Centre de documentation
scientifique

Large-scale supervised learning for 3D Point cloud labeling : Semantic3d.Net / Timo Hackel in Photogrammetric Engineering & Remote Sensing, PERS, vol 84 n° 5 (mai 2018)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 84 n° 5 (mai 2018) . - pp 297 - 308 Titre : Large-scale supervised learning for 3D Point cloud labeling : Semantic3d.Net Type de document : Article/Communication Auteurs : Timo Hackel, Auteur ; Jan Dirk Wegner, Auteur ; Nikolay Savinov, Auteur ; Lubor Ladicky, Auteur ; Konrad Schindler, Auteur ; Marc Pollefeys, Auteur Année de publication : 2018 Article en page(s) : pp 297 - 308 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] classification [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] état de l'art [Termes IGN] réseau neuronal convolutif [Termes IGN] scène urbaine [Termes IGN] segmentation sémantique [Termes IGN] semis de points Résumé : (Auteur) In this paper, we review current state-of-the-art in 3D point cloud classification, present a new 3D point cloud classification benchmark data set of single scans with over four billion manually labeled points, and discuss first available results on the benchmark. Much of the stunning recent progress in 2D image interpretation can be attributed to the availability of large amounts of training data, which have enabled the (supervised) learning of deep neural networks. With the data set presented in this paper, we aim to boost the performance of CNNs also for 3D point cloud labeling. Our hope is that this will lead to a breakthrough of deep learning also for 3D (geo-) data. The semantic3D.net data set consists of dense point clouds acquired with static terrestrial laser scanners. It contains eight semantic classes and covers a wide range of urban outdoor scenes, including churches, streets, railroad tracks, squares, villages, soccer fields, and castles. We describe our labeling interface and show that, compared to those already available to the research community, our data set provides denser and more complete point clouds, with a much higher overall number of labeled points. We further provide descriptions of baseline methods and of the first independent submissions, which are indeed based on CNNs, and already show remarkable improvements over prior art. We hope that semantic3D.net will pave the way for deep learning in 3D point cloud analysis, and for 3D representation learning in general. Numéro de notice : A2018-162 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.84.5.297 Date de publication en ligne : 01/05/2018 En ligne : https://doi.org/10.14358/PERS.84.5.297 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=89795 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2018051	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Fusing meter-resolution 4-D InSAR point clouds and optical images for semantic urban infrastructure monitoring / Yuanyuan Wang in IEEE Transactions on geoscience and remote sensing, vol 55 n° 1 (January 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 1 (January 2017) . - pp 14 - 26 Titre : Fusing meter-resolution 4-D InSAR point clouds and optical images for semantic urban infrastructure monitoring Type de document : Article/Communication Auteurs : Yuanyuan Wang, Auteur ; Xiao Xiang Zhu, Auteur ; Bernhard Zeisl, Auteur ; Marc Pollefeys, Auteur Année de publication : 2017 Article en page(s) : pp 14 - 26 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes IGN] données 4D [Termes IGN] fusion d'images [Termes IGN] géométrie de l'image [Termes IGN] image à résolution métrique [Termes IGN] image optique [Termes IGN] image radar moirée [Termes IGN] pont [Termes IGN] semis de points [Termes IGN] surveillance d'ouvrage [Termes IGN] voie ferrée [Termes IGN] zone urbaine Résumé : (Auteur) Using synthetic aperture radar (SAR) interferometry to monitor long-term millimeter-level deformation of urban infrastructures, such as individual buildings and bridges, is an emerging and important field in remote sensing. In the state-of-the-art methods, deformation parameters are retrieved and monitored on a pixel basis solely in the SAR image domain. However, the inevitable side-looking imaging geometry of SAR results in undesired occlusion and layover in urban area, rendering the current method less competent for a semantic-level monitoring of different urban infrastructures. This paper presents a framework of a semantic-level deformation monitoring by linking the precise deformation estimates of SAR interferometry and the semantic classification labels of optical images via a 3-D geometric fusion and semantic texturing. The proposed approach provides the first “SARptical” point cloud of an urban area, which is the SAR tomography point cloud textured with attributes from optical images. This opens a new perspective of InSAR deformation monitoring. Interesting examples on bridge and railway monitoring are demonstrated. Numéro de notice : A2017-018 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2554563 En ligne : https://doi.org/10.1109/TGRS.2016.2554563 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83949 [article]

Fast robust large-scale mapping from video and internet photo collections / J. Frahm in ISPRS Journal of photogrammetry and remote sensing, vol 65 n° 6 (November - December 2010)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 65 n° 6 (November - December 2010) . - pp 538 - 549 Titre : Fast robust large-scale mapping from video and internet photo collections Type de document : Article/Communication Auteurs : J. Frahm, Auteur ; Marc Pollefeys, Auteur ; S. Lazebnik, Auteur ; D. Gallup, Auteur ; B. Clipp, Auteur ; et al., Auteur Année de publication : 2010 Article en page(s) : pp 538 - 549 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] grande échelle [Termes IGN] image vidéo [Termes IGN] modélisation 3D [Termes IGN] photographie numérique [Termes IGN] reconnaissance automatique [Termes IGN] reconstruction 3D [Termes IGN] séquence d'images Résumé : (Auteur) This paper presents a system approaching fully automatic 3D modeling of large-scale environments. Our system takes as input either a video stream or collection of photographs obtained from Internet photo sharing web-sites such as Flickr. The system achieves high computational performance through algorithmic optimizations for efficient robust estimation, the use of image-based recognition for efficient grouping of similar images, and two-stage stereo estimation for video streams that reduces the computational cost while maintaining competitive modeling results. In addition to algorithmic advances, we achieve a major improvement in computational speed through parallelization and execution on commodity graphics hardware. These improvements lead to real-time video processing and to reconstruction from tens of thousands of images within the span of a day on a single commodity computer. We demonstrate modeling results on a variety of real-world video sequences and photo collections. Numéro de notice : A2010-486 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2010.08.009 En ligne : https://doi.org/10.1016/j.isprsjprs.2010.08.009 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30679 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2010061	SL	Revue	Centre de documentation	Revues en salle	Disponible

Virtualising the 3D real world: automatic method for the acquisition of detailed 3D models from image sequences / Marc Pollefeys in GIM international, vol 14 n° 4 (April 2000)

Public [article]  inGIM international > vol 14 n° 4 (April 2000) . - 3 p. ; pp 12 - 15 Titre : Virtualising the 3D real world: automatic method for the acquisition of detailed 3D models from image sequences Type de document : Article/Communication Auteurs : Marc Pollefeys, Auteur ; Luc Van Gool, Auteur Année de publication : 2000 Article en page(s) : 3 p. ; pp 12 - 15 Note générale : Bibliographie 3 ref Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] étalonnage d'instrument [Termes IGN] langage de modélisation [Termes IGN] modélisation 3D [Termes IGN] photogrammétrie numérique [Termes IGN] visualisation 3D Résumé : (Auteur) The author propose an approach to automatic recovery of a realistic 3D surface from photos or videos. There is no need whatsoever for measurements in the scene or calibration procedures. It is just as easy to model a small object (using a macro lens), as to model a complete building or even a whole landscape. The method thus offers a previously unknown flexilbility in 3D model acquisition, accompanied by a decrease in cost. This flexibility opens the way to many new applications. Copyright GITC Numéro de notice : A2000-053 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=21473 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
061-00041	RAB	Revue	Centre de documentation	En réserve L003	Disponible