光照突变下融合多类特征的场景分割方法(英文)  

Foreground segmentation under sudden illumination changes by feature fusion

作　　者：龚卫国[1] 刘润瑶 张睿[1] 

机构地区：[1]重庆大学光电技术及系统教育部重点实验室,重庆400044

出　　处：《红外与激光工程》2014年第12期4164-4169,共6页Infrared and Laser Engineering

基　　金：重庆市科技攻关计划(CSTC2012GG-YYJSB40001);重庆市集成示范计划(CSTC2013JCSF40009);中央高校基本科研业务费科研专项"研究生科技创新基金"(CDJXS11122216);国家自然科学基金(61105093)

摘　　要：为解决场景模型在快速光照变化下失效的问题,提出了一种新的前景目标分割方法。该方法共包括三个步骤。首先,利用全局光照函数建立高斯混合模型;其次,提取当前帧中的纹理、ZNCC及轮廓特征;最后,将提取到的特征分两阶段与高斯混合模型进行融合(第一阶段:融合纹理及ZNCC特征;第二阶段:融合轮廓特征),得到最终的场景分割结果。实验结果表明:该算法具有较好的鲁棒性,并且相较于基于全局光照建模的方法具有更高的精度值及召回值。To address the challenging problem of robust background subtraction under sudden illumination changes,a novel foreground segmentation method based on feature fusion was proposed.The method consisted of three stages.First,a scene model through integrating the global illumination function into the framework of Gaussian mixture models was built.Second,three kinds of illumination invariant features,i.e.zero mean normalized cross-correlation（ZNCC）,textures,and contours,were extracted from the current frame image.Third,the illumination invariant features were combined for foreground segmentation in two steps.Specifically,the ZNCC and textures were combined in the first step,and the contour was integrated in the second step.The experimental results show that the proposed method can effectively improve the accuracy and robustness of foreground segmentation.

关 键 词：特征融合 高斯混合模型 全局光照函数 图像主结构提取 光照突变 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]