No abstract

International audienceRecent advances in spectral-spatial classification of hyperspectral images are presented in this paper. Several techniques are investigated for combining both spatial and spectral information. Spatial information is extracted at the object (set of pixels) level rather than at the conventional pixel level. Mathematical morphology is first used to derive the morphological profile of the image, which includes character- istics about the size, orientation, and contrast of the spatial structures present in the image. Then, the morphological neighborhood is defined and used to derive additional features for classification. Classification is performed with support vector machines (SVMs) using the available spectral information and the extracted spatial information. Spatial postprocessing is next investigated to build more homogeneous and spatially consistent thematic maps. To that end, three presegmentation techniques are applied to define regions that are used to regularize the preliminary pixel-wise thematic map. Finally, a multiple-classifier (MC) system is defined to produce relevant markers that are exploited to segment the hyperspectral image with the minimum spanning forest algorithm. Experimental results conducted on three real hyperspectral images with different spatial and spectral resolutions and corresponding to various contexts are presented. They highlight the importance of spectral-spatial strategies for the accurate classification of hyperspectral images and validate the proposed methods

A satellite-derived cropland extent map at high spatial resolution (30-m or better) is a must for food and water security analysis. Precise and accurate global cropland extent maps, indicating cropland and non-cropland areas, are starting points to develop higher-level products such as crop watering methods (irrigated or rainfed), cropping intensities (e.g., single, double, or continuous cropping), crop types, cropland fallows, as well as for assessment of cropland productivity (productivity per unit of land), and crop water productivity (productivity per unit of water). Uncertainties associated with the cropland extent map have cascading effects on all higher-level cropland products. However, precise and accurate cropland extent maps at high spatial resolution over large areas (e.g., continents or the globe) are challenging to produce due to the small-holder dominant agricultural systems like those found in most of Africa and Asia. Cloud-based geospatial computing platforms and multi-date, multi-sensor satellite image inventories on Google Earth Engine offer opportunities for mapping croplands with precision and accuracy over large areas that satisfy the requirements of broad range of applications. Such maps are expected to provide highly significant improvements compared to existing products, which tend to be coarser in resolution, and often fail to capture fragmented small-holder farms especially in regions with high dynamic change within and across years. To overcome these limitations, in this research we present an approach for cropland extent mapping at high spatial resolution (30-m or better) using the 10-day, 10 to 20-m, Sentinel-2 data in combination with 16-day, 30-m, Landsat-8 data on Google Earth Engine (GEE). First, nominal 30-m resolution satellite imagery composites were created from 36,924 scenes of Sentinel-2 and Landsat-8 images for the entire African continent in 2015-2016. These composites were generated using a median-mosaic of five bands (blue, green, red, near-infrared, NDVI) during each of the two periods (period 1: January-June 2016 and period 2: July-December 2015) plus a 30-m slope layer derived from the Shuttle Radar Topographic Mission (SRTM) elevation dataset. Second, we selected Cropland/Non-cropland training samples (sample size = 9791) from various sources in GEE to create pixel-based classifications. As supervised classification algorithm, Random Forest (RF) was used as the primary classifier because of its efficiency, and when over-fitting issues of

[1] The Visible Infrared Imaging Radiometer Suite (VIIRS) sensor was launched 28 October 2011 on the Suomi National Polar-orbiting Partnership (SNPP) satellite. VIIRS has 22 spectral bands covering the spectrum between 0.412 μm and 12.01 μm, including 16 moderate resolution bands (M-bands) with a nominal spatial resolution of 750 m at nadir, five imaging resolution bands (I-bands) with a nominal spatial resolution of 375 m at nadir, and a day-night band (DNB) with a near-constant nominal 750 m spatial resolution throughout the scan. These bands are located in a visible and near-infrared focal plane assembly (FPA), a shortwave and midwave infrared FPA, and a long-wave infrared FPA. All bands, except the DNB, are coregistered for proper environmental data records retrievals. Observations from VIIRS instrument provide long-term measurements of biogeophysical variables for climate research and polar satellite data stream for the operational community's use in weather forecasting and disaster relief and other applications. Well Earth-located (geolocated) instrument data are important to retrieving accurate biogeophysical variables. This paper describes prelaunch pointing and alignment measurements, and the two sets of on-orbit correction of geolocation errors, the first of which corrected error from 1300 m to within 75 m (20% I-band pixel size) and the second of which fine-tuned scan-angle dependent errors, bringing VIIRS geolocation products to high maturity in one and a half years of the SNPP VIIRS on-orbit operations. Prelaunch calibration and the on-orbit characterization of sensor spatial impulse responses and band-to-band coregistration are also described.

A new multiple-classifier approach for spectralspatial classification of hyperspectral images is proposed. Several classifiers are used independently to classify an image. For every pixel, if all the classifiers have assigned this pixel to the same class, the pixel is kept as a marker, i.e., a seed of the spatial region with a corresponding class label. We propose to use spectral-spatial classifiers at the preliminary step of the marker-selection procedure, each of them combining the results of a pixelwise classification and a segmentation map. Different segmentation methods based on dissimilar principles lead to different classification results. Furthermore, a minimum spanning forest is built, where each tree is rooted on a classification-driven marker and forms a region in the spectral-spatial classification map. Experimental results are presented for two hyperspectral airborne images. The proposed method significantly improves classification accuracies when compared with previously proposed classification techniques.