Skip to Main content Skip to Navigation
Conference papers

Automatic Selection of Color Channels for Segmentation of Aerial Images with Photometric Variations

Abstract : The choice of a color model is of great importance for aerial image segmentation algorithms. However, there are many color models available; the inherent difficulty is how to automatically select a single color model or, alternatively, a subset of features from several color models producing the best result for a particular task. To achieve proper colors components selection, in this paper, it was proposed the use of wrapper method, a data mining approach, to perform the segmentation process. The result yields good feature discrimination. The method was verified experimentally with 108 images from Amsterdam Library of Objects Images (ALOI) and 97 aerial images with different photometric conditions. Furthermore, it has shown that the color model selection scheme provides repeatability and distinctiveness for aerial segmentation.
Complete list of metadata

Cited literature [11 references]  Display  Hide  Download

https://hal.inria.fr/inria-00264896
Contributor : Inria Rhône-Alpes Documentation <>
Submitted on : Monday, March 31, 2008 - 4:15:04 PM
Last modification on : Monday, March 31, 2008 - 4:31:19 PM
Long-term archiving on: : Tuesday, September 21, 2010 - 4:30:04 PM

File

paper32_PACCV2007.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00264896, version 2

Collections

Citation

Lúcio André de Castro Jorge, Ednaldo José Ferreira, Henrique Souza Ruiz, De, Valentin Obac, Adilson Gonzaga. Automatic Selection of Color Channels for Segmentation of Aerial Images with Photometric Variations. Proceedings of the First International Workshop on Photometric Analysis For Computer Vision - PACV 2007, Oct 2007, Rio de Janeiro, Brazil. 7 p. ⟨inria-00264896v2⟩

Share

Metrics

Record views

363

Files downloads

279