摘要
用TM图像对亚热带低山丘陵地区进行土壤遥感监测时,根据该地区的环境特点,采用线性光谱混合分解、缨帽变换、纹理提取等多种图像处理方法来突出土壤信息,消除噪声。研究结果表明,仅用TM遥感图像进行土壤分类,经过去噪处理的TM6可以使土壤分类精度提高5%以上;经过其它图像处理提取的一些图像特征对某些土壤类型表现出较强的区分能力,经线性光谱混合分解处理消除植被光谱的特征图像及其纹理对水稻土的识别精度较原图像普遍提高,缨帽变换对潴育型水稻土和测渗型水稻土有最好的分类精度,但在提高总分类精度上并没有优势,除了线性光谱混合分解图像处理方法外,其它的图像处理方法得到的特征图像加入原始图像信息能起到提高总分类精度的作用。
Soils in subtropical hilly lands were surveyed using TM image, and according to the environmen tal characteristics in this region, linear spectral mixture unmixing, K-T transformation, texture extracting were used to enhance soil information and eliminate noises. The results showed that the use of TM image in the accuracy of soil classification survey had an increase of more than 5 percent when the noise eliminated TM6 was added, and the characteristic images extracted by other several image processing methods discriminated some soil classes very well. The accuracy of paddy soils classfied using the images processed by linear spectral mixture unmixing and their texture images were generally higher than that of using raw ima ges, and water logged and percogenic paddy soils had the highest classification accuracy using K-T trans formation. However, the characteristic ira, ages extracted by these image processing methods were not better than the raw images on the increase of the total accuracy of soil classification, and all the characteristic images except that of processed by linear spectral mixture unmixing needed to add the raw images for im proving the total accuracy.
出处
《长江流域资源与环境》
CAS
CSSCI
CSCD
北大核心
2006年第1期41-47,共7页
Resources and Environment in the Yangtze Basin
基金
国家973项目(2003CB415205)
西南师范大学资源环境自然地理学博士点开放基金资助
关键词
遥感
土壤监测
图像处理
监督分类
remote sensing
soil surveying
image processing
supervised classification
