面向小麦种植面积反演的自监督学习光谱解混算法

胡金龙; 段金亮; 沙马阿各; 张瑞

doi:10.11834/jrs.20222315

浏览量 : 0 下载量: 254 CSCD: 0 更多指标

R-PDF
PDF
导出
分享
收藏
专辑

面向小麦种植面积反演的自监督学习光谱解混算法
Wheat acreage retrieval based on self-supervised learning-based spectral unmixing algorithm
2022年页码：1-12
网络出版日期： 2022-10-24 ，
DOI： 10.11834/jrs.20222315

扫描看全文

胡金龙，段金亮，沙马阿各，张瑞.XXXX.面向小麦种植面积反演的自监督学习光谱解混算法.遥感学报，XX（XX）： 1-12

HU Jinlong，DUAN Jinliang，SHAMA Age，ZHANG Rui. XXXX. Wheat acreage retrieval based on self-supervised learning-based spectral unmixing algorithm. National Remote Sensing Bulletin， XX（XX）：1-12
胡金龙，段金亮，沙马阿各，张瑞.XXXX.面向小麦种植面积反演的自监督学习光谱解混算法.遥感学报，XX（XX）： 1-12 DOI： 10.11834/jrs.20222315.

HU Jinlong，DUAN Jinliang，SHAMA Age，ZHANG Rui. XXXX. Wheat acreage retrieval based on self-supervised learning-based spectral unmixing algorithm. National Remote Sensing Bulletin， XX（XX）：1-12 DOI： 10.11834/jrs.20222315.

摘要

遥感作为大范围地表覆盖提取和时空动态监测的有力工具，在小麦种植面积反演领域具有显著优势。然而，混合像元现象限制了小麦种植面积估计的精度，而端元的光谱变异性现象也使得传统的混合像元分解方法表现不佳。针对小麦种植面积估计过程中存在的混合像元和端元光谱变异性等问题，本文提出基于自监督学习的光谱解混算法（Self-supervised Learning-based Spectral Unmixing Algorithm， SLSU）。首先，使用变分自编码器实现无监督的端元光谱变异性解释和端元库生成；其后，使用交替最小二乘法和全约束最小二乘模型估计各类端元对应的丰度；最后，利用概率松弛标记法对解混结果进行空间邻域校正，以进一步提高光谱解混和小麦面积估计的精度。以河南省新乡市3个典型的小麦种植区为实验区，利用Sentinel 2影像获取小麦种植面积并利用实地测量的小麦分布现状数据计算提取精度。结果表明：基于SLSU算法获取的小麦种植面积的相对提取误差中位数小于1.3个像素，显著优于全约束最小二乘、扩展线性混合模型等传统混合像元分解算法以及支持向量机、随机森林等监督学习分类方法所提结果。所提SLSU算法可以提高小麦提取的精度和稳定性，为农作物分布提取和种植面积估算提供了有效的方法。

Abstract

Wheat is an important food crop in China

and its distribution acquisition and planting area estimation are of great significance to ensure national food security and development planning. As a powerful tool for large-scale land cover extraction and temporal and spatial dynamic monitoring

remote sensing has significant advantages in the field of wheat planting area estimation. However

wheat is often mixed with other ground objects and forms mixed-pixels limited by the spatial resolution of remote sensing images and the influence of various factors in the transmission of electromagnetic radiation. The spectral mixing limits the accuracy of wheat planting area estimation. Meanwhile

endmember spectral variability also makes traditional spectral unmixing methods perform poorly. Thus

this paper proposes a Self-supervised Learning-based Spectral Unmixing Algorithm (SLSU) to alleviate the influence of spectral mixing and endmember spectral variability wheat planting area estimation. Firstly

the variational autoencoder is used to achieve unsupervised interpretation of the endmember spectral variability and endmember library generation. Then

abundances corresponding to various endmembers are estimated by using the alternating least-squares strategy and fully constrained least squares. Finally

the unmixed results are corrected based on the spatial neighborhood by using the probabilistic relaxation labeling algorithm to further improve the accuracy of spectral unmixing and wheat extraction. Three typical wheat planting areas in Xinxiang

Henan Province

were selected as experimental areas

and the wheat planting area was obtained by Sentinel 2 images. The extraction accuracy was evaluated by wheat distribution data measured in the field

and the results show that the median value and the R2 score of the wheat extraction’s relative extraction error are close to 1.3 pixels and 1.00

respectively

which are significantly better than the results extracted by traditional spectral unmixing algorithms (including fully constrained least squares

extended linear mixed model and so on) and traditional supervised learning classification methods (such as support vector machines and random forests). The proposed SLSU algorithm can improve the accuracy and stability of wheat planting area estimation and provide an effective method for crop distribution extraction and planting area estimation.

关键词

自监督学习变分自编码器混合像元分解地物提取作物面积估计

Keywords

self-supervised learningvariational auto encoderspectral mixingfeature extractioncrop area estimation

references

Boardman J W. 1993. Automating spectral unmixing of AVIRIS data using convex geometry concepts. JPL, Summaries of the 4th Annual JPL Airborne Geoscience Workshop. Volume 1: AVIRIS Workshop. California

Borsoi R A, Imbiriba T and Bermudez J C M. 2019. Deep generative endmember modeling: an application to unsupervised spectral unmixing. IEEE Transactions on Computational Imaging, 6: 374-384

Borsoi R A, Imbiriba T and Bermudez J C M. 2020. A data dependent multiscale model for hyperspectral unmixing with spectral variability. IEEE Transactions on Image Processing, 29: 3638-3651

Drumetz L, Chanussot J and Jutten C. 2016a. Variability of the endmembers in spectral unmixing: recent advances. 2016 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS): IEEE: 1-5

Drumetz L, Veganzones M, Henrot S, Phlypo R, Chanussot J and Jutten C. 2016b. Blind hyperspectral unmixing using an extended linear mixing model to address spectral variability. IEEE Transactions on Image Processing, 25(8): 3890-3905

Han S, Pool J, Tran J and Dally W. 2015. Learning both weights and connections for efficient neural network. Advances in neural information processing systems, 28: 1135-1143

He Y, Liu P, Wang Z, Hu Z and Yang Y. 2019. Filter pruning via geometric median for deep convolutional neural networks acceleration. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition: 4340-4349

Heinz D C. 2001. Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery. IEEE transactions on geoscience and remote sensing, 39(3): 529-545

Imbiriba T, Bermudez J C, Tourneret J and Richard C. 2014. Detection of nonlinear mixtures using gaussian processes: application to hyperspectral imaging. 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): IEEE: 7949-7953

Imbiriba T, Borsoi R A and Bermudez J C M. 2018. Generalized linear mixing model accounting for endmember variability. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP): IEEE: 1862-1866

Kingma D P and Welling M. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114

Lee J and Won C. 2010. Topology preserving relaxation labeling for nonrigid point matching. IEEE transactions on pattern analysis and machine intelligence, 33(2): 427-432

Okujeni A, van der Linden S, Tits L, Somers B and Hostert P. 2013. Support vector regression and synthetically mixed training data for quantifying urban land cover. Remote Sensing of Environment, 137: 184-197

Pohl C and Van Genderen J. 2016. Remote sensing image fusion: a practical guide. Boca Raton, Florida: Crc Press.

Ren H and Chang C. 2003. Automatic spectral target recognition in hyperspectral imagery. IEEE Transactions on Aerospace and Electronic Systems, 39(4): 1232-1249

Rosenfeld A, Hummel R A and Zucker S W. 1976. Scene labeling by relaxation operations. IEEE Transactions on Systems, Man, and Cybernetics, 6: 420-433

Su Y, Li J, Plaza A, Marinoni A, Gamba P and Chakravortty S. 2019. DAEN: Deep Autoencoder Networks for Hyperspectral Unmixing. IEEE Transactions on Geoscience and Remote Sensing, 57(7), 4309-4321.

Thouvenin P, Dobigeon N and Tourneret J. 2015. Hyperspectral unmixing with spectral variability using a perturbed linear mixing model. IEEE Transactions on Signal Processing, 64(2): 525-538

Wang H and Hancock E R. 2008. Probabilistic relaxation labelling using the Fokker-Planck equation. Pattern Recognition, 41(11): 3393-3411

Wang L, Liu D, Wang Q and Wang Y. 2013. Spectral unmixing model based on least squares support vector machine with unmixing residue constraints. IEEE Geoscience and Remote Sensing Letters, 10(6): 1592-1596

Winter M E. 1999. N-FINDR: an algorithm for fast autonomous spectral end-member determination in hyperspectral data. Imaging Spectrometry V: International Society for Optics and Photonics, 3753: 266-275

Zare A and Ho K C. 2013. Endmember variability in hyperspectral analysis: addressing spectral variability during spectral unmixing. IEEE Signal Processing Magazine, 31(1): 95-104

Zhu Q Q, Deng W H, Zheng Z, Zhong Y F, Guan Q F, Lin W H, Zhang L P and Li D R. 2021. A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification. IEEE Transactions on Cybernetics: 1-15.

Zhu Q Q, Lei Y, Sun X L, Guan Q F, Zhong Y F, Zhang L P and Li D R. 2022a. Knowledge-guided land pattern depiction for urban land use mapping: A case study of Chinese cities. Remote Sensing of Environment, 272: 112916.

Zhu Q Q, Wang L L, Chen J L, Zeng W, Zhong Y F, Guan Q F and Yang Z J. 2022b. S3TRM: Spectral-Spatial Unmixing of Hyperspectral Imagery Based on Sparse Topic Relaxation-Clustering Model. IEEE Transactions on Geoscience and Remote Sensing 60, 1-13.

Duan J L, Wang J and Zhang T. 2018. A kind of vegetation cover fraction retrieval algorithm based on spectral normalization frame. Remote Sensing Technology and Application, 33(02): 778-786

段金亮, 王杰, 张婷. 2018. 一种基于光谱归一化下的植被覆盖度反演算法. 遥感技术与应用, 33(02): 778-786

Duan J L, Zhang R, Li K and Pang J T. 2021. A kind of extended linear spectral unmixing algorithm based on noise level estimation. Remote Sensing Technology and Application, 36(04): 820-826

段金亮, 张瑞, 李奎, 庞家泰. 2021. 一种基于噪声水平估计的扩展线性光谱分解算法. 遥感技术与应用, 36(04): 820-826

Feng Z L, Xiao F, Lu X P, Hao B, Wang R Y and Zhu R. 2022. Winter wheat classification method based on feature optimization of random forest. Bulletin of surveying and mapping03: 70-75

冯志立, 肖锋, 卢小平, 郝波, 王如意, 朱睿. 2022. 基于随机森林特征优选的冬小麦分类方法. 测绘通报03: 70-75

Hu M G and Wang J F. 2010. Mixed-pixel decomposition and super-resolution reconstruction of RS image. Progress in Geography, 29(06): 747-756

胡茂桂, 王劲峰. 2010. 遥感影像混合像元分解及超分辨率重建研究进展. 地理科学进展, 29(06): 747-756

Lan J H, Zhou J L, Hao Y S, Zeng Y L, Zhang Y Z and Dong M W. 2018. Research progress on unmixing of hyperspectral remote sensing imagery. Journal of Remote Sensing, 22(01): 13-27

蓝金辉, 邹金霖, 郝彦爽, 曾溢良, 张玉珍, 董铭巍. 2018. 高光谱遥感影像混合像元分解研究进展. 遥感学报, 22(01): 13-27

Liu Y, Fu Z Y and Zheng F B. 2015. Review on high resolution remote sensing image classification and recognition. Journal of Geo-information Science, 17(09): 1080-1091

刘扬, 付征叶, 郑逢斌. 2015. 高分辨率遥感影像目标分类与识别研究进展. 地球信息科学学报, 17(09): 1080-1091

Liu Z D, Duan A W, Gao Y and Liu H. Study on dynamic model of leaf area index (LAI) for winter wheat in Xinxiang area. Journal of Triticeae Crops, 28(04): 680-685

刘战东, 段爱旺, 高阳, 刘浩. 2008. 河南新乡地区冬小麦叶面积指数的动态模型研究. 麦类作物学报, 28(04): 680-685

Wang N, Li Q Z, Du X, Zhang Y, Zhao L C and Wang H Y. 2017. Identification of main crops based on the univariate feature selection in Subei. Journal of Remote Sensing, 21(04): 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(04): 519-530

Wang X Q. 2007. Study on wheat's productive potential and developental strategy in Henan province. Xianyang: Northwest A&F University, 129

王学强. 2007. 河南小麦生产潜力及发展战略研究. 咸阳: 西北农林科技大学, 129

Wu B F, Zhang M, Zheng H W, Yan N N, Zhang X, Xing Q and Chang S. 2019. Twenty years of CropWatch: Progress and prospect. Journal of Remote Sensing, 23(06): 1053-1063

吴炳方, 张淼, 曾红伟, 闫娜娜, 张鑫, 邢强, 常胜. 2019. 全球农情遥感速报系统20年. 遥感学报, 23(06): 1053-1063

Yin H M, Guli J, Yu T, Umuhoza J and LI X. 2022. Wheat yield estimation with remote sensing in northern Kazakhstan. Arid Land Geography, 45(02): 488-498

尹瀚民, 古丽·加帕尔, 于涛, UMUHOZA J, 李旭. 2022. 哈萨克斯坦北部小麦遥感估产方法研究. 干旱区地理, 45(02): 488-498

Yin J, Zhou L L, Li L W, Zhang Y Q, Huang W J, Zhang H L, Wang Y, Deng S J, Fan H S, Ji C, Chen J J and Peng D L. 2021. A comparative study on wheat identification and growth monitoring based on multi-source remote sensing data. Remote Sensing Technology and Application, 36(02): 332-341

尹捷, 周雷雷, 李利伟, 张雅琼, 黄文江, 张赫林, 王岩, 郑诗军, 范海生, 纪婵, 陈俊杰, 彭代亮. 2021. 多源遥感数据小麦识别及长势监测比较研究. 遥感技术与应用, 36(02): 332-341

Zhang D L, Chen Z L and Xie Z. 2018. Spatial scenes matching with on relaxation labeling approach. Geomatics and Information Science of Wuhan University, 43(05): 752-758

张丁文, 陈占龙, 谢忠. 2018. 利用松弛标记法进行空间场景匹配. 武汉大学学报(信息科学版), 43(05): 752-758

文章被引用时，请邮件提醒。

提交

遥感图像小样本舰船识别跨域迁移学习算法

基于阴影方向先验的高分辨率遥感影像地物阴影检测方法