Centre dedocumentation
scientifique

Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images / Ekrem Saralioglu in Geocarto international, vol 37 n° 18 ([01/09/2022])  

Public [article]  inGeocarto international > vol 37 n° 18 [01/09/2022] . - pp 5433 - 5452 Titre : Crowdsourcing-based application to solve the problem of insufficient training data in deep learning-based classification of satellite images Type de document : Article/Communication Auteurs : Ekrem Saralioglu, Auteur ; Oguz Gungor, Auteur Année de publication : 2022 Article en page(s) : pp 5433 - 5452 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] acquisition d'images [Termes IGN] apprentissage profond [Termes IGN] approche participative [Termes IGN] classification dirigée [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couleur (variable spectrale) [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] étiquette [Termes IGN] image multibande [Termes IGN] OpenStreetMap [Termes IGN] pixel [Termes IGN] plateforme collaborative [Termes IGN] texture d'image [Termes IGN] Worldview Résumé : (auteur) In order to solve insufficient training data problem in remote sensing, a web platform was created so that registered users can generate labeled data for various classes in a dynamic structure. Users were asked to select representative pixel groups for the forest, hazelnut, shadow, soil, tea, and building classes with the polygon tool, and then assign a class label corresponding to each created polygon thanks to the help document displaying descriptive information regarding the locations, colors, textures and distributions of the classes in the image. Crowdsourcing was again used to test the accuracy of the tagged data produced by crowdsourcing. The created data set was overlaid with the original WV-2 image, and the correctness of the labels ​​of the polygons was once visually verified. Finally, the WV-2 image, consisting of 40 patches, was classified with CNN and an average of over 95% accuracy was achieved. Numéro de notice : A2022-702 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2021.1917006 Date de publication en ligne : 26/05/2021 En ligne : https://doi.org/10.1080/10106049.2021.1917006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101561 [article]

Semantic segmentation of land cover from high resolution multispectral satellite images by spectral-spatial convolutional neural network / Ekrem Saralioglu in Geocarto international, vol 37 n° 2 ([15/01/2022])  

Public [article]  inGeocarto international > vol 37 n° 2 [15/01/2022] . - pp 657 - 677 Titre : Semantic segmentation of land cover from high resolution multispectral satellite images by spectral-spatial convolutional neural network Type de document : Article/Communication Auteurs : Ekrem Saralioglu, Auteur ; Oguz Gungor, Auteur Année de publication : 2022 Article en page(s) : pp 657 - 677 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] image Ikonos [Termes IGN] image multibande [Termes IGN] image Pléiades-HR [Termes IGN] image Worldview [Termes IGN] occupation du sol [Termes IGN] segmentation sémantique [Termes IGN] Turquie Résumé : (auteur) Research to improve the accuracy of very high-resolution satellite image classification algorithms is still one of the hot topics in the field of remote sensing. Successful results of deep learning methods in areas such as image classification and object detection have led to the application of these methods to remote sensing problems. Recently, Convolutional Neural Networks (CNNs) are among the most common deep learning methods used in image classification, however, the use of CNN’s in satellite image classification is relatively new. Due to the high computational complexity of 3D CNNs, which aim to extract both spatial and spectral information, 2D CNNs focussing on the extraction of spatial information are often preferred. High-resolution satellite images, however, contain crucial spectral information as well as spatial information. In this study, a 3D-2D CNN model using both spectral and spatial information was applied to extract more accurate land cover information from very high-resolution satellite images. The model was applied on a Worldview-2 satellite image including agricultural product areas such as tea, hazelnut groves and land use classes such as buildings and roads. The results of the CNN based model were also compared against those of the Support Vector Machine (SVM) and Random Forest (RF) algorithms. The post-classification accuracies were obtained using 800 control points generated by a web interface created for crowdsourcing purposes. The classification accuracy was 95.6% for the 3D-2D CNN model, 89.2% for the RF and 86.4% for the SVM. Numéro de notice : A2022-305 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/10106049.2020.1734871 Date de publication en ligne : 04/03/2020 En ligne : https://doi.org/10.1080/10106049.2020.1734871 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100379 [article]