An improved snake for automatic building extraction

Authors:
Lau Bee Theng;Raymond Chiong
Affiliations:
School of Information Technology and Multimedia, Swinburne University of Technology, Kuching, Sarawak, Malaysia;School of Information Technology and Multimedia, Swinburne University of Technology, Kuching, Sarawak, Malaysia
Venue:
CIMMACS'07 Proceedings of the 6th WSEAS international conference on Computational intelligence, man-machine systems and cybernetics
Year:
2007

Citing 2
Cited 0

Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning
Coherence-Enhancing Diffusion Filtering

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Using snakes to extract buildings from satellite imagery such as IKONOS and Quickbird is an active activity in remote sensing society. Building extraction from satellite imagery has more than 20 years of history but the automated extractions are still undergoing developmental stages due to increasing image variation, required level of details and higher resolution imagery are acquired. This paper discusses the prototyping of an improved snake model. Snake is initialized in cornered-radial cast in comparison to the existing centered-radial. Moreover the coefficients for snake energy are obtained through genetic algorithm.