Centre de documentation
scientifique

Cliff change detection using siamese KPCONV deep network on 3D point clouds / Iris de Gelis in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-3-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-3-2022 (2022 edition) . - pp 649 - 656 Titre : Cliff change detection using siamese KPCONV deep network on 3D point clouds Type de document : Article/Communication Auteurs : Iris de Gelis, Auteur ; Zoé Bessin, Auteur ; Pauline Letortu, Auteur ; Marion Jaud, Auteur ; C. Delacourt, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 649 - 656 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] détection de changement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] érosion côtière [Termes IGN] falaise [Termes IGN] semis de points [Termes IGN] surveillance géologique Mots-clés libres : KPConv = Kernel Point Convolution Résumé : (auteur) Mainly depending on their lithology, coastal cliffs are prone to changes due to erosion. This erosion could increase due to climate change leading to potential threats for coastal users, assets, or infrastructure. Thus, it is important to be able to understand and characterize cliff face changes at fine scale. Usually, monitoring is conducted thanks to distance computation and manual analysis of each cliff face over 3D point clouds to be able to study 3D dynamics of cliffs. This is time consuming and inclined to each one judgment in particular when dealing with 3D point clouds data. Indeed, 3D point clouds characteristics (sparsity, impossibility of working on a classical top view representation, volume of data, …) make their processing harder than 2D images. Last decades, an increase of performance of machine learning methods for earth observation purposes has been performed. To the best of our knowledge, deep learning has never been used for 3D change detection and categorization in coastal cliffs. Lately, Siamese KPConv brings successful results for change detection and categorization into 3D point clouds in urban area. Although the case study is different by its more random characteristics and its complex geometry, we demonstrate here that this method also allows to extract and categorize changes on coastal cliff face. Results over the study area of Petit Ailly cliffs in Varengeville-sur-Mer (France) are very promising qualitatively as well as quantitatively: erosion is retrieved with an intersection over union score of 83.86 %. Numéro de notice : A2022-444 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.5194/isprs-annals-V-3-2022-649-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-3-2022-649-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100779 [article]

Spatial analysis of coastal chalk cliff falls in upper Normandy (France). From Veules-les-Roses to Le Treport (2002-2009) / Pauline Letortu in Revue internationale de géomatique, vol 24 n° 3 (septembre - novembre 2014)  

Public [article]  inRevue internationale de géomatique > vol 24 n° 3 (septembre - novembre 2014) . - pp 335 - 354 Titre : Spatial analysis of coastal chalk cliff falls in upper Normandy (France). From Veules-les-Roses to Le Treport (2002-2009) Type de document : Article/Communication Auteurs : Pauline Letortu, Auteur ; Stéphane Costa, Auteur ; Emmanuel Bonnet, Auteur Année de publication : 2014 Article en page(s) : pp 335 - 354 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] base de données localisées [Termes IGN] cartographie des risques [Termes IGN] craie [Termes IGN] données spatiotemporelles [Termes IGN] éboulement [Termes IGN] estimation par noyau [Termes IGN] falaise [Termes IGN] Haute-Normandie [Termes IGN] inventaire [Termes IGN] prévention des risques Résumé : (Auteur) Coastal chalk cliff falls in Upper Normandy (France) are frequent and have specific spatial and temporal distributions. From 2002 to 2009, the ESTRAN organization (Scientific and Technical Space of Aquatic Resources and Navigation) conducted a weekly inventory of 331 cliff falls (location, volume, and date) between Veules-les-Roses and Le Treport (37.5 km). An amount of 331 falls was counted (date, location, measures of fall deposit). This database is remarkable because of the duration and high frequency of field surveys. The geographical and spatial statistics (locational analysis) methods used in this study aim to determine and understand the spatial and temporal distributions of coastal chalk cliff falls. Exhaustive cartography of such falls thus highlights the cap d’Ailly sector as being the most sensitive to an erosive dynamic along the coast from Veules-les-Roses to Le Treport. Furthermore, this cartography stresses many types of fall kinematics. This can be partly explained by lithological characteristics may predispose mass and particle movements. Using the combination of centrographic statistics, Ripley’s K-function, Besag’s L-function and kernel density, we have identified: 1) high cliff fall polarization at cap d’Ailly; 2) organization scales of fall locations per water year; 3) areas of massive and numerous falls (fall hazard areas). This information is essential for a better understanding of the working of the studied area and also for the set up of risk prevention tools. Numéro de notice : A2014-519 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.3166/rig.24.335-354 En ligne : https://doi.org/10.3166/rig.24.335-354 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74126 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
047-2014031	RAB	Revue	Centre de documentation	En réserve L003	Disponible