关键词: 混合高斯模型, 脉冲耦合神经网络, 多模态免疫进化算法, 图像分割

Abstract: The accurate segmentation of infrared body is a difficult problem under complicated background，especially in the environment that the gray values are very similar between the infrared human movement target and background when their temperatures vary slightly.Therefore，the background subtraction method based on Gaussian mixture model is improved.The fine segmentation is implemented by the modified Pulse Coupled Neural Network（PCNN） in its binary stage，and meanwhile the PCNN segmentation parameters are determined by using the multi-modal immune evolution algorithm（MIEA）.The simulation results show that this algorithm is achieved fast automatic segmentation，and has gotten the ideal effect of image segmentation that its precision is high.

Key words: Gaussian Mixture Model（GMM）, Pulse Coupled Neural Network（PCNN）, Multi-modal Immune Evolution Algorithm（MIEA）, image segmentation