Centre de documentation
scientifique

Revising cadastral data on land boundaries using deep learning in image-based mapping / Bujar Fetai in ISPRS International journal of geo-information, vol 11 n° 5 (May 2022)  

Public [article]  inISPRS International journal of geo-information > vol 11 n° 5 (May 2022) . - n° 298 Titre : Revising cadastral data on land boundaries using deep learning in image-based mapping Type de document : Article/Communication Auteurs : Bujar Fetai, Auteur ; Dejan Grigillo, Auteur ; Anka Lisec, Auteur Année de publication : 2022 Article en page(s) : n° 298 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] cadastre étranger [Termes IGN] cartographie cadastrale [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection de contours [Termes IGN] données cadastrales [Termes IGN] limite cadastrale [Termes IGN] point d'appui [Termes IGN] Slovénie Résumé : (auteur) One of the main concerns of land administration in developed countries is to keep the cadastral system up to date. The goal of this research was to develop an approach to detect visible land boundaries and revise existing cadastral data using deep learning. The convolutional neural network (CNN), based on a modified architecture, was trained using the Berkeley segmentation data set 500 (BSDS500) available online. This dataset is known for edge and boundary detection. The model was tested in two rural areas in Slovenia. The results were evaluated using recall, precision, and the F1 score—as a more appropriate method for unbalanced classes. In terms of detection quality, balanced recall and precision resulted in F1 scores of 0.60 and 0.54 for Ponova vas and Odranci, respectively. With lower recall (completeness), the model was able to predict the boundaries with a precision (correctness) of 0.71 and 0.61. When the cadastral data were revised, the low values were interpreted to mean that the lower the recall, the greater the need to update the existing cadastral data. In the case of Ponova vas, the recall value was less than 0.1, which means that the boundaries did not overlap. In Odranci, 21% of the predicted and cadastral boundaries overlapped. Since the direction of the lines was not a problem, the low recall value (0.21) was mainly due to overly fragmented plots. Overall, the automatic methods are faster (once the model is trained) but less accurate than the manual methods. For a rapid revision of existing cadastral boundaries, an automatic approach is certainly desirable for many national mapping and cadastral agencies, especially in developed countries. Numéro de notice : A2022-357 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi11050298 Date de publication en ligne : 04/05/2022 En ligne : https://doi.org/10.3390/ijgi11050298 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100562 [article]

Use of unsupervised classification for the determination of prevailing land use typology / Miha Konjar in Geodetski vestnik, vol 61 n° 4 (December 2017 - February 2018)  

Public [article]  inGeodetski vestnik > vol 61 n° 4 (December 2017 - February 2018) . - pp 541 - 581 Titre : Use of unsupervised classification for the determination of prevailing land use typology Type de document : Article/Communication Auteurs : Miha Konjar, Auteur ; Alma Zavodnik Lamovsek, Auteur ; Dejan Grigillo, Auteur Année de publication : 2017 Article en page(s) : pp 541 - 581 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] agrégation spatiale [Termes IGN] classification non dirigée [Termes IGN] complexité [Termes IGN] densité de population [Termes IGN] données socio-économiques [Termes IGN] image numérique [Termes IGN] indicateur spatial [Termes IGN] occupation du sol [Termes IGN] Slovénie [Termes IGN] utilisation du sol [Termes IGN] zone homogène Résumé : (Auteur) This paper presents classification methods that enable the division of space into homogeneous areas that combine the spatial characteristics with influence on land use and changes thereof. It was determined that the existing methods do not always include the criteria needed for the aggregation of spatial units into homogeneous groups. The results of the analysis showed that the identified homogenous groups do not fully capture the spatial complexity and diversity important for land use change analyses. For this reason, a new approach to the classification of spatial units based on the unsupervised classification of digital images was proposed. The methodology includes the selection of appropriate indicators, that consider land use more comprehensively and thus enable better classification results. The use of the unsupervised classification method for prevailing land use typology has been tested in Slovenia. At the municipal level, seven types of prevailing land use were identified. Numéro de notice : A2017-777 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.15292//geodetski-vestnik.2017.04.541-581 En ligne : http://www.geodetski-vestnik.com/61/4/gv61-4_konjar.pdf Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88981 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
139-2017041	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Remote sensing data as a potential source for establishment of the 3D cadastre in Slovenia / Petra Dobrež in Geodetski vestnik, vol 60 n° 3 (September - November 2016)  

Public [article]  inGeodetski vestnik > vol 60 n° 3 (September - November 2016) . - pp 392 - 422 Titre : Remote sensing data as a potential source for establishment of the 3D cadastre in Slovenia Type de document : Article/Communication Auteurs : Petra Dobrež, Auteur ; Dejan Grigillo, Auteur ; Anka Lisec, Auteur ; Mojca Kosmatin-Fras, Auteur Année de publication : 2016 Article en page(s) : pp 392 - 422 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cadastre étranger [Termes IGN] cadastre 3D [Termes IGN] cadastre étranger [Termes IGN] image aérienne [Termes IGN] lever des détails [Termes IGN] reconstruction 3D du bâti [Termes IGN] Slovénie Résumé : (Auteur) The topic of this paper is the challenges of using remote sensing technologies as one of the potential data sources for the establishment of a 3D real property cadastre in Slovenia. More than a decade ago, the legal basis for the registration of property rights on the buildings and parts of buildings was provided in Slovenia, and for this purpose, the Building Cadastre was established. The analyses of the current data within the Land Cadastre and the Building Cadastre revealed that the 3D graphical representation of buildings, where the second level of detail (LoD 2) was discussed, requires additional data in which significant roof points should be additionally acquired. For this purpose, i.e. the creation of a graphical 3D-model of a building at the level LoD 2, we use the cadastral and national topographic data that covers the entire state territory, which are stereopairs of aerial photographs of the cyclic aerial survey (CAS) and airborne laser scanning data. Using a case study, we have analysed and discussed the appropriateness of the state airborne laser scanning data as an additional data source, along with the current cadastral data, for the creation of 3D-building model at the second level of detail, which is important from the cadastral as well as topographic perspective. Numéro de notice : A2016-746 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.15292/geodetski-vestnik.2016.03.392-422 En ligne : https://dx.doi.org/10.15292/geodetski-vestnik.2016.03.392-422 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82292 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
139-2016031	RAB	Revue	Centre de documentation	En réserve L003	Disponible