基于多相水平集的多亮温太赫兹图像分割方法  

Multi brightness temperature terahertz image segmentation method based on multiphase level set

作　　者：陈艺琳 李超 CHEN Yilin;LI Chao(Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100094,China;Key Laboratory of Electromagnetic Radiation and Sensing Technology,Chinese Academy of Sciences,Beijing 100190,China;School of Electronic,Electrical and Communication Engineering,University of Chinese Academy of Sciences,Beijing 100049,China)

机构地区：[1]中国科学院空天信息创新研究院,北京100094 [2]中国科学院电磁辐射与探测技术重点实验室,北京100190 [3]中国科学院大学电子电气与通信工程学院,北京100049

出　　处：《电波科学学报》2025年第1期184-190,共7页Chinese Journal of Radio Science

基　　金：国家自然科学基金(61988102,61731020)。

摘　　要：为了能分割被动式太赫兹图像中的多亮温目标,满足太赫兹安检系统对不同亮温目标进行提取的需求,提出了一种基于多相水平集的被动式太赫兹图像分割方法。传统的单个水平集函数的方法仅能将图像划分为两个区域,当图像中存在多种亮温的目标物体时,不能将其完全提取出来。而该方法采用了多个水平集函数进行演化,能将图像分割成多个区域,满足分割多亮温物体的需要。使用多相水平集方法对多种目标物体进行处理,实验结果表明,该方法能够将被动式太赫兹图像中人体衣物下隐藏的多种亮温目标物体提取出来,比单个水平集的方法提高了准确性。In order to segment multiple brightness temperature targets in passive terahertz images and meet the requirements of terahertz inspection security systems for extracting different brightness temperature targets,a passive terahertz image segmentation method based on multiphase level sets is proposed.The traditional method of using a single level set function can only divide the image into two regions.When there are multiple brightness temperature target objects in the image,they can not be completely extracted.The proposed method uses multiple level set functions for evolution,which can segment the image into multiple regions and meet the needs of segmenting multiple bright and warm objects.Using the multiphase level set method to process multiple target objects,experimental results show that this method can extract multiple bright temperature target objects hidden under human clothing in passive terahertz images.Compared with the single level set method,it improves the accuracy of the extaction.

关 键 词：水平集 太赫兹图像 太赫兹安检 图像分割 图像处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]