Multiscale quality assessment of Global Human Settlement Layer scenes against reference data using statistical learning

Ouzounis, Georgios K.; Syrris, Vasileios; Pesaresi, Martino

doi:10.1016/j.patrec.2013.04.004

Cited by 16 publications

(13 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Strong correlation between PANTEX image features and local density of building footprints was proven in [28], [29] using cadastral data as reference. Observing the reality at the range of scales (resolution) of this study, the physical reasons behind the correlation between PANTEX measurements and the presence of BU areas can be resumed as follows: i) the fact that BU areas are generally made by relatively small patches of heterogeneous materials and the fact that BU structures generally cast shadows and ii) the fact that the human settlement areas show a strong dominance of objects with square corners.…”

Section: B Problem Solvingmentioning

confidence: 84%

A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results

Pesaresi

Guo

Blaes

et al. 2013

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

380

296

View full text Add to dashboard Cite

A general framework for processing high and veryhigh resolution imagery in support of a Global Human Settlement Layer (GHSL) is presented together with a discussion on the results of the first operational test of the production workflow. The test involved the mapping of 24.3 million km² of the Earth surface spread in four continents, corresponding to an estimated population of 1.3 billion people in 2010. The resolution of the input image data ranges from 0.5 to 10 meters, collected by a heterogeneous set of platforms including satellite SPOT (2 and 5), CBERS 2B, RapidEye (2 and 4), WorldView (1 and 2), GeoEye 1, QuickBird 2, Ikonos 2, and airborne sensors. Several imaging modes were tested including panchromatic, multispectral and pan-sharpened images. A new fully automatic image information extraction, generalization and mosaic workflow is presented that is based on multiscale textural and morphological image features extraction. New image feature compression and optimization are introduced, together with new learning and classification techniques allowing for the processing of HR/VHR image data using low-resolution thematic layers as reference. A new systematic approach for quality control and validation allowing global spatial and thematic consistency checking is proposed and applied. The quality of the results are discussed by sensor, band, resolution, and eco-regions. Critical points, lessons learned and next steps are highlighted.Index Terms-Built-up density, CSL, global human settlement layer, linear regression, PANTEX, urban limits.

show abstract

Section: B Problem Solvingmentioning

confidence: 84%

A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results

Pesaresi

Guo

Blaes

et al. 2013

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

380

296

View full text Add to dashboard Cite

show abstract

“…It attempts to improve the quality of the textural/morphological characteristics while retaining the computational burden in low levels. Generally speaking, it moves inside the concept of synergy between machine learning and image processing; one contiguous application has been presented recently in [13].…”

mentioning

confidence: 99%

Image Enhancement and Feature Extraction Based on Low-Resolution Satellite Data

Syrris

Stefano

Ehrlich

et al. 2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

The purpose of this study is to investigate the sensitivity of contrast-based textural measurements and morphological characteristics that derive from high-resolution satellite imagery (three-band SPOT-5) when diverse image enhancements techniques are piloted. The general framework of the application is the built-up/nonbuilt-up detection. In the existence of a low-resolution reference layer, we apply supervised learning that indirectly reduces the uncertainty and improves the quality of the reference layer. Based on the new class label assignments, the image histogram is adjusted suitably for the computation of contrast-based textural/morphological features. A case study is presented where we test a mixture of image enhancement operations like linear and decorrelation stretching and assess the performance through ROC analysis against available building footprints. Experimental results demonstrate that spectral band combination is the key factor that conditions the contrast of grayscale images. Contrast adjustment (before or after the band combination and merging) supports considerably the extraction of informative features from a low-contrast image; in case of a well-contrasted image, the improvement is marginal.

show abstract

“…The outputs from the three downscaling methods, A, B, and C, are all consistent with their source data when comparing total population within provinces (NUTS3). We use a multiscale approach (Ouzounis et al., ) to evaluate the quality of these outputs (Figs. , , and ).…”

Section: Resultsmentioning

confidence: 99%

“…Several global population grids are available, including GeoStat (European Forum for GeoStatistics, ), LandScan (Bhaduri et al., ), and the GWP (Balk & Yetman, ). The state of the art of global population grids today is the Global Human Settlement Layer (GHSL), which combines remote sensing, ancillary census data, and spatial modeling into a global data set, with a resolution of 250 m (Freire, MacManus, Pesaresi, Doxsey‐Whitfield, & Mills, ; Ouzounis, Syrris, & Pesaresi, ; Pesaresi, Ehrlich, & Freire, ). Although there is no single best dasymetric method, multiple ancillary data are expected to improve the results of the downscaling compared to the single‐data‐source method.…”

Section: Methodsmentioning

confidence: 99%

Mapping Socioeconomic Exposure for Flood Risk Assessment in Italy

2018

View full text Add to dashboard Cite

Detailed spatial representation of socioeconomic exposure and the related vulnerability to natural hazards has the potential to improve the quality and reliability of risk assessment outputs. We apply a spatially weighted dasymetric approach based on multiple ancillary data to downscale important socioeconomic variables and produce a grid data set for Italy that contains multilayered information about physical exposure, population, gross domestic product, and social vulnerability. We test the performances of our dasymetric approach compared to other spatial interpolation methods. Next, we combine the grid data set with flood hazard estimates to exemplify an application for the purpose of risk assessment.

show abstract

Multiscale quality assessment of Global Human Settlement Layer scenes against reference data using statistical learning

Cited by 16 publications

References 15 publications

A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results

A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results

Image Enhancement and Feature Extraction Based on Low-Resolution Satellite Data

Mapping Socioeconomic Exposure for Flood Risk Assessment in Italy

Contact Info

Product

Resources

About