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...

Mining activities have caused serious heavy metal pollution in soil and water resources. The weathering mullock and mining tailings transport the heavy metal in polluted areas into ambient soil, rivers, and groundwater, which destroys the surrounding ecosystem. The menace of heavy metal elements in minerals can lead to botanical variety and impact vegetal growth. With the development of remote ...

Aiming at properties of remote sensing image data such as high-dimension, nonlinearity and massive unlabeled samples, a kind of probability least squares support vector machine (PLSSVM) classification method based on hybrid entropy and L1 norm was proposed. Firstly, hybrid entropy was designed by combining quasi-entropy with entropy difference, which was used to select the most “valuable” sampl...

Aiming at properties of remote sensing image data such as high-dimension, nonlinearity and massive unlabeled samples, a kind of probability least squares support vector machine (PLSSVM) classification method based on hybrid entropy and L1 norm was proposed. Firstly, hybrid entropy was designed by combining quasi-entropy with entropy difference, which was used to select the most “valuable” sampl...

Deep learning continues to push state-of-the-art performance for the semantic segmentation of color (i.e., RGB) imagery; however, the lack of annotated data for many remote sensing sensors (i.e. hyperspectral imagery (HSI)) prevents researchers from taking advantage of this recent success. Since generating sensor specific datasets is time intensive and cost prohibitive, remote sensing researche...

Habitat monitoring of designated areas under the EU Habitats Directive requires every 6 years information on area, range, structure and function for the protected (Annex I) habitat types. First results from studies on heathland areas in Belgium and the Netherlands show that hyperspectral imagery can be an important source of information to assist the evaluation of the habitat conservation statu...

During its long history of developing and deploying remote sensing instruments, NASA has provided scientific data that have benefitted a variety of scientific applications among them archaeology. Multispectral and hyperspectral instruments mounted on orbiting and sub-orbital platforms have provided new and important information for the discovery, delineation and analysis of archaeological sites...

High nitrogen fertiliser applications are very common in many densely populated areas as in the North China Plain (NCP). A still growing population and an ongoing economic progress enforce that process. Remote sensing methods can help to optimize the N-management for diagnosing crop N status on a field and regional level. For that purpose, spectral and agronomic data were collected during the v...

Overhead multiand hyperspectral imaging has enabled a variety of quantitative remote sensing techniques, such as the determination of the abundance and health of vegetation through the Normalized Difference Vegetation Index (NDVI). In addition, anomaly and target detection have been made possible by advanced matched filter algorithms. However, the derived surface reflectance from which all thes...