Centre de documentation
scientifique

Fast weakly supervised detection of railway-related infrastructures in lidar acquisitions / Stéphane Guinard in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2021 (July 2021)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2021 (July 2021) . - pp 27 - 34 Titre : Fast weakly supervised detection of railway-related infrastructures in lidar acquisitions Type de document : Article/Communication Auteurs : Stéphane Guinard , Auteur ; Jean-Philippe Riant, Auteur ; Jean-Christophe Michelin , Auteur ; Sofia Costa d’Aguiar, Auteur Année de publication : 2021 Conférence : ISPRS 2021, Commission 2, 24th ISPRS Congress, Imaging today foreseeing tomorrow 05/07/2021 09/07/2021 Nice Virtuel France OA Annals Commission 2 Article en page(s) : pp 27 - 34 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] algorithme Cut Pursuit [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] réseau ferroviaire [Termes IGN] segmentation Résumé : (auteur) Railroad environments are peculiar, as they combine dense urban areas, along with rural parts. They also display a very specific spatial organization. In order to monitor a railway network a at country scale, LiDAR sensors can be equipped on a running train, performing a full acquisition of the network. Then most processing steps are manually done. In this paper, we propose to improve performances and production flow by creating a classification of the acquired data. However, there exists no public benchmark, and little work on LiDAR data classification in railroad environments. Thus, we propose a weakly supervised method for the pointwise classification of such data. We show that our method can be improved by using the l0-cut pursuit algorithm and regularize the noisy pointwise classification on the produced segmentation. As production is envisaged in our context, we designed our implementation such that it is computationally efficient. We evaluate our results against a manual classification, and show that our method can reach a FScore of 0.96 with just a few samples of each class. Numéro de notice : A2021-615 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.5194/isprs-annals-V-2-2021-27-2021 Date de publication en ligne : 17/06/2021 En ligne : http://dx.doi.org/10.5194/isprs-annals-V-2-2021-27-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97953 [article]