@inproceedings {pub2890,
	title = {Building a probabilistic grid-based road representation from direct and indirect visual cues},
	author = {Edoardo Casapietra AND Thomas H Weisswange AND Jannik Fritsch AND Franz Kummert AND Christian Goerick},
	year = {2015},
	month = {June},
	abstract = {Detecting the road area ahead of the ego-vehicle is an important issue for modern driver assistance systems. In particular, vehicle motion planning in inner city environment requires the detection of road up to 3 seconds in advance. State-of-the-art visual road detection systems have a hard time fulfilling this task, due to their relatively short range and the presence of occlusions (other vehicles, buildings, etc.), which are expected to occur often in complex scenarios. 
In this paper we propose a probabilistic grid-based approach based on the observation and interpretation of vehicles{\textquoteright} behaviour in the scene. It exploits their movements in order to infer the presence and location of road surface we cannot see. We will show that this approach presents various advantages over current visual road detection systems, especially in those situations that are the most challenging for them. However, those systems have their own advantages and can outperform our approach in certain aspects, such as road boundary detection, where the conditions are favorable (proximity to the ego-vehicle, no occlusions). 
Thus, we will demonstrate that our approach is well suited to complement already existing and established detection systems, and that in fact it is designed to work in concert with other available resources, e.g. offline road maps. We will show through qualitative results on real-world scenes taken from the {\textquotedblleft}KITTI{\textquotedblright} dataset, that the fusion of this method with the already existing road detection data can potentially extend our time horizon well over the 3 seconds mentioned above. Finally, we will show how our approach is planned to develop into a semantically enriched representation of the road, including road properties such as availability, lanes and directions, as well as vehicles{\textquoteright} motion prediction.},
	publisher = {IEEE},
	booktitle = {IEEE Intelligent Vehicles Symposium (IV 2015)},
	city = {Seoul},
	pages = {273-279}
}