摘要： 针对智能车辆视觉导航系统的路面标线实时感知问题，提出基于方向边缘匹配实现人行横道和停止线的检测算法。利用逆透视映射表快速建立车辆前方感兴趣区域俯视图，提取图像垂直边缘和水平边缘，通过亮度上升与下降相邻边缘匹配检测定位人行横道与停止线。实验结果表明，该检测算法满足实时性要求，具有强鲁棒性，能应用于复杂城市道路环境。
关键词:
方向边缘,
逆透视映射,
感兴趣区域,
线性拟合,
匹配,
随机抽样一致性
Abstract: In order to solve the real-time road marking recognition problem in the intelligent vehicle vision navigation system, a novel pedestrian crossing and stop line detection algorithm based on oriented-edge match is proposed. It builds top-view image through Inverse Perspective Mapping(IPM) transformation by a mapping table to accelerate IPM process. It abstracts vertical oriented-edge and horizontal oriented-edge. The pedestrian crossing and stop line can be detected by matching adjacent up and down edges to bands. Experimental results illustrate that the algorithm is effective for real-time analysis and robust under difficult urban road circumstances.
Key words:
oriented-edge,
Inverse Perspective Mapping(IPM),
Region of Interest(ROI),
linear fitting,
match,
random sample consensus
中图分类号:
谢锦, 蔡自兴, 李昭, 尤作. 基于方向边缘匹配的人行横道与停止线检测[J]. 计算机工程, 2013, 39(6): 261-265,282.
XIE Jin, CA Zi-Xin, LI Zhao, YOU Zuo. Pedestrian Crossing and Stop Line Detection Based on Oriented-edge Match[J]. Computer Engineering, 2013, 39(6): 261-265,282.