|本期目录/Table of Contents|

[1]温艳兰,陈友鹏,王克强,等.基于迁移学习和改进残差网络的复杂背景下害虫图像识别[J].江苏农业科学,2023,51(8):171-177.
 Wen Yanlan,et al.Recognition of pest images under complex background based on transfer learning and improved residual network[J].Jiangsu Agricultural Sciences,2023,51(8):171-177.
点击复制

基于迁移学习和改进残差网络的复杂背景下害虫图像识别(PDF)
分享到:

《江苏农业科学》[ISSN:1002-1302/CN:32-1214/S]

卷:
第51卷
期数:
2023年第8期
页码:
171-177
栏目:
农业工程与信息技术
出版日期:
2023-04-20

文章信息/Info

Title:
Recognition of pest images under complex background based on transfer learning and improved residual network
作者:
温艳兰1陈友鹏2王克强1程杏安1林钦永1蔡肯1马佳佳1孔翰博1
1.仲恺农业工程学院,广东广州 510225; 2.广州南洋理工职业学院,广东广州 510980
Author(s):
Wen Yanlanet al
关键词:
迁移学习卷积神经网络注意力机制图像识别
Keywords:
-
分类号:
TP391.41
DOI:
-
文献标志码:
A
摘要:
在农业生产中,虫害已经成为影响作物产量和质量的主要威胁之一,针对传统识别方法对复杂背景下虫害图像识别准确率和效率低等问题,本研究提出一种基于迁移学习和改进残差网络的虫害图像识别方法。首先,利用数据增强技术对采集的橘小实蝇虫害图像进行样本数据的扩充;再在ResNet-34模型的基础上,增加了2个注意力模块层,并重新设计了全连接层模块,获得能够改进后的网络模型;最后利用迁移学习的方法将预训练的参数权重迁移到本模型中进行训练,并在试验过程中分析学习方式、样本量、学习率、批量大小等参数对模型性能的影响。结果表明,采用旋转、翻转和亮度变换操作对图像进行数据扩充的数据集,在训练模型的全部层的迁移学习方法中获得9977%的测试准确率。本研究提出的模型具有较高的识别准确率和较强的鲁棒性,可为实现复杂背景下虫害的识别提供参考。
Abstract:
-

参考文献/References:

[1]国家统计局. 中国统计摘要2021[M]. 北京:中国统计出版社,2022.
[2]王明召,阳廷密,赵小龙,等. 橘小实蝇田间消长动态及对柑橘果实危害研究[J]. 应用昆虫学报,2019,56(3):485-491.
[3]Ding W G,Taylor G. Automatic moth detection from trap images for pest management[J]. Computers and Electronics in Agriculture,2016,123:17-28.
[4]于洪涛,袁明新,王琪,等. 基于VGG-F动态学习模型的苹果病虫害识别[J]. 科学技术与工程,2019,19(32):249-253.
[5]周宏威,沈恒宇,袁新佩,等. 基于迁移学习的苹果树叶片病虫害识别方法研究[J]. 中国农机化学报,2021,42(11):151-158.
[6]Xing S L,Lee M,Lee K K. Citrus pests and diseases recognition model using weakly dense connected convolution network[J]. Sensors,2019,19(14):3195.
[7]Morteza K,Ezzatollah A A,Ehsan K. Citrus pests classification using an ensemble of deep learning models[J]. Computers and Electronics in Agriculture,2021,186:106192.
[8]Partel V,Nunes L,Stansly P,et al. Automated vision-based system for monitoring Asian citrus psyllid in orchards utilizing artificial intelligence[J]. Computers and Electronics in Agriculture,2019,162:328-336.
[9]Alves A N,Souza W S R,Borges D L. Cotton pests classification in field-based images using deep residual networks[J]. Computers and Electronics in Agriculture,2020,174:105488.
[10]张建华,孔繁涛,吴建寨,等. 基于改进VGG卷积神经网络的棉花病害识别模型[J]. 中国农业大学学报,2018,23(11):161-171.
[11]Tetila E C,Machado B B,Menezes G K,et al. Automatic recognition of soybean leaf diseases using UAV images and deep convolutional neural networks[J]. IEEE Geoscience and Remote Sensing Letters,2020,17(5):903-907.
[12]Amorim W P,Tetila E C,Pistori H,et al. Semi-supervised learning with convolutional neural networks for UAV images automatic recognition[J]. Computers and Electronics in Agriculture,2019,164:104932.
[13]李静,陈桂芬,安宇. 基于优化卷积神经网络的玉米螟虫害图像识别[J]. 华南农业大学学报,2020,41(3):110-116.
[14]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.
[15]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.
[16]Jiang F,Lu Y,Chen Y,et al. Image recognition of four rice leaf diseases based on deep learning and support vector machine[J]. Computers and Electronics in Agriculture,2020,179:105824.
[17]Wang F Y,Wang R J,Xie C J,et al. Convolutional neural network based automatic pest monitoring system using hand-held mobile image analysis towards non-site-specific wild environment[J]. Computers and Electronics in Agriculture,2021,187:106268.
[18]Yao Q,Feng J,Tang J,et al. Development of an automatic monitoring system for rice light-trap pests based on machine vision[J]. Journal of Integrative Agriculture,2020,19(10):2500-2513.
[19]余小东,杨孟辑,张海清,等. 基于迁移学习的农作物病虫害检测方法研究与应用[J]. 农业机械学报,2020,51(10):252-258.
[20]万军杰,祁力钧,卢中奥,等. 基于迁移学习的GoogLeNet果园病虫害识别与分级[J]. 中国农业大学学报,2021,26(11):209-221.
[21]Kamal K C,Yin Z D,Wu M Y,et al. Depthwise separable convolution architectures for plant disease classification[J]. Computers and Electronics in Agriculture,2019,165:104948.
[22]Wang D W,Deng L M,Ni J G,et al. Recognition pest by image-based transfer learning[J]. Journal of the Science of Food and Agriculture,2019,99(10):4524-4531.
[23]温艳兰,陈友鹏,王克强,等. 基于机器视觉的病虫害检测综述[J]. 中国粮油学报,2022,37(10):271-279.
[24]赵立新,侯发东,吕正超,等. 基于迁移学习的棉花叶部病虫害图像识别[J]. 农业工程学报,2020,36(7):184-191.
[25]He Y,Zhou Z Y,Tian L H,et al. Brown rice planthopper (Nilaparvata lugens Stal) detection based on deep learning[J]. Precision Agriculture,2020,21(6):1385-1402.
[26]李衡霞,龙陈锋,曾蒙,等. 一种基于深度卷积神经网络的油菜虫害检测方法[J]. 湖南农业大学学报(自然科学版),2019,45(5):560-564.
[27]李昊,刘海隆,刘生龙. 基于深度学习的柑橘病虫害动态识别系统研发[J]. 中国农机化学报,2021,42(9):195-201,208.
[28]孙鹏,陈桂芬,曹丽英. 基于注意力卷积神经网络的大豆害虫图像识别[J]. 中国农机化学报,2020,41(2):171-176.
[29]Malathi V,Gopinath M P.Classification of pest detection in paddy crop based on transfer learning approach[J]. Acta Agriculturae Scandinavica,Section B-Soil & Plant Science,2021,71(7):552-559.
[30]Zhang Y Y,Zhong W B,Pan H. Identification of stored grain pests by modified residual network[J]. Computers and Electronics in Agriculture,2021,182:105983.
[31]曹跃腾,朱学岩,赵燕东,等. 基于改进ResNet的植物叶片病虫害识别[J]. 中国农机化学报,2021,42(12):175-181.
[32]贾少鹏,高红菊,杭潇. 基于深度学习的农作物病虫害图像识别技术研究进展[J]. 农业机械学报,2019,50(增刊1):313-317.
[33]王铎,温长吉,王希龙,等. 基于深度卷积条件生成对抗网络的虫害分类算法研究[J]. 中国农机化学报,2020,41(6):179-187.
[34]杨丽英,李之洪. 橘小实蝇的形态特征、影响因素和防治措施[J]. 湖北农机化,2020(1):58.
[35]He K M,Zhang X Y,Ren S Q,et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas,NV,USA:IEEE,2016:770-778.

相似文献/References:

[1]梁万杰,曹宏鑫.基于卷积神经网络的水稻虫害识别[J].江苏农业科学,2017,45(20):241.
 Liang Wanjie,et al.Identification of rice insect pests based on CNN model[J].Jiangsu Agricultural Sciences,2017,45(8):241.
[2]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.
 Zhao Jianmin,et al.Potato leaf disease identification system based on convolutional neural network[J].Jiangsu Agricultural Sciences,2018,46(8):251.
[3]刘嘉政.基于深度迁移学习模型的花卉种类识别[J].江苏农业科学,2019,47(20):231.
 Liu Jiazheng.Flower species identification based on deep transfer learning model[J].Jiangsu Agricultural Sciences,2019,47(8):231.
[4]魏青迪,范昊,张承明.基于ECLDeeplab模型提取华北地区耕地的方法[J].江苏农业科学,2020,48(04):209.
 Wei Qingdi,et al.A method for extracting cultivated land in North China based on ECLDeeplab model[J].Jiangsu Agricultural Sciences,2020,48(8):209.
[5]陈峰,谷俊涛,李玉磊,等.基于机器视觉和卷积神经网络的东北寒地玉米害虫识别方法[J].江苏农业科学,2020,48(18):237.
 Chen Feng,et al.Recognition method of corn pests in northeast cold region based on machine vision and convolutional neural network[J].Jiangsu Agricultural Sciences,2020,48(8):237.
[6]陈旭君,王承祥,孙福,等.基于改进Faster R-CNN的田间植株幼苗检测方法[J].江苏农业科学,2021,49(4):159.
 Chen Xujun,et al.Detection method for plant seedlings in fields based on improved Faster R-CNN[J].Jiangsu Agricultural Sciences,2021,49(8):159.
[7]范宏,刘素红,陈吉军,等.基于深度学习的白喉乌头与牧草高精度分类研究[J].江苏农业科学,2021,49(12):173.
 Fan Hong,et al.Study on high-precision classification of Aconitum leucostomum Worosch and pasture based on deep learning[J].Jiangsu Agricultural Sciences,2021,49(8):173.
[8]李萍,邵彧,齐国红,等.基于跨深度学习模型的作物病害检测方法[J].江苏农业科学,2022,50(8):193.
 Li Ping,et al.Crop disease detection method based on cross deep learning model[J].Jiangsu Agricultural Sciences,2022,50(8):193.
[9]李祥宇,任艳娜,马新明,等.面向小麦生育进程监测的卷积神经网络精简化研究[J].江苏农业科学,2022,50(8):199.
 Li Xiangyu,et al.Study on simplified convolutional neural network for monitoring wheat growth process[J].Jiangsu Agricultural Sciences,2022,50(8):199.
[10]徐振南,王建坤,胡益嘉,等.基于MobileNetV3的马铃薯病害识别[J].江苏农业科学,2022,50(10):176.
 Xu Zhennan,et al.Potato disease recognition based on MobileNetV3[J].Jiangsu Agricultural Sciences,2022,50(8):176.
[11]黎振,陆玲,熊方康.基于k-means分割和迁移学习的番茄病理识别[J].江苏农业科学,2021,49(12):156.
 Li Zhen,et al.Tomato pathological recognition based on k-means segmentation and transfer learning[J].Jiangsu Agricultural Sciences,2021,49(8):156.
[12]姜月明,王健,董光辉,等.基于改进卷积神经网络的苹果叶片病害识别[J].江苏农业科学,2024,52(14):214.
 Jiang Yueming,et al.Recognition of apple leaf disease based on improved convolutional neural network[J].Jiangsu Agricultural Sciences,2024,52(8):214.

备注/Memo

备注/Memo:
收稿日期:2022-07-01
基金项目:国家自然科学基金(编号:62003379);广东省科技计划(编号:KA1721404);广东省普通高校重点领域专项(编号:2019GZDXM007)。
作者简介:温艳兰(1995—),女,广东梅县人,硕士研究生,主要研究方向为机器视觉。E-mail:164734302@qq.com。
通信作者:王克强,硕士,教授,主要研究方向为农业机器人。E-mail:wangkq2003@126.com。
更新日期/Last Update: 2023-04-20