基于TM影像的城市绿地信息提取方法研究

Extraction method of urban vegetation information based on TM image

基于TM遥感影像,运用ERDAS,对某地城市绿地专题信息进行了提取。实验过程中首先对图像进行预处理,然后通过四种绿地信息提取方案进行比较分析,这四种方案分别为:原始波段合成法、主成份分析法、归一化植被指数(NDVI)法和实验波段组合法。将以上几种方案的图像进行反复比较,根据研究对象的实际情况,植被景观目视效果最好的是NDVI植被指数法。对以上四种方法的彩色合成图像进行监督分类,利用目视判读的方法对TM影像的分类结果进行精度检验,由此可以看出实验波段组合法的精度最高,该方法是一种有效的绿地提取的方法。

Based on remote sensing image, the special information of urban vegetation in one area was extracted using ERDAS. In the process of the experiment, image pretreatment was finished as the first step. Four methods for urban vegetation extraction were compared. They are original bands synthesis method, principal component analysis method, the normalized difference vegetation index （NDVI） method, experimental bands combination method. Comparing the images produced by the four projects, according to the actual situation of the study object, we find that NDVI vegetation index method has the best visual effect. Supervised classification was done with the four images synthesized in pseudo-color, and accurate assessment was finished with ERDAS. Test results show that experimental bands combination method has the highest accuracy in the four methods, and it is an effective method for the extraction of urban vegetation.