Road Segmentation Supervised by an Extended V-Disparity Algorithm for Autonomous Navigation
Authors:
- 1 June 2007
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2007 IEEE Intelligent Vehicles Symposium
- No. 19310587,p. 160-165
Abstract
This paper presents an original approach of road segmentation supervised by stereovision. It deals with free space estimation by stereovision and road detection by color segmentation. The v-disparity algorithm is extended to provide a reliable and precise road profile on all types of roads. The free space is estimated by classifying the pixels of the disparity map. This classification is performed by using the road profile and the u-disparity image. Then a color segmentation is performed on the free space. Here is the supervision. Each stage of the algorithm is presented and experimental results are shown.Keywords
This publication has 8 references indexed in Scilit:
- Robot Visual Navigation in Semi-structured Outdoor Environments2006
- Obstacle Detection with Stereo Vision for Off-Road Vehicle Navigation2006
- The Single Frame Stereo Vision System for Reliable Obstacle Detection Used during the 2005 DARPA Grand Challenge on TerraMax2006
- The DARPA grand challenge - development of an autonomous vehicle2004
- Team terramax and the DARPA grand challenge: a general overview2004
- Texture-Based Vanishing Point Voting for Road Shape Estimation2004
- UNSCARF-a color vision system for the detection of unstructured roads2002
- Detecting binocular half-occlusions: empirical comparisons of five approachesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002