基于MACA算法的运动目标自适应跟踪  

The Moving Target Adaptive Tracking Based on MACA Algorithm

作　　者：曲巨宝[1] 林宏基[2] 

机构地区：[1]武夷学院数学与计算机系,武夷山354300 [2]福州大学数学与计算机科学学院,福州350002

出　　处：《湖南工程学院学报（自然科学版）》2010年第4期35-39,共5页Journal of Hunan Institute of Engineering(Natural Science Edition)

基　　金：福建省自然科学基金资助项目(2006J0414)

摘　　要：通过对传统Camshift算法的研究,提出了一种多模式自适应CamShift算法(MACA).将CamShift算法对H分量敏感的特性推广到S、V分量,构造了凸函数组合模型,利用多目标规划最优求解法获取自适应颜色识别最佳组合解,配合倾角识别和基于ⅡR滤波的目标运动状态信息预测跟踪技术,取得了复杂场景下多色度目标发生旋转、遮挡和速率变化时都能精确跟踪的效果;最后用MACA算法设计了一套自适应实时跟踪系统.经大量实验证明,本算法鲁棒性强、实时性好,系统自动化程度高.Through the study on the traditional Camshift algorithm,a multi-mode and auto-adapted CamShift algorithm（MACA）is proposed.By spreading the characteristics of the Camshift algorithm from being sensitive in the H component to being sensitive in S,V components,the convex function combination model is constracted.It uses the multi-objective programming optimal solution method to get the auto-adapted color recognition optimal fit value.It coordinates the inclination angle recognition and bases on the ⅡR filter target travel status messages tracking technology to obtain the effect that multi-chromaticity goal can be accurately tracked during the revolving,mask and the speed changing under the complex circumstances.Finally,it uses MACA algorithm to design a set of auto-adapted real-time tracking system.After the massive experiments,it proves that this algorithm robustness is strong,timeliness is good and the system automaticity is high.

关 键 词：MACA CAMSHIFT 多模式 自适应 跟踪 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]