首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于均值反差滤波的红外小目标检测算法
引用本文:陈振学,汪国有,马于涛,张磊.基于均值反差滤波的红外小目标检测算法[J].武汉大学学报(信息科学版),2007,32(6):560-563.
作者姓名:陈振学  汪国有  马于涛  张磊
作者单位:1. 华中科技大学图像识别与人工智能研究所,武汉市珞喻路1037号,430074
2. 武汉大学软件工程国家重点实验室,武汉市珞珈山,430072
摘    要:在已有背景预测算法的基础上,提出了一种基于均值反差法作为不相似度量对图像进行滤波,在增强小目标的同时抑制了复杂背景,并通过自适应的背景预测算法,实现了对小目标的快速检测。实验结果表明,该算法对小目标适应性强,能大幅度地提高目标/背景的信噪比,从而快速而准确地检测出小目标的位置。

关 键 词:小目标  背景预测  自适应  均值反差  ROC曲线
文章编号:1671-8860(2007)06-0560-04
修稿时间:2007-03-10

A Algorithm of Infrared Small Targets Detection Based on Average Absolute Difference
CHEN Zhenxue,WANG Guoyou,MA Yutao,ZHANG Lei.A Algorithm of Infrared Small Targets Detection Based on Average Absolute Difference[J].Geomatics and Information Science of Wuhan University,2007,32(6):560-563.
Authors:CHEN Zhenxue  WANG Guoyou  MA Yutao  ZHANG Lei
Abstract:Based on background forecast algorithms existed already, an average absolute difference filter algorithm is presented as the dissimilarity measurement between object and background region. The system utilizes this filter to enhance small target and suppress the clutter, and then it forecasts self-adaptively background. Finally, the system segments and obtains the small targets by the setting threshold. The experiment results indicate that the algorithm has excellent adaptability to small object shape and greatly improved SNR performance.
Keywords:small targets  background forecast  self-adaptive  average absolute difference  ROC curve
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号