BROWSE
Detail
Conference Paper
Analyzing Live Video For Image-Based Navigation Systems
Cited - time in 
Share 
Share
- Authors
- Sung Hoon Kim, Jeong Ho Park, Seong-Ik Cho, Soon Young Park, Kyoung Ho Choi
- Issue Date
- 2007-01
- Citation
- Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2007, pp.394-399
- Language
- English
- Type
- Conference Paper
- Abstract
- Image-based navigation systems can provide more realistic navigation information to drivers by guiding their directions on real images. In this paper, we analyze live video captured from a moving vehicle and present a novel algorithm to extract road boundary. Based on the analysis, we 1) extracts the edge map of an input image, 2) deletes unnecessary edge components that do not belong to road boundary and merges broken edges of road boundary, and 3) removes shadows that generates false positive of road boundary, 4) combines extracted edges from multiple images to detect changes of road boundary, making possible to notice that an intersection is located ahead. Experimental results are provided to show the robustness and effectiveness of the proposed algorithm for image-based navigation systems under various road conditions such as shadows and snow, etc.
- KSP Keywords
- Belong to, Broken edges, Edge map, False positive, Image-based navigation, Moving Vehicle, Navigation information, Novel algorithm, Road condition, live video, navigation system