The Estimation Model of Fractional Vegetation Cover of Maize Based on the Real Image of Farmland

doi:10.11924/j.issn.1000-6850.casb2020-0820

Abstract

Abstract:

To acquire the fractional vegetation cover (FVC) of maize on real-time, which could provide a scientific basis for maize growth monitoring, we took the image shot by the digital camera installed in automatic weather observation station as data sources, built FVC estimation models using 9 color vegetation indices of images (NDI, ExG, ExR, ExG-ExR, R-G, G-B, VEG, CIVE and (G-B)/|R-G|) extracted by employing image processing technologies. The results showed that these indices could estimate the FVC of maize effectively with high accuracy except the (G-B)/|R-G|, the vegetative (VEG) was the optimal color vegetation index for estimation of maize FVC. The model with VEG as variable had the highest estimation accuracy for maize FVC, with the highest coefficient of determination (R²), and lowest root mean square error (RMSE) and mean absolute error (MAE) of 0.993, 0.0270 and 0.0223, respectively. The method could be applied to the extraction of crop FVC effectively.

Key words: maize, fractional vegetation cover, digital image, color vegetation index, estimation model

CLC Number:

S566.1

Zhang Dongdong, Zhou Kanshe, Dai Rui, Yuan Lei, Wang Jiarui, Bian Duo. The Estimation Model of Fractional Vegetation Cover of Maize Based on the Real Image of Farmland[J]. Chinese Agricultural Science Bulletin, 2021, 37(29): 84-91.

Figures/Tables 7

References 25

[1]	Jiapaer G, Chen X, Bao A. A comparison of methods for estimating fractional vegetation cover in arid regions[J]. Agric. For. Meteorol., 1923, 151:1698-1710. doi: 10.1016/j.agrformet.2011.07.004 URL
[2]	牛亚晓, 张立元, 韩文霆, 等. 基于无人机遥感与植被指数的冬小麦覆盖度提取方法[J]. 农业机械学报, 2018, 49(4):212-221.
[3]	杨焕波, 赵静, 兰玉彬, 等. 基于无人机可见光遥感和阈值法的玉米植被覆盖度提取[J]. 福建农林大学学报:自然科学版, 2020, 49(2):283-288.
[4]	Coy André, Dale R, Michael T, et al. Increasing the Accuracy and Automation of Fractional Vegetation Cover Estimation from Digital Photographs[J]. Remote Sensing, 2016, 8(7):474. doi: 10.3390/rs8070474 URL
[5]	Allen R G, Pereira L S. Estimating crop coefficients from fraction of ground cover and height[J]. Irrigation Science, 2009, 28(1):17-34. doi: 10.1007/s00271-009-0182-z URL
[6]	赵静, 杨焕波, 兰玉彬, 等. 基于无人机可见光图像的夏季玉米植被覆盖度提取方法[J]. 农业机械学报, 2019, 50(5):232-240.
[7]	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.
[8]	张东东. 在线式图像的甘蔗长势无损监测研究[D]. 杭州:浙江大学, 2017.
[9]	潘卫华, 陈家金, 李丽纯, 等. 福建罗源湾互花米草的遥感动态监测[J]. 中国农学通报, 2009, 25(13):216-219.
[10]	王三, 赵伟, 黄春芳, 等. 基于遥感的重庆市土地利用动态变化研究[J]. 中国农学通报, 2010, 26(2):250-256.
[11]	贾勤学, 张玮, 李建林, 等. 基于遥感技术的耕地面积动态监测研究[J]. 中国农学通报, 2006(7):530-534.
[12]	张喜旺, 吴炳方. 基于中高分辨率遥感的植被覆盖度时相变换方法[J]. 生态学报, 2015, 35(4):1155-1164.
[13]	唐亮, 何明珠, 许华, 等. 基于无人机低空遥感的荒漠植被覆盖度与归一化植被指数验证及其对水热梯度的响应[J]. 应用生态学报, 2020, 31(1):35-44.
[14]	吴焕丽, 崔可旺, 张馨, 等. 基于改进K-means图像分割算法的细叶作物覆盖度提取[J]. 农业机械学报, 2019, 50(1):42-50.
[15]	Woebbecke D M, Meyer G E, Bargen K V, et al. Color Indices for Weed Identification Under Various Soil, Residue, and Lighting Conditions[J]. Transactions of the Asae, 1995, 38(1):259-269. doi: 10.13031/2013.27838 URL
[16]	A.J. Pérez, F. López, J.V. Benlloch, et al. Colour and shape analysis techniques for weed detection in cereal fields[J]. Computers and Electronics in Agriculture, 2000, 25(3):197-212. doi: 10.1016/S0168-1699(99)00068-X URL
[17]	Kataoka T, Kaneko T, Okamoto H, et al. Crop growth estimation system using machine vision[C]// IEEE/ASME International Conference on Advanced Intelligent Mechatronics. IEEE, 2003.
[18]	Dongdong Z, Mansaray L R, Hongwei J, et al. A universal estimation model of fractional vegetation cover for different crops based on time series digital photographs[J]. Computers and Electronics in Agriculture, 2018, 151:93-103. doi: 10.1016/j.compag.2018.05.030 URL
[19]	Woebbecke D M, Meyer G E, Von Bargen K, et al. Color Indices for Weed Identification Under Various Soil, Residue, and Lighting Conditions[J]. Transactions of the Asae, 1995, 38(1):259-269. doi: 10.13031/2013.27838 URL
[20]	George E M, João C N. Verification of color vegetation indices for automated crop imaging applications[J]. Computers and Electronics in Agriculture, 2008, 63(2):282-293. doi: 10.1016/j.compag.2008.03.009 URL
[21]	Hague T, Tillett N D, Wheeler H. Automated Crop and Weed Monitoring in Widely Spaced Cereals[J]. Precision Agriculture, 2006, 7(1):21-32. doi: 10.1007/s11119-005-6787-1 URL
[22]	贾建华, 胡勇, 刘良云. 青藏高原数字照片植被覆盖度自动算法与应用[J]. 地球信息科学学报, 2010, 12(06):880-885.
[23]	章文波, 刘宝元, 吴敬东. 小区植被覆盖度动态快速测量方法研究[J]. 水土保持通报, 2001, 21(6):60-63.
[24]	Hamuda E, Glavin M, Jones E. A survey of image processing techniques for plant extraction and segmentation in the field[J]. Computers and Electronics in Agriculture, 2016, 125:184-199. doi: 10.1016/j.compag.2016.04.024 URL
[25]	Ye M, Cao Z, Yu Z, et al. Crop feature extraction from images with probabilistic superpixel Markov random field[J]. Computers and Electronics in Agriculture, 2015, 114:247-260. doi: 10.1016/j.compag.2015.04.010 URL

名称	计算公式
绿减红(G-B)	G-B
超绿减超红(ExG-ExR)	2×G-R-B-(1.4×R-G)
超绿算子(ExG)	2×G-R-B
超红算子(ExR)	1.4×R-G
红减绿(R-G)	R-G
归一化指数(NDI)	(G-R)/(G+R)
(G-B)/\|R-G\|	(G-B)/\|R-G\|
Vegetative (VEG)	g/(r^a×b^1-a), a=0.667
作物提取颜色算子(CIVE)	0.441×R-0.811×G+0.385×B+18.78745

名称	计算公式
绿减红(G-B)	G-B
超绿减超红(ExG-ExR)	2×G-R-B-(1.4×R-G)
超绿算子(ExG)	2×G-R-B
超红算子(ExR)	1.4×R-G
红减绿(R-G)	R-G
归一化指数(NDI)	(G-R)/(G+R)
(G-B)/\|R-G\|	(G-B)/\|R-G\|
Vegetative (VEG)	g/(r^a×b^1-a), a=0.667
作物提取颜色算子(CIVE)	0.441×R-0.811×G+0.385×B+18.78745

时间分组	含义
T₉	利用9:00获取的图像计算的颜色指数值
T₁₀	利用10:00获取的图像计算的颜色指数值
T₁₆	利用16:00获取的图像计算的颜色指数值
T_平均	利用9:00、10:00、16:00获取的图像计算的颜色指数值的平均值

时间分组	含义
T₉	利用9:00获取的图像计算的颜色指数值
T₁₀	利用10:00获取的图像计算的颜色指数值
T₁₆	利用16:00获取的图像计算的颜色指数值
T_平均	利用9:00、10:00、16:00获取的图像计算的颜色指数值的平均值

颜色指数	覆盖度
颜色指数	T₉	T₁₀	T₁₆	T_平均
G-B	0.909^**	0.901^**	0.907^**	0.887^**
ExG-ExR	0.980^**	0.980^**	0.981^**	0.977^**
ExG	0.964^**	0.963^**	0.967^**	0.956^**
ExR	-0.981^**	-0.985^**	-0.984^**	-0.985^**
R-G	-0.972^**	-0.975^**	-0.982^**	-0.976^**
NDI	0.973^**	0.974^**	0.973^**	0.975^**
G-B/\|R-G\|	-0.115	-0.103	-0.067	-0.143
VEG	0.958^**	0.959^**	0.945^**	0.951^**
CIVE	-0.968^**	-0.966^**	-0.970^**	-0.960^**
样本数量	43	74	49	84