论文部分内容阅读
针对高光谱遥感地物识别中存在的问题,从光谱的波形特征、运算速度、空间细节特征的光谱区分性等方面进行了算法的改进,在此基础上提出了分形信号的算法。利用CASI高光谱数据针对算法本身的性能、效率等进行了测试,对工作区的高光谱遥感影像岩性特征进行提取。针对高光谱遥感数据分形信号的初始值、迭代步长等特征进行了讨论。分形信号算法在一定程度上更细化了相似特征高光谱的可区分性,该算法应用在CASI数据的岩性特征提取,实现了基岩裸露区域地表岩性特征精确提取。
Aiming at the existing problems in the recognition of the topographic features of hyperspectral remote sensing, this paper improves the algorithm based on the spectral characteristics of waveforms, the speed of computation and the spectral distinguishing characteristics of spatial detail features. Based on this, the fractal signal algorithm is proposed. The CASI hyperspectral data was used to test the performance and efficiency of the algorithm, and the lithological characteristics of hyperspectral remote sensing image in the working area were extracted. The fractal signals’ initial values, iteration steps and other features are discussed for hyperspectral remote sensing data. The fractal signal algorithm can refine the distinguishability of hyperspectral of similar features to a certain degree. The algorithm is applied to the lithological feature extraction of CASI data, which can accurately extract the lithological characteristics of the surface of bare rock area.