复杂背景下圆形红外目标跟踪系统  

Tracking framework for found infrared object in clutter

作　　者：王芳林[1] 刘尔琦[2] 刘志[3] 杨杰[1] 刘瑞明[1] 程建[4] 

机构地区：[1]上海交通大学图像处理与模式识别研究所, 上海200240 [2]中国航天科工集团公司二院, 北京100854 [3]上海大学通信与信息工程学院 ,上海200072 [4]中国科学院成都计算机应用研究所 ,四川成都610041

出　　处：《红外与激光工程》2008年第1期139-142,共4页Infrared and Laser Engineering

基　　金：国家863计划资助项目(2007AA01Z164);国家自然科学基金资助项目(60675023);国家自然科学基金资助项目(60602012)

摘　　要：提出了一种复杂背景下红外图像序列中圆形目标提取、判别以及跟踪的系统框架。在目标提取阶段,采用支持向量回归的方法选择种子点,用自适应选择阈值区域的生长方法进行分割提取目标。对于目标判别,采用最多共圆像素点数除以总像素点数作为圆形程度的度量进行圆形判别,并提出改进的标准Hough变换来找到共圆点。跟踪算法中,应用了粒子滤波的跟踪方法,并针对红外目标的特点,建立实现粒子滤波算法的细节。实验证明了整个框架体系的有效性和稳健性。One whole framework,consists of object extraction,justification and tracking in infrared cluttered image sequence,is proposed.To extract objects,support vector regression is exploited to find seeds,and an adaptive threshold function is established.Then,to justify the roundness,the criterion is set as the value of number of the largest amount pixels localized in the same circle divided by the total number of pixels,which is implemented through an improved Hough transform presented in this paper.The particle filter method is exploited to track objects,the details are implemented according to the characteristics of infrared images.At last,the experiments result shows the effectiveness and robustness of the proposed framework.

关 键 词：支持向量回归 圆度 改进HOUGH变换 粒子滤波 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]