论文部分内容阅读
以塔克拉玛干沙漠南缘策勒绿洲为例,探讨了基于主成分融合的沙漠化信息的提取方法。由于Landsat-7 ETM+的全色波段与多光谱波段有相同成像条件,影像获取时间一致,两种不同分辨率的数据可以不经配准而实现高精度融合。首先,对Landsat-7ETM+的全色图像与多光谱图像进行主成分融合处理,再利用BP神经网络模型,以相同的训练样本分别对融合前后的影像进行分类,在此基础上进行沙漠化信息的提取。结果表明:主成分变换融合图像的光谱信息保持性、信息量以及空间分解力都较高,且分类精度比Landsat-7ETM+多光谱图像有较大提高,是监测沙漠化土地变化的有效手段。
Taking Cele Oasis in the southern margin of Taklamakan Desert as an example, the extraction method of desertification information based on principal component fusion is discussed. Due to the same imaging conditions of the full-color and multi-spectral bands of the Landsat-7 ETM + and the same image acquisition time, the data of two different resolutions can be fused without registration. First of all, the principal component fusion of panchromatic and multispectral images of Landsat-7ETM + is processed, and then the BP neural network model is used to classify the images before and after the fusion with the same training samples respectively, and then the desertification information is extracted . The results show that the spectral information retentivity, information content and spatial decomposing power of fusion image are higher than that of Landsat-7ETM + multispectral image, which is an effective method to monitor the change of desertification land.