Techniques and issues for the characterisation of an object-field representation that includes notions of semantics and uncertainty. The purpose of this model is to allow users to capture objects in field with internally variable levels of uncertainty, to visualize users’ conceptualizations of those geographic domains, and to share their understanding with others using embedded semantics. Conce...

This paper presents a semi-supervised learning algorithm called Gaussian process expectation maximization (GP-EM), for classification of landcover based on hyperspectral data analysis. Model parameters for each land cover class are first estimated by a supervised algorithm using Gaussian process regressions to find spatially adaptive parameters, and the estimated parameters are then used to ini...

The objective of this paper is to report on the crop classification activities carried out during the first year of the Italian project “Use of COSMO-SkyMed data for LANDcover classification and surface parameters retrieval over agricultural sites” (COSMOLAND), funded by the Italian Space Agency. The project intends to contribute to the COSMO-SkyMed mission objectives in the agriculture and hyd...

In this paper, we present some recent developments of Multiple Classifiers Systems (MCS) for remote sensing applications. Some standard MCS methods (boosting, bagging, consensus theory and random forests) are briefly described and applied to multisource data (satellite multispectral images, elevation, slope and aspect data) for landcover classification. In a second part, special attention is gi...

Boreal peatland covers large areas on the northern hemisphere and thus plays an important role especially as carbon storage. Results from a range of microwave sensors have already shown a large potential for hydrological applications. We tested the ScanSAR system ENVISAT ASAR Global Mode (1km) time series for wetland monitoring in boreal environments. With a simple threshold method homogeneous ...

Land-use change models are used to explore the dynamics and drivers of land-use/landcover change and to inform policies affecting such change. A broad array of applications and modeling methods are available and each type has certain advantages and disadvantages depending on the objective of the research. This work presents an approach combining cellular automata (CA) model and supported vector...

Cartographers often need to use information in existing landcover maps when compiling regional or global maps, but there are no standardized techniques for using such data effectively. An iterative, "map-guided" classification approach was developed to compile a spatially and thematically consistent, seamless land-cover map of the entire Intermountain Semi-Desert ecoregion from a set of semi-in...

Since thematic classes are represented with high spectral variance, pixel-based classifications generally result with incontinuous and inhomogeneous outputs. Objectbased classifications overcome this problem by the approach similar to human seeing and interpreting activity. First, image is segmented into smaller objects, and then image objects are assigned to classes according to their spectral...

This paper presents the integration of 50 cm 4 band (R, G, B, and infrared) imagery with 80 cm LIDAR, and 2.5 meter posting IFSAR surface elevation models for urban scene analysis. The goal is to characterize urban scenes in terms of buildings, trees, roads, other geometrical structures, open areas, and various natural land covers. This type of information is useful for applications such as urb...