摘要
为有效控制进而避免交通事故的发生,提出一种基于图像像素点检测前方车辆障碍物距离的方法。利用机器视觉检测到前方车辆可能存在的感兴趣区域,通过边缘特征确定前方车辆的位置,利用角点检测获取车辆在图像中的像素点位置,在对摄像机进行预先标定的基础上,通过透视投影的几何关系,计算出前方车辆距离的方法。
This paper proposed a method to measure the preceding vehicle distance based on the position of pixel in the picture to effectively control and prevent traffic accidents. Computer vision is used to detect areas in which a vehicle may exist, namely the area of interest. Then the position of the preceding vehicle is determined with edges feature. Furthermore the position of pixel in the picture is got through the interest points. A preceding vehicle distance evaluating method using the intrinsic parameters of the camera and projective geometry is discussed. The results indicate that this method is useful.
出处
《农业装备与车辆工程》
2016年第7期15-20,共6页
Agricultural Equipment & Vehicle Engineering
关键词
像素点
机器视觉
角点检测
摄像机标定
前车距离
position of pixel
computer vision
interest points
intrinsic parameters of the camera
preceding vehicle distance
