19 October 2005 A multiscale multitemporal land cover classification method using a Bayesian approach
Author Affiliations +
Proceedings Volume 5982, Image and Signal Processing for Remote Sensing XI; 598204 (2005); doi: 10.1117/12.627604
Event: SPIE Remote Sensing, 2005, Bruges, Belgium
Abstract
As vegetation time evolution is one of the most relevant information to discriminate the different land cover types, land cover classification requires both temporal and spatial information. Due to the physical properties of remote sensors, this temporal information can only be derived from coarse resolution sensors such as MERIS (300×300 m2 pixel size) or SPOT/VGT (1 km2 pixel size). In this paper, we propose to use jointly high and coarse spatial resolution to perform an efficient high resolution land cover classification. The method is based on Bayesian theory and on the linear mixture model permitting, through a simulated annealing algorithm, to perform a high resolution classification from a coarse resolution time series.
© (2005) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
A. Robin, S. Mascle-Le Hégarat, L. Moisan, "A multiscale multitemporal land cover classification method using a Bayesian approach", Proc. SPIE 5982, Image and Signal Processing for Remote Sensing XI, 598204 (19 October 2005); doi: 10.1117/12.627604; https://doi.org/10.1117/12.627604
PROCEEDINGS
12 PAGES


SHARE
KEYWORDS
Chromium

Image segmentation

Image resolution

Error analysis

Vegetation

Spatial resolution

Algorithms

Back to Top