一种复杂红外背景下的小目标检测识别算法研究  

Reserch on Recognition Algorithm for Detecting Small Targets under Complex Infrared Background

作　　者：白云塔[1] 臧寿洪[1] 杨彦杰[1] 叶宗民[1] 

机构地区：[1]91404部队93分队

出　　处：《红外》2008年第10期24-28,共5页Infrared

摘　　要：目标检测作为红外成像系统中前端的处理环节,是精确制导中一个重要的组成部分,也是其中的一个关键技术和难点问题。只有及时检测到场景中的目标,才能保证后继的目标跟踪、识别等一系列处理工作的顺利开展。为了尽早地发现目标,使得系统有足够的反应时间,就要求在很远的距离上能够检测到目标。因此,复杂红外场景中小目标的检测问题成了红外成像系统中一个亟待解决的关键问题,探索和研究新的小目标检测理论和算法以及如何将现有的检测理论用于小目标情况依然是十分重要的课题,具有深远的意义。As the front processing unit in an infrared imaging system, target detection is one of the important parts in precision-guidance and is also a critical technique or difficult problem. Only if the target in the scene is detected in time, a series of subsequent processing such as target tracking, target recognition and so on can be implemented smoothly. To find the target as soon as possible so as to let the system have enough time to react against it, the target must be detected at a very long distance. Therefore, the detection of the target in a complicated infrared scene becomes a very urgent problem to be solved. The discovery and study of new theory and algorithms for small target detection and how to use the current detection theory in small target detection is still a most important subject and is of great significance.

关 键 词：图像滤波 奇异点提取 单帧目标提取 图像杂波处理 

分 类 号：TP274.52[自动化与计算机技术—检测技术与自动化装置]