5 June 2012 Adaptive scale smoothing for road redundancy region elimination
Zhijian Huang, Jinfang Zhang, Jiaze Wu, Fanjiang Xu
Author Affiliations +
Abstract
In the process of road extraction, the road region often mixes with some redundancies caused by the phenomenon of "different objects with the same spectrum," which exists widely in remote sensing images. To eliminate these redundancies and preserve neat and accurate road regions, a method based on skeleton analysis is proposed. At first, the shortest path of a specified road segment is constructed with mixed region skeletons. The road width at the skeleton point is then selected as the smoothing scale on this point, on which basis an accumulative and bidirectional smoothing is taken. With the smoothed path and its average width, a buffer algorithm reconstructs the road region. The results show that redundancies of the road can be eliminated correctly, and accurate road center lines and neat road regions can be obtained.
© 2012 Society of Photo-Optical Instrumentation Engineers (SPIE) 0091-3286/2012/$25.00 © 2012 SPIE
Zhijian Huang, Jinfang Zhang, Jiaze Wu, and Fanjiang Xu "Adaptive scale smoothing for road redundancy region elimination," Optical Engineering 51(6), 066201 (5 June 2012). https://doi.org/10.1117/1.OE.51.6.066201
Published: 5 June 2012
Lens.org Logo
CITATIONS
Cited by 3 scholarly publications.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Roads

Reconstruction algorithms

Image segmentation

Remote sensing

Optical engineering

Distortion

Buildings

Back to Top