基于SMC的红外序列图像目标检测算法  

An Efficient Target Detection Algorithm on the Basis of SMC

作　　者：李赣华[1] 董黎[2] 蔡宣平[1] 周东翔[1] 刘云辉[1] 

机构地区：[1]国防科技大学电子科学与工程学院,湖南长沙410073 [2]西安卫星测控中心,陕西西安710043

出　　处：《国防科技大学学报》2007年第2期65-69,共5页Journal of National University of Defense Technology

基　　金：国家自然科学基金资助项目(6033401060475029)

摘　　要：提出一种海天背景下红外序列图像自动目标检测算法。该算法针对输入图像严重的非高斯分布噪声干扰和目标在序列图像中的非线性运动特性,基于SMC(Sequence Monte Carlo)方法通过目标的特征统计值影响蒙特卡罗采样的粒子权值,再利用该权值控制粒子状态变化,最终在目标特征图像中检测和跟踪目标,使用差分图像作为特征图像。试验结果证明,该算法可准确有效地检测目标,适合快速处理的实时性。An efficient target detection algorithm for infi-ared sequence image with sea-sky background is presented. For the big none-Gaussian noises and the none-linear movement of the target, the algorithm is established mainly on the basis of the Sequential Monte Carlo （SMC） method. The algorithm uses the statistic values of the target＇ s feature image to change the weight of the particles which are produced by Monte Carlo sampling, and the target is detected and tracked based on the control of these weights. The difference image is used as the feature image. The experimental results demonstrate the effectiveness and real-time efficient of the algorithm.

关 键 词：序列红外图像 SMC 目标检测 降噪处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]