基于人工蜂群算法的运动目标检测方法  

Moving target detection method based on artificial bee colony algorithm

作　　者：陈雷[1] 张立毅[1,2] 郭艳菊[3] 刘婷[1,2] 李锵[2] 

机构地区：[1]天津商业大学信息工程学院,天津300134 [2]天津大学电子信息工程学院,天津300072 [3]河北工业大学信息工程学院,天津300130

出　　处：《计算机工程与应用》2012年第21期178-181,221,共5页Computer Engineering and Applications

基　　金：国家自然科学基金(No.60802049)

摘　　要：提出了一种基于人工蜂群算法的运动目标检测方法。利用将运动目标检测问题转化为独立成分分析问题的原理,选用峭度作为求解信号独立成分的判据,使用人工蜂群算法对基于峭度的目标函数进行优化求解,通过去相关方法从序列图像中剔除分离出的信号成分,进而实现对运动目标轨迹的成功提取。针对模拟运动物体和实际运动物体图像的仿真实验表明,该方法可以很好地检测出序列图像中运动物体清晰的运动轨迹。A moving target detection method based on artificial bee colony algorithm is proposed.The principle that moving target detection problem is transformed into the problem of independent component analysis is utilized.Kurtosis is selected as the criterion for independent component analysis and artificial bee colony algorithm is used for optimizing the objective function based on kurtosis.The separated signal component is wiped off from sequence images using decorrelation method and the moving target trajectory can be extracted successfully.Computer experiments aim at simulation moving target and real moving target shows that the method proposed can achieve good results for finding out the trajectory of the moving target.

关 键 词：人工蜂群优化 运动目标检测 独立成分分析 峭度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]