Land cover classification using multi‐temporal MERIS vegetation indices

Abstract

The spectral, spatial, and temporal resolutions of Envisat's Medium Resolution Imaging Spectrometer (MERIS) data are attractive for regional-to global-scale land cover mapping. Moreover, two novel and operational vegetation indices derived from MERIS data have considerable potential as discriminating variables in land cover classification. Here, the potential of these two vegetation indices (the MERIS global vegetation index (MGVI), MERIS terrestrial chlorophyll index (MTCI)) was evaluated for mapping eleven broad land cover classes in Wisconsin. Data acquired in the high and low chlorophyll seasons were used to increase inter-class separability. The two vegetation indices provided a higher degree of inter-class separability than data acquired in many of the individual MERIS spectral wavebands. The most accurate landcover map (73.2%) was derived from a classification of vegetation index-derived data with a support vector machine (SVM), and was 4.4% more accurate than the corresponding map derived from a classification using the data acquired in the original spectral wavebands.

Support vector machines in remote sensing: A review

“…Inglada (2007), supported by empirical evidence, similarly argued that higher number of geometric image features enhances multi-way characterization of objects that naturally have many different geometric properties. Also, pointed out by Dash et al (2007), the choice of dataset source could help in remedying this hindrance by allowing the reduction in the size of the training set required.…”

“…At coarser spatial resolutions a study was undertaken to evaluate the discriminatory power of two vegetation indices (the global vegetation index and terrestrial chlorophyll index) obtained from MERIS for general land cover mapping (Dash et al, 2007). Although a moderate level of accuracy was achieved using discriminant analysis method, a repetition of the experiment using an SVM technique revealed that the latter methodology resulted in a 6% gain in overall accuracy.…”

Remotely sensed imagery intelligent interpretation based on image segmentation and support vector machines

“…In recent years, SVMs classification method was applied in remote sensing image interpretation and achieved good results [10][11][12] . However, there still exists one problem, the huge computation in testing phase caused by the large number of support vectors, which greatly blocks it into practical use.…”

BiomassID: A biomass type identification system for mobile devices

“…Usually, biomass classification refers to land cover type or forest biomass classification. Land cover classification (Dash et al, 2007) and forest biomass estimation (Wulder et al, 2008) are active research topics in the area of remote sensing.…”