35(20):202-209.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容