文章基本信息

标题：Land Use/Cover Change Detection Based on Artificial Neural Networks and Wavelet based Texture Analysis
本地全文：下载
作者：Ping XIAO ; Xi'an ZHAO ; Deren LI 等
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2002
卷号：XXXIV Part 2
页码：535-540
出版社：Copernicus Publications
摘要：In the paper, the integration of Artificial Neural Network(ANN) 、 Wavelets texture analysis and GIS has been introduced to and successfully used in Land use/cover change detection (LUCCD) detection to improve the change detection accuracy and efficiency. The input and output, and the settings of ANN have been studied for the change detection, and different ANN models and algorithms have been introduced to improve the performance of ANN. The results have shown that using ANN for change detection has many advantages over the traditional ones like images difference and post classification, such as being able to provide both changed areas and categories at same time, easy to integrate multi-source data, and free of the problems concerning the threshold determination and the error accumulation. The texture features of the images, which are calculated from wavelet transform, have been used as additional information in LUCCD to improve the results of gray-level based change detection. The geographic information in GIS has also been used to help automatically select sample points of urban land in the images during ANN training
关键词：Land use/cover change; Artificial Neural Network(ANN); Wavelet Transform; Texture Features; GIS; BPNN; LVQ; ; LUCCD