基于混合高斯与边缘检测的目标检测算法研究  

Research on target detection algorithm based on GMM and edge detection

作　　者：陈钟荣[1] 夏利娜[1] 郭晓伟[1] 

机构地区：[1]南京信息工程大学大气物理学院,南京210044

出　　处：《中国科技论文》2016年第2期231-235,共5页China Sciencepaper

基　　金：国家自然科学基金资助项目(41075025)

摘　　要：提出了一种基于混合高斯与边缘检测的目标检测方法,首先将混合高斯模型(Gaussian Mixture Model)的参数进行改进,并结合形态学等运算提取初步运动目标;其次将双边滤波与Sobel锐化检测算子结合对图像处理得到另一个目标;然后将两目标相减,并对相减的结果进行中值滤波,以及形态学和标记去除连通域等运算;最后与三帧差分结果逻辑"或"运算,得到最终目标。实验结果表明,该算法能够很好地去除阴影,且不易受环境变化的影响。A new target detection method is proposed in this paper.First,an improved Gaussian Mixture Model(GMM)and morphological operation are used to extract a preliminary target motion.Then,the image is filtered by Bilateral filter and sharpened by Sobel operator,to obtain another goal.Next,by subtracting one target to another,and filtering by median filter,and performing by morphology and tag to remove connected domain operations and so on,the ultimate goal can be achieved by combining it with results of three frame difference.Experimental results show that the algorithm is well done to remove the shadow,and not easily influenced by background environment.

关 键 词：混合高斯 边缘检测 双边滤波 阴影去除 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]