一种视频序列图像中运动目标的分割算法  

A Segmentation Method for Moving Objects in an Image Sequence

作　　者：王成儒[1] 刘豫[1] 

机构地区：[1]燕山大学信息科学与工程学院,秦皇岛066004

出　　处：《微处理机》2008年第1期119-120,123,共3页Microprocessors

摘　　要：提出了一种新的用于检测视频序列图像中运动目标的算法。该算法通过对差帧图像进行模板检测及形态学滤波,并结合Canny算子边缘检测获得运动目标的分割掩模,提取出运动目标。实验结果表明,该方法能够有效分割运动物体,具有较强的鲁棒性。This paper represents a new method for separating moving objects in an image sequence. It uses the detection method of moulding board and morphological processing. , combining with the Canny edge detection, to get the mask for the segmentation of moving objects. The experimental results demonstrate that this method can effectively separate the moving objects from the background and has strong robustness.

关 键 词：目标分割 CANNY边缘检测 模板检测 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]