Centre de documentation
scientifique

Automatic building footprint extraction from UAV images using neural networks / Zoran Kokeza in Geodetski vestnik, vol 64 n° 4 (December 2020 - February 2021)  

Public [article]  inGeodetski vestnik > vol 64 n° 4 (December 2020 - February 2021) . - pp 545 - 561 Titre : Automatic building footprint extraction from UAV images using neural networks Type de document : Article/Communication Auteurs : Zoran Kokeza, Auteur ; Miroslav Vujasinović, Auteur ; Miro Govedarica, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 545 - 561 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] cartographie cadastrale [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] détection du bâti [Termes IGN] empreinte [Termes IGN] image à haute résolution [Termes IGN] image captée par drone [Termes IGN] image RVB [Termes IGN] modèle numérique de surface [Termes IGN] orthoimage [Termes IGN] zone d'intérêt Résumé : (Auteur) Up-to-date cadastral maps are crucial for urban planning. Creating those maps with the classical geodetic methods is expensive and time-consuming. Emerge of Unmanned Aerial Vehicles (UAV) made a possibility for quick acquisition of data with much more details than it was possible before. The topic of the research refers to the challenges of automatic extraction of building footprints on high-resolution orthophotos. The objectives of this study were as follows: (1) to test the possibility of using different publicly available datasets (Tanzania, AIRS and Inria) for neural network training and then test the generalisation capability of the model on the Area Of Interest (AOI); (2) to evaluate the effect of the normalised digital surface model (nDSM) on the results of neural network training and implementation. Evaluation of the results shown that the models trained on the Tanzania (IoU 36.4%), AIRS (IoU 64.4%) and Inria (IoU 7.4%) datasets doesn't satisfy the requested accuracy to update cadastral maps in study area. Much better results are achieved in the second part of the study, where the training of the neural network was done on tiles (256x256) of the orthophoto of AOI created from data acquired using UAV. A combination of RGB orthophoto with nDSM resulted in a 2% increase of IoU, achieving the final IoU of over 90%. Numéro de notice : A2020-777 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.15292/geodetski-vestnik.2020.04.545-561 Date de publication en ligne : 26/10/2020 En ligne : http://www.geodetski-vestnik.com/en/2020-4 Format de la ressource électronique : URL bulletin Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96706 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
139-2020041	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Spatial analysis of high-resolution urban thermal patterns in Vojvodina, Serbia / Dusan Jovanovic in Geocarto international, vol 30 n° 5 - 6 (May - July 2015)  

Public [article]  inGeocarto international > vol 30 n° 5 - 6 (May - July 2015) . - pp 483 - 505 Titre : Spatial analysis of high-resolution urban thermal patterns in Vojvodina, Serbia Type de document : Article/Communication Auteurs : Dusan Jovanovic, Auteur ; Miro Govedarica, Auteur ; Filip Sabo, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 483 - 505 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] couvert végétal [Termes IGN] DMC [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-TM [Termes IGN] image Worldview [Termes IGN] occupation du sol [Termes IGN] régression linéaire [Termes IGN] Serbie [Termes IGN] surface imperméable [Termes IGN] température au sol Résumé : (auteur) Main objective of this study was to establish a relationship between land cover and land surface temperature (LST) in urban and rural areas. The research was conducted using Landsat, WorldView-2 (WV-2) and Digital Mapping Camera. Normalised difference vegetation index and normalised difference built-up index were used for establishing the relation between built-up area, vegetation cover and LST for spatial resolution of 30 m. Impervious surface and vegetation area generated from Digital Mapping Camera from Intergraph and WV-2 were used to establish the relation between built-up area, vegetation cover and LST for spatial resolutions of 0.1, 0.5 and 30 m. Linear regression models were used to determine the relationship between LST and indicators. Main contribution of this research is to establish the use of combining remote sensing sensors with different spectral and spatial resolution for two typical settlements in Vojvodina. Correlation coefficients between LST and LST indicators ranged from 0.602 to 0.768. Numéro de notice : A2015-293 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2014.985747#abstract Date de publication en ligne : 11/12/2014 En ligne : http://www.tandfonline.com/doi/full/10.1080/10106049.2014.985747#abstract Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76441 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2015031	RAB	Revue	Centre de documentation	En réserve L003	Disponible