An efficient 2D-WTMM and PNN approach to remove spurious radar echoes

Mohamed Khider; Boualem Haddad

doi:10.1117/12.2011192

14 March 2013 An efficient 2D-WTMM and PNN approach to remove spurious radar echoes

Mohamed Khider, Boualem Haddad

Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 876846 (2013) https://doi.org/10.1117/12.2011192
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore

Abstract

The proposed method aims to reduce the spurious echoes in weather radar images collected at Melbourne radar site, using parameters from 2D-WTMM method based on the continuous wavelet transform, and including the PNN probabilistic neural network for the classification of pixels into two types of echoes : precipitation or parasite. Indeed, we propose the introduction of parameters related to wavelet transform skeletons, these parameters are proportional to the image texture roughness, anisotropy and the distance of separation between non-zero radar echoes cells and give good separation between rain and non-rain echoes. Radar image is first segmented with Voronoi’s cells according to the spatial distribution of Holder exponents. By comparing with a direct method of classification which takes into account only one parameter at a time by using a threshold, it was found that the combination of these three parameters with PNN approach improves the final results in terms of preserving precipitation echoes and elimination of weather radar clutter. Initial results show approximately the removal of 98% of clutter and preservation of 97% of precipitation echoes.

Citation Download Citation

Mohamed Khider and Boualem Haddad "An efficient 2D-WTMM and PNN approach to remove spurious radar echoes", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 876846 (14 March 2013); https://doi.org/10.1117/12.2011192

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available