单目摄像头的车辆前方障碍物检测研究

Research on Obstacle Detection in Front of Intelligent Vehicle Based on Monocular Camera

本文基于单目摄像头对于车辆前方感兴趣区域进行提取,通过Canny算子对感兴趣区域内的障碍物边缘进行提取,利用形态学闭操作标记障碍物特征以及位置,最终利用拟合法对车辆前方障碍物的位置进行标定。试验结果表明,通过识别车辆前方障碍物可以得到车辆与障碍物间的距离,且精度合理。

In the paper,the system extracts the region of interest in front of the vehicle based on the monocular camera,extracts the edge of the obstacle in the region of interest through the Canny operator,marks the obstacle feature and position using the morphological closed operation,and finally uses the fitting method for the vehicle.The position of the obstacle in front is calibrated.The experiment results show that by identifying obstacles in front of the vehicle,the distance between the vehicle and the obstacle can be obtained with reasonable precision.