对卫星遥感云图进行自动分割是分析卫星云图资料的重要步骤。为了更加准确的对卫星遥感云图进行分割，提出了融合边缘信息CV模型的卫星遥感云图分割方法。对原卫星云图进行扩散，得到平滑图像，根据平滑图像计算边缘信息，将得到的边缘信息融入CV模型中，并加入距离规范项使得CV模型的水平集函数在演化过程中不需要重新初始化。实验结果表明，与传统CV模型、区域能量拟合水平集模型、偏置场修正水平集模型相比，所提方法分割出的云区域更加准确，分割速度更快。

Segmenting satellite remote sensing cloud images is an essential step of analyzing satellite cloud image data. In order to segment satellite remote sensing cloud images more accurately, a satellite remote sensing cloud image segmentation method based on Chan Vese (CV) model incorporating edge information is proposed. Satellite cloud image is diffused and a smooth image is obtained. The edge information is calculated based on the smooth image. The edge information is incorporated into the CV model, and a distance regularized term is added to avoid the reinitialization of the level set function during its evolution. Experimental results show that, compared with conventional CV model, region-scalable fitting energy level set model and bias field correction level set model, the proposed method can segment region of cloud more accurately and the speed is faster.