Principal component analysis applied to interpretation of aerial images

Gerard Brunet; Philippe Durand; Abdellah Qannari; Dariush Ghorbanzadeh

doi:10.1117/12.2524458

6 May 2019 Principal component analysis applied to interpretation of aerial images

Gerard Brunet, Philippe Durand, Abdellah Qannari, Dariush Ghorbanzadeh

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 110691B (2019) https://doi.org/10.1117/12.2524458
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

The aim of this study is to determine in aerial images the most significant parameters to automatic recognition of objects or textures such as house roof, vegetation, Ã Statistical method is Principal Component Analysis, a technique for classification and for examining relationships among quantitative variables. For Image Processing, Java Language is used. For statistics, SAS programs (Statistical Analysis System) with IML package (Interactive Matrix Language). Aerial Images are 400*400 pixels with 10 pixels for 1 meter on ground, with the three r,g,b components (red,green,blue). With image a first simple example and fast operator is performed to find contours, then algorithm has been adapted to dene regions with growing and merging of zones. On those zones a set of parameters is calculated to perform Principal Component Analysis for summarizing data. Results of this method allow classification of zones and find the most significant parameters to be selected, levels of r,g,b components, dispersion of those components, and one calculated value in relation with geometric characteristics of each zone.

Citation Download Citation

Gerard Brunet, Philippe Durand, Abdellah Qannari, and Dariush Ghorbanzadeh "Principal component analysis applied to interpretation of aerial images", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 110691B (6 May 2019); https://doi.org/10.1117/12.2524458

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