基于影像分割的覆膜玉米叶绿素含量反演

doi:10.3864/j.issn.0578-1752.2024.06.004

摘要/Abstract

摘要：

【目的】快速、准确监测覆膜玉米叶绿素含量，探明将影像地膜和阴影背景像元剔除能否提高光谱和纹理特征反演叶绿素含量的精度。【方法】以无人机多光谱遥感影像数据为基础，以覆膜玉米苗期、拔节期、抽雄期和灌浆期叶绿素含量为对象，使用监督分类分割影像背景像元和玉米像元，分析背景像元对玉米冠层光谱的影响，计算全像元和玉米像元影像的光谱特征和纹理特征并筛选较优变量输入，利用偏最小二乘、支持向量机和BP神经网络3种机器学习算法建立玉米叶绿素含量的反演模型。【结果】（1）苗期、拔节期、抽雄期和灌浆期多光谱影像中的背景像元对玉米冠层的光谱均有显著影响。（2）基于玉米像元影像提取的光谱特征、纹理特征和光谱特征+纹理特征为变量输入的反演精度均优于全像元影像(最佳模型建模R²提高0.078，RMSE和MAE分别降低0.060和0.055 mg·g^-1，验证R²提高0.109，RMSE和MAE分别降低0.075和0.047 mg·g^-1)。（3）基于玉米像元影像的光谱特征+纹理特征为变量输入的建模精度比仅使用光谱特征或纹理特征为变量输入的建模精度提升显著；其中光谱特征+纹理特征为变量输入的BP神经网络模型精度最高（验证R²、RMSE、MAE分别为0.690、0.468 mg·g^-1、0.375 mg·g^-1）。【结论】采用剔除背景像元的无人机多光谱影像光谱和纹理特征数据并结合BP神经网络可较好地实现覆膜玉米叶绿素含量的反演，研究结果可为无人机遥感快速、准确反演覆膜玉米叶绿素含量提供理论参考。

关键词: 无人机多光谱, 影像分割, 叶绿素含量, 覆膜, 纹理特征

Abstract:

【Objective】 In order to quickly and accurately monitor chlorophyll content of film-mulched maize, explore whether the removal of film and shadow background pixels can improve the accuracy of chlorophyll content inversion with spectral and texture features.【Method】 This study was based on multi-spectral remote sensing image data of unmanned aerial vehicle (UAV) and took chlorophyll content of film-mulched maize at seedling stage, jointing stage, tasseling stage and filling stage as objects. The support vector machine supervised classification was used to segment image background pixels and maize pixels, analyze the influence of background pixels on the spectra of maize canopy, the vegetation index and texture features of all pixels and maize pixels images were calculated and the better variable input was screened, and the inversion model of leaf chlorophyll content was established by using three machine learning algorithms, partial least squares, support vector machine and BP neural network.【Result】 (1) Background pixels in the multispectral images at seedling stage, jointing stage, tasseling stage and filling stage had significant effects on the spectra of maize canopy. (2) The inversion accuracy of vegetation index, texture feature and vegetation index + texture feature as variable input based on maize pixels image extraction was better than that of all pixels image (R² for optimal model was increased by 0.078, RMSE and MAE were decreased by 0.060 and 0.055 mg·g^-1, respectively, and R² for verification was increased by 0.109, RMSE and MAE were reduced by 0.075 and 0.047 mg·g^-1, respectively. (3) The modeling accuracy based on maize pixels image with spectral features + texture features as variable inputs was significantly improved over the modeling accuracy using only spectral features or texture features as variable inputs; The BP neural network model with spectral features + texture features as variable inputs had the highest accuracy (R², RMSE and MAE were 0.690, 0.468 mg·g^-1 and 0.375 mg·g^-1, respectively).【Conclusion】 The multispectral image spectral and texture feature data of UAV with removing background pixels and combined with BP neural network can better realize the inversion of chlorophyll content of film-mulched maize. The results can provide theoretical reference for quick and accurate retrieval of leaf chlorophyll content of film-mulched maize by UAV remote sensing.

Key words: UAV multispectral, image segmentation, chlorophyll content, film-mulching, texture feature

周智辉, 谷晓博, 程智楷, 常甜, 赵彤彤, 王玉明, 杜娅丹. 基于影像分割的覆膜玉米叶绿素含量反演[J]. 中国农业科学, 2024, 57(6): 1066-1079.

ZHOU ZhiHui, GU XiaoBo, CHENG ZhiKai, CHANG Tian, ZHAO TongTong, WANG YuMing, DU YaDan. Inversion of Chlorophyll Content of Film-Mulched Maize Based on Image Segmentation[J]. Scientia Agricultura Sinica, 2024, 57(6): 1066-1079.

0
/ / 推荐

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: https://www.chinaagrisci.com/CN/10.3864/j.issn.0578-1752.2024.06.004

https://www.chinaagrisci.com/CN/Y2024/V57/I6/1066

图/表 14

图1

表1

表2

图2

图3

表3

表4

图4

图5

表5

表6

表7

图6

图7

参考文献 46

[1]	薛颖昊, 周涛, 靳拓, 徐志宇. 农用地膜污染合作治理模式及其绩效损失研究. 中国农业资源与区划, 2022, 43(11): 39-50.
	XUE Y H, ZHOU T, JIN T, XU Z Y. Research on the cooperative governance model and performance loss of agricultural plastic film recovery. Chinese Journal of Agricultural Resources and Regional Planning, 2022, 43(11): 39-50. (in Chinese)
[2]	张金瑞, 任思洋, 戴吉照, 丁凡, 肖谋良, 刘学军, 严昌荣, 葛体达, 汪景宽, 刘勤, 王锴, 张福锁. 地膜对农业生产的影响及其污染控制. 中国农业科学, 2022, 55(20): 3983-3996. doi: 10.3864/j.issn.0578-1752.2022.20.010.
	ZHANG J R, REN S Y, DAI J Z, DING F, XIAO M L, LIU X J, YAN C R, GE T D, WANG J K, LIU Q, WANG K, ZHANG F S. Influence of plastic film on agricultural production and its pollution control. Scientia Agricultura Sinica, 2022, 55(20): 3983-3996. doi: 10.3864/j.issn.0578-1752.2022.20.010. (in Chinese)
[3]	方恒, 李援农, 谷晓博, 银敏华, 杨金宇. 覆膜与施氮组合下夏玉米籽粒灌浆过程拟合分析. 农业机械学报, 2018, 49(8): 245-252.
	FANG H, LI Y N, GU X B, YIN M H, YANG J Y. Fitting and analysis of grain filling of summer maize under combination of film mulching and nitrogen fertilizer. Transactions of the Chinese Society for Agricultural Machinery, 2018, 49(8): 245-252. (in Chinese)
[4]	周昌明, 李援农, 银敏华, 谷晓博, 赵玺. 连垄全覆盖降解膜集雨种植促进玉米根系生长提高产量. 农业工程学报, 2015, 31(7): 109-117.
	ZHOU C M, LI Y N, YIN M H, GU X B, ZHAO X. Ridge-furrow planting with biodegradable film mulching over ridges for rain harvesting improving root growth and yield of maize. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(7): 109-117. (in Chinese)
[5]	QIAO L, ZHAO R, TANG W, AN L, SUN H, LI M, WANG N, LIU Y, LIU G. Estimating maize LAI by exploring deep features of vegetation index map from UAV multispectral images. Field Crops Research, 2022, 289: 108739. doi: 10.1016/j.fcr.2022.108739
[6]	苏伟, 王伟, 刘哲, 张明政, 边大红, 崔彦宏, 黄健熙. 无人机影像反演玉米冠层LAI和叶绿素含量的参数确定. 农业工程学报, 2020, 36(19): 58-65.
	SU W, WANG W, LIU Z, ZHANG M Z, BIAN D H, CUI Y H, HUANG J X. Determining the retrieving parameters of corn canopy LAI and chlorophyll content computed using UAV image. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(19): 58-65. (in Chinese)
[7]	牛庆林, 冯海宽, 周新国, 朱建强, 雍蓓蓓, 李会贞. 冬小麦SPAD值无人机可见光和多光谱植被指数结合估算. 农业机械学报, 2021, 52(8): 183-194.
	NIU Q L, FENG H K, ZHOU X G, ZHU J Q, YONG B B, LI H Z. Combining UAV visible light and multispectral vegetation indices for estimating SPAD value of winter wheat. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(8): 183-194. (in Chinese)
[8]	HASITUYA, CHEN Z, WANG L, WU W B, JIANG Z W, LI H. Monitoring plastic-mulched farmland by Landsat-8 OLI imagery using spectral and textural features. Remote Sensing, 2016, 8(4): 353. doi: 10.3390/rs8040353
[9]	孟庆兰, 高军凯, 卢筱茜, 常学礼. 覆膜种植对玉米生长初期NDVI识别的影响. 生态学杂志, 2016, 35(7): 1761-1766.
	MENG Q L, GAO J K, LU X Q, CHANG X L. Impacts of film mulch planting on NDVI identification in corn early growth. Chinese Journal of Ecology, 2016, 35(7): 1761-1766. (in Chinese)
[10]	姚志华, 陈俊英, 张智韬, 谭丞轩, 魏广飞, 王新涛. 覆膜对无人机多光谱遥感反演土壤含盐量精度的影响. 农业工程学报, 2019, 35(19): 89-97.
	YAO Z H, CHEN J Y, ZHANG Z T, TAN C X, WEI G F, WANG X T. Effect of plastic film mulching on soil salinity inversion by using UAV multispectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(19): 89-97. (in Chinese)
[11]	黄茜, 杨伟才, 魏夏永, 毛晓敏. 不同覆膜处理下春玉米叶面积指数高光谱估算. 农业机械学报, 2021, 52(7): 184-194.
	HUANG X, YANG W C, WEI X Y, MAO X M. Hyperspectral estimation of leaf area index of spring maize under different film mulching treatments. Transactions of the Chinese Society for Agricultural Machinery, 2021, 52(7): 184-194. (in Chinese)
[12]	HUANG X, GUAN H, BO L, XU Z, MAO X. Hyperspectral proximal sensing of leaf chlorophyll content of spring maize based on a hybrid of physically based modelling and ensemble stacking. Computers and Electronics in Agriculture, 2023, 208: 107745. doi: 10.1016/j.compag.2023.107745
[13]	魏夏永, 黄茜, 薄丽媛, 毛晓敏. 西北旱区不同覆膜和灌溉水平下的玉米冠层氮含量垂直分布及高光谱反演. 中国农业大学学报, 2022, 27(11): 13-21.
	WEI X Y, HUANG X, BO L Y, MAO X M. Vertical distribution of nitrogen content in spring maize leaves and its hyperspectral inversion under different film mulching and irrigation levels in northwest arid region. Journal of China Agricultural University, 2022, 27(11): 13-21. (in Chinese)
[14]	JAY S, BARET F, DUTARTRE D, MALATESTA G, HÉNO S, COMAR A, WEISS M, MAUPAS F. Exploiting the centimeter resolution of UAV multispectral imagery to improve remote-sensing estimates of canopy structure and biochemistry in sugar beet crops. Remote Sensing of Environment, 2019, 231: 110898. doi: 10.1016/j.rse.2018.09.011
[15]	邓尚奇, 赵钰, 白雪源, 李旭, 孙振东, 梁健, 李振海, 成枢. 基于无人机图像分割的冬小麦叶绿素与叶面积指数反演. 农业工程学报, 2022, 38(3): 136-145.
	DENG S Q, ZHAO Y, BAI X Y, LI X, SUN Z D, LIANG J, LI Z H, CHENG S. Inversion of chlorophyll and leaf area index for winter wheat based on UAV image segmentation. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(3): 136-145. (in Chinese)
[16]	CHEN P, WANG F. Effect of crop spectra purification on plant nitrogen concentration estimations performed using high-spatial- resolution images obtained with unmanned aerial vehicles. Field Crops Research, 2022, 288: 108708. doi: 10.1016/j.fcr.2022.108708
[17]	刘畅, 杨贵军, 李振海, 汤伏全, 王建雯, 张春兰, 张丽妍. 融合无人机光谱信息与纹理信息的冬小麦生物量估测. 中国农业科学, 2018, 51(16): 3060-3073. doi: 10.3864/j.issn.0578-1752.2018.16.003.
	LIU C, YANG G J, LI Z H, TANG F Q, WANG J W, ZHANG C L, ZHANG L Y. Biomass estimation in winter wheat by UAV spectral information and texture information fusion. Scientia Agricultura Sinica, 2018, 51(16): 3060-3073. doi: 10.3864/j.issn.0578-1752.2018.16.003. (in Chinese)
[18]	ZHENG H, CHENG T, ZHOU M, LI D, YAO X, TIAN Y, CAO W, ZHU Y. Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery. Precision Agriculture, 2019, 20: 611-629. doi: 10.1007/s11119-018-9600-7
[19]	陈鹏, 冯海宽, 李长春, 杨贵军, 杨钧森, 杨文攀, 刘帅兵. 无人机影像光谱和纹理融合信息估算马铃薯叶片叶绿素含量. 农业工程学报, 2019, 35(11): 63-74.
	CHEN P, FENG H K, LI C C, YANG G J, YANG J S, YANG W P, LIU S B. Estimation of chlorophyll content in potato using fusion of texture and spectral features derived from UAV multispectral image. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(11): 63-74. (in Chinese)
[20]	王爱玉, 张春庆, 吴承来, 高明伟. 玉米叶绿素含量快速测定方法研究. 玉米科学, 2008(2): 97-100.
	WANG A Y, ZHANG C Q, WU C L, GAO M W. Study on a fast method of testing chlorophyll content in maize. Journal of Maize Sciences, 2008(2): 97-100. (in Chinese)
[21]	WANG Y, TAN S, JIA X, QI L, LIU S, LU H, WANG C, LIU W, ZHAO X, HE L, CHEN J, YANG C, WANG X, CHEN J, QIN Y, YU J, MA X. Estimating relative chlorophyll content in rice leaves using unmanned aerial vehicle multi-spectral images and spectral-textural analysis. Agronomy, 2023, 13(6): 1541. doi: 10.3390/agronomy13061541
[22]	ROUSE J W, HAAS R H, SCHELL J A, DEERING D W, HARLAN J C. Monitoring the Vernal Advancement of Retrogradation (Green Wave Effect) of Natural Vegetation. Texas A&M University: Remote Sensing Center, 1974.
[23]	GITELSON A A, KEYDAN G P, MERZLYAK M N. Three-band model for noninvasive estimation of chlorophyll, carotenoids, and anthocyanin contents in higher plant leaves. Geophysical Research Letters, 2006, 33(11): 431-433.
[24]	GITELSON A A, KAUFMAN Y J, MERZLYAK M N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS. Remote Sensing of Environment, 1996, 58(3): 289-298. doi: 10.1016/S0034-4257(96)00072-7
[25]	HUETE A R, HUA G, QI J, CHEHBOUNI A G, LEEUWEN W J. Normalization of multidirectional red and NIR reflectances with the SAVI. Remote Sensing of Environment, 1992, 41(2/3): 143-154. doi: 10.1016/0034-4257(92)90074-T
[26]	RONDEAUX G, STEVEN M, BARET F. Optimization of soil- adjusted vegetation indices. Remote Sensing of Environment, 1996, 55(2): 95-107. doi: 10.1016/0034-4257(95)00186-7
[27]	WU C Y, NIU Z, TANG Q, HUANG W J. Estimating chlorophyll content from hyperspectral vegetation indices: Modeling and validation. Agricultural and Forest Meteorology, 2008, 148(8/9): 1230-1241. doi: 10.1016/j.agrformet.2008.03.005
[28]	DASH J, CURRAN P J. The MERIS terrestrial chlorophyll index. International Journal of Remote Sensing, 2004, 25(23): 5403-5413. doi: 10.1080/0143116042000274015
[29]	FITZGERALD G J, RODRIGUEZ D, CHRISTENSEN L K, BELFORD R, SADRAS V O, CLARKE T R. Spectral and thermal sensing for nitrogen and water status in rainfed and irrigated wheat environments. Precision Agriculture, 2006, 7(4): 233-248. doi: 10.1007/s11119-006-9011-z
[30]	CHEN J M. Evaluation of vegetation indices and a modified simple ratio for boreal applications. Canadian Journal of Remote Sensing, 1996, 22(3): 229-242. doi: 10.1080/07038992.1996.10855178
[31]	谭丞轩, 张智韬, 许崇豪, 马宇, 姚志华, 魏广飞, 李宇. 无人机多光谱遥感反演各生育期玉米根域土壤含水率. 农业工程学报, 2020, 36(10): 63-74.
	TAN C X, ZHANG Z T, XU C H, MA Y, YAO Z H, WEI G F, LI Y. Soil water content inversion model in field maize root zone based on UAV multispectral remote sensing. Transactions of the Chinese Society of Agricultural Engineering, 2020, 36(10): 63-74. (in Chinese)
[32]	李美炫, 朱西存, 白雪源, 彭玉凤, 田中宇, 姜远茂. 基于无人机影像阴影去除的苹果树冠层氮素含量遥感反演. 中国农业科学, 2021, 54(10): 2084-2094. doi: 10.3864/j.issn.0578-1752.2021.10.005.
	LI M X, ZHU X C, BAI X Y, PENG Y F, TIAN Z Y, JIANG Y M. Remote sensing inversion of nitrogen content in apple canopy based on shadow removal in UAV multi-spectral remote sensing images. Scientia Agricultura Sinica, 2021, 54(10): 2084-2094. doi: 10.3864/j.issn.0578-1752.2021.10.005. (in Chinese)
[33]	YUE J, YANG G, TIAN Q, FENG H, XU K, ZHOU C. Estimate of winter-wheat above-ground biomass based on UAV ultrahigh-ground- resolution image textures and vegetation indices. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150: 226-244. doi: 10.1016/j.isprsjprs.2019.02.022
[34]	QIAO L, GAO D, ZHANG J, LI M, SUN H, MA J. Dynamic influence elimination and chlorophyll content diagnosis of maize using UAV spectral imagery. Remote Sensing, 2020, 12(16): 2650. doi: 10.3390/rs12162650
[35]	谷晓博, 程智楷, 周智辉, 常甜, 李汶龙, 杜娅丹. 基于特征降维和机器学习的覆膜冬小麦LAI遥感反演. 农业机械学报, 2023, 54(6): 148-157, 167.
	GU X B, CHENG Z K, ZHOU Z H, CHANG T, LI W L, DU Y D. Remote sensing inversion of leaf area index of mulched winter wheat based on feature downscaling and machine learning. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(6): 148-157, 167. (in Chinese)
[36]	FU H, LU J, CHEN J, WANG W, CUI G, SHE W. Influence of structure and texture feature on retrieval of ramie leaf area index. Agronomy, 2023, 13(7): 1690. doi: 10.3390/agronomy13071690
[37]	DUBE T, MUTANGA O. Investigating the robustness of the new Landsat-8 operational land imager derived texture metrics in estimating plantation forest aboveground biomass in resource constrained areas. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 108: 12-32. doi: 10.1016/j.isprsjprs.2015.06.002
[38]	罗小波, 谢天授, 董圣贤. 基于无人机多光谱影像的柑橘冠层叶绿素含量反演. 农业机械学报, 2023, 54(4): 198-205.
	LUO X B, XIE T S, DONG S X. Estimation of citrus canopy chlorophyll based on UAV multispectral images. Transactions of the Chinese Society for Agricultural Machinery, 2023, 54(4): 198-205. (in Chinese)
[39]	张东彦, 韩宣宣, 林芬芳, 杜世州, 张淦, 洪琪. 基于多源无人机影像特征融合的冬小麦LAI估算. 农业工程学报, 2022, 38(9): 171-179.
	ZHANG D Y, HAN X X, LIN F F, DU S Z, ZHANG G, HONG Q. Estimation of winter wheat leaf area index using multi-source UAV image feature fusion. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38(9): 171-179. (in Chinese)
[40]	田军仓, 杨振峰, 冯克鹏, 丁新军. 基于无人机多光谱影像的番茄冠层SPAD预测研究. 农业机械学报, 2020, 51(8): 178-188.
	TIAN J C, YANG Z F, FENG K P, DING X J. Prediction of tomato canopy SPAD based on UAV multispectral image. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51(8): 178-188. (in Chinese)
[41]	张春兰, 杨贵军, 李贺丽, 汤伏全, 刘畅, 张丽妍. 基于随机森林算法的冬小麦叶面积指数遥感反演研究. 中国农业科学, 2018, 51(5): 855-867. doi: 10.3864/j.issn.0578-1752.2018.05.005.
	ZHANG C L, YANG G J, LI H L, TANG F Q, LIU C, ZHANG L Y. Remote sensing inversion of leaf area index of winter wheat based on random forest algorithm. Scientia Agricultura Sinica, 2018, 51(5): 855-867. doi: 10.3864/j.issn.0578-1752.2018.05.005. (in Chinese)
[42]	李媛媛, 常庆瑞, 刘秀英, 严林, 罗丹, 王烁. 基于高光谱和BP神经网络的玉米叶片SPAD值遥感估算. 农业工程学报, 2016, 32(16): 135-142.
	LI Y Y, CHANG Q R, LIU X Y, YAN L, LUO D, WANG S. Estimation of maize leaf SPAD value based on hyperspectrum and BP neural network. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(16): 135-142. (in Chinese)
[43]	QI H, WU Z, ZHANG L, LI J, ZHOU J, JUN Z, ZHU B. Monitoring of peanut leaves chlorophyll content based on drone-based multispectral image feature extraction. Computers and Electronics in Agriculture, 2021, 187: 106292. doi: 10.1016/j.compag.2021.106292
[44]	BAI Y, ZHANG S, BHATTARAI N, MALLICK K, LIU Q, TANG L, IM J, GUO L, ZHANG J. On the use of machine learning based ensemble approaches to improve evapotranspiration estimates from croplands across a wide environmental gradient. Agricultural and Forest Meteorology, 2021, 298/299: 108308. doi: 10.1016/j.agrformet.2020.108308
[45]	VON BLOH M, NÓIA JÚNIOR R, WANGERPOHL X, SALTIK A O, HALLER V, KAISER L, ASSENG S. Machine learning for soybean yield forecasting in Brazil. Agricultural and Forest Meteorology, 2023, 341: 109670. doi: 10.1016/j.agrformet.2023.109670
[46]	费帅鹏, 禹小龙, 兰铭, 李雷, 夏先春, 何中虎, 肖永贵. 基于高光谱遥感和集成学习方法的冬小麦产量估测研究. 中国农业科学, 2021, 54(16): 3417-3427. doi: 10.3864/j.issn.0578-1752.2021.16.005.
	FEI S P, YU X L, LAN M, LI L, XIA X C, HE Z H, XIAO Y G. Research on winter wheat yield estimation based on hyperspectral remote sensing and ensemble learning method. Scientia Agricultura Sinica, 2021, 54(16): 3417-3427. doi: 10.3864/j.issn.0578-1752.2021.16.005. (in Chinese)

光谱特征 Spectral feature	公式 Formula	文献 Reference	光谱特征 Spectral feature	公式 Formula	文献 Reference
B	B=R450		GNDVI	GNDVI=(R840-R560)/(R840+R560)	[24]
G	G=R560		SAVI	SAVI=(1+0.5)×(R840-R650)/(R840+R650+0.5)	[25]
R	R=R650		OSAVI	OSAVI=(R840-R650)/(R840+R650+0.16)	[26]
RE	RE=R730		MCARI	MCARI=[(R730-R650) -0.2×(R730-R560)]×(R730/R650)	[27]
NIR	NIR (near infrared)=R840		MTCI	MTCI=(R840-R730)/(R730-R650)	[28]
NDVI	NDVI=(R840-R650)/(R840+R650)	[22]	NDRE	NDRE=(R840-R730)/(R840+R730)	[29]
CIgreen	CIgreen=R840/R560-1	[23]	MSR	MSR=(R840/R650-1)/(R840/R650+1)^0.5	[30]
CIre	CIre=R840/R730-1	[23]

生育期 Growth stage	总体精度 Overall accuracy (%)	Kappa系数 Kappa coefficient
苗期Seedling stage	99.60	0.994
拔节期Jointing stage	97.99	0.967
抽雄期Tasseling stage	98.78	0.981
灌浆期Filling stage	98.15	0.971

数据集 Dataset	样本量 Sample size	最小值 Minimum (mg·g^-1)	最大值 Maximum (mg·g^-1)	平均值 Average (mg·g^-1)	标准差 Standard deviation (mg·g^-1)	方差 Variance	变异系数Coefficient of variation (%)
样本集 Sample set	144	2.07	5.50	3.69	0.84	0.71	22.78
建模集 Modeling set	108	2.07	5.48	3.68	0.84	0.71	22.92
验证集 Validation set	36	2.25	5.50	3.73	0.84	0.71	22.66

生育期 Growth stage	B	G	R	RE	NIR
苗期Seedling stage	**	**	**	**	**
拔节期Jointing stage	**	**	**	*	**
抽雄期Tasseling stage	*	**	ns	**	**
灌浆期Filling stage	*	**	ns	**	**
全生育期Whole growth stages	**	**	*	**	**

纹理特征 Texture feature	相关系数Correlation coefficient
	全像元All pixels					玉米像元Maize pixels
	B	G	R	RE	NIR	B	G	R	RE	NIR
Mean	0.08ns	0.06ns	0.10ns	0.28**	0.54**	0.52**	0.43**	0.63**	0.25**	0.71**
Var	0.45**	0.62**	0.35**	0.47**	0.58**	0.40**	0.19*	0.38**	0.63**	0.67**
Hom	0.27**	0.28**	0.24**	0.37**	0.30**	0.34**	0.20*	0.52**	0.44**	0.37**
Con	0.46**	0.62**	0.36**	0.50**	0.55**	0.36**	0.15ns	0.36**	0.62**	0.67**
Dis	0.19*	0.28**	0.19*	0.19*	0.51**	0.37**	0.16*	0.45**	0.59**	0.59**
Ent	0.29**	0.29**	0.28**	0.34**	0.32**	0.30**	0.23**	0.52**	0.27**	0.27**
Sec	0.32**	0.32**	0.31**	0.34**	0.33**	0.32**	0.28**	0.53**	0.15ns	0.23**
Corr	0.15ns	0.09ns	0.15ns	0.11ns	0.16*	0.52**	0.37**	0.64**	0.27**	0.26**