基于热红外遥感影像的作物冠层温度提取
|
摘要
热红外影像较难直接提取作物冠层区域,因而无法获得较精准的作物冠层温度。本文以拔节期的玉米为研究对象,利用六旋翼无人机搭载热红外成像仪和大疆精灵四Pro无人机,获得热红外影像及正射影像。基于高分辨率正射影像,采用改进的Canny边缘检测算子、支持向量机(Support vector machine,SVM)和小波变换3种方法提取玉米冠层区域,将提取结果进行二值化处理后,在热红外影像中以此生成掩膜并提取玉米冠层温度。应用提取的矢量面分析提取效果并对3种提取算法的精度进行评价。实验结果表明,改进的Canny边缘检测算子提取效果最优、SVM算法次之、小波变换最差,提取精度分别为87. 3%、74. 5%、68. 2%。同时,将手持测温仪测得的玉米冠层温度与提取的冠层温度进行误差分析,结果表明,基于改进的Canny边缘检测算子提取的玉米冠层温度与地面实测值相关性最高,决定系数R~2=0. 929 5,SVM算法决定系数R~2=0. 895 7,小波变换决定系数R2=0. 876 0。改进的Canny边缘检测算子能够更好地提取玉米冠层区域,获取更加精确的玉米冠层温度,从而能够更有效地监测玉米生理状况,进行旱情预测,制定合理的灌溉、施肥措施以提高玉米产量。
For the low resolution of thermal infrared image,the crop canopy area can not be accurately extracted,and accurate canopy temperature can not be obtained. Maize in the jointing stage was taken as research object,and the thermal infrared image and orthophoto were obtained by using the UAV equipped with thermal infrared imager and the Dajiang Elf Pro UAV. Based on high-resolution orthophotos,the improved Canny edge detection operator,support vector machine( SVM) and wavelet transform were used to extract the maize canopy region,and the classification results were binarized in thermal infrared imaging. The maize canopy temperature was extracted by using the mask generated by the binarization result. The extracted vector surface analysis extraction effect was applied and the accuracy of the three extraction algorithms was evaluated. The experimental results showed that the effects of the three methods from strong to weak were as follows: improved Canny edge detection operator,SVM and wavelet transform; the extraction accuracy was 87. 3%,74. 5% and 68. 2%,respectively. At the same time,the error analysis of the maize canopy temperature measured by the hand-held thermometer and the extracted canopy temperature was performed. The experimental results showed that the correlation between the canopy temperature extracted by the three algorithms and the measured temperature of the ground from strong to weak was as follows: 0. 929 5,0. 895 7 and 0. 876 0. The improved Canny edge detection operator can better extract the maize canopy area and obtain more accurate maize canopy temperature,so as to more effectively monitor the physiological status of maize,predict drought,and formulate reasonable irrigation and fertilization measures to increase maize yield.
For the low resolution of thermal infrared image,the crop canopy area can not be accurately extracted,and accurate canopy temperature can not be obtained. Maize in the jointing stage was taken as research object,and the thermal infrared image and orthophoto were obtained by using the UAV equipped with thermal infrared imager and the Dajiang Elf Pro UAV. Based on high-resolution orthophotos,the improved Canny edge detection operator,support vector machine( SVM) and wavelet transform were used to extract the maize canopy region,and the classification results were binarized in thermal infrared imaging. The maize canopy temperature was extracted by using the mask generated by the binarization result. The extracted vector surface analysis extraction effect was applied and the accuracy of the three extraction algorithms was evaluated. The experimental results showed that the effects of the three methods from strong to weak were as follows: improved Canny edge detection operator,SVM and wavelet transform; the extraction accuracy was 87. 3%,74. 5% and 68. 2%,respectively. At the same time,the error analysis of the maize canopy temperature measured by the hand-held thermometer and the extracted canopy temperature was performed. The experimental results showed that the correlation between the canopy temperature extracted by the three algorithms and the measured temperature of the ground from strong to weak was as follows: 0. 929 5,0. 895 7 and 0. 876 0. The improved Canny edge detection operator can better extract the maize canopy area and obtain more accurate maize canopy temperature,so as to more effectively monitor the physiological status of maize,predict drought,and formulate reasonable irrigation and fertilization measures to increase maize yield.
引文
[1]张智韬,边江,韩文霆,等.无人机热红外图像计算冠层温度特征数诊断棉花水分胁迫[J].农业工程学报,2018,34(15):77-84.ZHANG Zhitao,BIAN Jiang,HAN Wenting,et al.Cotton moisture stress diagnosis based on canopy temperature characteristics calculated from UAV thermal infrared image[J].Transactions of the CSAE,2018,34(15):77-84.(in Chinese)
[2]WEBBER H,WHITE J W,KIMBALL B A,et al.Physical robustness of canopy temperature models for crop heat stress simulation across environments and production conditions[J].Field Crops Research,2018,216:75-88.
[3]史长丽,郭家选,梅旭荣,等.夏玉米农田表面温度影响因素分析[J].中国农业科学,2006,39(1):48-56.SHI Changli,GUO Jiaxuan,MEI Xurong.Analysis of the factors influencing surface temperature in summer maize field[J].Scientia Agricultura Sinica,2006,39(1):48-56.(in Chinese)
[4]SADLER E J,CAMP C R,EVANS D E,et al.Maize canpoy temperatures measured with a moving infrared thermometer array[J].Transactions of the ASAE,2002,45(3):581-591.
[5]KHANAL S,FULTON J,SHEARER S.An overview of current and potential applications of thermal remote sensing in precision agriculture[J].Computers and Electronics in Agriculture,2017,139:22-32.
[6]TANNER C B.Plant temperatures 1[J].Agronomy Journal,1963,55(2):210-211.
[7]MAHAN J R,BURKE J J,WANJURA D F,et al.Determination of temperature and time thresholds for BIOTIC irrigation of peanut on the Southern High Plains of Texas[J].Irrigation Science,2005,23(4):145-152.
[8]HAM J M,HEILMAN J L,LASCANO R J.Determination of soil water evaporation and transpiration from energy balance and stem flow measurements[J].Agricultural&Forest Meteorology,1990,52(3):287-301.
[9]KUENZER C,DECH S K.Thermal infrared remote sensing:sensors,methods,applications[J].Photogrammetric Engineering&Remote Sensing,2013,81(5):359-360.
[10]DEERY D M,REBETZKE G J,JIMENZE-BERNI J A,et al.Methodology for high-throughput field phenotyping of canopy temperature using airborne thermography[J].Frontiers in Plant Science,2016(7):1801-1814.
[11]侯英雨,孙林,何延波,等.利用EOS-MODIS数据提取作物冠层温度研究[J].农业工程学报,2006,22(12):8-12.HOU Yingyu,SUN Lin,HE Yanbo,et al.Extraction of crop canopy temperature using EOS-MODIS data[J].Transactions of the CSAE,2006,22(12):8-12.(in Chinese)
[12]杨贵军,李长春,于海洋,等.农用无人机多传感器遥感辅助小麦育种信息获取[J].农业工程学报,2015,31(21):184-190.YANG Guijun,LI Changchun,YU Haiyang,et al.Multi-sensor remote sensing assisted wheat breeding information acquisition for agricultural drones[J].Transactions of the CSAE,2015,31(21):184-190.(in Chinese)
[13]KATO A,OBANAWA H,HAYAKAWA Y,et al.Fusion between UAV-SFM and terrestrial laser scanner for field validation of satellite remote sensing[C]∥2015 IEEE International Geoscience&Remote Sensing Symposium,2015:2642-2645.
[14]MATESE A,TOSCANO P,GENNARO S F D,et al.Intercomparison of UAV,aircraft and satellite remote sensing platforms for precision agriculture[J].Remote Sensing,2015,7(3):2971-2990.
[15]POBLETE T,ORTEGAFARIAS S,RYU D.Automatic coregistration algorithm to remove canopy shaded pixels in UAV-Borne thermal images to improve the estimation of crop water stress index of a drip-irrigated cabernet sauvignon vineyard[J].Sensors,2018,18(2):397-414.
[16]ORTEGA-FARIAS S,ORTEGA-SALAZAR S,POBLETE T,et al.Estimation of energy balance components over a dripirrigated olive orchard using thermal and multispectral cameras placed on a helicopter-based unmanned aerial vehicle(UAV)[J].Remote Sensing,2016,8(8):638-656.
[17]CRAWFORD K E.Remote sensing of almond and walnut tree canopy temperatures using an inexpensive infrared sensor on a small unmanned aerial vehicle[J].Dissertations&Theses-Gradworks,2014,54(3):250-274.
[18]LUDOVISI R,TAURO F,SALVATI R,et al.UAV-based thermal imaging for high-throughput field phenotyping of black poplar response to drought[J].Frontiers in Plant Science,2017(8):1681-1699.
[19]CANNY J.Collision detection for moving polyhedra[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1986,8(2):200-209.
[20]张问银,金宁德.基于改进Canny算子的气液两相泡状流图像分割算法[J].计算机工程与科学,2009,31(8):137-139.ZHANG Wenyin,JIN Ningde.Image segmentation algorithm for gas-liquid two-phase bubble flow based on improved Canny operator[J].Computer Engineering and Science,2009,31(8):137-139.(in Chinese)
[21]凌凤彩,康牧,林晓.改进的Canny边缘检测算法[J].计算机科学,2016,43(8):309-312.LING Fengcai,KANG Mu,LIN Xiao.Improved Canny edge detection algorithm[J].Computer Science,2016,43(8):309-312.(in Chinese)
[22]BISWAS R,SIL J.An improved Canny edge detection algorithm based on type-2 fuzzy sets[J].Procedia Technology,2012,4(11):820-824.
[23]PARK S,LEE H,KIM J.Seed growing for interactive image segmentation using SVM classification with geodesic distance[J].Electronics Letters,2016,53(1):22-24.
[24]张睿,马建文.改进的P-SVM支持向量机与遥感数据分类[J].遥感学报,2009,13(3):437-452.ZHANG Rui,MA Jianwen.Improved P-SVM support vector machine and classification of remote sensing data[J].Journal of Remote Sensing,2009,13(3):437-452.(in Chinese)
[25]XIE X,WANG T.A projection twin SVM-based active contour model for image segmentation[C]∥2016 23rd International Conference on Mechatronics&Machine Vision in Practice,2017:1-4.
[26]邓晓飞,徐蔚鸿.一种结合多特征的SVM图像分割方法[J].计算机工程与科学,2013,35(2):154-158.DENG Xiaofei,XU Weihong.A SVM image segmentation method combining multiple features[J].Computer Engineering and Science,2013,35(2):154-158.(in Chinese)
[27]丁永军,张晶晶,SUK L W,等.小波变换与分水岭算法融合的番茄冠层叶片图像分割[J/OL].农业机械学报,2017,48(9):32-37.DING Yongjun,ZHANG Jingjing,SUK L W,et al.Image segmentation of tomato canopy blades based on wavelet transform and watershed algorithm[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(9):32-37.http:∥www.jcsam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20170904&flag=1.DOI:10.6041/j.issn.1000-1298.2017.09.004.(in Chinese)
[28]DA L,NIU D,HUI W,et al.Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm[J].Renewable Energy,2014,62(3):592-597.
[29]刘洲峰,徐庆伟,李春雷.基于小波变换的图像分割研究[J].计算机应用与软件,2009,26(4):62-64.LIU Zhoufeng,XU Qingwei,LI Chunlei.Research on image segmentation based on wavelet transform[J].Journal of Computer Applications and Software,2009,26(4):62-64.(in Chinese)
[30]SENTHILKANI A S,ANANTH C,CHAKKA R M,et al.Overlap wavelet transform for image segmentation[C]∥Proceedings of the International Journal of Electronics Communication&Computer Technology,2017.
[31]THAKUR R,YADAV A.Hybrid segmentation approach and preprocessing of color image based on Haar wavelet transform[J].International Journal of Computer Applications,2012,46(16):1-5.
[32]WIEDEMANN C,HEIPKE C,MAYER H.Empirical evaluation of automatically extracted road axes[J].Empirical Evaluation Techniques in Computer Vision,1998,47(3):172-187.
[2]WEBBER H,WHITE J W,KIMBALL B A,et al.Physical robustness of canopy temperature models for crop heat stress simulation across environments and production conditions[J].Field Crops Research,2018,216:75-88.
[3]史长丽,郭家选,梅旭荣,等.夏玉米农田表面温度影响因素分析[J].中国农业科学,2006,39(1):48-56.SHI Changli,GUO Jiaxuan,MEI Xurong.Analysis of the factors influencing surface temperature in summer maize field[J].Scientia Agricultura Sinica,2006,39(1):48-56.(in Chinese)
[4]SADLER E J,CAMP C R,EVANS D E,et al.Maize canpoy temperatures measured with a moving infrared thermometer array[J].Transactions of the ASAE,2002,45(3):581-591.
[5]KHANAL S,FULTON J,SHEARER S.An overview of current and potential applications of thermal remote sensing in precision agriculture[J].Computers and Electronics in Agriculture,2017,139:22-32.
[6]TANNER C B.Plant temperatures 1[J].Agronomy Journal,1963,55(2):210-211.
[7]MAHAN J R,BURKE J J,WANJURA D F,et al.Determination of temperature and time thresholds for BIOTIC irrigation of peanut on the Southern High Plains of Texas[J].Irrigation Science,2005,23(4):145-152.
[8]HAM J M,HEILMAN J L,LASCANO R J.Determination of soil water evaporation and transpiration from energy balance and stem flow measurements[J].Agricultural&Forest Meteorology,1990,52(3):287-301.
[9]KUENZER C,DECH S K.Thermal infrared remote sensing:sensors,methods,applications[J].Photogrammetric Engineering&Remote Sensing,2013,81(5):359-360.
[10]DEERY D M,REBETZKE G J,JIMENZE-BERNI J A,et al.Methodology for high-throughput field phenotyping of canopy temperature using airborne thermography[J].Frontiers in Plant Science,2016(7):1801-1814.
[11]侯英雨,孙林,何延波,等.利用EOS-MODIS数据提取作物冠层温度研究[J].农业工程学报,2006,22(12):8-12.HOU Yingyu,SUN Lin,HE Yanbo,et al.Extraction of crop canopy temperature using EOS-MODIS data[J].Transactions of the CSAE,2006,22(12):8-12.(in Chinese)
[12]杨贵军,李长春,于海洋,等.农用无人机多传感器遥感辅助小麦育种信息获取[J].农业工程学报,2015,31(21):184-190.YANG Guijun,LI Changchun,YU Haiyang,et al.Multi-sensor remote sensing assisted wheat breeding information acquisition for agricultural drones[J].Transactions of the CSAE,2015,31(21):184-190.(in Chinese)
[13]KATO A,OBANAWA H,HAYAKAWA Y,et al.Fusion between UAV-SFM and terrestrial laser scanner for field validation of satellite remote sensing[C]∥2015 IEEE International Geoscience&Remote Sensing Symposium,2015:2642-2645.
[14]MATESE A,TOSCANO P,GENNARO S F D,et al.Intercomparison of UAV,aircraft and satellite remote sensing platforms for precision agriculture[J].Remote Sensing,2015,7(3):2971-2990.
[15]POBLETE T,ORTEGAFARIAS S,RYU D.Automatic coregistration algorithm to remove canopy shaded pixels in UAV-Borne thermal images to improve the estimation of crop water stress index of a drip-irrigated cabernet sauvignon vineyard[J].Sensors,2018,18(2):397-414.
[16]ORTEGA-FARIAS S,ORTEGA-SALAZAR S,POBLETE T,et al.Estimation of energy balance components over a dripirrigated olive orchard using thermal and multispectral cameras placed on a helicopter-based unmanned aerial vehicle(UAV)[J].Remote Sensing,2016,8(8):638-656.
[17]CRAWFORD K E.Remote sensing of almond and walnut tree canopy temperatures using an inexpensive infrared sensor on a small unmanned aerial vehicle[J].Dissertations&Theses-Gradworks,2014,54(3):250-274.
[18]LUDOVISI R,TAURO F,SALVATI R,et al.UAV-based thermal imaging for high-throughput field phenotyping of black poplar response to drought[J].Frontiers in Plant Science,2017(8):1681-1699.
[19]CANNY J.Collision detection for moving polyhedra[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1986,8(2):200-209.
[20]张问银,金宁德.基于改进Canny算子的气液两相泡状流图像分割算法[J].计算机工程与科学,2009,31(8):137-139.ZHANG Wenyin,JIN Ningde.Image segmentation algorithm for gas-liquid two-phase bubble flow based on improved Canny operator[J].Computer Engineering and Science,2009,31(8):137-139.(in Chinese)
[21]凌凤彩,康牧,林晓.改进的Canny边缘检测算法[J].计算机科学,2016,43(8):309-312.LING Fengcai,KANG Mu,LIN Xiao.Improved Canny edge detection algorithm[J].Computer Science,2016,43(8):309-312.(in Chinese)
[22]BISWAS R,SIL J.An improved Canny edge detection algorithm based on type-2 fuzzy sets[J].Procedia Technology,2012,4(11):820-824.
[23]PARK S,LEE H,KIM J.Seed growing for interactive image segmentation using SVM classification with geodesic distance[J].Electronics Letters,2016,53(1):22-24.
[24]张睿,马建文.改进的P-SVM支持向量机与遥感数据分类[J].遥感学报,2009,13(3):437-452.ZHANG Rui,MA Jianwen.Improved P-SVM support vector machine and classification of remote sensing data[J].Journal of Remote Sensing,2009,13(3):437-452.(in Chinese)
[25]XIE X,WANG T.A projection twin SVM-based active contour model for image segmentation[C]∥2016 23rd International Conference on Mechatronics&Machine Vision in Practice,2017:1-4.
[26]邓晓飞,徐蔚鸿.一种结合多特征的SVM图像分割方法[J].计算机工程与科学,2013,35(2):154-158.DENG Xiaofei,XU Weihong.A SVM image segmentation method combining multiple features[J].Computer Engineering and Science,2013,35(2):154-158.(in Chinese)
[27]丁永军,张晶晶,SUK L W,等.小波变换与分水岭算法融合的番茄冠层叶片图像分割[J/OL].农业机械学报,2017,48(9):32-37.DING Yongjun,ZHANG Jingjing,SUK L W,et al.Image segmentation of tomato canopy blades based on wavelet transform and watershed algorithm[J/OL].Transactions of the Chinese Society for Agricultural Machinery,2017,48(9):32-37.http:∥www.jcsam.org/jcsam/ch/reader/view_abstract.aspx?file_no=20170904&flag=1.DOI:10.6041/j.issn.1000-1298.2017.09.004.(in Chinese)
[28]DA L,NIU D,HUI W,et al.Short-term wind speed forecasting using wavelet transform and support vector machines optimized by genetic algorithm[J].Renewable Energy,2014,62(3):592-597.
[29]刘洲峰,徐庆伟,李春雷.基于小波变换的图像分割研究[J].计算机应用与软件,2009,26(4):62-64.LIU Zhoufeng,XU Qingwei,LI Chunlei.Research on image segmentation based on wavelet transform[J].Journal of Computer Applications and Software,2009,26(4):62-64.(in Chinese)
[30]SENTHILKANI A S,ANANTH C,CHAKKA R M,et al.Overlap wavelet transform for image segmentation[C]∥Proceedings of the International Journal of Electronics Communication&Computer Technology,2017.
[31]THAKUR R,YADAV A.Hybrid segmentation approach and preprocessing of color image based on Haar wavelet transform[J].International Journal of Computer Applications,2012,46(16):1-5.
[32]WIEDEMANN C,HEIPKE C,MAYER H.Empirical evaluation of automatically extracted road axes[J].Empirical Evaluation Techniques in Computer Vision,1998,47(3):172-187.
© 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 |