Centre de documentation
scientifique

Building detection with convolutional networks trained with transfer learning / Simon Šanca in Geodetski vestnik, vol 65 n° 4 (December 2021 - February 2022)  

Public [article]  inGeodetski vestnik > vol 65 n° 4 (December 2021 - February 2022) . - pp 559 - 576 Titre : Building detection with convolutional networks trained with transfer learning Type de document : Article/Communication Auteurs : Simon Šanca, Auteur ; Krištof Oštir, Auteur ; Alen Mangafić, Auteur Année de publication : 2021 Article en page(s) : pp 559 - 576 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification automatique d'objets [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection du bâti [Termes IGN] données cadastrales [Termes IGN] image aérienne [Termes IGN] image infrarouge couleur [Termes IGN] image proche infrarouge [Termes IGN] image RVB [Termes IGN] orthoimage couleur [Termes IGN] segmentation d'image [Termes IGN] Slovénie Résumé : (Auteur) Building footprint detection based on orthophotos can be used to update the building cadastre. In recent years deep learning methods using convolutional neural networks have been increasingly used around the world. We present an example of automatic building classification using our datasets made of colour near-infrared orthophotos (NIR-R-G) and colour orthophotos (R-G-B). Building detection using pretrained weights from two large scale datasets Microsoft Common Objects in Context (MS COCO) and ImageNet was performed and tested. We applied the Mask Region Convolutional Neural Network (Mask R-CNN) to detect the building footprints. The purpose of our research is to identify the applicability of pre-trained neural networks on the data of another colour space to build a classification model without re-learning. Numéro de notice : A2021-930 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.15292/geodetski-vestnik.2021.04.559-593 Date de publication en ligne : 03/11/2021 En ligne : https://doi.org/10.15292/geodetski-vestnik.2021.04.559-593 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99409 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
139-2021041	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Fluvial gravel bar mapping with spectral signal mixture analysis / Liza Stančič in European journal of remote sensing, vol 54 sup 1 (2021)  

Public [article]  inEuropean journal of remote sensing > vol 54 sup 1 (2021) . - pp 31 - 46 Titre : Fluvial gravel bar mapping with spectral signal mixture analysis Type de document : Article/Communication Auteurs : Liza Stančič, Auteur ; Krištof Oštir, Auteur ; Žiga Kokalj, Auteur Année de publication : 2021 Article en page(s) : pp 31 - 46 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse des mélanges spectraux [Termes IGN] bassin hydrographique [Termes IGN] carte thématique [Termes IGN] gravier [Termes IGN] image Landsat [Termes IGN] image Sentinel-MSI [Termes IGN] précision infrapixellaire [Termes IGN] réflectance spectrale [Termes IGN] rivière [Termes IGN] signature spectrale [Termes IGN] Slovénie Résumé : (auteur) The paper presents a method for mapping fluvial gravel bars based on Sentinel-2 and Landsat imagery. The proposed method therefore uses spectral signal mixture analysis (SSMA) because its results allow the development of land cover fraction maps for surface water, gravel, and vegetation. The method is validated on a spatially heterogeneous mountainous area in the upper Soča river basin in north-west Slovenia, Central Europe. Unmixing results in highly accurate fraction maps with MAE of around 0.1. Gravel fractions are mapped the most accurately, indicating that the approach can be used successfully for fluvial gravel bar mapping. Endmember sets selected automatically perform slightly worse (MAE higher by at most 0.05) than sets selected manually based on high resolution reference data. Both Sentinel-2 and Landsat imagery can be used for accurate mapping with differences between the two remote sensing systems within 0.05 MAE. For the study area, the SSMA-based soft classification method is more accurate for land cover mapping than a Spectral Angle Mapping-based hard classification. The method is promising for an effective use in other cases where highly accurate subpixel information is needed, because it is able to detect small-scale changes that could go unnoticed with hard classification mapping. Numéro de notice : A2021-817 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/22797254.2020.1811776 Date de publication en ligne : 30/08/2020 En ligne : https://doi.org/10.1080/22797254.2020.1811776 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98906 [article]

Delineation of vacant building land using orthophoto and lidar data object classification / Dejan Jenko in Geodetski vestnik, vol 63 n° 3 (September - November 2019)  

Public [article]  inGeodetski vestnik > vol 63 n° 3 (September - November 2019) . - pp 344 - 378 Titre : Delineation of vacant building land using orthophoto and lidar data object classification Type de document : Article/Communication Auteurs : Dejan Jenko, Auteur ; Mojca Foški, Auteur ; Krištof Oštir, Auteur ; Žiga Kokalj, Auteur Année de publication : 2019 Article en page(s) : pp 344 - 378 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] classification orientée objet [Termes IGN] couche thématique [Termes IGN] détection du bâti [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] logement [Termes IGN] orthoimage [Termes IGN] Slovénie Résumé : (Auteur) Exact data about the location and area of vacant building land have been a major issue in several Slovene municipalities. This article deals with automatic vacant building land delineation. The presented methodology is based on the object-based classification that derives the land cover layer from orthophoto and laser scanning data. With post-processing and data cleaning in GIS, we create the vacant building land layer. The methodology was tested in study areas in the Municipality of Trebnje. The results were compared to the vacant building land layer generated by visual interpretation (manual vectorisation). We found that the presented methodology of automatic delineation of vacant buildings can speed up the processing and lower the cost of manual vectorisation and, in particular, data updating but we cannot completely replace manual work. Numéro de notice : A2019-500 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article DOI : 10.15292/geodetski-vestnik.2019.03.344-378 En ligne : http://dx.doi.org/10.15292/geodetski-vestnik.2019.03.344-378 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93782 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
139-2019031	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Automatic orthorectification of high-resolution optical satellite images using vector roads / Aleš Marsetič in IEEE Transactions on geoscience and remote sensing, vol 53 n° 11 (November 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 11 (November 2015) . - pp 6035 - 6047 Titre : Automatic orthorectification of high-resolution optical satellite images using vector roads Type de document : Article/Communication Auteurs : Aleš Marsetič, Auteur ; Krištof Oštir, Auteur ; Mojca Kosmatin-Fras, Auteur Année de publication : 2015 Article en page(s) : pp 6035 - 6047 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] capteur en peigne [Termes IGN] chaîne de traitement [Termes IGN] colinéarité [Termes IGN] élément d'orientation externe [Termes IGN] estimation de position [Termes IGN] extraction de données [Termes IGN] géoréférencement [Termes IGN] image RapidEye [Termes IGN] modélisation géométrique de prise de vue [Termes IGN] orthorectification automatique [Termes IGN] système de coordonnées Résumé : (Auteur) This paper presents a completely automatic processing chain for orthorectification of optical pushbroom sensors. The procedure is robust and works without manual intervention from raw satellite image to orthoimage. It is modularly divided in four main steps: metadata extraction, automatic ground control point (GCP) extraction, geometric modeling, and orthorectification. The GCP extraction step uses georeferenced vector roads as a reference and produces a file with a list of points and their accuracy estimation. The physical geometric model is based on collinearity equations and works with sensor-corrected (level 1) optical satellite images. It models the sensor position and attitude with second-order piecewise polynomials depending on the acquisition time. The exterior orientation parameters are estimated in a least squares adjustment, employing random sample consensus and robust estimation algorithms for the removal of erroneous points and fine-tuning of the results. The images are finally orthorectified using a digital elevation model and positioned in a national coordinate system. The usability of the method is presented by testing three RapidEye images of regions with different terrain configurations. Several tests were carried out to verify the efficiency of the procedure and to make it more robust. Using the geometric model, subpixel accuracy on independent check points was achieved, and positional accuracy of orthoimages was around one pixel. The proposed procedure is general and can be easily adapted to various sensors. Numéro de notice : A2015-772 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2431434 Date de publication en ligne : 01/06/2015 En ligne : https://doi.org/10.1109/TGRS.2015.2431434 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78828 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015111	SL	Revue	Centre de documentation	Revues en salle	Disponible