Abstract
This paper describes a real-time 3-D vision system which uses stereo matching of vertical edge segments. The system is designed to permit a mobile robot to avoid obstacles and to position itself within an indoor environment. The system uses real-time edge tracking to lock onto stereo matches. Stereo matching is performed using global version of dynamic programming for matching stereo segments. The paper starts by describing the hypotheses which make possible an inexpensive real-time stereo system. The process for detecting vertical edge points and describing these points as vertical edge segments is then described. This is followed by a brief description of the edge tracking process. Stereo matching by global dynamic programming is then described. Stereo matching makes it possible to recover the 3-D position of vertical lines. The mathematics for projecting 3-D vertical segments from stereo matches is presented. A parametric representation for 3-D vertical segments is then described. This representation describes 3-D segments as a vector of parameters with their uncertainty.
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.
