Colour space influence for vegetation image classification application to Caribbean forest and agriculture

M. Abadi; E. Grandchamp

doi:10.1117/12.799886

Translator Disclaimer

14 October 2008 Colour space influence for vegetation image classification application to Caribbean forest and agriculture

M. Abadi, E. Grandchamp

Author Affiliations +

Proceedings Volume 7109, Image and Signal Processing for Remote Sensing XIV; 710909 (2008) https://doi.org/10.1117/12.799886
Event: SPIE Remote Sensing, 2008, Cardiff, Wales, United Kingdom

Abstract

This paper deals with a comparison of different colour space in order to improve high resolution images classification. The background of this study is the measure of the agriculture impact on the environment in islander context. Biodiversity is particularly sensitive and relevant in such areas and the follow-up of the forest front is a way to ensure its preservation. Very high resolution satellite images are used such as QuickBird and IKONOS scenes. In order to segment the images into forest and agriculture areas, we characterize both ground covers with colour and texture features. A classical unsupervised classifier is then used to obtain labelled areas. As features are computed on coloured images, we can wonder if the colour space choice is relevant. This study has been made considering more than fourteen colour spaces (RGB, YUV, Lab, YIQ, YC_rC_s, XYZ, CMY, LMS, HSL, KLT, IHS, I₁I₂I₃, HSV, HSI, etc.) and shows the visual and quantitative superiority of IHS on all others. For conciseness reasons, results only show RGB, I₁I₂I₃ and IHS colour spaces.

Citation Download Citation

M. Abadi and E. Grandchamp "Colour space influence for vegetation image classification application to Caribbean forest and agriculture", Proc. SPIE 7109, Image and Signal Processing for Remote Sensing XIV, 710909 (14 October 2008); https://doi.org/10.1117/12.799886

ACCESS THE FULL ARTICLE