Open AccessIRNet: A Real-time Intersection Recognition Network Based on Graph Classification and 3D LiDAR Point Cloud for UGVs
Author(s) -
Hanbo Tang,
Tao Wu,
Bin Dai,
Ying Cai,
Kai Cao,
Shi Li
Publication year - 2022
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2203/1/012002
Subject(s) - computer science , point cloud , intersection (aeronautics) , lidar , graph , key (lock) , artificial intelligence , convolution (computer science) , point (geometry) , pattern recognition (psychology) , data mining , computer vision , theoretical computer science , mathematics , remote sensing , engineering , geography , computer security , geometry , artificial neural network , aerospace engineering
The intersections are junctions of roads. Recognizing intersections based on LiDAR accurately and quickly is a key task for UGVs. In this paper, we propose an end-to-end real-time intersections recognition network (IRNet) with graph attention convolution based on graph classification and 3D LiDAR point cloud. Multiple evaluations on KITTI and Tunnel dataset demonstrate that our model performs better than other competitive models and meets the real-time recognition. We research the performance of our model under different number of input points, and certify that neither of two spatial transformation networks is effective for our model. Ablation experiments certify effectiveness of the proposed features skip connection.