Sub-pixel Mapping Based on SVM of Hyperspectral Remotely Sensed Imagery

WANG Yi; LI Ji

doi:10.13203/j.whugis20150443

Volume 42 Issue 2

Feb. 2017

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2017 > 42(2): 198-201. > DOI: 10.13203/j.whugis20150443

WANG Yi, LI Ji. Sub-pixel Mapping Based on SVM of Hyperspectral Remotely Sensed Imagery[J]. Geomatics and Information Science of Wuhan University, 2017, 42(2): 198-201. DOI: 10.13203/j.whugis20150443

Citation:

PDF (1748 KB)

Sub-pixel Mapping Based on SVM of Hyperspectral Remotely Sensed Imagery

WANG Yi^{1, 2,},
LI Ji^{1, 2}

1.
Institute of Geophysics and Geomatics, China University of Geosciences, Wuhan 430074, China
2.
Subsurface Multi-scale Imaging Laboratory of Hubei Province, China University of Geosciences, Wuhan 430074, China

Funds:

The National Natural Science Foundation of China No. 61271408

More Information

Author Bio:
WANG Yi, PhD, associate professor, specializes in hyper spectral remote sensing image information analysis and processing. E-mail: cug.yi.wang@gmail.com
Received Date: April 19, 2016
Published Date: February 04, 2017

Graphical Abstract

Abstract

Abstract

In this paper, an image sub-pixel mapping algorithm based on support vector machine (SVM)has been presented for hyper spectral imagery. Since the total variation(TV) model is classic Edge-preserving smoothing filter, the authors introduce this model as a presmoothing to improve accuracies of spectral unmixing and sub-pixel mapping. Also, according to the spatial correlation theory, our algorithm not only considers the impact of the abundance for the current pixel on sub-pixel classification, but also takes the effect of adjacent pixels into account. In addition, to improve the efficiency of our algorithm, we propose to decrease the number of samples by eliminating pure pixels during the training and testing procedure in supervised classification. Experimental results on real-world hyper spectral remote sensing dataset show the validity of our algorithm on both visual inspection and quantitative analysis.
- subpixel mapping,
- hyper spectral remote sensing,
- SVM,
- TV,
- image classification

FullText(HTML)

References (11)

References

[1]	Atkinson P M. Mapping Sub-pixel Boundaries from Remotely Sensed Images[J]. Innovations in GIS, 1997, 4:166-180
[2]	Mertens K C, Verbeke L P C, Ducheyne E I, et al. Using Genetic Algorithms in Sub-pixel Mapping[J]. International Journal of Remote Sensing, 2003, 24(21):4241-4247 doi: 10.1080/01431160310001595073
[3]	Aplin P, Atkinson P M. Sub-pixel Land Cover Mapping for Per-field Classification[J]. International Journal of Remote Sensing, 2001, 22(14):2853-2858 doi: 10.1080/01431160110053176
[4]	Kasetkasem T, Arora M K, Varshney P K. Super-resolution Land-cover Mapping Using a Markov Random Field Based Approach[J]. Remote Sensing of Environment, 2005,96(3):302-314 http://cn.bing.com/academic/profile?id=9aa01bf1324cec6240448c3cd203910e&encoded=0&v=paper_preview&mkt=zh-cn
[5]	凌峰, 张秋文, 王乘, 等. 基于元胞自动机模型的遥感图像亚像元定位[J]. 中国图象图形学报, 2005, 10(7):916-921 http://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB200507018.htm Ling Feng, Zhang Qiuwen, Wang Cheng, et al. Sub-pixel Mapping of Remote Sensing Images Basedon Cellular Automata Model[J]. Journal of Image and Graphics, 2005, 10(7):916-921 http://www.cnki.com.cn/Article/CJFDTOTAL-ZGTB200507018.htm
[6]	Ling F, Xiao F, Du Y, et al. Waterline Mapping at the Subpixel Scale from Remote Sensing Imagery with High-resolution Digital Elevation Models[J]. International Journal of Remote Sensing, 2008, 29(6):1809-1815 doi: 10.1080/01431160701802489
[7]	吴柯, 李平湘, 张良培, 等.基于正则MAP模型的遥感影像亚像元定位[J]. 武汉大学学报·信息科学版, 2007, 32(7):593-597 http://ch.whu.edu.cn/CN/abstract/abstract1944.shtml Wu Ke, Li Pingxiang, Zhang Liangpei, et al. Sub-pixel Mapping of Remote Sensing Images Based on MAP Model[J]. Geomatics and Information Science of Wuhan University, 2007, 32(7):593-597 http://ch.whu.edu.cn/CN/abstract/abstract1944.shtml
[8]	吴柯, 牛瑞卿, 李平湘, 等.基于FUZZY ARTMAP神经网络模型的遥感影像亚像元定位[J]. 武汉大学学报· 信息科学版, 2009, 34(3):297-300 http://ch.whu.edu.cn/CN/abstract/abstract1202.shtml Wu Ke, Niu Ruiqing, Li Pingxiang, et al.Sub-pixel Mapping of Remote Sensing Images Based on Fuzzy ARTMAP Neural Network Model[J]. Geomatics and Information Science of Wuhan University, 2009, 34(3):297-300 http://ch.whu.edu.cn/CN/abstract/abstract1202.shtml
[9]	Zhong Y F, Zhang L P. Remote Sensing Image Subpixel Mapping Based on Adaptive Differential Evolution[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B:Cybernetics, 2012, 42(5):1306-1329 doi: 10.1109/TSMCB.2012.2189561
[10]	王毅,张良培,李平湘. 基于自动搜索和光谱匹配技术的训练样本纯化算法[J]. 武汉大学学报·信息科学版,2007, 32(3):216-219 http://ch.whu.edu.cn/CN/abstract/abstract1836.shtml Wang Yi, Zhang Liangpei, Li Pingxiang. Purified Algorithm for Training Samples Based on Automatic Searching and Spectral Matching Technique[J]. Geomatics and Information Science of Wuhan University, 2007, 32(3):216-219 http://ch.whu.edu.cn/CN/abstract/abstract1836.shtml
[11]	刘娟娟, 王茂芝, 葛世国, 等. 全约束下高光谱混合像元线性分解[J]. 四川理工学院学报(自然科学版), 2013, 26(3):76-79 http://www.cnki.com.cn/Article/CJFDTOTAL-SCQX201303017.htm Liu Juanjuan, Wang Maozhi, Ge Shiguo, et al. Fully Constrained Linear Decomposition of Hyperspectral Mixed Pixels[J]. Journal of Sichuan University of Science & Engineering (Natural Science Edition), 2013, 26(3):76-79 http://www.cnki.com.cn/Article/CJFDTOTAL-SCQX201303017.htm

Cited By

Get Citation

PDF

XML

Article views (2140) PDF downloads (498)

Sub-pixel Mapping Based on SVM of Hyperspectral Remotely Sensed Imagery

Abstract

References

Catalog

Related

Sub-pixel Mapping Based on SVM of Hyperspectral Remotely Sensed Imagery

Abstract

References

Catalog

Related

Export File

Citation

Format

Content