基于卷积神经网络的白背飞虱识别方法
|
摘要
为了实现白背飞虱虫情信息的自动收集和监测,提出一种基于卷积神经网络的白背飞虱识别方法并进行应用研究。首先,用改进的野外环境昆虫图像自动采集装置,采集田间自然状态下的白背飞虱图像,对所获取的图像进行归一化处理。然后,随机选取1/2图像样本作为训练集、1/4作为测试集。利用5×5卷积核对训练样本进行卷积操作,将所获取的特征图以2×2邻域进行池化操作。再次经过卷积操作和3×3邻域池化操作后,通过自动学习获取网络模型参数和确定网络模型参数,得到白背飞虱的最佳网络识别模型。试验结果显示,利用训练后的网络识别模型,对训练集白背飞虱的识别正确率可达96.17%,对测试集白背飞虱的识别正确率为94.14%。
In order to realize the pest information automatic collection and monitoring for Sogatella furcifera,an automatic recognition method based on convolutional neural network was presented and its application was carried out. The images of Sogatella furcifera were collected in the natural state of the field by using the improved automatic acquisition system for insect images in field environment and the acquired images were normalized. Six hundred of images were randomly selected from the normalized images as training set and three hundred ones were chosen as test set. The convolution operation was performed on the training set with 5 × 5 convolution kernel and the acquired feature graphs were pooled in a 2 × 2 neighborhood. After the convolution operation and 3 × 3 neighborhood pooling operation,the network model parameters were obtained by using automatic learning and the optimal network identification model for Sogatella furcifera was achieved. The experimental results showed that the recognition accuracy for Sogatella furcifera could reach 96. 17% for training set,and for test set,the recognition accuracy was 94. 14%.
In order to realize the pest information automatic collection and monitoring for Sogatella furcifera,an automatic recognition method based on convolutional neural network was presented and its application was carried out. The images of Sogatella furcifera were collected in the natural state of the field by using the improved automatic acquisition system for insect images in field environment and the acquired images were normalized. Six hundred of images were randomly selected from the normalized images as training set and three hundred ones were chosen as test set. The convolution operation was performed on the training set with 5 × 5 convolution kernel and the acquired feature graphs were pooled in a 2 × 2 neighborhood. After the convolution operation and 3 × 3 neighborhood pooling operation,the network model parameters were obtained by using automatic learning and the optimal network identification model for Sogatella furcifera was achieved. The experimental results showed that the recognition accuracy for Sogatella furcifera could reach 96. 17% for training set,and for test set,the recognition accuracy was 94. 14%.
引文
1何忠全,陈德西,封传红,等.水稻主要害虫发生区划研究[J].西南农业学报,2014,27(5):1937-1944.HE Zhongquan,CHEN Dexi,FENG Chuanhong,et al.Study on occurrence regionalization of rice major pests[J].Southwest China Journal of Agricultural Sciences,2014,27(5):1937-1944.(in Chinese)
2 吕进,祝增荣,娄永根,等.稻飞虱灾变和治理研究透析[J].应用昆虫学报,2013,50(3):565-574.LJin,ZHU Zengrong,LOU Yonggen,et al.Review of research into outbreaks and management of rice planthoppers[J].Chinese Journal of Applied Entomology,2013,50(3):565-574.(in Chinese)
3 唐小艳,李正跃,陈斌.水稻白背飞虱的综合防治[J].湖南农业科学,2009(8):70-73.TANG Xiaoyan,LI Zhengyue,CHEN Bin.Integrated control of Sogatella furcifera on rice[J].Hunan Agricultural Sciences,2009(8):70-73.(in Chinese)
4 沈君辉,尚金梅,刘光杰.中国的白背飞虱研究概况[J].中国水稻科学,2003,17(增刊):7-22.SHEN Junhui,SHANG Jinmei,LIU Guangjie.Management of the whitebacked planthopper,Sogatella furcifera in China:a minireview[J].Chinese Journal of Rice Science,2003,17(Supp.):7-22.(in Chinese)
5 YAO Q,XIAN D X,LIU Q J,et al.Automated counting of rice planthoppers in paddy fields based on image processing[J].Journal of Integrative Agriculture,2014,13(8):1736-1745.
6 桂连友,黄秀琴,李传仁.昆虫谐波雷达的发展和利用[J].应用昆虫学报,2011,48(3):732-738.GUI Lianyou,HUANG Xiuqin,LI Chuanren.The development and the use of insect harmonic radar[J].Chinese Journal of Applied Entomology,2011,48(3):732-738.(in Chinese)
7 朱与波.稻纵卷叶螟危害水稻的高光谱监测方法研究[D].南京:南京农业大学,2012.ZHU Yubo.Hyper spectral monitoring the damage of rice by rice leaf folder cnaphalocrocis medinalis güenée[D].Nanjing:Nanjing Agricultural University,2012.(in Chinese)
8 韦雪青,温俊宝,赵源吉,等.害虫声音监测技术研究进展[J].林业科学,2010,46(5):147-154.WEI Xueqing,WEN Junbao,ZHAO Yuanji,et al.Review on monitoring technology of the insect acoustic[J].Scientia Silvae Sinicae,2010,46(5):147-154.(in Chinese)
9 田冉,陈梅香,董大明,等.红外传感器与机器视觉融合的果树害虫识别及计数方法[J].农业工程学报,2016,32(20):195-201.TIAN Ran,CHEN Meixiang,,DONG Daming,et al.Identification and counting method of orchard pests based on fusion method of infrared sensor and machine vision[J].Transactions of the CSAE,2016,32(20):195-201.(in Chinese)
10 JIANG J A,TSENG C L,LU Fuming,et al.A GSM-based remote wireless automatic monitoring system for field information:a case study for ecological monitoring of the oriental fruit fly,Bactrocera dorsalis(Hendel)[J].Computers and Electronics in Agriculture,2008,62(2):243-259.
11 李文勇,陈梅香,李明,等.基于姿态描述的果园靶标害虫自动识别方法[J/OL].农业机械学报,2014,45(11):54-59.http:∥www.jcsam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20141109&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2014.11.009.LI Wenyong,CHEN Meixiang,LI Ming,et al.Orchard pest automated identification method based on posture description[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2014,45(11):54-59.(in Chinese)
12 毛罕平,张红涛.储粮害虫图像识别的研究进展及展望[J].农业机械学报,2008,39(4):175-179.MAO Hanping,ZHANG Hongtao.Research progress and prospect for image recognition of stored-grain pests[J].Transactions of the Chinese Society for Agricultural Machinery,2008,39(4):176-179.(in Chinese)
13 韩瑞珍,何勇.基于计算机视觉的大田害虫远程自动识别系统[J].农业工程学报,2013,29(2):156-162.HAN Ruizhen,HE Yong.Remote automatic identification system of field pests based on computer vision[J].Transactions of the CSAE,2013,29(2):156-162.(in Chinese)
14 毛文华,郑永军,张银桥,等.基于机器视觉的草地蝗虫识别方法[J].农业工程学报,2008,24(11):155-158.MAO Wenhua,ZHENG Yongjun,ZHANG Yinqiao,et al.Grasshopper detection method based on machine vision[J].Transactions of the CSAE,2008,24(11):155-158.(in Chinese)
15 胡永强,宋良图,张洁,等.基于稀疏表示的多特征融合害虫图像识别[J].模式识别与人工智能,2014,27(11):985-992.HU Yongqiang,SONG Liangtu,ZHANG Jie,et al.Pest image recognition of multi-feature fusion based on sparse representation[J].Pattern Recognition and Artificial Intelligence,2014,27(11):985-992.(in Chinese)
16 刘德营,丁为民,陈坤杰.野外环境昆虫图像自动采集装置[J].农业机械学报,2011,42(6):184-187,173.LIU Deying,DING Weimin,CHEN Kunjie.Automatic acquisition system for insects images in field environment[J].Transactions of the Chinese Society for Agricultural Machinery,2011,42(6):184-187,173.(in Chinese)
17 卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016(1):1-17.LU Hongtao,ZHANG Qinchuan.Applications of deep convolutional neural network in computer vision[J].Journal of Data Acquisition and Processing,2016(1):1-17.(in Chinese)
18 孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.SUN Zhijun,XUE Lei,XU Yangming,et al.Overview of deep learning[J].Application Research of Computers,2012,29(8):2806-2810.(in Chinese)
19 杨斌,钟金英.卷积神经网络的研究进展综述[J].南华大学学报:自然科学版,2016,30(3):66-72.YANG Bin,ZHONG Jinying.Review of convolution neural network[J].Journal of University of South China:Science and Technology,2016,30(3):66-72.(in Chinese)
20 胡正平,陈俊岭,王蒙,等.卷积神经网络分类模型在模式识别中的新进展[J].燕山大学学报,2015,39(4):283-291.HU Zhengping,CHEN Junling,WANG Meng,et al.Recent progress on convolutional neural network in pattern recognition[J].Journal of Yanshan University,2015,39(4):283-291.(in Chinese)
21 高震宇,王安,刘勇,等.基于卷积神经网络的鲜茶叶智能分选系统研究[J/OL].农业机械学报,2017,48(7):53-58.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20170707&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2017.07.007.GAO Zhenyu,WANG An,LIU Yong,et al.Intelligent fresh-tea-leaves sorting system research based on convolution neural network[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(7):53-58.(in Chinese)
22 Deep Learn Toolbox[EB/OL].[2014-01-12].https:∥github.com/rasmusbergpalm/Deep Learn Toolbox.
23 LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
2 吕进,祝增荣,娄永根,等.稻飞虱灾变和治理研究透析[J].应用昆虫学报,2013,50(3):565-574.LJin,ZHU Zengrong,LOU Yonggen,et al.Review of research into outbreaks and management of rice planthoppers[J].Chinese Journal of Applied Entomology,2013,50(3):565-574.(in Chinese)
3 唐小艳,李正跃,陈斌.水稻白背飞虱的综合防治[J].湖南农业科学,2009(8):70-73.TANG Xiaoyan,LI Zhengyue,CHEN Bin.Integrated control of Sogatella furcifera on rice[J].Hunan Agricultural Sciences,2009(8):70-73.(in Chinese)
4 沈君辉,尚金梅,刘光杰.中国的白背飞虱研究概况[J].中国水稻科学,2003,17(增刊):7-22.SHEN Junhui,SHANG Jinmei,LIU Guangjie.Management of the whitebacked planthopper,Sogatella furcifera in China:a minireview[J].Chinese Journal of Rice Science,2003,17(Supp.):7-22.(in Chinese)
5 YAO Q,XIAN D X,LIU Q J,et al.Automated counting of rice planthoppers in paddy fields based on image processing[J].Journal of Integrative Agriculture,2014,13(8):1736-1745.
6 桂连友,黄秀琴,李传仁.昆虫谐波雷达的发展和利用[J].应用昆虫学报,2011,48(3):732-738.GUI Lianyou,HUANG Xiuqin,LI Chuanren.The development and the use of insect harmonic radar[J].Chinese Journal of Applied Entomology,2011,48(3):732-738.(in Chinese)
7 朱与波.稻纵卷叶螟危害水稻的高光谱监测方法研究[D].南京:南京农业大学,2012.ZHU Yubo.Hyper spectral monitoring the damage of rice by rice leaf folder cnaphalocrocis medinalis güenée[D].Nanjing:Nanjing Agricultural University,2012.(in Chinese)
8 韦雪青,温俊宝,赵源吉,等.害虫声音监测技术研究进展[J].林业科学,2010,46(5):147-154.WEI Xueqing,WEN Junbao,ZHAO Yuanji,et al.Review on monitoring technology of the insect acoustic[J].Scientia Silvae Sinicae,2010,46(5):147-154.(in Chinese)
9 田冉,陈梅香,董大明,等.红外传感器与机器视觉融合的果树害虫识别及计数方法[J].农业工程学报,2016,32(20):195-201.TIAN Ran,CHEN Meixiang,,DONG Daming,et al.Identification and counting method of orchard pests based on fusion method of infrared sensor and machine vision[J].Transactions of the CSAE,2016,32(20):195-201.(in Chinese)
10 JIANG J A,TSENG C L,LU Fuming,et al.A GSM-based remote wireless automatic monitoring system for field information:a case study for ecological monitoring of the oriental fruit fly,Bactrocera dorsalis(Hendel)[J].Computers and Electronics in Agriculture,2008,62(2):243-259.
11 李文勇,陈梅香,李明,等.基于姿态描述的果园靶标害虫自动识别方法[J/OL].农业机械学报,2014,45(11):54-59.http:∥www.jcsam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20141109&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2014.11.009.LI Wenyong,CHEN Meixiang,LI Ming,et al.Orchard pest automated identification method based on posture description[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2014,45(11):54-59.(in Chinese)
12 毛罕平,张红涛.储粮害虫图像识别的研究进展及展望[J].农业机械学报,2008,39(4):175-179.MAO Hanping,ZHANG Hongtao.Research progress and prospect for image recognition of stored-grain pests[J].Transactions of the Chinese Society for Agricultural Machinery,2008,39(4):176-179.(in Chinese)
13 韩瑞珍,何勇.基于计算机视觉的大田害虫远程自动识别系统[J].农业工程学报,2013,29(2):156-162.HAN Ruizhen,HE Yong.Remote automatic identification system of field pests based on computer vision[J].Transactions of the CSAE,2013,29(2):156-162.(in Chinese)
14 毛文华,郑永军,张银桥,等.基于机器视觉的草地蝗虫识别方法[J].农业工程学报,2008,24(11):155-158.MAO Wenhua,ZHENG Yongjun,ZHANG Yinqiao,et al.Grasshopper detection method based on machine vision[J].Transactions of the CSAE,2008,24(11):155-158.(in Chinese)
15 胡永强,宋良图,张洁,等.基于稀疏表示的多特征融合害虫图像识别[J].模式识别与人工智能,2014,27(11):985-992.HU Yongqiang,SONG Liangtu,ZHANG Jie,et al.Pest image recognition of multi-feature fusion based on sparse representation[J].Pattern Recognition and Artificial Intelligence,2014,27(11):985-992.(in Chinese)
16 刘德营,丁为民,陈坤杰.野外环境昆虫图像自动采集装置[J].农业机械学报,2011,42(6):184-187,173.LIU Deying,DING Weimin,CHEN Kunjie.Automatic acquisition system for insects images in field environment[J].Transactions of the Chinese Society for Agricultural Machinery,2011,42(6):184-187,173.(in Chinese)
17 卢宏涛,张秦川.深度卷积神经网络在计算机视觉中的应用研究综述[J].数据采集与处理,2016(1):1-17.LU Hongtao,ZHANG Qinchuan.Applications of deep convolutional neural network in computer vision[J].Journal of Data Acquisition and Processing,2016(1):1-17.(in Chinese)
18 孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810.SUN Zhijun,XUE Lei,XU Yangming,et al.Overview of deep learning[J].Application Research of Computers,2012,29(8):2806-2810.(in Chinese)
19 杨斌,钟金英.卷积神经网络的研究进展综述[J].南华大学学报:自然科学版,2016,30(3):66-72.YANG Bin,ZHONG Jinying.Review of convolution neural network[J].Journal of University of South China:Science and Technology,2016,30(3):66-72.(in Chinese)
20 胡正平,陈俊岭,王蒙,等.卷积神经网络分类模型在模式识别中的新进展[J].燕山大学学报,2015,39(4):283-291.HU Zhengping,CHEN Junling,WANG Meng,et al.Recent progress on convolutional neural network in pattern recognition[J].Journal of Yanshan University,2015,39(4):283-291.(in Chinese)
21 高震宇,王安,刘勇,等.基于卷积神经网络的鲜茶叶智能分选系统研究[J/OL].农业机械学报,2017,48(7):53-58.http:∥www.j-csam.org/jcsam/ch/reader/view_abstract.aspx?flag=1&file_no=20170707&journal_id=jcsam.DOI:10.6041/j.issn.1000-1298.2017.07.007.GAO Zhenyu,WANG An,LIU Yong,et al.Intelligent fresh-tea-leaves sorting system research based on convolution neural network[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(7):53-58.(in Chinese)
22 Deep Learn Toolbox[EB/OL].[2014-01-12].https:∥github.com/rasmusbergpalm/Deep Learn Toolbox.
23 LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.