基于激光雷达点云与图像融合的车辆目标检测方法

Vehicle object detection method based on data fusion of LADAR points and image

提出了一种基于4线激光雷达(LADAR)与摄像头融合的方案,用于提高智能车辆对车辆目标的检测精度。首先调用卷积神经网络来识别图像中的目标,然后将点云与图像数据进行空间匹配,最后采用R-Tree算法快速配准检测框与相应的点云数据。利用点云的深度信息就能获得目标的准确位置。经过真实道路场景采集的图像与点云数据进行测试,结果表明:该融合算法将漏检概率(FN)从Mask R-CNN方法的14.86%降低到8.03%;因而,该融合算法能够有效的降低图像漏检的概率。

A fusion scheme with 4 lines LADAR(laser detection and ranging)sensor and camera was adopted to provide more precise detection for traf fic,for an intelligent vehicle.Firstly,by using deep learning technique to detect image.Then,mapping LADAR data to image through a space transfer matrix.Finally,by using an R-Tree algorithm to quickly match LADAR points and corresponding detection boxes.The traffic’s real location was calculated easily by laser’s ranging.The proposed fusion frame was tested by images and point cloud data collected from real motorway scenes.The results show that the false negative(FN)of the fusion frame method is 8.03%,which is lower than that of 14.86%come from the Mask R-CNN method.Therefore,the fusion data could decrease probability of the FN compare with single data.