The paper deals with a new quantitative, vision-based approach to road following. It is based on the theoretical framework of recently developed optical flow-based visual field theory. By building on this theory, the authors suggest that motion commands can be generated directly from a visual feature, or cue, consisting of the projection into the image of the tangent point to the edge of the road, along with the optical flow of this point. Using this cue, they suggest several different vision-based control approaches. There are several advantages to using this visual cue: it is directly extracted from the image, i.e., there is no need to reconstruct the scene; for many road following situations this is the only necessary visual cue; only the horizontal component of the optical flow of the tangent point needs to be extracted; it has a scientific basis. i.e., the described techniques are not ad-hoc; and the related computations are relatively simple and thus suitable for real-time applications. For each control approach, they derive the value of related steering commands.

  • Corporate Authors:

    National Institute of Standards and Technology

    Technical Analysis Division
    Gaithersburg, MD  United States  20760
  • Authors:
    • Raviv, D
    • Herman, M
  • Publication Date: 1991-1

Media Info

  • Pagination: 46 p.

Subject/Index Terms

Filing Info

  • Accession Number: 00615961
  • Record Type: Publication
  • Source Agency: National Technical Information Service
  • Report/Paper Numbers: NISTIR-4476
  • Files: TRIS
  • Created Date: Sep 30 1991 12:00AM