论文部分内容阅读
受大气环境等因素的影响,高光谱遥感矿物识别难以达到较高的精度.为解决该问题,根据光谱吸收特征参数在大气变化中能保持相对稳定的特点,提出一种基于光谱特征参数组合的高光谱矿物类型识别方法.文中计算了多种光谱特征参数,通过最佳指数因子(optimum index factor,OIF)优选特征参数组合,选定最佳特征参数组合,利用模式识别方法实现矿物识别.利用机载可见/红外成像光谱仪(airborne visible infrared imaging spectrometer,AVIRIS)高光谱数据,在美国内华达州Cuprite矿区进行了该方法的应用试验研究,并与前人矿物填图结果做了对比.结果表明:吸收波谷位置-吸收面积-吸收右肩位置(P-A-S2)光谱特征参数组合的矿物识别效果最优,整体精度达到74.68%.
Due to the influence of the atmospheric environment and other factors, it is difficult to achieve high accuracy in the identification of hyperspectral remote sensing minerals.In order to solve this problem, based on the characteristic that the spectral absorption parameters can be kept relatively stable in the atmospheric changes, a spectral characteristic parameter combination Hyperspectral mineral type identification method.A variety of spectral characteristic parameters are calculated, and the optimal combination of characteristic parameters is selected by optimal index factor (OIF), the best combination of characteristic parameters is selected, and the pattern recognition method is used to realize the mineral identification. The application of AVIRIS hyperspectral data to the Cuprite mine in Nevada, USA, has been carried out and compared with the previous mineral mapping results.The results show that: The combination of the absorption trough position-absorption area-absorption right shoulder position (PA-S2) has the best identification effect of the mineral, and the overall accuracy reaches 74.68%.