Rectangular discrete radon transform for buildings extraction from high resolution satellite images

Authors:
Elouedi Ines;Hamouda Atef;Rojbani Hmida
Affiliations:
Computer Technology Department, The Sciences Institute, Tunis, Tunisia;Computer Technology Department, The Sciences Institute, Tunis, Tunisia;Computer Technology Department, The Sciences Institute, Tunis, Tunisia
Venue:
ICIAR'12 Proceedings of the 9th international conference on Image Analysis and Recognition - Volume Part I
Year:
2012

Citing 6
Cited 0

Pattern recognition by means of the Radon transform and the continuous wavelet transform

Signal Processing
An edge preserving noise smoothing technique using multiscale morphology

Signal Processing
Building Outline Extraction from Digital Elevation Models Using Marked Point Processes

International Journal of Computer Vision
A new approach to building identification from very-high-spatial-resolution images

International Journal of Remote Sensing
Radon Transform and Forstner Operator Applying in Buildings Contour Extraction

FSKD '09 Proceedings of the 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery - Volume 05
A model of the effect of image motion in the Radon transform domain

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a new approach titled Rectangular Discrete Radon Transform (RDRT) which is based on the generalization of the classical Radon transform to project the images with rectangular objects instead of straight lines. The RDRT was conceived to accurately locate and recognize Rectangular Buildings from high resolution satellite images. Experimental results show the efficiency of our method.