基于激光雷达数据的行人检测

Pedestrian detection is a task which is necessary among all tasks leveraged in automatic driving domain. Traditional pedestrian detection algorithms took fully advantage of image data, unable to obtain depth of objects. To address aforementioned issue, this paper proposed a method based on raw LiDAR point cloud data. The proposed method combines traditional moving object detection in LiDAR data and point cloud recognition by deep learning, and is capable of perception and pedestrian detection without images, obtaining 3d location of pedestrian, therefore helping central control system make reasonable decisions. This method experimented in 3d object detection task of KITTI dataset, obtained 33.37% AP (Average Precision) on moderate cases. The results showed that proposed method performed better than other algorithm based on LiDAR data, which hence indicated the effectiveness of proposed method.