基于序列图像分组决策算法  

Grouped Decision Algorithm Based on Sequence Image

作　　者：蔡君[1] 张尚悦[1] 王书晓[1] 刘晓光[1] 

机构地区：[1]海军大连舰艇学院,辽宁大连116018

出　　处：《光电技术应用》2013年第2期55-58,75,共5页Electro-Optic Technology Application

基　　金：海军大连舰艇学院科研发展基金资助项目(201212)

摘　　要：针对红外运动弱小目标检测中单帧图像检测率低的问题,在分析了红外图像中运动弱小目标特性的基础上,提出了一种基于序列图像分组决策检测红外弱小目标的方法。该方法利用图像差分法进行目标信息的提取,对图像进行扩边,选取连通域质心来构建滑动邻域块,最后充分利用目标航迹的连续性和噪声的随机分布特性进行目标位置的决策。实验证明,序列图像检测方法对红外弱小目标的检测率要高于单帧图像检测率。According to the problem of low detection rate for single frame image during the small moving in- frared target detection process, on the basis of analyzing the characteristics of infrared images of small moving tar- gets, a method for detecting small infrared targets based on sequence image grouped decision is put forward. Image difference method is used to extract target information. Edges of images are expanded and centroid of connected do- mains is chosen to construct sliding neighborhood blocks. Decisions of target positions are made by making full use of continuity of target tracks and random distribution characteristics of noise finally. The experiments prove that the detection method of sequence image has a higher detection rate than that of single frame image detection method.

关 键 词：序列图像 分组决策 目标检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]