Search publications, data, projects and authors
Mapping of the natural vegetable trainings on a regional scale by classification of temporal series of satellite images




Forest cover mapping is an essential tool for forest management. Detailed maps, characterizing forest types at a régional scale, are needed. This need can be fulfilled by médium spatial resolution optical satellite images time sériés. This thesis aims at improving the supervised classification procédure applied to a time sériés, to produce maps detailing forest types at a régional scale. To meet this goal, the improvement of the results obtained by the classification of a MODIS time sériés, performed with a stratification of the study area, was assessed. An improvement of classification accuracy due to stratification built by object-based image analysis was observed, with an increase of the Kappa index value and an increase of the reject fraction rate. These two phenomena are correlated to the classified végétation area. A minimal and a maximal value were identified, respectively related to a too high reject fraction rate and a neutral stratification impact.We carried out a second study, aiming at assessing the influence of the médium spatial resolution time sériés organization and of the algorithm on classification quality. Three distinct classification algorithms (maximum likelihood, Support Vector Machine, Random Forest) and several time sériés were studied. A significant improvement due to temporal and radiométrie effects and the superiority of Random Forest were highlighted by the results. Thematic confusions and low user's and producer's accuracies were still observed for several classes. We finally studied the improvement brought by a spatial resolution change for the images composing the time sériés to discriminate classes of mixed forest species. The conclusions of the former study (MODIS images) were confirmed with DEIMOS images. We can conclude that these effects are independent from input data and their spatial resolution. A significant improvement was also observed with an increase of the Kappa index value from 0,60 with MODIS data to 0,72 with DEIMOS data, due to a decrease of the mixed pixels rate.

Report a bug

Under construction

We're in Beta!

The GoTriple platform is still in Beta and we keep adding new features everyday. Check the project's website to see what's new and subscribe to our Mailing List.