基于粗精交互融合和迭代图割的舰船可见光图像分割方法  

Ship visible image segmentation method based on combining coarse and precise interaction and iterative graph cut

作　　者：刘松涛[1,2] 陆斌[3] 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,辽宁大连116024 [2]海军大连舰艇学院信息与通信工程系,辽宁大连116018 [3]海军航空工程学院控制工程系,山东烟台264001 [4]水下测控技术国家级重点实验室,辽宁大连116013

出　　处：《光电子．激光》2012年第8期1609-1615,共7页Journal of Optoelectronics·Laser

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)资助项目

摘　　要：在深入分析典型图割算法的基础上,提出了一种基于粗精交互融合和迭代图割的舰船可见光图像分割方法,主要包括矩形包围盒式的粗交互、基于高斯混合模型的迭代图割、多边形编辑式的精交互和窄带区域内的图割优化。仿真结果表明,本文方法基本达到了预期目标,交互少、分割效果好,可满足后续特征提取和目标识别的需求。Image segmentation is one of the difficult problems in the field of computer vision. Under the conditions of automatic segmentation being difficult,it may be practical to use interactive image segmentation method. Based on the deep analysis of classic graph cut method, the segmentation method for ship visible image based on combining coarse and precise interaction and iterative graph cut is proposed, which mainly includes four steps： coarse interaction by rectangle bounding box, iterative graph cut based on Gaussian mixture model, precise interaction by polygon border editing, and graph cut refinement in the strip zone. The simulation results show that the proposed method has arrived at the expectation, i. e. , small interaction and good segmentation effects, and it is able to meet the needs of feature extraction and target recoanition.

关 键 词：交互式图像分割 图割 粗精交互融合 高斯混合模型 

分 类 号：TN391.4[电子电信—物理电子学]