Spatial-spectral combined preprocessing method for hyperspectral endmember extraction

Yin-hua WU; Peng-chong WANG; Shen-jiang WU; Fa-qiang ZHANG

doi:10.37188/YJYXS20203509.0955

您当前的位置：

首页 >

文章列表页 >

Spatial-spectral combined preprocessing method for hyperspectral endmember extraction

Image Processing | 更新时间：2020-09-08

- Spatial-spectral combined preprocessing method for hyperspectral endmember extraction
- Chinese Journal of Liquid Crystals and Displays Vol. 35, Issue 9, Pages: 955-964(2020)
- 作者机构：
  
  1.西安工业大学光电工程学院, 陕西西安 710021
  2.中国科学院光谱成像技术重点实验室, 陕西西安 710029
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China(61905275);Open Research Fund of Key Laboratory of Spectral Imaging Technology of the Chinese Academy of Sciences(LSIT201902W);Open Research Fund of Key Laboratory of Spectral Imaging Technology of the Chinese Academy of Sciences(LSIT201802G)
- DOI：10.37188/YJYXS20203509.0955
  CLC： O433
- Received：26 March 2020，
  
  Revised：24 April 2020，
  
  Accepted：24 April 2020，
  
  Published：05 September 2020
- 稿件说明：
移动端阅览
Yin-hua WU, Peng-chong WANG, Shen-jiang WU, et al. Spatial-spectral combined preprocessing method for hyperspectral endmember extraction[J]. Chinese journal of liquid crystals and displays, 2020, 35(9): 955-964.
DOI：

Yin-hua WU, Peng-chong WANG, Shen-jiang WU, et al. Spatial-spectral combined preprocessing method for hyperspectral endmember extraction[J]. Chinese journal of liquid crystals and displays, 2020, 35(9): 955-964. DOI： 10.37188/YJYXS20203509.0955.

摘要

混合像元的存在是制约高光谱遥感应用精度的主要原因，因此必须进行高光谱解混合。端元提取作为高光谱解混合的关键，往往易受噪声和异常点的干扰。为了提高端元提取精度，针对高光谱端元提取提出了一种空谱联合的预处理方法。首先，定义了新概念光谱纯度指数，主要用于预估高光谱图像中每个像元的光谱纯度；其次，给出了基于光谱纯度指数的空间去冗余方法，利用真实地物的空间分布连续性，判断和移除高光谱图像中冗余像元，最终形成精简的候选端元集。实验结果表明：采用提出的预处理方法后，对于模拟高光谱图像，提取的端元与原始端元之间夹角平均减少了9.022 3°，候选端元数量少于原始像元数量的10%。该预处理方法不仅有效消除了噪声和异常点的干扰，提高了端元提取精度，且大幅降低了时间复杂度。

Abstract

The existence of mixed pixels is the main reason that restricts the application accuracy of hyperspectral remote sensing

so hyperspectral unmixing is necessary. As the key of hyperspectral unmixing

the endmember extraction is often susceptible to noise and outliers. In order to improve the accuracy of endmember extraction

a spatial-spectral combined preprocessing method for hyperspectral endmember extraction is proposed in this paper. Firstly

a new concept of spectral purity index (SPI) is defined

which is used to estimate the spectral purity of each pixel in hyperspectral image. Secondly

a spatial de-redundancy method based on SPI is provided

utilizing the continuity of spatial distribution of real objects in the image to judge and eliminate redundant pixels in hyperspectral image

and finally a fine set of candidate endmembers is formed. Experimental results show that after using the proposed preprocessing method

for the simulated hyperspectral image

the angle between the extracted endmembers and the original endmembers is reduced by 9.022 3° on average

and the number of candidate endmembers is less than 10% of the number of original pixels. The proposed preprocessing method not only eliminates the interference of noise and outliers effectively and improves the accuracy of endmember extraction

but also reduces the time complexity greatly.

关键词

Keywords

references

Y H WU , B L HU , X H GAO , 等 . Hyperspectral image classification based on adaptive segmentation . Optik , 2018 . 172 612 - 621 . DOI: 10.1016/j.ijleo.2018.07.058 http://doi.org/10.1016/j.ijleo.2018.07.058 .

成宝芝 , 张丽丽 . 基于双边滤波的最优波段子空间高光谱异常目标检测 . 液晶与显示 , 2019 . 34 ( 9 ): 897 - 904 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384725&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384725&Fpath=&index=-1&l=zh .

B Z CHENG , L L ZHANG . Optimal bands subspace anomaly detection for hyperspectral imagery based on bilateral filtering . Chinese Journal of Liquid Crystals and Displays , 2019 . 34 ( 9 ): 897 - 904 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384725&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1384725&Fpath=&index=-1&l=zh .

黄元超 , 王阿川 . 基于空谱联合和波段分类的高光谱压缩感知重构 . 液晶与显示 , 2018 . 33 ( 4 ): 291 - 298 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1377924&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1377924&Fpath=&index=-1&l=zh .

Y C HUANG , A C WANG . Hyperspectral compressed perceptual reconstruction based on space spectrum combination and band classification . Chinese Journal of Liquid Crystals and Displays , 2018 . 33 ( 4 ): 291 - 298 . http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1377924&Fpath=&index=-1&l=zh http://cjlcd.lightpublishing.cn/thesisDetails?columnId=1377924&Fpath=&index=-1&l=zh .

李冠东 , 张春菊 , 高飞 , 等 . 双卷积池化结构的3D-CNN高光谱遥感影像分类方法 . 中国图象图形学报 , 2019 . 24 ( 4 ): 639 - 654 .

G D LI , C J ZHANG , F GAO , 等 . Doubleconvpool-structured 3D-CNN for hyperspectral remote sensing image classification . Journal of Image and Graphics , 2019 . 24 ( 4 ): 639 - 654 .

谭翠媚 , 许廷发 , 马旭 , 等 . 图-谱结合的压缩感知高光谱视频图像复原 . 中国光学 , 2018 . 11 ( 6 ): 949 - 957 .

C M TAN , T F XU , X MA , 等 . Graph-spectral hyperspectral video restoration based on compressive sensing . Chinese Optics , 2018 . 11 ( 6 ): 949 - 957 .

闫歌 , 许廷发 , 马旭 , 等 . 动态测量的高光谱图像压缩感知 . 中国光学 , 2018 . 11 ( 4 ): 550 - 559 .

G YAN , T F XU , X MA , 等 . Hyperspectral image compression sensing based on dynamic measurement . Chinese Optics , 2018 . 11 ( 4 ): 550 - 559 .

杜小平 , 刘明 , 夏鲁瑞 , 等 . 基于光谱角累加的高光谱图像异常检测算法 . 中国光学 , 2013 . 6 ( 3 ): 325 - 331 .

X P DU , M LIU , L R XIA , 等 . Anomaly detection algorithm for hyperspectral imagery based on summation of spectral angles . Chinese Optics , 2013 . 6 ( 3 ): 325 - 331 .

方帅 , 祝凤娟 , 董张玉 , 等 . 样本优化选择的高光谱图像分类 . 中国图象图形学报 , 2019 . 24 ( 1 ): 135 - 148 .

S FANG , F J ZHU , Z Y DONG , 等 . Sample optimized selection of hyperspectral image classification . Journal of Image and Graphics , 2019 . 24 ( 1 ): 135 - 148 .

冉琼 , 于浩洋 , 高连如 , 等 . 结合超像元和子空间投影支持向量机的高光谱图像分类 . 中国图象图形学报 , 2018 . 23 ( 1 ): 95 - 105 .

Q RAN , H Y YU , LI R GAO , 等 . Superpixel and subspace projection-based support vector machines for hyperspectral image classification . Journal of Image and Graphics , 2018 . 23 ( 1 ): 95 - 105 .

K WU , X X FENG , H G XU , 等 . A novel endmember extraction method using sparse component analysis for hyperspectral remote sensing imagery . IEEE Access , 2018 . 6 75206 - 75215 . DOI: 10.1109/ACCESS.2018.2882187 http://doi.org/10.1109/ACCESS.2018.2882187 .

SONG M P, XU M, CHANG C I. Algorithm research on endmember extraction combined with distribution statistics[C]// Proceedings of the 2018 9 th Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing. Amsterdam, Netherlands: IEEE, 2018: 1-4.

KOWKABI F, KESHAVARZ A. Hyperspectral endmember extraction preprocessing using combination of Euclidean and geodesic distances[C]// Proceedings of 2018 IEEE International Geoscience and Remote Sensing Symposium . Valencia, Spain: IEEE, 2018: 4265-4268.

J M P NASCIMENTO , J M B DIAS . Vertex component analysis:a fast algorithm to unmix hyperspectral data . IEEE Transactions on Geoscience and Remote Sensing , 2005 . 43 ( 4 ): 898 - 910 . DOI: 10.1109/TGRS.2005.844293 http://doi.org/10.1109/TGRS.2005.844293 .

GRUNINGERJ H, RATKOWSKI A J, HOKE M L. The sequential maximum angle convex cone (SMACC) endmember model[C]// Proceedings of SPIE 5425, Algorithms and Technologies for Multispectral , Hyperspectral , and Ultraspectral Imagery X . Orlando, USA: SPIE, 2004.

S H MEI , M Y HE , Z Y WANG , 等 . Spatial purity based endmember extraction for spectral mixture analysis . IEEE Transactions on Geoscience and Remote Sensing , 2010 . 48 ( 9 ): 3434 - 3445 . DOI: 10.1109/TGRS.2010.2046671 http://doi.org/10.1109/TGRS.2010.2046671 .

崔建涛 , 王晶 , 厉小润 , 等 . 基于空间像素纯度指数的端元提取算法 . 浙江大学学报:工学版 , 2013 . 47 ( 9 ): 1524 - 1530, 1565 .

J T CUI , J WANG , X R LI , 等 . Endmember extraction algorithm based on spatial pixel purity index . Journal of Zhejiang University:Engineering Science , 2013 . 47 ( 9 ): 1524 - 1530, 1565 .

HEINZ D, CHANG C I, ALTHOUSE M L G. Fully constrained least-squares based linear unmixing[hyperspectral image classification][C] // Proceedings of IEEE 1999 International Geoscience and Remote Sensing Symposium . Hamburg, Germany: IEEE, 1999: 1401-1403.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰