%0 Conference Paper %1 IV2012 %A Chen, Long %A Li, Qingquan %A Zhu, Quanwen %A Li, Ming %A Nüchter, A. %B Proceedings of the 2012 IEEE Intelligent Vehicles Symposium (IV '12) %C Alcala de Henares, Madrid, Spain %D 2012 %K imported %P 456--461 %R 10.1109/IVS.2012.6232219 %T 3D LIDAR Point Cloud based Intersection Recognition for Autonomous Driving %U https://robotik.informatik.uni-wuerzburg.de/telematics/download/iv2012.pdf %X Finding road intersections in advance is crucial for navigation and path planning of moving autonomous vehicles, especially when there is no position or geographic auxiliary information available. In this paper, we investigate the use of a 3D point cloud based solution for intersection and road segment classification in front of an autonomous vehicle. It is based on the analysis of the features from the designed beam model. First, we build a grid map of the point cloud and clear the cells which belong to other vehicles. Then, the proposed beam model is applied with a specified distance in front of autonomous vehicle. A feature set based on the length distribution of the beam is extracted from the current frame and combined with a trained classifier to solve the road-type classification problem, i.e., segment and intersection. In addition, we also make the distinction between +-shaped and T-shaped intersections. The results are reported over a series of real-world data. A performance of above 80\% correct classification is reported at a real-time classification rate of 5 Hz.

@inproceedings{IV2012, abstract = {Finding road intersections in advance is crucial for navigation and path planning of moving autonomous vehicles, especially when there is no position or geographic auxiliary information available. In this paper, we investigate the use of a 3D point cloud based solution for intersection and road segment classification in front of an autonomous vehicle. It is based on the analysis of the features from the designed beam model. First, we build a grid map of the point cloud and clear the cells which belong to other vehicles. Then, the proposed beam model is applied with a specified distance in front of autonomous vehicle. A feature set based on the length distribution of the beam is extracted from the current frame and combined with a trained classifier to solve the road-type classification problem, i.e., segment and intersection. In addition, we also make the distinction between +-shaped and T-shaped intersections. The results are reported over a series of real-world data. A performance of above 80\% correct classification is reported at a real-time classification rate of 5 Hz.}, added-at = {2017-09-19T13:40:53.000+0200}, address = {Alcala de Henares, Madrid, Spain}, author = {Chen, Long and Li, Qingquan and Zhu, Quanwen and Li, Ming and N{\"u}chter, A.}, biburl = {https://www.bibsonomy.org/bibtex/241abb2cf6e872aac7bfa365594afa571/nuechter76}, booktitle = {Proceedings of the 2012 IEEE Intelligent Vehicles Symposium (IV '12)}, doi = {10.1109/IVS.2012.6232219}, interhash = {0c0769970dfdcb673caa8f61a54b0740}, intrahash = {41abb2cf6e872aac7bfa365594afa571}, keywords = {imported}, month = {June}, pages = {456--461}, timestamp = {2017-09-29T16:01:21.000+0200}, title = {{3D LIDAR Point Cloud based Intersection Recognition for Autonomous Driving}}, url = {https://robotik.informatik.uni-wuerzburg.de/telematics/download/iv2012.pdf}, year = 2012 }