SemanticDepth: Fusing Semantic Segmentation and Monocular Depth Estimation for Enabling Autonomous Driving in Roads without Lane Lines

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, the authors 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, the authors 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.The authors 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. The authors then compute the width of the road at a certain point on the planned trajectory and, additionally, what the authors denote as the fence-to-fence distance.The authors' 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. The authors quantitatively test their method on a set of images featuring streets of the city of Munich that contain a road-fence structure, so as to compare their two proposed variants, namely the road’s width and the fence-to-fence distance computation. In addition, the authors also validate their 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 their system can be deployed in a standard city-like environment. For the benefit of the community,the authors make their software open source.

Language

  • English

Media Info

  • Media Type: Web
  • Features: Figures; References; Tables;
  • Pagination: 3224
  • Serial:
  • Publication flags:

    Open Access (libre)

Subject/Index Terms

Filing Info

  • Accession Number: 01715573
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Aug 1 2019 12:17PM