基于图割和模糊连接度的交互式舰船红外图像分割方法  

Interactive Ship Infrared Image Segmentation Method Based on Graph Cut and Fuzzy Connectedness

作　　者：刘松涛[1,2] 王慧丽 殷福亮[1] 

机构地区：[1]大连理工大学电子信息与电气工程学部,大连116024 [2]海军大连舰艇学院信息与通信工程系,大连116018 [3]水下测控技术国家级重点实验室,大连116013

出　　处：《自动化学报》2012年第11期1735-1750,共16页Acta Automatica Sinica

基　　金：中国博士后科学基金(20100471451);水下测控技术国家级重点实验室基金(9140C2603051003)资助~~

摘　　要：针对舰船红外图像分割中的低对比度、边缘模糊和目标灰度不均匀问题,提出了基于图割和模糊连接度的交互式图像分割方法.交互方式为矩形笔刷,选择目标和背景种子点.分割方法为基于图割的图像分割方法,引入模糊连接度来计算图割的似然能,给出了模糊连接度权重的自动确定方法,提出了基于直方图分解的高斯混合模型(Gaussian mixture model,GMM)成分个数和参数估计方法.仿真结果表明,新方法可实现各种复杂环境下舰船红外图像目标的有效分割.In order to solve the problem of low contrast, fuzzy edges, and inhomogeneous target gray level in the ship infrared image segmentation, an interactive segmentation method based on graph cut and fuzzy connectedness is proposed. The interaction process uses a rectangular pen brush for selecting the seed points of target and background. The segmentation method is based on graph cut method, in which fuzzy connectedness is introduced to compute the likelihood energy of graph cut, and the automatic computation of its weights is also given, furthermore, a histogram decomposition method is proposed for estimating the number of components of a mixture and the parameters of that model. The simulation results show that the proposed method can segment ship infrared image target effectively under various complicated environments.

关 键 词：交互式图像分割 图割 模糊连接度 高斯混合模型 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]