玉米大豆生长中后期遥感辨识的指示性特征研究

沈宇; 李强子; 杜鑫; 王红岩; 张源

doi:10.11834/jrs.20209078

农业遥感 | 浏览量 : 0 下载量: 288 CSCD: 1 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

玉米大豆生长中后期遥感辨识的指示性特征研究
Indicative features for identifying corn and soybean using remote sensing imagery at middle and later growth season
2022年26卷第7期页码：1410-1422
纸质出版日期： 2022-07-07 ，
DOI： 10.11834/jrs.20209078

扫描看全文

沈宇，李强子，杜鑫，王红岩，张源.2022.玉米大豆生长中后期遥感辨识的指示性特征研究.遥感学报，26（7）： 1410-1422

Shen Y，Li Q Z， Du X， Wang H Y and Zhang Y. 2022. Indicative features for identifying corn and soybean using remote sensing imagery at middle and later growth season. National Remote Sensing Bulletin， 26（7）：1410-1422
沈宇，李强子，杜鑫，王红岩，张源.2022.玉米大豆生长中后期遥感辨识的指示性特征研究.遥感学报，26（7）： 1410-1422 DOI： 10.11834/jrs.20209078.

Shen Y，Li Q Z， Du X， Wang H Y and Zhang Y. 2022. Indicative features for identifying corn and soybean using remote sensing imagery at middle and later growth season. National Remote Sensing Bulletin， 26（7）：1410-1422 DOI： 10.11834/jrs.20209078.

摘要

玉米和大豆是两种主要的粮食作物，及时准确地监测两者的种植面积对于产量预测和市场价格的制定具有重要的意义。利用遥感技术探究在生长季中后期能有效区分玉米和大豆的指示性特征集，为在不同实验区进行推广应用和提前玉米和大豆种植面积信息发布的时间提供技术支撑。文章以玉米和大豆为研究对象，以黑龙江和安徽省两个典型种植区为实验区，以高分一号影像为数据源，计算多种植被指数特征和两种纹理特征，同时利用特征优选方法评价特征间的相对重要性，并结合随机森林分类算法分析特征个数对精度的影响，得到不同试验区区分两者的最佳特征子集。随后根据不同实验区最佳特征子集的共同点和差异，遴选出对玉米和大豆中后期区分的遥感指示性识别特征集，并设计实验方案验证其有效性和稳定性。实验表明：在玉米和大豆生长中后期存在具有高效辨识两者的遥感特征集，能有效和稳定地增强两者的遥感识别能力；在不同实验区，基于特征优选方法可以选择出区分玉米和大豆的最佳分类特征子集，得到两者最优的识别效果，比仅仅使用原始波段特征的分类精度提升了近10个百分点，总体分类精度能够平均达到97%，Kappa系数0.96，玉米和大豆的单类分类精度平均超过95%；在不同的种植区，利用玉米和大豆的指示性特征集可以得到几乎与优选出的最佳特征子集同样的分类精度和制图效果，且具有稳定性和有效性，较最佳特征集更具推广使用意义。指示性特征集包含6种：植被指数中的比值植被指数（RVI），差值植被指数（DVI），转换型植被指数（TVI），改进型叶绿素吸收比率指数（MCARI）和灰度共生矩阵（GLCM）纹理特征中的二阶矩（the Second Moment）和熵（Entropy）。

Abstract

Corn and soybean are two major crops maintaining food security

and thus the timely and accurate monitoring of their planting areas are of great importance to forecasting their production and market prices. The objectives of this study were to use a remote-sensing technology in exploring indicative features that can effectively identify corn and soybean in their middle and late growth seasons and provide technical support for the broad geographical application of corn and soybean mapping. This study can facilitate the early release of corn and soybean planting acreages for policy makers. In this study

two typical planting areas of corn and soybean in the provinces of Heilongjiang and Anhui were selected. GaoFen-1 satellite images with 30 m spatial resolution were acquired in the middle and latter growth stages and used as data sources for calculating various vegetation indices and textural features. Then

a feature optimization method was used in evaluating the relative importance scores of input features

and optimal feature combinations for identifying corn and soybean were determined. The random forest classification algorithm was used in analyzing the relationship between the number of input features and classification accuracy

and then the best feature groups in different experimental areas were identified. Finally

according to similarities and differences among the selected features in different regions

the indicative features for mapping corn and soybean in the middle and latter stages were established. The validity and stability were confirmed using our experimental designs. The following results were obtained: (1) indicative remote sensing features for efficiently identifying corn and soybean in their middle and late growing seasons were identified; (2) the classification performance of the indicative features of corn and soybean in both experimental areas was approximately 10% higher than that when original spectral band combinations were used. In different planting areas

high classification accuracy was obtained using the indicative features of corn and soybean as the optimal features selected in individual local area. Our selected indicative features for soybean and corn mapping were found stable

effective

and useful for large areas of implementation. These features included Ratio Vegetation Index (RVI)

Difference Vegetation Index (DVI)

Conversion Vegetation Index (TVI)

improved chlorophyll absorption ratio index (MCARI)

and the second moment and entropy in Gray Level Co-occurrence Matrix (GLCM).

关键词

遥感玉米大豆遥感识别特征分类GF-1

Keywords

remote sensingcornsoybeanremote sensing identificationsatellite featureclassificationGF-1

references

Cui L, Du H Q, Zhou G M, Li X J, Mao F J, Xu X J, Fan W L, Li Y G, Zhu D E, Liu T Y and Xin L Q. 2019. Combination of decision tree and mixed pixel decomposition for extracting bamboo forest information in China. Journal of Remote Sensing, 23(1): 166-176

崔璐, 杜华强, 周国模, 李雪建, 毛方杰, 徐小军, 范渭亮, 李阳光, 朱迪恩, 刘腾艳, 邢璐琪. 2019. 决策树结合混合像元分解的中国竹林遥感信息提取. 遥感学报, 23(1): 166-176 [DOI: 10.11834/jrs.20187155http://dx.doi.org/10.11834/jrs.20187155]

Dash M and Liu H. 1997. Feature selection for classification. Intelligent Data Analysis, 1(1/4): 131-156 [DOI: 10.1016/S1088-467X(97)00008-5http://dx.doi.org/10.1016/S1088-467X(97)00008-5]

Dong J W, Xiao X M, Menarguez M A, Zhang G L, Qin Y W, Thau D, Biradar C and Moore III B. 2016. Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine. Remote Sensing of Environment, 185: 142-154 [DOI: 10.1016/j.rse.2016.02.016http://dx.doi.org/10.1016/j.rse.2016.02.016]

Feng Z M, Yang L and Yang Y Z. 2014. Temporal and spatial distribution patterns of grain crops in the West Liaohe River Basin. Journal of Resources and Ecology, 5(3): 244-252

封志明, 杨玲, 杨艳昭. 2014. 基于MODIS NDVI的西辽河流域主要粮食作物时空分布格局(英文). 资源与生态学报, 5(3): 244-252 [DOI: 10.5814/j.issn.1674-764X.2014.03.007http://dx.doi.org/10.5814/j.issn.1674-764X.2014.03.007]

Hall M A and Smith L A. 1999. Feature selection for machine learning: comparing a correlation-based filter approach to the wrapper//Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference. Orlando, Florida, USA: ACM: 235-239

Haralick R M. 1982. Image texture survey. Handbook of Statistics, 2: 399-415 [DOI: 10.1016/S0169-7161(82)02021-5http://dx.doi.org/10.1016/S0169-7161(82)02021-5]

Hasituya, Chen Z X, Wang L M, Wu W B, Jiang Z W and Li H. 2016. Monitoring plastic-mulched farmland by Landsat-8 OLI imagery using spectral and textural features. Remote Sensing, 8(4): 353 [DOI: 10.3390/rs8040353http://dx.doi.org/10.3390/rs8040353]

Huang J X, Hou Y Z, Su W, Liu J M and Zhu D H. 2017. Mapping corn and soybean cropped area with GF-1 WFV data. Transactions of the Chinese Society of Agricultural Engineering, 33(7): 164-170

黄健熙, 侯矞焯, 苏伟, 刘峻明, 朱德海. 2017. 基于GF-1WFV数据的玉米与大豆种植面积提取方法. 农业工程学报, 33(7): 164-170 [DOI: 10.11975/j.issn.1002-6819.2017.07.021http://dx.doi.org/10.11975/j.issn.1002-6819.2017.07.021]

Jia K, Li Q Z, Tian Y C and Wu B F. 2011. A review of classification methods of remote sensing imagery. Spectroscopy and Spectral Analysis, 31(10): 2618-2623

贾坤, 李强子, 田亦陈, 吴炳方. 2011. 遥感影像分类方法研究进展. 光谱学与光谱分析, 31(10): 2618-2623 [DOI: 10.3964/j.issn.1000-0593(2011)10-2618-06http://dx.doi.org/10.3964/j.issn.1000-0593(2011)10-2618-06]

Jia K, Li Q Z, Tian Y C, Wu B F, Zhang F F and Meng J H. 2012. Crop classification using multi-configuration SAR data in the North China Plain. International Journal of Remote Sensing, 33(1): 170-183 [DOI: 10.1080/01431161.2011.587844http://dx.doi.org/10.1080/01431161.2011.587844]

Li W G, Huang W J, Dong Y Y, Chen H, Wang J J and Shan J. 2017. Estimation on winter wheat scab based on combination of temperature, humidity and remote sensing vegetation index. Transactions of the Chinese Society of Agricultural Engineering, 33(23): 203-210

李卫国, 黄文江, 董莹莹, 陈华, 王晶晶, 单婕. 2017. 基于温湿度与遥感植被指数的冬小麦赤霉病估测. 农业工程学报, 33(23): 203-210 [DOI: 10.11975/j.issn.1002-6819.2017.23.026http://dx.doi.org/10.11975/j.issn.1002-6819.2017.23.026]

Li X C, Xu X G, Wang J H, Wu H F, Jin X L, Li C J and Bao Y S. 2013. Crop classification recognition based on time-series images from HJ satellite. Transactions of the Chinese Society of Agricultural Engineering, 29(2): 169-176

李鑫川, 徐新刚, 王纪华, 武洪峰, 金秀良, 李存军, 鲍艳松. 2013. 基于时间序列环境卫星影像的作物分类识别. 农业工程学报, 29(2): 169-176

Liu J, Wang L M, Teng F, Yang L B, Gao J M, Yao B M and Yang F G. 2016. Impact of red-edge waveband of RapidEye satellite on estimation accuracy of crop planting area. Transactions of the Chinese Society of Agricultural Engineering, 32(13): 140-148

刘佳, 王利民, 滕飞, 杨玲波, 高建孟, 姚保民, 杨福刚. 2016. RapidEye卫星红边波段对农作物面积提取精度的影响. 农业工程学报, 32(13): 140-148 [DOI: 10.11975/j.issn.1002-6819.2016.13.020http://dx.doi.org/10.11975/j.issn.1002-6819.2016.13.020]

Liu J, Wang L M, Yang F G, Yang L B and Wang X L. 2015. Remote sensing estimation of crop planting area based on HJ time-series images. Transactions of the Chinese Society of Agricultural Engineering, 31(3): 199-206

刘佳, 王利民, 杨福刚, 杨玲波, 王小龙. 2015. 基于HJ时间序列数据的农作物种植面积估算. 农业工程学报, 31(3): 199-206 [DOI: 10.3969/j.issn.1002-6819.2015.03.026http://dx.doi.org/10.3969/j.issn.1002-6819.2015.03.026]

Liu Q S, Huang C, Liu G H, Chai S Y, Chu L and Jing X. 2014. Planting area extraction of a crop key growth period in Wudi County based on HJ satellite data. Chinese Agricultural Science Bulletin, 30(26): 284-290

刘庆生, 黄翀, 刘高焕, 柴思跃, 褚琳, 荆鑫. 2014. 基于关键期HJ卫星数据提取无棣县作物种植面积. 中国农学通报, 30(26): 284-290

Liu X X, Wang L, Xu S H and Liang Y. 2017. A remote sensing feature selection method of forest biomass estimation based on RF-RFE. Science of Surveying and Mapping, 42(5): 100-105

刘笑笑, 王亮, 徐胜华, 梁勇. 2017. 一种后向迭代的森林生物量遥感特征选择方法. 测绘科学, 42(5): 100-105 [DOI: 10.16251/j.cnki.1009-2307.2017.05.017http://dx.doi.org/10.16251/j.cnki.1009-2307.2017.05.017]

Liu Y, Du P J, Zheng H, Xia J S and Liu S C. 2012. Classification of China small satellite remote sensing image based on random forests. Science of Surveying and Mapping, 37(4): 194-196

刘毅, 杜培军, 郑辉, 夏俊士, 柳思聪. 2012. 基于随机森林的国产小卫星遥感影像分类研究. 测绘科学, 37(4): 194-196 [DOI: 10.16251/j.cnki.1009-2307.2012.04.027http://dx.doi.org/10.16251/j.cnki.1009-2307.2012.04.027]

Ojala T, Pietikäinen M and Mäenpää T. 2001. A generalized local binary pattern operator for multiresolution gray scale and rotation invariant texture classification//Proceedings of the 2nd International Conference on Advances in Pattern Recognition. Rio de Janeiro, Brazil: Springer: 399-408 [DOI: 10.1007/3-540-44732-6_41http://dx.doi.org/10.1007/3-540-44732-6_41]

Pan Y Z, Li L, Zhang J S, Liang S L and Hou D. 2011. Crop area estimation based on MODIS-EVI time series according to distinct characteristics of key phenology phases: a case study of winter wheat area estimation in small-scale area. Journal of Remote Sensing, 15(3): 578-594

潘耀忠, 李乐, 张锦水, 梁顺林, 侯东. 2011. 基于典型物候特征的MODIS-EVI时间序列数据农作物种植面积提取方法——小区域冬小麦实验研究. 遥感学报, 15(3): 578-594 [DOI: 10.11834/jrs.20110066http://dx.doi.org/10.11834/jrs.20110066]

Peng G X, Li J, He Y H and Hu D Y. 2007. Extracting land cover information from CBERS-2's CCD image using texture analysis. Remote Sensing Technology and Application, 22(1): 8-13

彭光雄, 李京, 何宇华, 胡德勇. 2007. 利用纹理分析方法提取CBERS02星CCD图像土地覆盖信息. 遥感技术与应用, 22(1): 8-13 [DOI: 10.11873/j.issn.1004-0323.2007.1.8http://dx.doi.org/10.11873/j.issn.1004-0323.2007.1.8]

Ren J Q, Chen Z X, Zhou Q B, Liu J and Tang H J. 2015. MODIS vegetation index data used for estimating corn yield in USA. Journal of Remote Sensing, 19(4): 568-577

任建强, 陈仲新, 周清波, 刘佳, 唐华俊. 2015. MODIS植被指数的美国玉米单产遥感估测. 遥感学报, 19(4): 568-577 [DOI: 10.11834/jrs.20154146http://dx.doi.org/10.11834/jrs.20154146]

Song C Y, Li P J and Yang F J. 2011. Remote sensing image classification based on texture features by multivariate local binary pattern. Remote Sensing Technology and Application, 26(3): 322-327

宋翠玉, 李培军, 杨锋杰. 2011. 基于多元局部二值模式的遥感图像纹理提取与分类. 遥感技术与应用, 26(3): 322-327 [DOI: 10.11873/j.issn.1004-0323.2011.3.322http://dx.doi.org/10.11873/j.issn.1004-0323.2011.3.322]

Song D M, Liu B, Chen S C, Ma Y, Ma M G, Li L W, Zhang Y J, Shen C and Cui J Y. 2015. Hyperspectral data spectrum and texture band selection based on the subspace-rough set method. Remote Sensing Technology and Application, 30(2): 258-266

宋冬梅, 刘斌, 陈寿长, 马毅, 马明国, 李利伟, 张雅洁, 沈晨, 崔建勇. 2015. 基于子空间—粗集法的高光谱数据光谱与纹理特征优选. 遥感技术与应用, 30(2): 258-266 [DOI: 10.11873/j.issn.1004http://dx.doi.org/10.11873/j.issn.1004

\|0323.2015.2.0258]

Song K S, Zhang B, Wang Z M and Duan H T. 2005. Study on hyperstectral remote sensing estimation model for the corn LAI with canopy reflectance. Chinese Agricultural Science Bulletin, 21(1): 318-333

宋开山, 张柏, 王宗明, 段洪涛. 2005. 玉米和大豆LAI高光谱遥感估算模型研究. 中国农学通报, 21(1): 318-322 [DOI: 10.3969/j.issn.1000-6850.2005.01.091http://dx.doi.org/10.3969/j.issn.1000-6850.2005.01.091]

Song X F, Duan Z and Jiang X G. 2012. Comparison of artificial neural networks and support vector machine classifiers for land cover classification in Northern China using a SPOT-5 HRG image. International Journal of Remote Sensing, 33(10): 3301-3320 [DOI: 10.1080/01431161.2011.568531http://dx.doi.org/10.1080/01431161.2011.568531]

Sun N, Chen Q X, Luo J C, Shen Z F and Hu X D. 2010. Coupling GA with SVM for feature selection in high-resolution remote sensing target recognition. Journal of Remote Sensing, 14(5): 928-943

孙宁, 陈秋晓, 骆剑承, 沈占锋, 胡晓东. 2010. 面向遥感目标识别耦合GA与SVM的特征优选方法. 遥感学报, 14(5): 928-943 [DOI: 10.11834/jrs.20100508http://dx.doi.org/10.11834/jrs.20100508]

Tang X G, Liu D W, Song K S, Zhang B, Jiang G J, Yang F and Xu J P. 2010. A study for estimating the main tree species leaf area index in Northeast based on hyperspectral data. Remote Sensing Technology and Application, 25(3): 334-341

汤旭光, 刘殿伟, 宋开山, 张柏, 姜广甲, 杨飞, 徐京萍. 2010. 东北主要绿化树种叶面积指数(LAI)高光谱估算模型研究. 遥感技术与应用, 25(3): 334-341 [DOI: 10.11873/j.issn.1004-0323.2010.3.334http://dx.doi.org/10.11873/j.issn.1004-0323.2010.3.334]

Tian Q J and Min X J. 1998. Advances in study on vegetation indices. Advance in Earth Sciences, 13(4): 327-333

田庆久, 闵祥军. 1998. 植被指数研究进展. 地球科学进展, 13(4): 327-333 [DOI: 10.3321/j.issn:1001-8166.1998.04.002http://dx.doi.org/10.3321/j.issn:1001-8166.1998.04.002]

Wang L M, Liu J, Yang L B, Yang F G and Fu C H. 2018. Application of random forest method in maize-soybean accurate identification. Acta Agronomica Sinica, 44(4): 569-580

王利民, 刘佳, 杨玲波, 杨福刚, 富长虹. 2018. 随机森林方法在玉米—大豆精细识别中的应用. 作物学报, 44(4): 569-580 [DOI: 10.3724/SP.J.1006.2018.00569http://dx.doi.org/10.3724/SP.J.1006.2018.00569]

Wang N, Li Q Z, Du X, Zhang Y, Zhao L C and Wang H Y. 2017a. Identification of main crops based on the univariate feature selection in Subei. Journal of Remote Sensing, 21(4): 519-530

王娜, 李强子, 杜鑫, 张源, 赵龙才, 王红岩. 2017. 单变量特征选择的苏北地区主要农作物遥感识别. 遥感学报, 21(4): 519-530 [DOI: 10.11834/jrs.20176373http://dx.doi.org/10.11834/jrs.20176373]

Wang W J, Zhang X, Zhao Y D and Wang S D. 2017b. Cotton extraction method of integrated multi-features based on multi-temporal Landsat 8 images. Journal of Remte Sensing, 21(1): 115-124

王文静, 张霞, 赵银娣, 王树东. 2017. 综合多特征的Landsat8时序遥感图像棉花分类方法. 遥感学报, 21(1): 115-124 [DOI: 10.11834/jrs.20175317http://dx.doi.org/10.11834/jrs.20175317]

Wei L J, Huang L, Zhang Y Q, Jia Y Y, Xu W T, Yin Y P, Dong W H, Xie S Q and Liang Q. 2013. Analysis on intercropped patterns and effect in maize/soybean intercropping system. Southwest China Journal of Agricultural Sciences, 26(1): 67-72

韦柳佳, 黄莉, 张雅琼, 贾阳映, 徐文婷, 尹元萍, 董文汉, 谢世清, 梁泉. 2013. 玉米/大豆间作模式及效应分析. 西南农业学报, 26(1): 67-72 [DOI: 10.3969/j.issn.1001-4829.2013.01.014http://dx.doi.org/10.3969/j.issn.1001-4829.2013.01.014]

Wu C Y and Niu Z. 2008. Improvement in linearity between hyperspectral vegetation indices and chlorophyll content, leaf area index based on radiative transfer models. Chinese Bulletin of Botany, 25(6): 714-721

吴朝阳, 牛铮. 2008. 基于辐射传输模型的高光谱植被指数与叶绿素浓度及叶面积指数的线性关系改进. 植物学通报, 25(6): 714-721 [DOI: 10.3969/j.issn.1674-3466.2008.06.012http://dx.doi.org/10.3969/j.issn.1674-3466.2008.06.012]

Xu X G, Li Q Z, Zhou W C and Wu B F. 2008. Classification application of QuickBird imagery to obtain crop planting area. Remote Sensing Technology and Application, 23(1): 17-23

徐新刚, 李强子, 周万村, 吴炳方. 2008. 应用高分辨率遥感影像提取作物种植面积. 遥感技术与应用, 23(1): 17-23 [DOI: 10.11873/j.issn.1004-0323.2008.1.17http://dx.doi.org/10.11873/j.issn.1004-0323.2008.1.17]

Zhang C, Qiao M, Liu Z, Jin H S, Ning M Y and Sun H Y. 2017. Identification of texture feature scales for seed production of cornfields based on UAV and satellite remote sensing images. Transactions of the Chinese Society of Agricultural Engineering, 33(17): 98-104

张超, 乔敏, 刘哲, 金虹杉, 宁明宇, 孙海艳. 2017. 基于无人机和卫星遥感影像的制种玉米田识别纹理特征尺度优选. 农业工程学报, 33(17): 98-104 [DOI: 10.11975/j.issn.1002-6819.2017.17.013http://dx.doi.org/10.11975/j.issn.1002-6819.2017.17.013]

Zheng S D, Zheng J H, Shi M H, Guo B L, Sen B T, Sun Z Q, Jia X G and Li X T. 2014. Classification of cultivated Chinese medicinal plants based on fractal theory and gray level co-occurrence matrix textures. Journal of Remote Sensing, 18(4): 868-886

郑淑丹, 郑江华, 石明辉, 郭宝林, 森巴提, 孙志群, 贾晓光, 李晓瑾. 2014. 基于分形和灰度共生矩阵纹理特征的种植型药用植物遥感分类. 遥感学报, 18(4): 868-886 [DOI: 10.11834/jrs.20143282http://dx.doi.org/10.11834/jrs.20143282]

Zhu X F, Jia B, Pan Y Z, Gu X H, Han L J and Zhang Y Q. 2007. Effects of various feature information on the accuracy of winter wheat planting area measurement. Transactions of the CSAE, 23(9): 122-129

朱秀芳, 贾斌, 潘耀忠, 顾晓鹤, 韩立建, 张宇泉. 2007. 不同特征信息对TM尺度冬小麦面积测量精度影响研究. 农业工程学报, 23(9): 122-129 [DOI: 10.3321/j.issn:1002-6819.2007.09.023http://dx.doi.org/10.3321/j.issn:1002-6819.2007.09.023]

文章被引用时，请邮件提醒。

提交

高光谱图像类别独立的域适应分类

洞庭湖湿地净初级生产力估算研究

面向对象与卷积神经网络模型的GF-6 WFV影像作物分类

ICESat-2机载实验光子云数据自适应去噪及分类算法