基于红外热成像边缘检测算法的小麦叶锈病分级研究
|
摘要
小麦叶锈病对我国小麦生产危害巨大,实现小麦叶锈病的监测和快速分级是进行科学生产管理的基础。针对常规图像检测技术的不足,提出一种基于红外热成像技术的快速检测和分级方法。首先,采集整株小麦样本的红外热成像图像,分别计算健康植株、潜伏期植株和显症植株的平均叶温,探明真菌入侵过程中的温度变化规律;然后,将经过直方图均衡化和中值滤波预处理的红外热成像中低于显症植株温度阈值的区域提取出来;通过温度区域划分、低温区域提取和阈值分割,计算病斑面积在整体植株热成像总面积中的百分比;最后,对病情指数进行相关分析,获得相关系数为0. 975 5,预测均方根误差为9. 79%,总识别正确率为90%。结果表明,基于红外热成像边缘检测算法的小麦叶锈病分级方法是可行的。
Wheat rust has a great harm to wheat production in worldwide. The rapid monitoring and classification of wheat rust is the basis for scientific production and management,and it is also the prerequisite to realize the treatment of wheat rust as soon as possible. In view of the shortcomings of conventional image detection algorithms,a fast detection and classification method based on infrared thermal imaging technology was proposed. Wheat samples were planted in a growth chamber at the University of Alberta,Canada. Growth chamber parameters settings were as following: temperature( max15℃,min 11℃),photoperiod( day 12 h),light intensity( 10 000 lx),RH( 60% ～ 70%). The spring wheat variety( Peace) was susceptible to rust. The infrared thermal imager brand was FLIR E6,USA. Thermal sensitivity was less than 0. 06℃; FOV was less than 45°ohorizontal × 34°overtical; IFOV was 5. 2 × 10~(-3) rad; IR was 160 pixels × 120 pixels. The infrared thermal imaging of the whole wheat samples were collected to calculate the average leaf temperature of the healthy plants,the submersible plants and the symptomatic plants,and the temperature changes during the invasion of the fungi were detected. Infrared thermography can be used to detect leaf temperature drop caused by pathogen infection at 6 d of pathogen infection incubation period,which was 7 d ahead of the naked eye observation of leaf rust spores. The Prewitt operator( PO),Sobel operator( SO),Canny operator( CO) and Laplacian operator( LO) were used to extract the edges of visible light images. The edge extraction results of PO and SO on the lesion area was not satisfactory for the complex noise processing,and the boundary gray area was seriously ghosting. LO and CO were too lean for the edges,the detection accuracy was reduced,and the background error was too large. Obviously,the direct use of conventional edge detection operators cannot meet the ultimate goal of rapid classification of diseases. Therefore,a fast detection and classification method based on infrared thermal imaging technology was proposed. The experiment was divided into two kinds of extraction methods: single leaf and whole plant. When the whole plant was extracted,the flower pot was removed and only the wheat plant was kept for extraction. From the results of the whole wheat extraction,the area of the whole plant disease can be extracted successfully by the method of area occupation ratio calculation based on the temperature edge. The error of the regional extraction results of the single leaf focus was slightly larger than that of the single leaf focus,but the final calculation results were satisfactory. The region below the temperature threshold was extracted from the infrared thermal image which was preprocessed by histogram equalization and median filtering. The ratio of lesion area to total area of plant thermography was calculated after three steps,including temperature division,low temperature region extraction and threshold segmentation. Finally,the correlation analysis was carried out with the disease index. The correlation coefficient was 0. 975 5,the root mean square error was 9. 79%,and the overall recognition rate was 90%. The research result showed that the wheat leaf rust classification method based on the infrared thermal imaging temperature information was feasible.It provided the theoretical and method basis for the early scientific application and the establishment of more accurate disease identification expert system.
Wheat rust has a great harm to wheat production in worldwide. The rapid monitoring and classification of wheat rust is the basis for scientific production and management,and it is also the prerequisite to realize the treatment of wheat rust as soon as possible. In view of the shortcomings of conventional image detection algorithms,a fast detection and classification method based on infrared thermal imaging technology was proposed. Wheat samples were planted in a growth chamber at the University of Alberta,Canada. Growth chamber parameters settings were as following: temperature( max15℃,min 11℃),photoperiod( day 12 h),light intensity( 10 000 lx),RH( 60% ～ 70%). The spring wheat variety( Peace) was susceptible to rust. The infrared thermal imager brand was FLIR E6,USA. Thermal sensitivity was less than 0. 06℃; FOV was less than 45°ohorizontal × 34°overtical; IFOV was 5. 2 × 10~(-3) rad; IR was 160 pixels × 120 pixels. The infrared thermal imaging of the whole wheat samples were collected to calculate the average leaf temperature of the healthy plants,the submersible plants and the symptomatic plants,and the temperature changes during the invasion of the fungi were detected. Infrared thermography can be used to detect leaf temperature drop caused by pathogen infection at 6 d of pathogen infection incubation period,which was 7 d ahead of the naked eye observation of leaf rust spores. The Prewitt operator( PO),Sobel operator( SO),Canny operator( CO) and Laplacian operator( LO) were used to extract the edges of visible light images. The edge extraction results of PO and SO on the lesion area was not satisfactory for the complex noise processing,and the boundary gray area was seriously ghosting. LO and CO were too lean for the edges,the detection accuracy was reduced,and the background error was too large. Obviously,the direct use of conventional edge detection operators cannot meet the ultimate goal of rapid classification of diseases. Therefore,a fast detection and classification method based on infrared thermal imaging technology was proposed. The experiment was divided into two kinds of extraction methods: single leaf and whole plant. When the whole plant was extracted,the flower pot was removed and only the wheat plant was kept for extraction. From the results of the whole wheat extraction,the area of the whole plant disease can be extracted successfully by the method of area occupation ratio calculation based on the temperature edge. The error of the regional extraction results of the single leaf focus was slightly larger than that of the single leaf focus,but the final calculation results were satisfactory. The region below the temperature threshold was extracted from the infrared thermal image which was preprocessed by histogram equalization and median filtering. The ratio of lesion area to total area of plant thermography was calculated after three steps,including temperature division,low temperature region extraction and threshold segmentation. Finally,the correlation analysis was carried out with the disease index. The correlation coefficient was 0. 975 5,the root mean square error was 9. 79%,and the overall recognition rate was 90%. The research result showed that the wheat leaf rust classification method based on the infrared thermal imaging temperature information was feasible.It provided the theoretical and method basis for the early scientific application and the establishment of more accurate disease identification expert system.
引文
[1]金夏红,冯国华,刘东涛,等.小麦抗叶锈病遗传研究进展[J].麦类作物学报,2017,37(4):504-512.JIN Xiahong,FENG Guohua,LIU Dongtao,et al.Review on genetic research on leaf rust in wheat[J].Journal of Triticeae Crops,2017,37(4):504-512.(in Chinese)
[2]李真,史智兴,王成,等.红外热成像技术在作物胁迫检测方面的应用[J].农机化研究,2016,38(1):232-237.LI Zhen,SHI Zhixing,WANG Cheng,et al.The application progress of infrared thermography for crop stress detection[J].Journal of Agricultural Mechanization Research,2016,38(1):232-237.(in Chinese)
[3]GUO Jiuxin,TIAN Guangli,ZHOU Yi.Evaluation of the grain yield and nitrogen nutrient status of wheat(Triticum aestivum L.)using thermal imaging[J].Journal of Animal&Plant Sciences,2015,25(3):202-207.
[4]JIAO Leizi,DONG Daming,FENG Haikuan,et al.Monitoring spray drift in aerial spray application based on infrared thermal imaging technology[J].Computers&Electronics in Agriculture,2016,121(C):135-140.
[5]FANG Wenhui,LU Wei,XU Hongli,et al.Study on the detection of rice seed germination rate based on infrared thermal imaging technology combined with generalized regression neural network[J].Spectroscopy&Spectral Analysis,2016,36(8):2692-2697.
[6]JIAN Bolin,CHEN Chiehli,CHU Wenlin,et al.The facial expression of schizophrenic patients applied with infrared thermal facial image sequence[J].BMC Psychiatry,2017,17(1):229-236.
[7]陈斌,田桂华.红外热成像技术在植物病害检测中的应用研究进展[J].江苏农业科学,2014,42(9):1-4.CHEN Bin,TIAN Guihua.Research progress of application of infrared thermography in plant disease detection[J].Jiangsu Agricultural Sciences,2014,42(9):1-4.(in Chinese)
[8]周建民,周其显,刘燕德.红外热成像技术在农业生产中的应用[J].农机化研究,2010,32(2):1-4.ZHOU Jianmin,ZHOU Qixian,LIU Yande.Application of infrared thermography techniques in agricultural production[J].Journal of Agricultural Mechanization Research,2010,32(2):1-4.(in Chinese)
[9]JIAO Litao,WU Weibing,ZHENG Wanguo,et al.The infrared thermal image-based monitoring process of peach decay under under uncontrolled temperature conditions[J].Journal of Animal and Plant Sciences,2015,25(1):202-207.
[10]MASRI A A,HAU B,DEHNEH W,et al.Impact of primary infection site of Fusarium species on head blight development in wheat ears evaluated by IR-thermography[J].European Journal of Plant Pathology,2016,147(4):1-14.
[11]ANKUSH P,HSMLYN G J.Assessing drought responsesusing thermal infrared imaging[J].Environmental Responses in Plants,2016,1398(6):209-219.
[12]CHEN Zilong,REN Xiangrong,CONG Hua,et al.Study on the relationship between the winter wheat thermal infrared image characteristics and physiological indicators[J].International Symposium on Optoelectronic Technology and Application:Infrared Technology and Applications,2014,11:291-298.
[13]ALIREZA E,KAZEM P,HOJAT A,et al.Use of IR thermography in screening wheat(Triticum aestivum L.)cultivars for salt tolerance[J].Archives of Agronomy&Soil Science,2016,63(2):161-170.
[14]MAHLEIN A K,OERKE E C,STEINER U,et al.Recent advances in sensing plant diseases for precision crop protection[J].European Journal of Plant Pathology,2012,133(1):197-209.
[15]ZHANG Yan,MENG Qinglong,SHANG Jing,et al.The application and perspective of new imaging technology in detection of plant diseases[J].Laser Journal,2017,38(12):7-13.
[16]李小龙,王库,马占鸿,等.基于热红外成像技术的小麦病害早期检测[J].农业工程学报,2014,30(18):183-189.LI Xiaolong,WANG Ku,MA Zhanhong,et al.Early detection of wheat disease based on thermal infrared imaging[J].Transactions of the CSAE,2014,30(18):183-189.(in Chinese)
[17]OERKE E C,FROHLING P,STEINER U.Thermographic assessment of scab disease on apple leaves[J].Precision Agriculture,2011,12(5):699-715.
[18]BELIN E,ROUSSEAU D,BOUREAU T,et al.Thermography versus chlorophyll fluorescence imaging for detection and quantification of apple scab[J].Computers and Electronics in Agriculture,2013,90:159-163.
[19]WANG Fei,OMASA K,XING Shangjun,et al.Thermographic analysis of leaf water and energy information of Japanese spindle and glossy privet trees in low temperature environment[J].Ecological Informatics,2013,16:35-40.
[20]WANG Min,LING Ning,DONG Xian,et al.Thermographic visualization of leaf response in cucumber plants infected with the soilborne pathogen Fusarium oxysporum f.sp.cucumerinum[J].Plant Physiology and Biochemistry,2012,61:153-161.(下转第页)
[21]徐小龙,蒋焕煜,杭月兰.热红外成像用于番茄花叶病早期检测的研究[J].农业工程学报,2012,28(5):145-149.XU Xiaolong,JIANG Huanyu,HANG Yuelan.Study on detection of tomato mosaic disease at early stage based on infrared thermal imaging[J].Transactions of the CSAE,2012,28(5):145-149.(in Chinese)
[22]MAHLEIN A K,OERK E C,STEINER U,et al.Recent advances in sensing plant diseases for precision crop protection[J].European Journal of Plant Pathology,2012,133(1):197-209.
[23]RAZA S A,SANCHEZ V,PRINCE G,et al.Registration of thermal and visible light images of diseased plants using silhouette extraction in the wavelet domain[J].Pattern Recognition,2015,48(7):2119-2128.
[24]JIAO Leizi,WU Weibing,ZHENG Wenge,et al.The infrared thermal image-based monitoring process of peach decay under uncontrolled temperature conditions[J].Journal of Animal and Plant Sciences,2015,25(3Supp.1):202-207.
[25]王栋,尚堃.基于改进蚁群算法的红外图像边缘检测方法[J].四川兵工学报,2014,35(7):87-90.WANG Dong,SHANG Kun.Edge detection algorithm of image based on improved ant colony optimization[J].Journal of Sichuan Ordnance,2014,35(7):87-90.(in Chinese)
[26]陈浩,方勇,朱大洲,等.基于蚁群算法的玉米植株热红外图像边缘检测[J].农机化研究,2015,37(6):49-52.CHEN Hao,FANG Yong,ZHU Dazhou,et al.Thermal infrared image edge detection method based on ant colony algorithm for corm plant[J].Journal of Agricultural Mechanization Research,2015,37(6):49-52.(in Chinese)
[27]李存兵,姜伟,华金.基于小波变换的水果红外图像目标识别[J].机电工程,2007,24(8):24-26.LI Cunbing,JIANG Wei,HUA Jin.Wavelet transformation for infared fruit images object identify[J].Mechanical and Electrical Engineering,2007,24(8):24-26.(in Chinese)
[28]周建民,尹洪妍,张瑞丰,等.基于红外热成像树上板栗机器识别研究[J].中国农机化学报,2012,33(3):132-136.ZHOU Jianmin,YIN Hongyan,ZHANG Ruifeng,et al.Study on machine recognition of Chinese chestnut on trees based on infrared thermograghy[J].Chinese Agricltural Mechanization,2012,33(3):132-136.(in Chinese)
[2]李真,史智兴,王成,等.红外热成像技术在作物胁迫检测方面的应用[J].农机化研究,2016,38(1):232-237.LI Zhen,SHI Zhixing,WANG Cheng,et al.The application progress of infrared thermography for crop stress detection[J].Journal of Agricultural Mechanization Research,2016,38(1):232-237.(in Chinese)
[3]GUO Jiuxin,TIAN Guangli,ZHOU Yi.Evaluation of the grain yield and nitrogen nutrient status of wheat(Triticum aestivum L.)using thermal imaging[J].Journal of Animal&Plant Sciences,2015,25(3):202-207.
[4]JIAO Leizi,DONG Daming,FENG Haikuan,et al.Monitoring spray drift in aerial spray application based on infrared thermal imaging technology[J].Computers&Electronics in Agriculture,2016,121(C):135-140.
[5]FANG Wenhui,LU Wei,XU Hongli,et al.Study on the detection of rice seed germination rate based on infrared thermal imaging technology combined with generalized regression neural network[J].Spectroscopy&Spectral Analysis,2016,36(8):2692-2697.
[6]JIAN Bolin,CHEN Chiehli,CHU Wenlin,et al.The facial expression of schizophrenic patients applied with infrared thermal facial image sequence[J].BMC Psychiatry,2017,17(1):229-236.
[7]陈斌,田桂华.红外热成像技术在植物病害检测中的应用研究进展[J].江苏农业科学,2014,42(9):1-4.CHEN Bin,TIAN Guihua.Research progress of application of infrared thermography in plant disease detection[J].Jiangsu Agricultural Sciences,2014,42(9):1-4.(in Chinese)
[8]周建民,周其显,刘燕德.红外热成像技术在农业生产中的应用[J].农机化研究,2010,32(2):1-4.ZHOU Jianmin,ZHOU Qixian,LIU Yande.Application of infrared thermography techniques in agricultural production[J].Journal of Agricultural Mechanization Research,2010,32(2):1-4.(in Chinese)
[9]JIAO Litao,WU Weibing,ZHENG Wanguo,et al.The infrared thermal image-based monitoring process of peach decay under under uncontrolled temperature conditions[J].Journal of Animal and Plant Sciences,2015,25(1):202-207.
[10]MASRI A A,HAU B,DEHNEH W,et al.Impact of primary infection site of Fusarium species on head blight development in wheat ears evaluated by IR-thermography[J].European Journal of Plant Pathology,2016,147(4):1-14.
[11]ANKUSH P,HSMLYN G J.Assessing drought responsesusing thermal infrared imaging[J].Environmental Responses in Plants,2016,1398(6):209-219.
[12]CHEN Zilong,REN Xiangrong,CONG Hua,et al.Study on the relationship between the winter wheat thermal infrared image characteristics and physiological indicators[J].International Symposium on Optoelectronic Technology and Application:Infrared Technology and Applications,2014,11:291-298.
[13]ALIREZA E,KAZEM P,HOJAT A,et al.Use of IR thermography in screening wheat(Triticum aestivum L.)cultivars for salt tolerance[J].Archives of Agronomy&Soil Science,2016,63(2):161-170.
[14]MAHLEIN A K,OERKE E C,STEINER U,et al.Recent advances in sensing plant diseases for precision crop protection[J].European Journal of Plant Pathology,2012,133(1):197-209.
[15]ZHANG Yan,MENG Qinglong,SHANG Jing,et al.The application and perspective of new imaging technology in detection of plant diseases[J].Laser Journal,2017,38(12):7-13.
[16]李小龙,王库,马占鸿,等.基于热红外成像技术的小麦病害早期检测[J].农业工程学报,2014,30(18):183-189.LI Xiaolong,WANG Ku,MA Zhanhong,et al.Early detection of wheat disease based on thermal infrared imaging[J].Transactions of the CSAE,2014,30(18):183-189.(in Chinese)
[17]OERKE E C,FROHLING P,STEINER U.Thermographic assessment of scab disease on apple leaves[J].Precision Agriculture,2011,12(5):699-715.
[18]BELIN E,ROUSSEAU D,BOUREAU T,et al.Thermography versus chlorophyll fluorescence imaging for detection and quantification of apple scab[J].Computers and Electronics in Agriculture,2013,90:159-163.
[19]WANG Fei,OMASA K,XING Shangjun,et al.Thermographic analysis of leaf water and energy information of Japanese spindle and glossy privet trees in low temperature environment[J].Ecological Informatics,2013,16:35-40.
[20]WANG Min,LING Ning,DONG Xian,et al.Thermographic visualization of leaf response in cucumber plants infected with the soilborne pathogen Fusarium oxysporum f.sp.cucumerinum[J].Plant Physiology and Biochemistry,2012,61:153-161.(下转第页)
[21]徐小龙,蒋焕煜,杭月兰.热红外成像用于番茄花叶病早期检测的研究[J].农业工程学报,2012,28(5):145-149.XU Xiaolong,JIANG Huanyu,HANG Yuelan.Study on detection of tomato mosaic disease at early stage based on infrared thermal imaging[J].Transactions of the CSAE,2012,28(5):145-149.(in Chinese)
[22]MAHLEIN A K,OERK E C,STEINER U,et al.Recent advances in sensing plant diseases for precision crop protection[J].European Journal of Plant Pathology,2012,133(1):197-209.
[23]RAZA S A,SANCHEZ V,PRINCE G,et al.Registration of thermal and visible light images of diseased plants using silhouette extraction in the wavelet domain[J].Pattern Recognition,2015,48(7):2119-2128.
[24]JIAO Leizi,WU Weibing,ZHENG Wenge,et al.The infrared thermal image-based monitoring process of peach decay under uncontrolled temperature conditions[J].Journal of Animal and Plant Sciences,2015,25(3Supp.1):202-207.
[25]王栋,尚堃.基于改进蚁群算法的红外图像边缘检测方法[J].四川兵工学报,2014,35(7):87-90.WANG Dong,SHANG Kun.Edge detection algorithm of image based on improved ant colony optimization[J].Journal of Sichuan Ordnance,2014,35(7):87-90.(in Chinese)
[26]陈浩,方勇,朱大洲,等.基于蚁群算法的玉米植株热红外图像边缘检测[J].农机化研究,2015,37(6):49-52.CHEN Hao,FANG Yong,ZHU Dazhou,et al.Thermal infrared image edge detection method based on ant colony algorithm for corm plant[J].Journal of Agricultural Mechanization Research,2015,37(6):49-52.(in Chinese)
[27]李存兵,姜伟,华金.基于小波变换的水果红外图像目标识别[J].机电工程,2007,24(8):24-26.LI Cunbing,JIANG Wei,HUA Jin.Wavelet transformation for infared fruit images object identify[J].Mechanical and Electrical Engineering,2007,24(8):24-26.(in Chinese)
[28]周建民,尹洪妍,张瑞丰,等.基于红外热成像树上板栗机器识别研究[J].中国农机化学报,2012,33(3):132-136.ZHOU Jianmin,YIN Hongyan,ZHANG Ruifeng,et al.Study on machine recognition of Chinese chestnut on trees based on infrared thermograghy[J].Chinese Agricltural Mechanization,2012,33(3):132-136.(in Chinese)
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |