文章基本信息

标题：QUANTUM SEGMENTATION APPROACH FOR VERY HIGH SPATIAL RESOLUTION SATELLITE IMAGE: APPLICATION TO QUICKBIRD IMAGE
本地全文：下载
作者：SALAH EDDINE MECHKOURI ; RACHID ZENNOUHI ; SALEH EL JOUMANI 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：62
期号：2
出版社：Journal of Theoretical and Applied
摘要：Through previous studies on the extraction of information for the land use and land cover, and the segmentation for the Very High Spatial Resolution Satellite Images �VHSRSI� have shown satisfaction, such as the unsupervised classification (ISODATA and KMEANS) and the hierarchical analysis of the 2D-histograms. However, in various situations, closed areas are classified as homogeneous. We believe that the quantum mechanics theory which is connected with information theory in communication and digital image processing, could take into account more information about pixels classification process and permits to distinguish between closed distinct areas. Based on this theory, we develop a new image segmentation algorithm for Very High Spatial Resolution Satellite Images. Pixels classification is performed by unsupervised classification method via the hierarchical analysis of the 2D-histograms which is constructed using the wavefunction. The proposed approach has been tested on synthetic image, and applied to urban environment classification for Quickbird data of a selected urban zone of the region of Rabat-Sale-Zemour-Zayer, prefecture of Skhirat-Temara, Morocco.
关键词：Classification; 2D-histogram; Wavefunction; Quickbird image; Segmentation ;