基于三帧间差分的障碍物检测算法  

Obstacle Detection Algorithm Based on Three Inter-Frame Difference Method

作　　者：郭文俊[1] 乔世东[1] 

机构地区：[1]山西大同大学数学与计算机科学学院,山西大同037009

出　　处：《山西大同大学学报（自然科学版）》2015年第6期11-13,51,共4页Journal of Shanxi Datong University(Natural Science Edition)

摘　　要：机动车私人拥有量的不断上升,导致了交通事故在逐年的增加。故此,怎样最大程度的减少交通事故成了我们关注的焦点。本文以基于机器视觉的道路识别技术与障碍物检测技术为研究对象,提出了基于三帧间的差分方法,该方法利用相邻三帧图像两两差分,再将两个差分结果相"与"并进行二值化,最终确定运动目标在图像中的位置。The continuously rising in privately owned motor vehicle leads to the increase in traffic accidents. Therefore, how to reduce the traffic accidents and the losses caused by the accidents have became our focus. The thesis is based on road recognition technology and obstacle detection technology, it puts forward a new algorithm called three inter-frame difference method. This method uses neighboring three frames to make different inter-frame difference, then uses the two different inter-frame results to conduct an operation＂＂, and then runs the binary operation. Finally, the targets are located in the image.

关 键 词：计算机视觉 障碍物检测 帧间差分 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]