基于改进变分水平集的红外图像分割方法

提出一种基于水平集的红外图像偏微分分割方法，通过改进Chan-Vese模型中的能量函数获得偏微分方程，该能量函数将红外图像边缘与区域信息相结合，取得了全局极小值，该能量模型对水平集初始曲线的位置不敏感，并可定位图像边缘。基于该模型的变分水平集分割方法可分割出红外图像目标。实验结果表明，该方法效果良好，便于下一步的红外目标识别与跟踪。

Infrared Image Segmentation Based on Improved Variational Level Set

This paper proposes a novel level set-based Partial Differential Equation(PDE) for infrared image segmentation. The PDE is derived from an energy functional which is a modified version of the fitting term of the Chan-Vese model. The improved energy functional is designed to obtain more accurate infrared image edges and global minimum. The existence of a global minimum makes the algorithm invariant to the initialization of the level set function. Variation level set based on this energy model is suitable for the segmentation of infrared image targets. Experimental results verify the effectives and robustness of this segmentation method which facilitates the target recognition and track in the next step.