改进高帽变换的红外目标增强和提取算法  

Improved high-cap transform algorithm for infrared target enhancement and extraction

作　　者：刘莉 钱雪飞 刘珊 曹盟盟 LIU Li;QIAN Xue-fei;LIU Shan;CAO Meng-meng(Electronic and Control Engineering School,North China Institute of Aerospace Engineering,Langfang 065000,China;Mechanical Engineering School,Shenyang Jianzhu University,Shenyang 110000,China;China Petroleum Pipeline Engineering Co.,Ltd.,Langfang 065000,China;Mechanical and Electrical Engineering School,North China Institute of Aerospace Engineering,Langfang 065000,China)

机构地区：[1]北华航天工业学院电子与控制工程学院,河北廊坊065000 [2]沈阳建筑大学机械工程学院,辽宁沈阳110000 [3]中国石油管道局工程有限公司,河北廊坊065000 [4]北华航天工业学院机电工程学院,河北廊坊065000

出　　处：《激光与红外》2020年第7期882-888,共7页Laser & Infrared

基　　金：河北省教育厅青年基金项目(No.QN2020179);北华航天工业学院科研基金项目(No.KY-2020-10,KY-2020-18)资助。

摘　　要：红外图像增强及其目标提取是军事航空航天领域和国民经济发展的一项至关重要的技术。针对红外图像对比度低、特征信息不明确、杂波严重、信噪比低、视觉效果模糊的问题,对形态学中传统的高帽变换算法进行优化,提出了基于改进高帽变换的红外目标增强和提取算法。该算法通过引进判断值和加权系数,对高帽变换进行改进,对红外小目标进行增强,利用迭代算法对图像阈值进行处理,进而实现小目标的提取。实验结果表明,提出的算法可以很好地增强红外图像视觉效果,有效的提取红外小目标,方便后续的目标识别和目标跟踪等,应用前景广泛。Infrared image enhancement and target extraction is an important technology in military aerospace field and national economic development.Aiming at the problems of low contrast,unclear feature information,serious clutter,low signal-to-noise ratio and blurred visual effects,the traditional high-cap transformation algorithm in morphology was optimized.An improved high-cap transform algorithm for infrared target enhancement and extraction is proposed.By introducing judgment value and weighted coefficient,the algorithm improves the high cap transformation enhances the infrared small target,uses iterative algorithm to process the image threshold,and then realizes the extraction of the small target.The experimental results show that the proposed algorithm can enhance the visual effect of infrared images,effectively extract small infrared objects,and facilitate the subsequent target identification and target tracking processing,which has a wide application prospect.

关 键 词：红外图像 图像增强 目标提取 图像阈值 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]