首页  >  科研动态  >  正文
科研动态
苏俊英的论文在FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY 刊出
发布时间:2019-09-25 09:42:48     发布者:易真     浏览次数:

标题: A NEW SPECTRAL SPATIAL JOINTED HYPERSPECTRAL IMAGE CLASSIFICATION APPROACH BASED ON FRACTAL DIMENSION ANALYSIS

作者: Su, JY (Su, Junying); Li, YK (Li, Yingkui); Hu, QW (Hu, Qingwu)

来源出版物: FRACTALS-COMPLEX GEOMETRY PATTERNS AND SCALING IN NATURE AND SOCIETY  : 27  : 5  文献号: 1950079  DOI: 10.1142/S0218348X19500798  出版年: AUG 2019  

摘要: ID maximize the advantages of both spectral and spatial information, we introduce a new spectral-spatial jointed hyperspectral image classification approach based on fractal dimension (FD) analysis of spectral response curve (SRC) in spectral domain and extended morphological processing in spatial domain. This approach first calculates the FD image based on the whole SRC of the hyperspectral image and decomposes the SRC into segments to derive the FD images with each SRC segment. These FD images based on the segmented SRC are composited into a multidimensional FD image set in spectral domain. Then, the extended morphological profiles (EMPs) are derived from the image set through morphological open and close operations in spatial domain. Finally, all these EMPs and FD features are combined into one feature vector for a probabilistic support vector machine (SVM) classification. This approach was demonstrated using three hyperspectral images in urban areas of the university campus and downtown area of Pavia, Italy, and the Washington DC Mall area in the USA, respectively. We assessed the potential and performance of this approach by comparing with PCA-based method in hyperspectral image classification. Our results indicate that the classification accuracy of our proposed method is much higher than the accuracies of the classification methods based on the spectral or spatial domain alone, and similar to or slightly higher than the classification accuracy of PCA-based spectral-spatial jointed classification method. The proposed FD approach also provides a new self-similarity measure of land class in spectral domain, a unique property to represent hyperspectral self-similarity of SRC in hyperspectral imagery.

入藏号: WOS:000484177000011

语言: English

文献类型: Article

作者关键词: Hyperspectral image Classification; Fractal Dimension (FD); Spectral Response Curve (SRC); Extended Morphological Profiles (EMPs); Support Vector Machine (SVM)

地址: [Su, Junying] Wuhan Univ, Sch Resource & Environm Sci, Wuhan 430079, Hubei, Peoples R China.

[Hu, Qingwu] Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430079, Hubei, Peoples R China.

[Li, Yingkui] Univ Tennessee, Dept Geog, Knoxville, TN 37996 USA.

通讯作者地址: Hu, QW (通讯作者)Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430079, Hubei, Peoples R China.

电子邮件地址: jysu_sjy@whu.edu.cn; yli32@utk.edu; huqw@whu.edu.cn

影响因子:2.971


信息服务
学院网站教师登录 学院办公电话 学校信息门户登录

版权所有 © 武汉大学资源与环境科学学院
地址:湖北省武汉市珞喻路129号 邮编:430079 
电话:027-68778381,68778284,68778296 传真:027-68778893