高光谱遥感影像不但具有高分辨率的空间信息还包含连续的光谱信息, 因此在目标探测领域具有独特的应用优势。 传统的高光谱遥感影像目标探测侧重于光谱信息的应用, 形成了确定性算法和统计学算法。 确定性算法通过计算目标光谱与待检测光谱之间的距离来查找目标, 不能检测亚像素目标, 而且容易受到噪声的影响; 统计学目标检测计算背景统计特性, 通过探测异常点来检测目标, 可以检测亚像素目标和小目标, 但容易受到目标尺寸的影响, 不能很好的检测大目标。 随着高光谱遥感影像的空间分辨率的增加, 探测目标已有亚像素目标逐步转换为单像素及多像素目标, 此时, 在高光谱图像中, 相同类别的地物在空间分布上呈现聚类特性, 因此, 在利用高光谱遥感影像进行目标探测时, 需要将其空间信息融入算法中。 将空间特征引入传统目标探测算法。 提出了一种新的空谱结合的高光谱目标探测算法, 将传统的基于统计的目标探测算子与空域邻域聚类算法相结合, 首先利用目标探测算子将影像划分为潜在目标区域与背景区域; 通过计算潜在目标区域的质心, 以质心为中心进行邻域聚类, 剔除潜在目标区域中的背景区域, 通过迭代计算获取最终目标探测结果。 传统的基于统计的目标探测算子, 将整个探测区域定义为背景区域, 实现对背景区域的统计特征提取, 而该方法将背景区域与潜在目标区域分离, 剔除了目标区域对背景区域的统计干扰。 将本算子与传统的约束能量最小化算子和自适应余弦探测算子进行分析比较可知, 该算子的大目标探测性能优于传统的统计算子。

With high-resolution spatial information and continuous spectrum information, hyperspectral remote sensing image -has a unique advantage in the field of target detection. Traditional hyperspectral remote sensing image target detection methods emphasis on using spectral information to determine deterministic algorithm and statistical algorithms. Deterministic algorithms find the target by calculating the distance between the target spectrum and detected spectrum however, they are unable to detect sub-pixel target and are easily affected by noise. Statistical methods which calculate background statistical characteristics to detect abnormal point as target. It can detect subpixel target targets and small targets better thanbig size target,. With the spatial resolution increasing, subpixel target detection target has gradually grown to a single pixel and multi-pixel target. At this point, hyperspectral image usually has large homogeneous regions where the neighboring pixels wihin the regions consist of the same type of materials and have a similar spectral characteristics, therefore, the spatial information should be needed to incorporate into the algorithm for targe detection. This paper proposes an algorithm for hyperspectral target detection combined spectrum characteristics and spatial characteristics. The algorithm is based on traditional target detection operator and combined neighborhood clustering statistics. Firstly, the algorithm uses target detection operator to divided hyperspectral image into a potential target region and background region. Then, it calculates the centroid of the potential target area. Finally, as the centroid for neighborhood clustering center to clust data in order to exclud background from potential target area, through iterative calculation to obtain the final results of the target detection. The traditional statistics algorithms defines the total image as background area in order to extract background statistics features, and the algorithm propsed devided the total image into background part and potential target part, which cut off the target interference for background statistics feature extraction. Compared with CEM operators and ACE operators, the algorithm proposed outperforms than traditional operators in big target detection .