为了充分利用高光谱图像中包含的空间信息, 将一种改进的双边滤波应用到其目标检测中, 提出基于光谱角匹配的双边滤波稀疏表示高光谱目标检测算法。通过将光谱角匹配与双边滤波相结合, 用高光谱图像像元之间的相似性作为双边滤波器中值域距离的权值, 在抑制了图像各波段中噪声的同时突出了目标, 然后通过稀疏表示算法进行目标检测。实测的高光谱数据实验显示, 与传统稀疏表示方法和普通双边滤波稀疏表示方法比较, 所提方法在检测效果上有一定的提高。证明了充分利用高光谱图像的空间信息能进一步提高其目标检测的效果。

In order to make full use of the spatial information contained in the hyperspectral image,an improved bilateral filtering is applied to the target detection,and a bilateral filtering algorithm based on spectral angle matching for sparse representation of hyperspectral target detection is proposed.By combining the spectral angle matching with the bilateral filtering,the similarity between the pixels of hyperspectral image is used as the weight of bilateral filtering.The noise in the band is suppressed and the target is highlighted.Then the target detection is carried out by sparse representation algorithm.Experimental results show that:Compared with the traditional sparse representation method and the sparse representation algorithm with normal bilateral filtering,the proposed method has better detection performance.It is proved that making full use of the spatial information of hyperspectral images can further improve the target detection results.