基于改进K-means图像分割算法的细叶作物覆盖度提取
|
摘要
植被覆盖度是重要的农学指标,图像法作为一种方便、快捷、准确度较高的地面测量方法,在该领域得到了广泛应用。图像背景分割是获取植被覆盖度最关键的步骤,已有分割算法的分割对象局限于大叶植物或者长势较为稀疏的作物,针对细叶作物的研究较少,或者未根据分割结果得出更有价值的规律。本文以小麦为例,提出了基于HSV空间的自适应果蝇均值聚类算法(IFOA-K-means),用来分割图像背景,以此作为获取覆盖度变化的理论基础。采用小波分析按比例去噪算法单独对亮度分量去噪,主体分割算法采用自适应步长果蝇算法(IFOA)改进的Kmeans算法对小麦图像进行背景分割,综合了自适应果蝇算法的全局最优和K-means算法的局部最优特点,使分割效果达到最优。其分割效果优于基于遗传算法的最大类间方差分割法,较好地去除了滴灌带等较明显干扰因素,与传统的K-means算法相比,运行时间和峰值信噪比指标都较优,小麦覆盖度准确率在90%以上,与作物系数之间的决定系数为0. 953 1。
Canopy coverage is an important agronomic indicator. Image method is widely used in this field as a convenient,fast and accurate ground measurement method. Image background segmentation is the most critical step to obtain canopy coverage. Some segmentation algorithms have been limited to largeleaf plants or crops with relatively sparse growth. Few studies were on fine leaf crops,or no more valuable rules based on segmentation results. Therefore,taking wheat as an example,an IFOA-K-means algorithm based on HSV space was proposed. The K-means algorithm split the image background as a theoretical basis for obtaining coverage changes. Then the wavelet denoising algorithm was used to denoise the luminance component separately. The main segmentation algorithm was improved by the adaptive step size fruit fly algorithm( IFOA). The K-means algorithm was used to perform background segmentation on wheat images,and the global optimality of the adaptive fruit fly algorithm and local optimal features of the K-means algorithm were integrated to optimize the segmentation effect. The segmentation effect was better than the Ostu method based on genetic algorithm. It was better to remove the obvious interference factors such as drip irrigation belt,compared with the traditional K-means algorithm,the segmentation results were superior to the traditional algorithms in terms of running time and peak signal-to-noise ratio. The accuracy of wheat coverage was over 90%,the fit to the crop coefficient was as high as 0. 953 1,and the estimation of wheat growth status was estimated.
Canopy coverage is an important agronomic indicator. Image method is widely used in this field as a convenient,fast and accurate ground measurement method. Image background segmentation is the most critical step to obtain canopy coverage. Some segmentation algorithms have been limited to largeleaf plants or crops with relatively sparse growth. Few studies were on fine leaf crops,or no more valuable rules based on segmentation results. Therefore,taking wheat as an example,an IFOA-K-means algorithm based on HSV space was proposed. The K-means algorithm split the image background as a theoretical basis for obtaining coverage changes. Then the wavelet denoising algorithm was used to denoise the luminance component separately. The main segmentation algorithm was improved by the adaptive step size fruit fly algorithm( IFOA). The K-means algorithm was used to perform background segmentation on wheat images,and the global optimality of the adaptive fruit fly algorithm and local optimal features of the K-means algorithm were integrated to optimize the segmentation effect. The segmentation effect was better than the Ostu method based on genetic algorithm. It was better to remove the obvious interference factors such as drip irrigation belt,compared with the traditional K-means algorithm,the segmentation results were superior to the traditional algorithms in terms of running time and peak signal-to-noise ratio. The accuracy of wheat coverage was over 90%,the fit to the crop coefficient was as high as 0. 953 1,and the estimation of wheat growth status was estimated.
引文
[1] LAW B E,VAN T S,CESCATTI A,et al. Estimation of leaf area index in open-canopy ponderosa pine forests at different successional stages and management regimes in Oregon[J]. Agricultural and Forest Meteorology,2001,108(1):1-14.
[2]孙佳佳,于东升,史学正,等.植被叶面积指数与覆盖度定量表征红壤区土壤侵蚀关系的对比研究[J].土壤学报,2010,47(6):1060-1066.SUN Jiajia,YU Dongsheng,SHI Xuezheng,et al. Comparison of between LAI and VFC in relationship with soil erosion in the red soil hilly region of South China[J]. Acta Pedologica Sinica,2010,47(6):1060-1066.(in Chinese)
[3] ADANS J E,ARKIN G F. A light interception method for measuring row copy ground cover[J]. Soil Science Society of America Journal,1977,41(4):789-791.
[4] WANJURA D F,HATFIELD J L. Sensitivity of spectral vegetative indice to crop biomass[J]. Transactions of the ASAE,1987,30(3):811-816.
[5]方雨晨,王培燕,田庆久.不同覆盖度下小麦农田土壤对NDVI影响模拟分析[J].遥感技术与应用,2017,32(4):660-666.FANG Yuchen,WANG Peiyan,TIAN Qingjiu. Simulation and analysis on the influence of soil background of wheat farmland on NDVI under different vegetation coverage[J]. Remote Sensing Technology and Application,2017,32(4):660-666.(in Chinese)
[6]王春梅,顾行发,余涛,等.农田春小麦叶面积指数和覆盖度时空变异性研究[J/OL].农业机械学报,2014,45(8):254-261,235. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20140841&journal_id=jcsam.DOI:10. 6041/j. issn. 1000-1298. 2014. 08. 041.WANG Chunmei,GU Xingfa,YU Tao,et al. Spatial and temporal variability of spring wheat leaf area index and coverage in northwest China[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(8):254-261,235.(in Chinese)
[7] ARMBRUST D V. Rapid measurement of crop canopy cover[J]. Agronomy Journal,1990,82(6):1170-1171.
[8] ROBERT P E,ROBERT H. Quantitative color image analysis of agronomic images[J]. Agronomy Journal,1999,91(1):148-153.
[9]王爱芸,赵志芳.基于遥感的植被覆盖度估算方法研究进展[J].绿色科技,2015(3):10-14.WANG Aiyun,ZHAO Zhifang. Research advances on the method of estimating vegetation coverage based on remote sensing[J].Journal of Green Science and Technology,2015(3):10-14.(in Chinese)
[10] LIU Manhua,ZHAO Hui,TAO Wei,et al. Leaf extraction from complicated background[C]∥Image and Signal Processing,CISP'09. 2nd International Congress,2009.
[11] DEEPIKA K,RUTH I,KEERTHANA S,et al. Robust plant recognition using graph cut based flower segmentation and PHOG based feature extraction[C]∥2012 International Conference on Machine Vision and Image Processing,2012:14-15.
[12]万园洁,卿粼波,何小海,等.基于改进全卷积网络的小麦图像分割[J].计算机系统应用,2018,27(3):221-227.WAN Yuanjie,QING Linbo,HE Xiaohai,et al. Wheat grain image segmentation based on improved fully convolutional network[J]. Computer Systems&Applications,2018,27(3):221-227.(in Chinese)
[13]孙立新,张栩之,邓先瑞.自适应果蝇算法优化模糊均值聚类算法图像分割[J].控制工程,2016,23(4):494-499.SUN Lixin,ZHANG Xuzhi,DENG Xianrui. Image segmentation based on self-adaptive fruit fly algorithm optimizing fuzzy means clustering algorithm[J]. Control Engineering of China,2016,23(4):494-499.(in Chinese)
[14]黄芬,于琪,姚霞.小麦冠层图像H分量的K均值聚类分割[J].计算机工程与应用,2014,50(3):129-134.HUANG Fen,YU Qi,YAO Xia,et al. K-means clustering segmentation for H weight of wheat canopy image[J]. Computer Engineering and Applications,2014,50(3):129-134.(in Chinese)
[15]何建斌,梁威,李晓明.基于K均值聚类和数学形态学的小麦彩色图像分割[J].浙江农业学报,2011,23(4):829-832.HE Jianbin,LIANG Wei,LI Xiaoming. The color image segmentation of wheat based on K-means clustering and mathematical morphology[J]. Acta Agriculturae Zhejiangensis,2011,23(4):829-832.(in Chinese)
[16]邬春学,刘训洋.改进粒子群结合K-均值聚类的图像分割算法[J].电子科技,2016,29(8):93-95.WU Chunxue,LIU Xunyang. A modified PSO combined K-means clustering algorithm for image segmentation[J]. Electronic Science and Technology,2016,29(8):93-95.(in Chinese)
[17]丁政建,孙进.基于颜色空间和核函数的FCM图像分割算法[J].计算机应用与软件,2014,31(2):222-225.DING Zhengjian,SUN Jin. FCM image segmentation algorithm based on colour space and kernel function[J]. Computer Applications and Software,2014,31(2):222-225.(in Chinese)
[18]李灿灿,王宝,王静,等.基于K-means聚类的植物叶片图像叶脉提取[J].农业工程学报,2012,28(17):157-162.LI Cancan,WANG Bao,WANG Jing,et al. Extracting vein of leaf image based on K-means clustering[J]. Transactions of the CSAE,2012,28(17):157-162.(in Chinese)
[19]霍迎秋,秦仁波,邢彩燕,等.基于CUDA的并行K-means聚类图像分割算法优化[J/OL].农业机械学报,2014,45(11):47-53. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20141108&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2014. 11. 008.HUO Yingqiu,QIN Renbo,XING Caiyan,et al. CUDA-based parallel K-means clustering algorithm[J/OL]. Transaction of the Chinese Society for Agricultural Machinery,2014,45(11):47-53.(in Chinese)
[20]沈跃,徐慧,刘慧,等.基于K-means和近邻回归算法的Kinect植株深度图像修复[J].农业工程学报,2016,32(19):188-194.SHEN Yue,XU Hui,LIU Hui,et al. Kinect scanning plant depth image restoration based on K-means and K-nearest neighbor algorithms[J]. Transactions of the CSAE,2016,32(19):188-194.(in Chinese)
[21]徐黎明,吕继东.基于同态滤波和K均值聚类算法的杨梅图像分割[J].农业工程学报,2015,31(14):202-208.XU Liming,LJidong. Bayberry image segmentation based on homomorphic filtering and K-means clustering algorithm[J].Transactions of the CSAE,2015,31(14):202-208.(in Chinese)
[22]王丹丹,徐越,宋怀波,等.融合K-means与Ncut算法的无遮挡双重叠苹果目标分割与重建[J].农业工程学报,2015,31(10):227-234.WANG Dandan,XU Yue,SONG Huaibo,et al. Fusion of K-means and Ncut algorithm to realize segmentation and reconstruction of two overlapped apples without blocking by branches and leaves[J]. Transactions of the CSAE,2015,31(10):227-234.(in Chinese)
[23] JOHN H H. Hidden order:how adaptation builds complexity[M]. MA:Addision—Wesley Publishing Company,Inc.,1995.
[24] SUN Penfei,REN Honge,DONG Benzhi. Partial minimum error thresholding method of cavity image combined with genetic algorithm[J]. Computer Engineering and Applications,2012,48(7):169-171.
[25]赵继印,郝志成,李建坡.小波自适应比例改进算法在图像去噪中的应用[J].光电工程,2006,33(1):81-84,102.ZHAO Jiyin,HAO Zhicheng,LI Jianpo. Image denoising using improved adaptive proportion-shrinking algorithm in wavelet field[J]. Opto-Electronic Engineering,2006,33(1):81-84,102.(in Chinese)
[26]濮震宇.基于小波收缩的图像去噪[D].苏州:苏州大学,2010.PU Zhenyu. Image de-noising based on wavelet shrinkage[D]. Suzhou:Suzhou University,2010.(in Chinese)
[27]胡能发.演化式果蝇算法及其应用研究[J].计算机技术与发展,2013,23(7):131-133.HU Nengfa. Evolutionary fruit algorithm and its application research[J]. Computer Technology and Development,2013,23(7):131-133.(in Chinese)
[28]潘文超.应用果蝇优化算法优化广义回归神经网络进行企业经营绩效评估[J].太原理工大学学报(社会科学版),2011,29(4):1-5.PAN Wenchao. Using of fruit fly optimization algorithm optimized general regression neural network to construct the operating performance of enterprise model[J]. Journal of Taiyuan University of Technology(Social Sciences Edition),2011,29(4):1-5.(in Chinese)
[29] PAN Wenchao. A new fruit fly optimization algorithm:taking the financial distress model as an example[J]. Knowledge Based Systems,2012,26:69-74.
[30]霍慧慧.果蝇优化算法及其应用研究[D].太原:太原理工大学,2015.HUO Huihui. Fruit fly optimization algorithm and its application[D]. Taiyuan:Taiyuan University of Technology,2015.(in Chinese)
[31]肖祥元,景文博,赵海丽.基于峰值信噪比改进的图像增强算法[J].长春理工大学学报(自然科学版),2017,40(4):83-86.XIAO Xiangyuan,JING Wenbo,ZHAO Haili. An improved image enhancement algorithm based on peak-signal to noise ratio[J].Journal of Changchun University of Science and Technology(Natural Science Edition),2017,40(4):83-86.(in Chinese)
[32]秦伟,朱清科,张学霞,等.植被覆盖度及其测算方法研究进展[J].西北农林科技大学学报(自然科学版),2006,34(9):163-170.QIN Wei,ZHU Qingke,ZHANG Xuexia,et al. Review of vegetation covering and its measuring and calculating method[J].Journal of Northwest A&F University(Natural Science Edition),2006,34(9):163-170.(in Chinese)
[33]李翠娜,张雪芬,余正泓,等.基于图像提取技术计算夏玉米覆盖度和反演叶面积指数的精度评价[J].中国农业气象,2016,37(4):479-491.LI Cuina,ZHANG Xuefen,YU Zhenghong,et al. Accuracy evaluation of summer maize coverage and leaf area index inversion based on image extraction technology[J]. Chinese Agrometeorology,2016,37(4):479-491.(in Chinese)
[34]吉增宝.用数码照片和Photoshop计算植被覆盖度的简易方法[J].水土保持应用技术,2015(5):10-11.JI Zengbao. A simple method for calculating vegetation coverage using digital photos and Photoshop[J]. Technology of Soil and Water Conservation,2015(5):10-11.(in Chinese)
[2]孙佳佳,于东升,史学正,等.植被叶面积指数与覆盖度定量表征红壤区土壤侵蚀关系的对比研究[J].土壤学报,2010,47(6):1060-1066.SUN Jiajia,YU Dongsheng,SHI Xuezheng,et al. Comparison of between LAI and VFC in relationship with soil erosion in the red soil hilly region of South China[J]. Acta Pedologica Sinica,2010,47(6):1060-1066.(in Chinese)
[3] ADANS J E,ARKIN G F. A light interception method for measuring row copy ground cover[J]. Soil Science Society of America Journal,1977,41(4):789-791.
[4] WANJURA D F,HATFIELD J L. Sensitivity of spectral vegetative indice to crop biomass[J]. Transactions of the ASAE,1987,30(3):811-816.
[5]方雨晨,王培燕,田庆久.不同覆盖度下小麦农田土壤对NDVI影响模拟分析[J].遥感技术与应用,2017,32(4):660-666.FANG Yuchen,WANG Peiyan,TIAN Qingjiu. Simulation and analysis on the influence of soil background of wheat farmland on NDVI under different vegetation coverage[J]. Remote Sensing Technology and Application,2017,32(4):660-666.(in Chinese)
[6]王春梅,顾行发,余涛,等.农田春小麦叶面积指数和覆盖度时空变异性研究[J/OL].农业机械学报,2014,45(8):254-261,235. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20140841&journal_id=jcsam.DOI:10. 6041/j. issn. 1000-1298. 2014. 08. 041.WANG Chunmei,GU Xingfa,YU Tao,et al. Spatial and temporal variability of spring wheat leaf area index and coverage in northwest China[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2014,45(8):254-261,235.(in Chinese)
[7] ARMBRUST D V. Rapid measurement of crop canopy cover[J]. Agronomy Journal,1990,82(6):1170-1171.
[8] ROBERT P E,ROBERT H. Quantitative color image analysis of agronomic images[J]. Agronomy Journal,1999,91(1):148-153.
[9]王爱芸,赵志芳.基于遥感的植被覆盖度估算方法研究进展[J].绿色科技,2015(3):10-14.WANG Aiyun,ZHAO Zhifang. Research advances on the method of estimating vegetation coverage based on remote sensing[J].Journal of Green Science and Technology,2015(3):10-14.(in Chinese)
[10] LIU Manhua,ZHAO Hui,TAO Wei,et al. Leaf extraction from complicated background[C]∥Image and Signal Processing,CISP'09. 2nd International Congress,2009.
[11] DEEPIKA K,RUTH I,KEERTHANA S,et al. Robust plant recognition using graph cut based flower segmentation and PHOG based feature extraction[C]∥2012 International Conference on Machine Vision and Image Processing,2012:14-15.
[12]万园洁,卿粼波,何小海,等.基于改进全卷积网络的小麦图像分割[J].计算机系统应用,2018,27(3):221-227.WAN Yuanjie,QING Linbo,HE Xiaohai,et al. Wheat grain image segmentation based on improved fully convolutional network[J]. Computer Systems&Applications,2018,27(3):221-227.(in Chinese)
[13]孙立新,张栩之,邓先瑞.自适应果蝇算法优化模糊均值聚类算法图像分割[J].控制工程,2016,23(4):494-499.SUN Lixin,ZHANG Xuzhi,DENG Xianrui. Image segmentation based on self-adaptive fruit fly algorithm optimizing fuzzy means clustering algorithm[J]. Control Engineering of China,2016,23(4):494-499.(in Chinese)
[14]黄芬,于琪,姚霞.小麦冠层图像H分量的K均值聚类分割[J].计算机工程与应用,2014,50(3):129-134.HUANG Fen,YU Qi,YAO Xia,et al. K-means clustering segmentation for H weight of wheat canopy image[J]. Computer Engineering and Applications,2014,50(3):129-134.(in Chinese)
[15]何建斌,梁威,李晓明.基于K均值聚类和数学形态学的小麦彩色图像分割[J].浙江农业学报,2011,23(4):829-832.HE Jianbin,LIANG Wei,LI Xiaoming. The color image segmentation of wheat based on K-means clustering and mathematical morphology[J]. Acta Agriculturae Zhejiangensis,2011,23(4):829-832.(in Chinese)
[16]邬春学,刘训洋.改进粒子群结合K-均值聚类的图像分割算法[J].电子科技,2016,29(8):93-95.WU Chunxue,LIU Xunyang. A modified PSO combined K-means clustering algorithm for image segmentation[J]. Electronic Science and Technology,2016,29(8):93-95.(in Chinese)
[17]丁政建,孙进.基于颜色空间和核函数的FCM图像分割算法[J].计算机应用与软件,2014,31(2):222-225.DING Zhengjian,SUN Jin. FCM image segmentation algorithm based on colour space and kernel function[J]. Computer Applications and Software,2014,31(2):222-225.(in Chinese)
[18]李灿灿,王宝,王静,等.基于K-means聚类的植物叶片图像叶脉提取[J].农业工程学报,2012,28(17):157-162.LI Cancan,WANG Bao,WANG Jing,et al. Extracting vein of leaf image based on K-means clustering[J]. Transactions of the CSAE,2012,28(17):157-162.(in Chinese)
[19]霍迎秋,秦仁波,邢彩燕,等.基于CUDA的并行K-means聚类图像分割算法优化[J/OL].农业机械学报,2014,45(11):47-53. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? flag=1&file_no=20141108&journal_id=jcsam. DOI:10. 6041/j. issn. 1000-1298. 2014. 11. 008.HUO Yingqiu,QIN Renbo,XING Caiyan,et al. CUDA-based parallel K-means clustering algorithm[J/OL]. Transaction of the Chinese Society for Agricultural Machinery,2014,45(11):47-53.(in Chinese)
[20]沈跃,徐慧,刘慧,等.基于K-means和近邻回归算法的Kinect植株深度图像修复[J].农业工程学报,2016,32(19):188-194.SHEN Yue,XU Hui,LIU Hui,et al. Kinect scanning plant depth image restoration based on K-means and K-nearest neighbor algorithms[J]. Transactions of the CSAE,2016,32(19):188-194.(in Chinese)
[21]徐黎明,吕继东.基于同态滤波和K均值聚类算法的杨梅图像分割[J].农业工程学报,2015,31(14):202-208.XU Liming,LJidong. Bayberry image segmentation based on homomorphic filtering and K-means clustering algorithm[J].Transactions of the CSAE,2015,31(14):202-208.(in Chinese)
[22]王丹丹,徐越,宋怀波,等.融合K-means与Ncut算法的无遮挡双重叠苹果目标分割与重建[J].农业工程学报,2015,31(10):227-234.WANG Dandan,XU Yue,SONG Huaibo,et al. Fusion of K-means and Ncut algorithm to realize segmentation and reconstruction of two overlapped apples without blocking by branches and leaves[J]. Transactions of the CSAE,2015,31(10):227-234.(in Chinese)
[23] JOHN H H. Hidden order:how adaptation builds complexity[M]. MA:Addision—Wesley Publishing Company,Inc.,1995.
[24] SUN Penfei,REN Honge,DONG Benzhi. Partial minimum error thresholding method of cavity image combined with genetic algorithm[J]. Computer Engineering and Applications,2012,48(7):169-171.
[25]赵继印,郝志成,李建坡.小波自适应比例改进算法在图像去噪中的应用[J].光电工程,2006,33(1):81-84,102.ZHAO Jiyin,HAO Zhicheng,LI Jianpo. Image denoising using improved adaptive proportion-shrinking algorithm in wavelet field[J]. Opto-Electronic Engineering,2006,33(1):81-84,102.(in Chinese)
[26]濮震宇.基于小波收缩的图像去噪[D].苏州:苏州大学,2010.PU Zhenyu. Image de-noising based on wavelet shrinkage[D]. Suzhou:Suzhou University,2010.(in Chinese)
[27]胡能发.演化式果蝇算法及其应用研究[J].计算机技术与发展,2013,23(7):131-133.HU Nengfa. Evolutionary fruit algorithm and its application research[J]. Computer Technology and Development,2013,23(7):131-133.(in Chinese)
[28]潘文超.应用果蝇优化算法优化广义回归神经网络进行企业经营绩效评估[J].太原理工大学学报(社会科学版),2011,29(4):1-5.PAN Wenchao. Using of fruit fly optimization algorithm optimized general regression neural network to construct the operating performance of enterprise model[J]. Journal of Taiyuan University of Technology(Social Sciences Edition),2011,29(4):1-5.(in Chinese)
[29] PAN Wenchao. A new fruit fly optimization algorithm:taking the financial distress model as an example[J]. Knowledge Based Systems,2012,26:69-74.
[30]霍慧慧.果蝇优化算法及其应用研究[D].太原:太原理工大学,2015.HUO Huihui. Fruit fly optimization algorithm and its application[D]. Taiyuan:Taiyuan University of Technology,2015.(in Chinese)
[31]肖祥元,景文博,赵海丽.基于峰值信噪比改进的图像增强算法[J].长春理工大学学报(自然科学版),2017,40(4):83-86.XIAO Xiangyuan,JING Wenbo,ZHAO Haili. An improved image enhancement algorithm based on peak-signal to noise ratio[J].Journal of Changchun University of Science and Technology(Natural Science Edition),2017,40(4):83-86.(in Chinese)
[32]秦伟,朱清科,张学霞,等.植被覆盖度及其测算方法研究进展[J].西北农林科技大学学报(自然科学版),2006,34(9):163-170.QIN Wei,ZHU Qingke,ZHANG Xuexia,et al. Review of vegetation covering and its measuring and calculating method[J].Journal of Northwest A&F University(Natural Science Edition),2006,34(9):163-170.(in Chinese)
[33]李翠娜,张雪芬,余正泓,等.基于图像提取技术计算夏玉米覆盖度和反演叶面积指数的精度评价[J].中国农业气象,2016,37(4):479-491.LI Cuina,ZHANG Xuefen,YU Zhenghong,et al. Accuracy evaluation of summer maize coverage and leaf area index inversion based on image extraction technology[J]. Chinese Agrometeorology,2016,37(4):479-491.(in Chinese)
[34]吉增宝.用数码照片和Photoshop计算植被覆盖度的简易方法[J].水土保持应用技术,2015(5):10-11.JI Zengbao. A simple method for calculating vegetation coverage using digital photos and Photoshop[J]. Technology of Soil and Water Conservation,2015(5):10-11.(in Chinese)