作　　者： ; ; (沈文超）;

机构地区： 华南理工大学

出　　处： 《电子设计工程》 2013年第18期149-152,共4页

摘　　要： 针对复杂行车环境下的智能车辆行车安全问题,提出了一种基于特征的多目标前方车辆检测算法。算法首先利用车辆底部阴影特征、车辆轮廓特征的先验知识,探测前方感兴趣区域,然后利用车辆边界特征、对称性特征对感兴趣区域进行判别。该算法针对复杂路况下的车辆分布特征进行了适应性设计,能够快速、准确的检测到具有潜在安全威胁的前方行驶车辆。 Focused on the intelligent vehicle safety issues under complex traffic environment,this paper presents a feature- based algorithm to detect the front vehicles. Firstly, use the characteristics of shape and bottom shadow as priori knowledge to get the regions of interest, then discriminate these areas by edge features and symmetry to find the front vehicles in moving. We adopt adaptable design for the characteristics of front vehicles under complex traffic conditions, make the algorithm can quickly and accurately detect moving vehicles nearby within sight of the camera.

关 键 词： 智能车辆 车辆检测 多特征融合 复杂路况

领　　域： [自动化与计算机技术] [自动化与计算机技术]