Abstract
Typically, lane departure warning systems rely on lane lines being present on the road. However, in many scenarios, e.g., secondary roads or some streets in cities, lane lines are either not present or not sufficiently well signaled. In this work, we present a vision-based method to locate a vehicle within the road when no lane lines are present using only RGB images as input. To this end, we propose to fuse together the outputs of a semantic segmentation and a monocular depth estimation architecture to reconstruct locally a semantic 3D point cloud of the viewed scene. We only retain points belonging to the road and, additionally, to any kind of fences or walls that might be present right at the sides of the road. We then compute the width of the road at a certain point on the planned trajectory and, additionally, what we denote as the fence-to-fence distance. Our system is suited to any kind of motoring scenario and is especially useful when lane lines are not present on the road or do not signal the path correctly. The additional fence-to-fence distance computation is complementary to the road’s width estimation. We quantitatively test our method on a set of images featuring streets of the city of Munich that contain a road-fence structure, so as to compare our two proposed variants, namely the road’s width and the fence-to-fence distance computation. In addition, we also validate our system qualitatively on the Stuttgart sequence of the publicly available Cityscapes dataset, where no fences or walls are present at the sides of the road, thus demonstrating that our system can be deployed in a standard city-like environment. For the benefit of the community, we make our software open source.
Highlights
Research in the field of self-driving cars has largely increased in the last few years
We present a novel vision-based method (Figure 4) to locate a vehicle within the road when no lane lines are present, naturally complementing traditional Lane Departure Warning Systems (LDWSs) which only rely on the existence of road markings
We begin by describing our strategy for semantic segmentation, briefly outline the monocular depth estimation step, and we show how the output of these first two modules can be fused together to compute a semantic 3D point cloud from which relevant information about the viewed scene can be extracted
Summary
Research in the field of self-driving cars has largely increased in the last few years. Current AVs mainly rely on a combination of Light Detection and Ranging (LiDAR), radar, and camera sensors to build a (semantic) 3D map of the scene. Such a sensor suite is still too expensive to be integrated on a large scale in mass production of vehicles. A notable example are Lane Departure Warning Systems (LDWSs), which warn the driver if the vehicle drifts outside the current lane. For such a system to work, lane lines must be present on the road. In many scenarios, e.g., secondary roads or some streets in cities, lane markings are either not present or not sufficiently well signaled (e.g., see Figure 1a)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
