In this work, a deep learning approach has been developed to carry out road detection using only LIDAR data. Starting from an unstructured point cloud, top-view images encoding several basic statistics such as mean elevation and density are generated. By considering a top-view representation, road detection is reduced to a single-scale problem that can be addressed with a simple and fast fully convolutional neural network (FCN). The FCN is specifically designed for the task of pixel-wise semantic segmentation by combining a large receptive field with high-resolution feature maps. The proposed system achieved excellent performance and it is among the top-performing algorithms on the KITTI road benchmark. Its fast inference makes it particularly suitable for real-time applications.
@article{arxiv.1703.03613,
title = {Fast LIDAR-based Road Detection Using Fully Convolutional Neural Networks},
author = {Luca Caltagirone and Samuel Scheidegger and Lennart Svensson and Mattias Wahde},
journal= {arXiv preprint arXiv:1703.03613},
year = {2017}
}