Human-Assisted Virtual Environment Modeling for Robots

  • Authors:

  • J. G. Wang;Y. F. Li

  • Affiliations:

  • Department of Manufacturing Engineering and Engineering Management, City University of Hong Kong, Kowloon, Hong Kong;Department of Manufacturing Engineering and Engineering Management, City University of Hong Kong, Kowloon, Hong Kong. meyfli@cityu.edu.hk

  • Venue:
  • Autonomous Robots
  • Year:
  • 1999

Quantified Score

Hi-index 0.00

Visualization

Abstract

In order to avoid the complex calculation and poorrobustness in automatic visual modeling process, a man-machineinteraction based stereo vision system is developed for modeling anunknown environment. The operator‘s knowledge about a scene is usedas a guidance for modeling 3D environment. The modeling technique hasadvantage in terms of reliability and robustness over other automaticmodeling approaches. The data points needed for modeling an objectsare obtained through the intersection of lines, or calculation fromequations of curve, derived via fitting from human guided edgedetection. The modeling accuracy is ensured by using image featureextraction. A multi-viewpoint modeling approach has been developed inorder to deal with occlusion problems.Both accuracy and speed issues are addressed in this paper. Thesystem implementation and some 3D measurements on real scene havebeen performed using cameras lenses of 16 mm and 8 mm with anaccuracy 0.5 mm and 0.8 mm over the field of view, respectively. Thevirtual environment rendering based on the modeling data of realscenes with known model of mobile robot is given at the end of thispaper.