Technical Report TRnnn:
Vanishing Point: a visual road-detection program for a DARPA Grand challenge vehicle.
Danko Antolovic, Alex Leykin and Steven D. Johnson.

Project:

This work was performed in collaboration with the Indy Robot Racing Team in cooperation with Pervasive Technology Labs at Indiana University.

Abstract:

This report describes a visual approach to road detection. A field of dominant trend lines is established over the image, by convolution with Gabor filters; the trend lines are then grouped into "visual segments," providing evidence for macroscopic linear features. Sets of these macroscopic features are evaluated against a list of heuristic criteria, to determine their likelihood of representing a road in the image. This procedure was implemented as software, for use by the Indy Robot Racing Team, a participant in the DARPA Grand Challenge 2005. It is capable of road detection at rates appropriate for driving at moderate speeds on dirt roads (ca. 5 Hz on a 3.4 GHz processor).

Bibtex Entry:

@techreport{IUCS-TRnnn
 , author = {Danko Antolovic and Alex Leykin and Steven D. Johnson}
 , title = {Vanishing Point:a visual road-detection program for a DARPA Grand challenge vehicle}
 , institution= {Indiana University Computer Science Department}
 , type = {Technical Report}
 , year = {2005}
 , month = {December}
 , number = {nnn}
 , address = {Bloomington, Indiana}
 , url = {www.cs.indiana.edu}
  }

Documentation:

• Danko Antolovic. Using the Fast Fourier Transform Library FFTW. [DOC]  [PDF]  [PS] 

Data:

• Video test footage, 29 September 2005 [AVI, 289Mb] [RM, 14Mb]
• Source test images [HTM]
• Source test clips [HTM]