Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks
Abstract
Recently, vision-based Advanced Driver Assist Systems have gained broad interest. In this work, we investigate free-space detection, for which we propose to employ a Fully Convolutional Network (FCN). We show that this FCN can be trained in a self-supervised manner and achieve similar results compared to training on manually annotated data, thereby reducing the need for large manually annotated training sets. To this end, our self-supervised training relies on a stereo-vision disparity system, to automatically generate (weak) training labels for the color-based FCN. Additionally, our self-supervised training facilitates online training of the FCN instead of offline. Consequently, given that the applied FCN is relatively small, the free-space analysis becomes highly adaptive to any traffic scene that the vehicle encounters. We have validated our algorithm using publicly available data and on a new challenging benchmark dataset that is released with this paper. Experiments show that the online training boosts performance with 5% when compared to offline training, both for Fmax and AP.
Cite
@article{arxiv.1604.02316,
title = {Free-Space Detection with Self-Supervised and Online Trained Fully Convolutional Networks},
author = {Willem P. Sanberg and Gijs Dubbelman and Peter H. N. de With},
journal= {arXiv preprint arXiv:1604.02316},
year = {2017}
}
Comments
version as accepted at IS&T Electronic Imaging - Autonomous Vehicles and Machines Conference (San Francisco USA, January 2017); updated with two additional robustness experiments and formatted in conference style; 8 pages, public data available