A LiDAR–Camera Fusion 3D Object Detection Algorithm

3D object detection with LiDAR and camera fusion has always been a challenge for autonomous driving. This work proposes deep neural network (namely FuDNN) LiDAR–camera detection. Firstly, 2D backbone is designed to extract features from images. Secondly, an attention-based sub-network fuse the extracted by point clouds PointNet++. Besides, FuDNN, which uses RPN refinement of PointRCNN obtain box predictions, was tested on public KITTI dataset. Experiments validation set show that proposed FuDNN achieves AP values 92.48, 82.90, 80.51 at easy, moderate, hard difficulty levels car The improves performance in category