Curvelet transform for water bodies extraction from high resolution satellite images | ||||
The International Conference on Electrical Engineering | ||||
Article 71, Volume 8, 8th International Conference on Electrical Engineering ICEENG 2012, May 2012, Page 1-19 PDF (916.81 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2012.30818 | ||||
View on SCiNiTO | ||||
Authors | ||||
Mohamed Elhabiby1; A. S. Elsharkawy2; N. El-Sheimy3 | ||||
1Ain Shams University, Cairo. | ||||
2Egyptian Armed Forces. | ||||
3Dept. of Geomatics Engineering, University of Calgary, Calgary, Alberta. | ||||
Abstract | ||||
In this research paper, a new implementation on the second generation curvelet transform in the edge detection of coastline is presented and applied on WorldView-2 imagery, together with a comparison with the classical edge detection methods such as Canny operator and the traditional wavelet transforms. This implementation is aiming to compare this new approach to the traditional edge detection techniques. It is found that the curvelet proposed implementation performs better in detecting larger and elongated structures compared to the Canny and the wavelet transforms. However, Although this method is promising and efficient for edge detection, the quality of the edge detection is still a function of the pre-processing steps (the classification step in this research paper) , as any edge detector will suffer from the heterogeneity of the images especially when using very high resolution imagery. | ||||
Keywords | ||||
Curvelet transform; Wavelet Transform; edge detection; high resolution satellite imagery | ||||
Statistics Article View: 112 PDF Download: 106 |
||||