基于红外双波段图像融合的点目标识别  

Point Target Detection Based on Image Fusion of Two Infrared Bands

作　　者：马治国[1] 王江安[1] 雷选华[1] 宗思光[1] 

机构地区：[1]海军工程大学兵器工程系,湖北武汉430033

出　　处：《激光与红外》2003年第3期228-230,共3页Laser & Infrared

摘　　要：为解决红外警戒系统中点目标的识别问题,提出了一种新的点目标识别方法。该方法首先分别对单波段红外图像进行背景预测与抑制,然后对取自适应阈值后的双波段图像根据目标的运动特征进行融合,最后通过图像序列分析给出最终的目标识别结果。仿真实验表明,该方法对背景有很好的抑制效果,可大大减少目标识别中候选目标点的数目,因而有利于点目标的识别。A new method of point target detection is presented in order to solve the problem of point target detection in the infrared surveillance system. The method consists of three steps. First, the background in the image of single band is predicted and restrained; Second, the images of two infrared bands are fused after they are done the adaptive threshold value; Finally, the result of target detection is given by the analysis of the image sequence. The experimental results show that the performance of background restraining is very good and the number of the candidate targets decreases greatly, so the method can improve the performance of the point target detection.

关 键 词：红外警戒系统 点目标识别 图像融合 红外图像 图像序列 图像处理 

分 类 号：TN911.73[电子电信—通信与信息系统] TN219[电子电信—信息与通信工程]