Tél, Ferenc and Lantos, Béla (2009) Stereo image processing system for robot vision. In: KÉPAF 2009. 7. conference Hungarian Association for Image Processing and Pattern Recognition, 2009.01.28-2009.01.30., Budapest, Magyarország.
|
Text
1180783.pdf Download (257kB) | Preview |
Abstract
More and more applications (path planning, collision avoidance methods) require 3D description of the surround world. This paper describes a stereo vision system that uses 2D (grayscale or color) images to extract simple 2D geometric entities (points, lines) applying a low-level feature detector. The features are matched across views with a graph matching algorithm. During the projective reconstruction the 3D description of the scene is recovered. The developed system uses uncalibrated cameras, therefore only projective 3D structure can be detected defined up to a collineation. Using the Euclidean information about a known set of predefined objects stored in database and the results of the recognition algorithm, the description can be updated to a metric one.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | T Technology / alkalmazott, műszaki tudományok > T2 Technology (General) / műszaki tudományok általában |
| Depositing User: | Erika Bilicsi |
| Date Deposited: | 26 Aug 2013 09:51 |
| Last Modified: | 26 Aug 2013 09:51 |
| URI: | http://real.mtak.hu/id/eprint/6281 |
Actions (login required)
 |
Edit Item |
