一款无人机高光谱传感器的验证及其在玉米叶面积指数反演中的应用

doi:10.3864/j.issn.0578-1752.2018.08.004

摘要/Abstract

摘要： 【目的】验证无人机机载高光谱传感器S185，并基于其获得的影像探讨无人机高光谱遥感反演叶面积指数的新方法。【方法】以东北玉米为研究对象，在吉林省公主岭市开展了玉米氮肥梯度试验，共设5处理，每个处理3次重复。分别在玉米的V5—V6，V11，R1—R2等生育期（Ritchie生育期）进行无人机飞行试验和地面光谱及叶面积指数测定，共获得数据45组。为验证S185影像数据，在相同尺度下提取S185影像信息与地面光谱信息，一方面从测定同一目标地物两者光谱反射率间的相关性进行分析，另一方面筛选15种常用的各类光谱指数，从整个生育期通过影像数据计算的各光谱指值与地面光谱仪计算的相应值变化趋势的一致性进行分析；将45组样品随机选择30组，基于人工神经网络算法利用S185数据建立反演叶面积指数的模型，剩下15组样品作为外部验证样品，用来验证神经网络模型的预测效果。另外，基于相同的分组数据，利用前面筛选的各光谱指数分别建立叶面积指数的反演模型，以与人工神经网络建模结果进行比较。【结果】在各个生育时期，同种目标地物S185测定数据与地面光谱仪测定数据间具有很强的相关性，相关系数在0.99以上；在玉米整个生育期，S185数据计算的各光谱指数与地面光谱仪计算的各光谱指数变化趋势相同，相关系数在0.88以上；在构建基于人工神经网络法反演叶面积指数的模型中，建模时的决定系数为0.96，均方根误差为0.42，相对均方根误差为13.15%；外部验证时的决定系数为0.95，均方根误差为0.54，相对均方根误差为16.74%，这一结果优于基于各光谱指数建立的叶面积指数反演模型。【结论】无人机搭载S185传感器可用于准确获取玉米冠层高光谱信息，且可利用人工神经网络法基于这一数据建立玉米叶面积指数的反演模型。

关键词: 无人机, 高光谱, 叶面积指数, 玉米, S185

Abstract: 【Objective】 The objective of this study is to validate the unmanned aerial vehicle (UAV) hyperspectral sensor S185, and then to design a new method for maize leaf area index (LAI) estimation based on its collected image. 【Method】 Taking maize in northeastern China as study material, nitrogen fertilizer experiment was conducted in Gongzhuling city in Jilin province. In the experiment, five nitrogen treatments and three replications were applied. The UAV flight experiment, the ground spectrum and LAI were measured at V5-V6, V11, R1-R2 growth stage (Ritchie growth stage) of maize. At last, 45 groups of data were collected. To validate images from hyperspectral sensor S185, the spectra from S185 image and from ground spectral device were extracted and compared in the same scale. On the one hand, the correlation analysis was taken to analysis the relationship between S185 data and ground measured spectra, which were from the same target; On the other hand, 15 commonly used spectral indices were selected, and then they were calculated from S185 date and from the ground spectra, respectively, and at last, the relationship between them during the whole maize growth stage was analyzed to show their change trend consistency. 30 groups of data were randomly selected from the collected 45 groups of data, artificial neural network method (ANN) was used to establish LAI prediction model by using S185 images, and then the remainder 15 groups of data were used to validate the performance of ANN model. In addition, based on the same calibration and validation dataset, LAI prediction models were designed by using each selected spectral index individually in order to compare with ANN LAI prediction model. 【Result】 In each maize growth stage, S185 spectra had a high relationship with corresponding spectra measured by ground spectral device for the same target, with correlation coefficients higher than 0.99; in the whole maize growth stage, the calculated spectral indices from the S185 images had a high relationship with the corresponding value calculated from ground measured spectra, with correlation coefficient higher than 0.88; During the design of the ANN prediction model for LAI, the model had an R2 value of 0.96, a RMSE value of 0.42 and a RMSE% value of 13.15% during calibration and had an R2 value of 0.95, an RMSE value of 0.54 and an RMSE% value of 16.74% during external validation. The model performed better than models designed by spectral indices. 【Conclusion】 The results showed S185 can be mounted on UAV to measure maize canopy hyperspectra image accurately, and ANN method can be used to design LAI prediction model based on UAV.

Key words: unmanned aerial vehicle, hyperspectra, leaf area index, maize, S185

陈鹏飞，李刚，石雅娇，徐志涛，杨粉团，曹庆军. 一款无人机高光谱传感器的验证及其在玉米叶面积指数反演中的应用[J]. 中国农业科学, 2018, 51(8): 1464-1474.

CHEN PengFei, LI Gang, SHI YaJiao, XU ZhiTao, YANG FenTuan, CAO QingJun. Validation of an Unmanned Aerial Vehicle Hyperspectral Sensor and Its Application in Maize Leaf Area Index Estimation[J]. Scientia Agricultura Sinica, 2018, 51(8): 1464-1474.

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.0578-1752.2018.08.004

https://www.chinaagrisci.com/CN/Y2018/V51/I8/1464

参考文献

[1] 史舟, 梁宗正, 杨媛媛, 郭燕. 农业遥感研究现状与展望. 农业机械学报, 2015, 46(2): 247-260.

SHI Z, LIANG Z Z, YANG Y Y, GUO Y. Status and prospect of agricultural remote sensing. Transaction of the Chinese Society for Agricultural Machinery, 2015, 46(2): 247-260. (in Chinese)

[2] 秦占飞, 常庆瑞, 谢宝妮, 申健. 基于无人机高光谱影像的引黄灌区水稻叶片全氮含量估测. 农业工程学报, 2016, 32(23): 77-85.

QIN Z F, CHANG Q R, XIE B N, SHEN J. Rice leaf nitrogen content estimation based on hysperspectral imagery of UAV in Yellow River diversion irrigation district. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(23): 77-85. (in Chinese)

[3] 杨贵军, 李长春, 于海洋, 徐波, 冯海宽, 高林, 朱冬梅. 农用无人机多传感器遥感辅助小麦育种信息获取. 农业工程学报, 2015, 31(21): 184-190.

YANG G J, LI C C, YU H Y, XU B, FENG H K, GAO L, ZHU D M. UAV based multi-load remote sensing technologies for wheat breeding information acquirement. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(21): 184-190. (in Chinese)

[4] 葛明锋. 基于轻小型无人机的高光谱成像系统研究[D]. 北京: 中国科学院大学, 2015.

GE M F. Hyperspectral imagery remote sensing technology based on light weight unmanned aerial vehicle[D]. Beijing: University of Chinese Academy of Sciences, 2015. (in Chinese)

[5] BARETH G, AASEN H, BENDIG J, GNYP M L, BOLTEN A, JUNG A, MICHELS R, SOUKKAMÄKI J. Low-weight and UAV-based hyperspectral full-frame cameras for monitoring crops: Spectral comparison with portable spectroradiometer measurements. Photogrammetrie-Fernerkundung-Geoinformation, 2015, 2015(1): 69-79.

[6] 高林, 杨贵军, 于海洋, 徐波, 赵晓庆, 董锦绘, 马亚斌. 基于无人机高光谱遥感的冬小麦叶面积指数反演. 农业工程学报, 2016, 32(22): 113-120.

GAO L, YANG G J, YU H Y, XU B, ZHAO X Q, DONG J H, MA Y B. Retrieving winter wheat leaf area index based on unmanned aerial vehicle hyperspectral remoter sensing. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(22): 113-120. (in Chinese)

[7] 高林, 杨贵军, 王宝山, 于海洋, 徐波, 冯海宽. 基于无人机遥感影像的大豆叶面积指数反演研究. 中国生态农业学报, 2015, 23(7): 868-876.

GAO L, YANG G, WANG B, YU H Y, XU B, FENG H K. Soybean leaf area index retrieval with UAV (unmanned aerial vehicle) remote sensing imagery. Chinese Journal of Eco-Agriculture, 23(7): 868-876.

(in Chinese)

[8] 陆国政, 李长春, 杨贵军, 于海洋, 赵晓庆, 张晓燕. 基于成像高光谱仪的大豆叶面积指数反演研究. 大豆科学, 2016, 35(4): 599-608.

LU G Z, LI C C, YANG G J, YU H Y, ZHAO X Q, ZHANG X Y. Retrieving soybean leaf area index based on high imaging spectrometer. Soybean Science, 2016, 35(4): 599-608. (in Chinese)

[9] 田明璐, 班松涛, 常庆瑞, 由明明, 罗丹, 王力, 王烁. 基于低空无人机成像光谱仪影像估算棉花叶面积指数. 农业工程学报, 2016, 32(21): 102-108.

TIAN M L, BAN S T, CHANG Q R, YOU M M, LUO D, WANG L, WANG S. Use of hyperspectral images from UAV-based imaging spectroradiometer to estimate cotton leaf area index. Transactions of the Chinese Society of Agricultural Engineering, 2016, 32(21): 102-108. (in Chinese)

[10] BERBEROGLU S, SATIR O, ATKINSON P M. Mapping percentage tree cover from Envisat MERIS data using linear and nonlinear techniques. International Journal of Remote Sensing, 2009, 30(18): 4747-4766.

[11] YANG G, ZHAO C, LIU Q, HUANG W, WANG J. Inversion of a radiative transfer model for estimating forest LAI from multisource and multiangular optical remote sensing data. IEEE Transactions on Geoscience & Remote Sensing, 2011, 49(3): 988-1000.

[12] RITCHIE S W, HANAWAY J J, BENSON G O. How a corn plant develops. Special Report 48, USA: Iowa State University, 1997.

[13] ROUSE J W, HAAS R W, SCHELL J A, Deering D W, Harlan J C. Monitoring the vernal advancement and retrogradation (Green wave effect) of natural vegetation. NASA/GSFCT Type III final report, USA: NASA, 1974.

[14] PEARSON R L, MILLER L D. Remote mapping of standing crop biomass for estimation of the productivity of the Shortgrass Prairie Pawnee National Grasslands, Colorado[C]// Proceedings of the Eighth International Symposium on Remote Sensing of Environment, Ann Arbor, Michigan, USA, 1972: 1355-1379.

[15] HUETE A, JUSTICE C, LIU H. Development of vegetation and soil indices for MODIS-EOS. Remote Sensing of Environment, 1994, 49(3): 224-234.

[16] BROGE N H, LEBLANC E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density. Remote Sensing of Environment, 2001, 76(2): 156-172.

[17] QI J, CHEHBOUNI A, HUETE A R, KERR Y H, SOROOSHIAN S. A modified soil adjusted vegetation index. Remote Sensing of Environment, 1994, 48(2): 119-126.

[18] RONDEAUX G, STEVEN M, BARET F. Optimization of soil-adjusted vegetation indices. Remote Sensing of Environment, 1996, 55(2): 95-107.

[19] 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.

[20] HABOUDANE D, MILLER J R, PATTEY E, ZARCO-TEJADA P J, STRACHAN I B. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies: Modeling and validation in the context of precision agriculture. Remote Sensing of Environment, 2004, 90(3): 337-352.

[21] 陈鹏飞, TREMBLAY N, 王纪华, VIGNEAULT P, 黄文江, 李保国. 估测作物冠层生物量的新植被指数的研究. 光谱学与光谱分析, 2010, 30(2): 512-517.

CHEN P F, TREMBLAY N, WANG J H, VIGNEAULT P, HUANG W J, LI B G. New index for crop canopy fresh biomass estimation. Spectroscopy & Spectral Analysis, 2010, 30(2): 512-517. (in Chinese)

[22] REYNIERS M, WALVOORT D J J, De BAARDEMAAKER J. A linear model to predict with a multi-spectral radiometer the amount of nitrogen in winter wheat. International Journal of Remote Sensing, 2006, 27(19): 4159-4179.

[23] DAUGHTRY C S T, WALTHALL C L, KIM M S, COLSTOUN E B D, McMurtrey III J E. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 2000, 74(2): 229-239.

[24] DASH J, CURRAN P J. The MERIS terrestrial chlorophyll index. International Journal of Remote Sensing, 2004, 25(23): 5403-5413.

[25] GITELSON A A, VIÑA A, CIGANDA V, RUNDQUIST D C, ARKEBAUER T J. Remote estimation of canopy chlorophyll content in crops. Geophysical Research Letters, 2005, 32(8): 93-114.

[26] SIMS D A, LUO H Y, HASTINGS S, OECHEL W C, RAHMAN A F, GAMON J A. Parallel adjustments in vegetation greenness and ecosystem CO₂, exchange in response to drought in a southern California chaparral ecosystem. Remote Sensing of Environment, 2006, 103(3): 289-303.

[27] GUYOT G, BARET F, MAJOR D J. High spectral resolution: Determination of spectral shifts between the red and the near infrared. International Archives of Photogrammetry and Remote Sensing, 1988, 11(11): 750-760.

[28] HORNIK K, STINCHCOMBE M, WHITE H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 1990, 3(5): 551-560.

[29] FARIFTEH J, MEER F V D, ATZBERGER C, CARRANZA E J M. Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN). Remote Sensing of Environment, 2007, 110(1): 59-78.

[30] CHEN P, JING Q. A comparison of two adaptive multivariate analysis methods (PLSR and ANN) for winter wheat yield forecasting using Landsat-8 OLI images. Advances in Space Research, 2017, 59(4): 987-995.

[31] HUANG W, FOO S. Neural network modeling of salinity variation in Apalachicola River. Water Research, 2002, 36(1): 356-362.

[32] 苏理宏, 李小文, 黄裕霞. 遥感尺度问题研究进展. 地球科学进展, 2001, 16(4): 544-548.

SU L H, LI X W, HUANG Y X. An review on scale in remote sensing. Advance in Earth Sciences, 2001, 16(4): 356-362. (in Chinese)

[33] FRIEDL M A, DAVIS F W, MICHAELSEN J, MORITZ M A. Scaling and uncertainty in the relationship between the NDVI and land surface BIOPHYSICAL variables: An analysis using a scene simulation model and data from FIFE. Remote Sensing of Environment, 1995, 54(3): 233-246.

[34] WOODCOCK C E, STRAHLER A H. The factor of scale in remote sensing. Remote Sensing of Environment, 1987, 21(3): 311-332.

[35] HUFKENS K, BOGAERT J, DONG Q H, LU L, HUANG C L, MA M G, CHE T, LI X, VEROUSTRAETE F, CEULEMANS R. Impacts and uncertainties of upscaling of remote-sensing data validation for a semi-arid woodland. Journal of Arid Environments, 2008, 72(8): 1490-1505.

[36] AASEN H, BURKART A, BOLTEN A, BARETH G. Generating 3D hyperspectral information with lightweight UAV snapshot cameras for vegetation monitoring: from camera calibration to quality assurance. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, 108(5): 245-259.