An investigation into the use of wavelets and scaling for the extraction of buildings in aerial images

Author

Levitt, Stephen ; Aghdasi, Farzin

Author_Institution

Dept. of Electr. Eng., Univ. of the Witwatersrand, Johannesburg, South Africa

fYear

1998

fDate

7-8 Sep 1998

Firstpage

133

Lastpage

138

Abstract

In this paper we examine the applicability of the wavelet transform and image scaling to the detection of buildings in monocular, greyscale aerial photography. Both of these techniques have strong frequency domain interpretations and thus differ from the traditional methods used in building extraction systems. Our results from employing the different techniques indicate that both the high and low frequency components of an aerial image offer useful information for the detection of buildings and other man-made features

Keywords

feature extraction; image recognition; photography; remote sensing; wavelet transforms; aerial images; building extraction systems; buildings detection; frequency domain interpretations; high frequency components; image scaling; low frequency components; man-made features; monocular greyscale aerial photography; wavelets; Buildings; Computer vision; Detectors; Discrete wavelet transforms; Frequency domain analysis; Image edge detection; Image recognition; Image segmentation; Photography; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Communications and Signal Processing, 1998. COMSIG '98. Proceedings of the 1998 South African Symposium on

Conference_Location

Rondebosch

Print_ISBN

0-7803-5054-5

Type

conf

DOI

10.1109/COMSIG.1998.736936

Filename

736936