基于SPOT-5遥感影像的城市信息自动提取技术研究

Research on Automatic Extraction of Urban Information Based on SPOT- 5 Remote Sensing Images

城市信息的提取是城市动态监测和分析的基础,而城市动态监测对社会发展和人类生活具有重要意义。本文基于三峡地区的SPOT-5遥感影像,以城市绿地和建筑物为研究对象,用ENVI FX影像处理软件,对实验区的绿地和建筑物进行多尺度影像分割信息提取。结果表明,采用多尺度分割技术提取高分辨率影像中地物的提取精度更高,并有效地避免了"椒盐现象"。

Extraction of city information is the basis of dynamic monitoring and analysis of the city, while dynamic monitoring and analysis of the city has an important significance for social development and human life. In text, Based on SPOT - 5 remote sensing images of the Three Gorges region, For the study by urban green information and buildings information, with ENVI FX image processing software as a platform, extraction on green information and building information of experimental area by multi - scale image segmentation technology. In extraction process, first of all, building classification system of green information and building information based on Satellite imaging features of two objects; secondly, extracting information by set the scale parameter of multi - scale segmentation ; and finally, comparison on the extraction results of multi - scale segmentation between of traditional classification based on experimental area. The results show that the multi - scale image segmentation technology has higher precision results using a high - resolution to extract surface features. The most important is, It effectively avoid the ＂salt and pepper phenomenon＂.