高光谱影像感兴趣区域提取的活动轮廓模型研究

Study on active contour model for extracting regions of interest from hyperspectral image

提出一种基于活动轮廓模型的高光谱影像感兴趣区域(ROI)提取方法,首先根据地物像元的标准反射率建立标准光谱反射率向量;然后,通过计算其与待处理像元的光谱向量的相关系数,得到像元相关系数偏差矩阵;最后,构造一种基于该偏差矩阵的C-V活动轮廓模型,并利用有限差分法对该模型求解,来提取感兴趣区域的像元.该方法可实现对高光谱区域宏观大类的快速提取,为高光谱影像压缩等进一步的信息处理奠定了基础.仿真实验验证了所提出方法的有效性.

In this paper,a method for extracting Region Of Interest（ROI）from hyperspectral image based on active contour model is proposed.Firstly,a standard mixing vector of spectral reflectivity of object of interest is established according to spectral reflectance vector of pure object pixel.Then,the pixel correlation coefficient deviation matrix is obtained by calculating the correlation coefficient between the spectral reflectivity standard mixing vector of the object of interest and the spectral vector of each pixel in the hyperspectral image to be processed.Finally,a C-V active contour model based on the deviation matrix is constructed,and the finite difference method is used to solve the model to extract the pixels of the region of interest.This method can quickly extract the macroscopically large class of hyperspectral region of interest.It lays a foundation for further information processing such as hyperspectral image compression.The effectiveness of the proposed method is verified by the simulation experiment.