Research on an Urban Building Area Extraction Method with High-Resolution PolSAR Imaging Based on Adaptive Neighborhood Selection Neighborhoods for Preserving Embedding

doi:10.3390/ijgi9020109

CORC > 自动化研究所 > 中国科学院自动化研究所 > 中国科学院分子影像重点实验室

	Research on an Urban Building Area Extraction Method with High-Resolution PolSAR Imaging Based on Adaptive Neighborhood Selection Neighborhoods for Preserving Embedding
	Cheng, Bo 1; Cui, Shiai 1; Ma, Xiaoxiao 2; Liang, Chenbin 3
刊名	ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
	2020-02-01
卷号	9 期号:2 页码:15
关键词	PolSAR machine learning ANSNPE SVM
DOI	10.3390/ijgi9020109
通讯作者	Cui, Shiai(cuisa@radi.ac.cn)
英文摘要	Feature extraction of an urban area is one of the most important directions of polarimetric synthetic aperture radar (PolSAR) applications. Ahigh-resolution PolSAR image has the characteristics of high dimensions and nonlinearity. Therefore, to find intrinsic features for target recognition, a building area extraction method for PolSAR images based on the Adaptive Neighborhoods selection Neighborhood Preserving Embedding (ANSNPE) algorithm is proposed. First, 52 features are extracted by using the Gray level co-occurrence matrix (GLCM) and five polarization decomposition methods. The feature set is divided into 20 dimensions, 36 dimensions, and 52 dimensions. Next, the ANSNPE algorithm is applied to the training samples, and the projection matrix is obtained for the test image to extract the new features. Lastly, the Support Vector machine (SVM) classifier and post processing are used to extract the building area, and the accuracy is evaluated. Comparative experiments are conducted using Radarsat-2, and the results show that the ANSNPE algorithm could effectively extract the building area and that it had a better generalization ability; the projection matrix is obtained using the training data and could be directly applied to the new sample, and the building area extraction accuracy is above 80%. The combination of polarization and texture features provide a wealth of information that is more conducive to the extraction of building areas.
资助项目	National Natural Science Foundation of China[61731022]
WOS关键词	NONLINEAR DIMENSIONALITY REDUCTION ; TARGET RECOGNITION ; SAR ; CLASSIFICATION
WOS研究方向	Physical Geography ; Remote Sensing
语种	英语
出版者	MDPI
WOS记录号	WOS:000522449700049
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/38782]
专题	自动化研究所_中国科学院分子影像重点实验室
通讯作者	Cui, Shiai
作者单位	1.Chinese Acad Sci, Inst Remote Sensing & Digital Earth, 9 Dengzhuang South Rd, Beijing 100094, Peoples R China 2.Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Sch Artif Intelligence, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Cheng, Bo,Cui, Shiai,Ma, Xiaoxiao,et al. Research on an Urban Building Area Extraction Method with High-Resolution PolSAR Imaging Based on Adaptive Neighborhood Selection Neighborhoods for Preserving Embedding[J]. ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,2020,9(2):15.
APA	Cheng, Bo,Cui, Shiai,Ma, Xiaoxiao,&Liang, Chenbin.(2020).Research on an Urban Building Area Extraction Method with High-Resolution PolSAR Imaging Based on Adaptive Neighborhood Selection Neighborhoods for Preserving Embedding.ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION,9(2),15.
MLA	Cheng, Bo,et al."Research on an Urban Building Area Extraction Method with High-Resolution PolSAR Imaging Based on Adaptive Neighborhood Selection Neighborhoods for Preserving Embedding".ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION 9.2(2020):15.