基于小波分解的多源图像融合在交通目标跟踪中的应用  

APPLYING WAVELET DECOMPOSITION-BASED MULTISOURCE IMAGE FUSION IN TRAFFIC TARGET TRACKING

作　　者：马宏锋[1,2] 党建武[2] 包理群[1] 

机构地区：[1]兰州交通大学电子与信息工程学院,甘肃兰州730070 [2]兰州工业高等专科学校电子信息工程系,甘肃兰州730050

出　　处：《计算机应用与软件》2010年第10期62-64,共3页Computer Applications and Software

基　　金：高等学校博士学科点专项科研基金项目(20060732002);甘肃省自然科学基金项目(096RJZA084);甘肃省教育厅研究生导师科研计划项目(0814-4)

摘　　要：针对交通监控中目标跟踪这个研究热点和难点,研究图像的小波分解算法,提出一种改进的基于小波分解的多源图像融合算法。对各分解层的小波系数,按照其不同频率分量的特点,采用不同的融合规则,弥补了采用单一融合规则的不足,最后将改进算法应用于交通目标跟踪。实验结果表明改进算法是可行的、有效的,能够实现目标跟踪和达到工程应用的目的。In view of the research focus and nodus with regard to target tracking in traffic monitoring,we studied the image wavelet decomposition algorithm and proposed an improved algorithm of multisource image fusion which is based on wavelet decomposition.It adopts different fusion rules in accordance with the characteristics of different frequency components of wavelet coefficients at different decomposition level,and makes up the deficiency of single fusion rale.The method has been applied to traffic target tracking at last,experimental results show that the improved algorithm is feasible and effective,and is able to achieve the goal of target tracking as well as engineering applications.

关 键 词：目标跟踪 小波分解 多源图像融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]