A Novel Multi-radius Neighborhood Rough Set Weighted Feature Extraction Method for Remote Sensing Image Classification

CHEN Tieqiao; LIU Jiahang; ZHU Feng; WANG Yihao; LIU Jia; CHEN Jie

doi:10.13203/j.whugis20150290

Volume 43 Issue 2

Feb. 2018

Turn off MathJax

Article Contents

Abstract

References

Geomatics and Information Science of Wuhan University > 2018 > 43(2): 311-317. > DOI: 10.13203/j.whugis20150290

CHEN Tieqiao, LIU Jiahang, ZHU Feng, WANG Yihao, LIU Jia, CHEN Jie. A Novel Multi-radius Neighborhood Rough Set Weighted Feature Extraction Method for Remote Sensing Image Classification[J]. Geomatics and Information Science of Wuhan University, 2018, 43(2): 311-317. DOI: 10.13203/j.whugis20150290

Citation:

PDF (1258 KB)

A Novel Multi-radius Neighborhood Rough Set Weighted Feature Extraction Method for Remote Sensing Image Classification

CHEN Tieqiao^{1, 2, 3,},
LIU Jiahang^1, ,,
ZHU Feng^{1, 2, 3},
WANG Yihao¹,
LIU Jia¹,
CHEN Jie⁴

1.
Xi'an Institute of Optics and Precision Mechanics of CAS, Xi'an 710119, China
2.
University of Chinese Academy of Sciences, Beijing 100049, China
3.
Key Laboratory of Lunar and Deep Space Exploration, Beijing 100012, China
4.
Department of Geo-informatics, Central South University, Changsha 410083, China

Funds:

The National Key Research and Development Program of China 2016YFF0103604

the Western Youth Scholars Program XAB2015A07

the Open Fund of Key Laboratory of Lunar and Deep Space Exploration

the Major State Basic Research Development Programme of China (973 Programme) 2012CB719906

More Information

Author Bio:
CHEN Tieqiao, PhD candidate, specializes in remote sensing image processing. E-mail: chentieqiao@opt.ac.cn
Corresponding author:
LIU Jiahang, PhD, professor. E-mail: jhliu@opt.cn
Received Date: September 04, 2017
Published Date: February 04, 2018

Graphical Abstract

Abstract

Abstract

The neighborhood rough set model can be effective for keeping or even improving classification accuracy. This model however, still has some disadvantages as it has low stability in classification precision, requires repeated neighborhood radius adjustments, and cannot realize automatic feature extraction. In order to solve these problems, this paper presents a multi-radius neighborhood rough set weighted feature extraction method for high resolution remote sensing image classification. The neighborhood rough set model was used to extract texture and spectrum features of image by setting gradually increasing radius with equally spaced steps, as a result effective subset features under different radius were obtained. The presence probablity of each feature under all the different radius was calculated, each feature was endowed with weight by its presence probability, so the final weighted features of image were acquired. The newly obtained features were applied to image classification using a support vector machine. Experiments on QuickBird images demonstrate that the proposed method can provide better classification results. Compared with other state-off-art neighborhood rough set model with effective radius, the overall accuracy exceeded about 3.88% while the Kappa coefficient exceeded about 5.16%. A classification experiment on a GeoEye-1 image also showed the effectiveness of the proposed method. All the classification experiment results show that the proposed method can improve classification precision and automation of high resolution remote sensing images.

FullText(HTML)

References (17)

References

[1]	Van Der Sande C J, De Jong S M, De Roo A P J. A Segmentation and Classification Approach of IKONOS-2 Imagery for Land Cover Mapping to Assist Flood Risk and Flood Damage Assessment[J]. International Journal of Applied Earth Observation and Geoinformation, 2003, 4(3):217-229 doi: 10.1016/S0303-2434(03)00003-5
[2]	Myitn S W, Lam N, and Tyler J. An Evaluation of Four Different in Wavelet Decomposition Procedures for Spatial Feature Discrimination in Urban Areas[J]. Transactions in GIS, 2002, 6(4):403-429 doi: 10.1111/1467-9671.00120
[3]	陈杰, 邓敏, 肖鹏峰, 等.粗糙集高分辨率遥感影像面向对象分类[J].遥感学报, 2010, 14(6):1139-1155 http://www.oalib.com/paper/1469929 Chen Jie, Deng Min, Xiao Pengfeng, et al. RoughSet Theory Based Object-oriented Classification of High Resolution Remotely Sensed Imagery[J]. Journal of Remote Sensing, 2010, 14(6):1139-1155 http://www.oalib.com/paper/1469929
[4]	Lobo A, Chic O and Casterad A. Classification of Mediterranean Crops with Multisensor Data:Per-pixel Versus Per-object Statistics and Image Segmentation[J]. International Journal of Remote Sensing, 1996, 17(12):2358-2400 doi: 10.1080/01431169608948779
[5]	陶超, 谭毅华, 彭碧发, 等.一种基于概率潜在语义模型的高分辨率遥感影像分类方法[J].测绘学报, 2011, 40(2):156-162 http://industry.wanfangdata.com.cn/dl/Detail/Periodical?id=Periodical_chxb201102004 Tao Chao, Tan Yihua, Peng Bifa, et al.A Probabilistic Latent Semantic Analysis Based Classification for High Resolution Remotely Sensed Imagery[J].Acta Geodaetica et Cartographica Sinica, 2011, 40(2):156-162 http://industry.wanfangdata.com.cn/dl/Detail/Periodical?id=Periodical_chxb201102004
[6]	赵银娣, 张良培, 李平湘.一种纹理特征融合分类算法[J].武汉大学学报·信息科学版, 2006, 31(3):278-281 http://ch.whu.edu.cn/CN/abstract/abstract2406.shtml Zhao Yindi, Zhang Liangpei, Li Pingxiang. A Texture Classification Algorithm Based on Feature Fusion[J].Geomatics and Information Science of Wuhan University, 2006, 31(3):278-281 http://ch.whu.edu.cn/CN/abstract/abstract2406.shtml
[7]	Hu Q H, Yu D R, Xie Z X, et, al. Fuzzy Probabilistic Approximation Spaces and their Information Measures[J]. IEEE Transactions on Fuzzy Systems. 2006, 14(2):191-201 doi: 10.1109/TFUZZ.2005.864086
[8]	潘励, 张祖勋, 张剑清.粗集理论在图像特征选择中的应用[J].数据采集与处理, 2002, 17(1):42-45 doi: 10.3969/j.issn.1004-9037.2002.01.010 Pan Li, Zhang Zhuxun, Zhang Jianqing. Application of Rough Sets in Image Feature Selection[J].Journal of Data Acquisition & Processing, 2002, 17(1):42-45 doi: 10.3969/j.issn.1004-9037.2002.01.010
[9]	Hu Q H, Yu D R, Xie Z X. Information-preservingHybrid Data Reduction Based on Fuzzy-rough Techniques[J]. Pattern Recognition Letters. 2006, 27:414-423 doi: 10.1016/j.patrec.2005.09.004
[10]	Hu Q H, Yu D R, Liu J F, et, al. Neighborhood Rough Set Based Heterogeneous Feature Subset Selection[J]. Information Sciences, 2008, 178(18):3577-3594 doi: 10.1016/j.ins.2008.05.024
[11]	蒋云良, 杨章显, 刘勇.不协调信息系统快速属性分布约简方法[J].自动化学报, 2012, 38(3):383-388 http://www.cqvip.com/QK/90250X/201203/41190663.html Jiang Yunliang, Yang Zhangxian, Liu Yong. Quick Distribution Reduction Algorithm in Inconsistent Information System[J]. Acta Automatica Sinica, 2012, 38(3):383-388 http://www.cqvip.com/QK/90250X/201203/41190663.html
[12]	陈铁桥, 陈杰, 梅小明, 等.基于多层次场聚类的高分辨率遥感影像分割方法[J].地理与地理信息科学, 2013, 29(6):10-13 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dlxygtyj201306003 Chen Tieqiao, Chen Jie, Mei Xiaoming, et al.Field Theory Based Multi-level Clustering for High-spatial Resolution Remote Sensing Imagery Segmentation[J]. Geography and Geo-Information Science, 2013, 29(6):10-13 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=dlxygtyj201306003
[13]	梅天灿, 李德仁, 秦前清.基于直线和区域特征的遥感影像线状目标检测[J].武汉大学学报·信息科学版, 2005, 30(8):689-693 http://ch.whu.edu.cn/CN/abstract/abstract2254.shtml Mei Tiancan, Li Deren, Qin Qianqing. Knowledge Based High Resolution Remote Sensing Image Segmentation[J].Geomatics and Information Science of Wuhan University, 2005, 30(8):689-693 http://ch.whu.edu.cn/CN/abstract/abstract2254.shtml
[14]	Zhang J G, Tan T N, Ma L. Invariant Texture Segmentation via Circular Gabor Filters[C]. Proceedings of the 16th IAPR International Conference on Pattern Recognition, Beijing, 2002
[15]	张学工.关于统计学习理论与支持向量机[J].自动化学报, 2000, 26(1):32-42 http://bianke.cnki.net/Web/Article/MOTO200001005.html Zhang Xuegong. Introduction Statistical Learning Theory and Support Vector Machines[J]. Acta Automatica Sinica, 2000, 26(1):32-42 http://bianke.cnki.net/Web/Article/MOTO200001005.html
[16]	陈杰, 邓敏, 肖鹏峰, 等.结合支持向量机与粒度计算的高分辨率遥感影像面向对象分类[J].测绘学报, 2011, 40(2):135-147 http://www.cqvip.com/QK/90069X/201102/37425529.html Chen Jie, Deng Min, Xiao Pengfeng, et al.Object-oriented Classification of High Resolution Imagery Combining Support Vector Machine with Granular Computing[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(2):135-147 http://www.cqvip.com/QK/90069X/201102/37425529.html
[17]	谭琨, 杜培军.基于支持向量机的高光谱遥感图像分类[J].红外与毫米波学报, 2008, 27(2):123-128 http://www.cqvip.com/Main/Detail.aspx?id=27059691 Tan Kun, Du Peijun. Hyperspectral Remote Sensing Image Classification Based on Support Vector Machine[J]. Journal of Infrared Millim Waves, 2008, 27(2):123-128 http://www.cqvip.com/Main/Detail.aspx?id=27059691

Cited By

Get Citation

PDF

XML

Article views (1554) PDF downloads (320)

A Novel Multi-radius Neighborhood Rough Set Weighted Feature Extraction Method for Remote Sensing Image Classification

Abstract

References

Catalog

Related

A Novel Multi-radius Neighborhood Rough Set Weighted Feature Extraction Method for Remote Sensing Image Classification

Abstract

References

Catalog

Related

Export File

Citation

Format

Content