Centre de documentation
scientifique

A comparative study on deep-learning methods for dense image matching of multi-angle and multi-date remote sensing stereo-images / Hessah Albanwan in Photogrammetric record, vol 37 n° 180 (December 2022)  

Public [article]  inPhotogrammetric record > vol 37 n° 180 (December 2022) . - pp 385 - 409 Titre : A comparative study on deep-learning methods for dense image matching of multi-angle and multi-date remote sensing stereo-images Type de document : Article/Communication Auteurs : Hessah Albanwan, Auteur ; Rongjun Qin, Auteur Année de publication : 2022 Article en page(s) : pp 385 - 409 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] appariement d'images [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couple stéréoscopique [Termes IGN] modèle stéréoscopique [Termes IGN] précision géométrique (imagerie) Résumé : (auteur) Deep-learning (DL) stereomatching methods gained great attention in remote sensing satellite datasets. However, most of these existing studies conclude assessments based only on a few/single stereo-images lacking a systematic evaluation on how robust DL methods are on satellite stereo-images with varying radiometric and geometric configurations. This paper provides an evaluation of four DL stereomatching methods through hundreds of multi-date multi-site satellite stereopairs with varying geometric configurations, against the traditional well-practiced Census-semi-global matching (SGM), to comprehensively understand their accuracy, robustness, generalisation capabilities, and their practical potential. The DL methods include a learning-based cost metric through convolutional neural networks (MC-CNN) followed by SGM, and three end-to-end (E2E) learning models using Geometry and Context Network (GCNet), Pyramid Stereo Matching Network (PSMNet), and LEAStereo. Our experiments show that E2E algorithms can achieve upper limits of geometric accuracies, while may not generalise well for unseen data. The learning-based cost metric and Census-SGM are rather robust and can consistently achieve acceptable results. All DL algorithms are robust to geometric configurations of stereopairs and are less sensitive in comparison to the Census-SGM, while learning-based cost metrics can generalise on satellite images when trained on different datasets (airborne or ground-view). Numéro de notice : A2022-938 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/phor.12430 Date de publication en ligne : 09/11/2022 En ligne : https://doi.org/10.1111/phor.12430 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102684 [article]

3D iterative spatiotemporal filtering for classification of multitemporal satellite data sets / Hessah Albanwan in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 1 (January 2020)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 86 n° 1 (January 2020) . - pp 23 - 31 Titre : 3D iterative spatiotemporal filtering for classification of multitemporal satellite data sets Type de document : Article/Communication Auteurs : Hessah Albanwan, Auteur ; Rongjun Qin, Auteur ; Xiaohu Lu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 23 - 31 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de données [Termes IGN] changement d'occupation du sol [Termes IGN] changement d'utilisation du sol [Termes IGN] classification orientée objet [Termes IGN] données multitemporelles [Termes IGN] filtrage spatiotemporel [Termes IGN] image à très haute résolution [Termes IGN] itération [Termes IGN] orthoimage Résumé : (Auteur) The current practice in land cover/land use change analysis relies heavily on the individually classified maps of the multi-temporal data set. Due to varying acquisition conditions (e.g., illumination, sensors, seasonal differences), the classification maps yielded are often inconsistent through time for robust statistical analysis. 3D geometric features have been shown to be stable for assessing differences across the temporal data set. Therefore, in this article we investigate the use of a multi-temporal orthophoto and digital surface model derived from satellite data for spatiotemporal classification. Our approach consists of two major steps: generating per-class probability distribution maps using the random-forest classifier with limited training samples, and making spatiotemporal inferences using an iterative 3D spatiotemporal filter operating on per-class probability maps. Our experimental results demonstrate that the proposed methods can consistently improve the individual classification results by 2%–6% and thus can be an important postclassification refinement approach. Numéro de notice : A2020-049 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.86.1.23 Date de publication en ligne : 01/01/2020 En ligne : https://doi.org/10.14358/PERS.86.1.23 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94534 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2020011	SL	Revue	Centre de documentation	Revues en salle	Disponible