Research on the classification of terrain texture from DEMs based on BP neural network

TitleResearch on the classification of terrain texture from DEMs based on BP neural network
Publication TypeConference Paper
Year of Publication2013
AuthorsKai, Liu, Tang Guoan, and Jiang Sheng
Refereed DesignationRefereed
Conference NameGeomorphometry 2013
Date Published2013
Conference LocationNanjing, China
AbstractTerrain texture is an important natural texture. DEM based terrain texture attracts more and more attention in the research area for its purity in representing surface topography and tis derivability in terrain analysis. In this paper, eight sample areas from different landform types of Shaanxi Province in China are selected to make a classification analysis on the terrain texture by Gray level co-occurrence matrix (GLCM) model and BP neural network. First, GLCM was used to extract the feature parameters of the terrain texture from DEMs and its derivative data. Then, the quantitative analysis was conducted by using difference value between the variation coefficient among class and variation coefficient within class in order to find the optimal parameter combination. At last, the BP neural network was applied to classify the terrain texture. The highest recognition rate is 90% which shows a great potential in landform recognition and classification.
AttachmentSizeHitsLast download
Kai2013geomorphometry.pdf435.63 KB107418 hours 1 min ago
3.333335
Your rating: None Average: 3.3 (3 votes)