Improved land cover mapping using aerial photographs and satellite images

Varga, Katalin; Szabó, Szilárd; Szabó, Gergely; Tóthmérész, Béla

doi:10.1515/geo-2015-0002

Cited by 14 publications

(12 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Using the original RGB bands, at least in our study area, resulted a good result with 82% OA, but we have to consider that there can be areas where the accuracy is smaller due to similar land cover categories. Varga et al [117] found that visible range orthophotos provided only 61-68% OA, depending on the given image; in their image forests, vegetation on arable lands and even the water had green tone causing a large amount of misclassification. Cots-Folch et al [118] gained 74% OA with the application of textural information.…”

Section: Discussionmentioning

confidence: 99%

Building Extraction Using Orthophotos and Dense Point Cloud Derived from Visual Band Aerial Imagery Based on Machine Learning and Segmentation

et al. 2020

Self Cite

View full text Add to dashboard Cite

Urban sprawl related increase of built-in areas requires reliable monitoring methods and remote sensing can be an efficient technique. Aerial surveys, with high spatial resolution, provide detailed data for building monitoring, but archive images usually have only visible bands. We aimed to reveal the efficiency of visible orthophotographs and photogrammetric dense point clouds in building detection with segmentation-based machine learning (with five algorithms) using visible bands, texture information, and spectral and morphometric indices in different variable sets. Usually random forest (RF) had the best (99.8%) and partial least squares the worst overall accuracy (~60%). We found that >95% accuracy can be gained even in class level. Recursive feature elimination (RFE) was an efficient variable selection tool, its result with six variables was like when we applied all the available 31 variables. Morphometric indices had 82% producer’s and 85% user’s Accuracy (PA and UA, respectively) and combining them with spectral and texture indices, it had the largest contribution in the improvement. However, morphometric indices are not always available but by adding texture and spectral indices to red-green-blue (RGB) bands the PA improved with 12% and the UA with 6%. Building extraction from visual aerial surveys can be accurate, and archive images can be involved in the time series of a monitoring.

show abstract

Section: Discussionmentioning

confidence: 99%

Building Extraction Using Orthophotos and Dense Point Cloud Derived from Visual Band Aerial Imagery Based on Machine Learning and Segmentation

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Detailed maps act as a digital representation of both natural and historical elements and they are now common as a result of data availability (Varga et al 2015, Werle 2016. Within this new context, our approach tries to find a solution for an accurate and precise GIS mapping of the urban medieval site, using UAv photogrammetric techniques to reveal topographic and historical features.…”

Section: Methodsmentioning

confidence: 99%

Photogrammetric Modelling for Urban Medieval Site Mapping. A Case Study from Curtea de Argeş, Romania

Nistor

Mihai

Toma

et al. 2017

Quaestiones Geographicae

View full text Add to dashboard Cite

nistor C., Mihai B., toMa L., CarLan i., 2017. Photogrammetric modelling for urban medieval site mapping. A case study from Curtea de Argeş, Romania. Quaestiones Geographicae 36(3), Bogucki Wydawnictwo Naukowe, Poznań, pp. 87-96. 10 figs.aBstraCt: Detailed mapping of urban historical sites superposed on natural landforms within built-up areas is a real challenge. Digital photogrammetric techniques meet the requirements for mapping archaeological sites within dense built-up areas. The objectives are to reveal the landform value in medieval site development and to analyse its impact on the landforms. The aim of the present study is to highlight the contribution of geomatics technologies for the evaluation and preservation of historical sites using UAV (Unmanned Aerial Vehicle) imagery and field photos for 3D modelling. Curtea de Argeş medieval site, established on Argeş River terraces and attested since the 13 th century, represents the town core for which the specific methodology was applied.

show abstract

“…Notably, the soil cover map was prepared based on the images' supervised classification procedure, using the Maximum Likelihood algorithm and accuracy was assured by the KIA statistical index (Poznanovic et al, 2014;Calijuri et al, 2015;Varga et al, 2015;Mishra and Rai, 2016). The image used was from Landsat 8, in the bands of the Operational Land Imager (OLI) sensor, dated September 03rd 2017, provided by the Division of Image Generation (DGI) of the National Institute for Space Research (Instituto Nacional de Pesquisas Espaciais -INPE).…”

Section: Soil Cover Standardizationmentioning

confidence: 99%

Defining environmental conservation levels considering anthropic activity in the Uberaba River Basin protected area

Santos

Silva²,

Assis³

et al. 2019

Rev. ambiente água

View full text Add to dashboard Cite

Environmental conservation of river basins in general is essential for water quality and ecological maintenance, especially in spring areas. Despite being characterized as a Conservation Unit (CU) of Sustainable Use (SU), the Uberaba River Basin highlands are highly influenced by anthropic activities. The aim of this study was to determine different levels of conservation required to maintain environmental quality. The Multicriteria evaluation method was used as follows: i) applied fuzzy membership functions to standardization of the continuous data values or reclassified when categorical criteria; (ii) established criteria ranking through the pairwise relative importance comparison approach by the Analytical Hierarchy Process (AHP) method and; (iii) performed Weighted Linear Combination (WLC). The selected criteria were maps of the: land cover obtained by supervised classification of a satellite image, with 94% of Kappa Index of Agreement (KIA); soil types, slope; distances from rivers, roads; railways and urban limits. A main outcome of the criteria evaluated is a map of continuous data values expressing distinct levels of environmental conservation requirements. The highest values that express the need for conservation occurred near the ridgetop, corresponding to forest land cover, high slope and hydromorphic soils. The lowest values were observed in the peri-urban areas, in more stable soil and soil cover with a higher degree of occupation. It is concluded that the resulting map can assist in decision-making regarding proper management of the area, to achieve sustainability in the application of occupation policies.

show abstract

Improved land cover mapping using aerial photographs and satellite images

Cited by 14 publications

References 68 publications

Building Extraction Using Orthophotos and Dense Point Cloud Derived from Visual Band Aerial Imagery Based on Machine Learning and Segmentation

Building Extraction Using Orthophotos and Dense Point Cloud Derived from Visual Band Aerial Imagery Based on Machine Learning and Segmentation

Photogrammetric Modelling for Urban Medieval Site Mapping. A Case Study from Curtea de Argeş, Romania

Defining environmental conservation levels considering anthropic activity in the Uberaba River Basin protected area

Contact Info

Product

Resources

About