基于空间直方图的海杂波背景下红外目标跟踪  

Infrared target tracking in sea clutter background based on spatiograms

作　　者：蔡念[1] 张楠[1] 张海员[1] 

机构地区：[1]广东工业大学信息工程学院,广东广州510006

出　　处：《激光与红外》2010年第8期910-916,共7页Laser & Infrared

基　　金：国防973项目(No.51323020203-2);广东省自然科学基金(No.07301038);广东省自然科学基金(No.9451009001002667)资助

摘　　要：空间直方图融合了目标的灰度分布信息和灰度的空间分布信息,比传统的灰度直方图更具有目标鉴别能力。为实现海杂波背景下稳健跟踪红外目标,本文在基于粒子滤波算法的红外目标跟踪系统框架中,将加权样本集表示红外目标的状态后验概率分布;采用简单的随机漂移模型表示系统状态模型;利用目标区域的空间直方图描述红外目标,其中通过核概率密度估计建立红外目标的灰度分布,然后统计灰度分布的空间信息建立空间直方图;通过空间直方图的相似度定义来建立系统观测概率模型,最终提出一种在海杂波背景下的基于空间直方图的粒子滤波红外目标跟踪算法。实验结果表明,相比传统的基于灰度直方图的粒子滤波算法,本文提出的算法具有明显的优势,对于部分遮挡以及全遮挡等复杂的海杂波背景下红外目标跟踪具有更好的鲁棒性。Spatiograms outperform the traditional gray histogram,which contain intensity information and spatial layout of the intensity distribution for the target.In particle filters framework,the posterior distribution of the infrared target is approximated by a set of weighted samples and a normal random drift model is utilized to describe the state model.Infrared targets are represented by the spatiograms,which is defined by the spatial information of the intensity distribution estimated by kernel-based density.A similarity function of spatiograms is used as the probability model for observation.We propose an infrared target tracking algorithm using particle filters based on spatiograms to robustly track the infrared target in sea clutter background.Experimental results indicate that the proposed algorithm outperforms the traditional particle filters based on the gray histogram,and has better robustness under local occlusion and global occlusion of infrared target tracking in sea clutter background.

关 键 词：空间直方图 海杂波 粒子滤波 红外目标跟踪 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]