The Library
Planar direct method: A new framework for stereo vision based guidance and obstacle detection
Tools
UNSPECIFIED (2005) Planar direct method: A new framework for stereo vision based guidance and obstacle detection. In: IEEE International Conference on Image Processing (ICIP 2005), Genoa, ITALY, SEP 11-14, 2005. Published in: 2005 International Conference on Image Processing (ICIP), Vols 1-5 pp. 3077-3080. ISBN 0-7803-9134-9. ISSN 1522-4880.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Abstract
In the context of real-time collision/obstacle avoidance this paper investigates an improvement of a direct method of estimating dense scene structure and image motion. Our proposed method combines stereo-vision (involving geometric constraints), optical flow (involving photometric constraints) and additional model constraints. Modifications to the direct method are introduced through a planarity constraint, an illumination model and a new computational framework in order to deal with significant illumination drifts and obstacle detection on static objects or moving vehicle. Experimental results on real image sequences demonstrate the effectiveness of the method.
Item Type: | Conference Item (UNSPECIFIED) | ||||
---|---|---|---|---|---|
Subjects: | T Technology > TR Photography | ||||
Series Name: | IEEE International Conference on Image Processing (ICIP) | ||||
Journal or Publication Title: | 2005 International Conference on Image Processing (ICIP), Vols 1-5 | ||||
Publisher: | IEEE | ||||
ISBN: | 0-7803-9134-9 | ||||
ISSN: | 1522-4880 | ||||
Official Date: | 2005 | ||||
Dates: |
|
||||
Number of Pages: | 4 | ||||
Page Range: | pp. 3077-3080 | ||||
Publication Status: | Published | ||||
Title of Event: | IEEE International Conference on Image Processing (ICIP 2005) | ||||
Location of Event: | Genoa, ITALY | ||||
Date(s) of Event: | SEP 11-14, 2005 |
Data sourced from Thomson Reuters' Web of Knowledge
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |