Centre dedocumentation
scientifique

A survey and benchmark of automatic surface reconstruction from point clouds / Raphaël Sulzer (2023)  

Public Titre : A survey and benchmark of automatic surface reconstruction from point clouds Type de document : Article/Communication Auteurs : Raphaël Sulzer , Auteur ; Loïc Landrieu , Auteur ; Renaud Marlet, Auteur ; Bruno Vallet , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2023 Projets : BIOM / Vallet, Bruno Importance : 24 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] benchmark spatial [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] reconstruction d'objet [Termes IGN] semis de points Résumé : (auteur) We survey and benchmark traditional and novel learning-based algorithms that address the problem of surface reconstruction from point clouds. Surface reconstruction from point clouds is particularly challenging when applied to real-world acquisitions, due to noise, outliers, non-uniform sampling and missing data. Traditionally, different handcrafted priors of the input points or the output surface have been proposed to make the problem more tractable. However, hyperparameter tuning for adjusting priors to different acquisition defects can be a tedious task. To this end, the deep learning community has recently addressed the surface reconstruction problem. In contrast to traditional approaches, deep surface reconstruction methods can learn priors directly from a training set of point clouds and corresponding true surfaces. In our survey, we detail how different handcrafted and learned priors affect the robustness of methods to defect-laden input and their capability to generate geometric and topologically accurate reconstructions. In our benchmark, we evaluate the reconstructions of several traditional and learning-based methods on the same grounds. We show that learning-based methods can generalize to unseen shape categories, but their training and test sets must share the same point cloud characteristics. We also provide the code and data to compete in our benchmark and to further stimulate the development of learning-based surface reconstruction: https://github.com/raphaelsulzer/dsr-benchmark. Numéro de notice : P2023-004 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers ArXiv Thématique : IMAGERIE/INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.2301.13656 Date de publication en ligne : 31/01/2023 En ligne : https://hal.science/hal-03968453 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102847

A Voronoi-based method for land-use optimization using semidefinite programming and gradient descent algorithm / Vorapong Suppakitpaisarn in International journal of geographical information science IJGIS, vol 35 n° 5 (May 2021)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 35 n° 5 (May 2021) . - pp 999 - 1031 Titre : A Voronoi-based method for land-use optimization using semidefinite programming and gradient descent algorithm Type de document : Article/Communication Auteurs : Vorapong Suppakitpaisarn, Auteur ; Atthaphon Ariyarit, Auteur ; Supanut Chaidee, Auteur Année de publication : 2021 Article en page(s) : pp 999 - 1031 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] algorithme du gradient [Termes IGN] algorithme génétique [Termes IGN] benchmark spatial [Termes IGN] diagramme de Voronoï [Termes IGN] mode d'occupation du sol [Termes IGN] Thaïlande [Termes IGN] utilisation du sol Résumé : (Auteur) The land-use optimization involves divisions of land into subregions to obtain spatial configuration of compact subregions and desired connections among them. Computational geometry-based algorithms, such as Voronoi diagram, are known to be efficient and suitable for iterative design processes to achieve land-use optimization. However, such algorithms assume that generating point positions are given as inputs, while we usually do not know the positions in advance. In this study, we propose a method to automatically calculate the suitable point positions. The method uses (1) semidefinite programming to approximate locations while maintaining relative positions among locations; and (2) gradient descent to iteratively update locations subject to area constraints. We apply the proposed framework to a practical case at Chiang Mai University and compare its performance with a benchmark, the differential genetic algorithm. The results show that the proposed method is 28 times faster than the differential genetic algorithm, while the resulting land allocation error is slightly larger than that of the benchmark but still acceptable. Additionally, the output does not contain disconnected areas, as found in all evolutionary computations, and the compactness is almost equal to the maximum possible value. Numéro de notice : A2021-336 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2020.1841203 Date de publication en ligne : 23/11/2020 En ligne : https://doi.org/10.1080/13658816.2020.1841203 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97555 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2021051	SL	Revue	Centre de documentation	Revues en salle	Disponible

PPD: Pyramid Patch Descriptor via convolutional neural network / Jie Wan in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 9 (September 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 9 (September 2019) . - pp 673 - 686 Titre : PPD: Pyramid Patch Descriptor via convolutional neural network Type de document : Article/Communication Auteurs : Jie Wan, Auteur ; Alper Yilmaz, Auteur ; Lei Yan, Auteur Année de publication : 2019 Article en page(s) : pp 673 - 686 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] benchmark spatial [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données localisées de référence [Termes IGN] échantillonnage d'image [Termes IGN] état de l'art [Termes IGN] extraction de données [Termes IGN] image aérienne [Termes IGN] image satellite [Termes IGN] jeu de données localisées Résumé : (Auteur) Local features play an important role in remote sensing image matching, and handcrafted features have been excessively used in this area for a long time. This article proposes a pyramid convolutional neural triplet network that extracts a 128-dimensional deep descriptor that significantly improves the matching performance. The proposed approach first extracts deep descriptors of the anchor patches and corresponding positive patches in a batch using the proposed pyramid convolutional neural network. Following this step, the approaches chooses the closest negative patch for each anchor patch and corresponding positive patch pair to form the triplet sample based on the descriptor distances among all other image patches in the batch. These triplets are used to optimize the parameters of the network using a new loss function. We evaluated the proposed deep descriptors on two benchmark data sets (Brown and HPatches) as well as real image data sets. The results reveal that the proposed descriptor achieves the state-of-the-art performance on the Brown data set and a comparatively very high performance on the HPatches data set. The proposed approach finds more correct matches than the classical handcrafted feature descriptors on aerial image pairs and is observed to be robust to variations in the viewpoint and illumination. Numéro de notice : A2019-416 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.9.673 Date de publication en ligne : 01/09/2019 En ligne : https://doi.org/10.14358/PERS.85.9.673 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93543 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019091	SL	Revue	Centre de documentation	Revues en salle	Disponible

International benchmarking of terrestrial laser scanning approaches for forest inventories / Xinlian Liang in ISPRS Journal of photogrammetry and remote sensing, vol 144 (October 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 144 (October 2018) . - pp 137 - 179 Titre : International benchmarking of terrestrial laser scanning approaches for forest inventories Type de document : Article/Communication Auteurs : Xinlian Liang, Auteur ; Juha Hyyppä, Auteur ; Harri Kaartinen, Auteur ; Matti Lehtomäki, Auteur ; Jiri Pyorala, Auteur ; Norbert Pfeifer, Auteur ; Markus Holopainen, Auteur ; Gabor Brolly, Auteur ; Francesco Pirotti, Auteur ; Jan Hackenberg , Auteur Année de publication : 2018 Projets : DIABOLO / Packalen, Tuula Article en page(s) : pp 137 - 179 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] algorithmique [Termes IGN] benchmark spatial [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] état de l'art [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] lasergrammétrie [Termes IGN] semis de points [Vedettes matières IGN] Inventaire forestier Résumé : (Auteur) The last two decades have witnessed increasing awareness of the potential of terrestrial laser scanning (TLS) in forest applications in both public and commercial sectors, along with tremendous research efforts and progress. It is time to inspect the achievements of and the remaining barriers to TLS-based forest investigations, so further research and application are clearly orientated in operational uses of TLS. In such context, the international TLS benchmarking project was launched in 2014 by the European Spatial Data Research Organization and coordinated by the Finnish Geospatial Research Institute. The main objectives of this benchmarking study are to evaluate the potential of applying TLS in characterizing forests, to clarify the strengths and the weaknesses of TLS as a measure of forest digitization, and to reveal the capability of recent algorithms for tree-attribute extraction. The project is designed to benchmark the TLS algorithms by processing identical TLS datasets for a standardized set of forest attribute criteria and by evaluating the results through a common procedure respecting reliable references. Benchmarking results reflect large variances in estimating accuracies, which were unveiled through the 18 compared algorithms and through the evaluation framework, i.e., forest complexity categories, TLS data acquisition approaches, tree attributes and evaluation procedures. The evaluation framework includes three new criteria proposed in this benchmarking and the algorithm performances are investigated through combining two or more criteria (e.g., the accuracy of the individual tree attributes are inspected in conjunction with plot-level completeness) in order to reveal algorithms’ overall performance. The results also reveal some best available forest attribute estimates at this time, which clarify the status quo of TLS-based forest investigations. Some results are well expected, while some are new, e.g., the variances of estimating accuracies between single-/multi-scan, the principle of the algorithm designs and the possibility of a computer outperforming human operation. With single-scan data, i.e., one hemispherical scan per plot, most of the recent algorithms are capable of achieving stem detection with approximately 75% completeness and 90% correctness in the easy forest stands (easy plots: 600 stems/ha, 20 cm mean DBH). The detection rate decreases when the stem density increases and the average DBH decreases, i.e., 60% completeness with 90% correctness (medium plots: 1000 stem/ha, 15 cm mean DBH) and 30% completeness with 90% correctness (difficult plots: 2000 stems/ha, 10 cm mean DBH). The application of the multi-scan approach, i.e., five scans per plot at the center and four quadrant angles, is more effective in complex stands, increasing the completeness to approximately 90% for medium plots and to approximately 70% for difficult plots, with almost 100% correctness. The results of this benchmarking also show that the TLS-based approaches can provide the estimates of the DBH and the stem curve at a 1–2 cm accuracy that are close to what is required in practical applications, e.g., national forest inventories (NFIs). In terms of algorithm development, a high level of automation is a commonly shared standard, but a bottleneck occurs at stem detection and tree height estimation, especially in multilayer and dense forest stands. The greatest challenge is that even with the multi-scan approach, it is still hard to completely and accurately record stems of all trees in a plot due to the occlusion effects of the trees and bushes in forests. Future development must address the redundant yet incomplete point clouds of forest sample plots and recognize trees more accurately and efficiently. It is worth noting that TLS currently provides the best quality terrestrial point clouds in comparison with all other technologies, meaning that all the benchmarks labeled in this paper can also serve as a reference for other terrestrial point clouds sources. Numéro de notice : A2018-400 Affiliation des auteurs : LIF+Ext (2012-2019) Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.06.021 Date de publication en ligne : 24/07/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.06.021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90829 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018101	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2018103	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2018102	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

A deep learning approach to DTM extraction from imagery using rule-based training labels / Caroline M. Gevaert in ISPRS Journal of photogrammetry and remote sensing, vol 142 (August 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 142 (August 2018) . - pp 106 - 123 Titre : A deep learning approach to DTM extraction from imagery using rule-based training labels Type de document : Article/Communication Auteurs : Caroline M. Gevaert, Auteur ; Claudio Persello, Auteur ; M. George Vosselman, Auteur Année de publication : 2018 Article en page(s) : pp 106 - 123 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] base de règles [Termes IGN] benchmark spatial [Termes IGN] Dar-es-Salam (Tanzanie) [Termes IGN] drone [Termes IGN] échantillonnage d'image [Termes IGN] extraction automatique [Termes IGN] Kigali (Rwanda) [Termes IGN] Lombardie [Termes IGN] modèle numérique de terrain [Termes IGN] photogrammétrie aérienne [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Existing algorithms for Digital Terrain Model (DTM) extraction still face difficulties due to data outliers and geometric ambiguities in the scene such as contiguous off-ground areas or sloped environments. We postulate that in such challenging cases, the radiometric information contained in aerial imagery may be leveraged to distinguish between ground and off-ground objects. We propose a method for DTM extraction from imagery which first applies morphological filters to the Digital Surface Model to obtain candidate ground and off-ground training samples. These samples are used to train a Fully Convolutional Network (FCN) in the second step, which can then be used to identify ground samples for the entire dataset. The proposed method harnesses the power of state-of-the-art deep learning methods, while showing how they can be adapted to the application of DTM extraction by (i) automatically selecting and labelling dataset-specific samples which can be used to train the network, and (ii) adapting the network architecture to consider a larger surface area without unnecessarily increasing the computational burden. The method is successfully tested on four datasets, indicating that the automatic labelling strategy can achieve an accuracy which is comparable to the use of manually labelled training samples. Furthermore, we demonstrate that the proposed method outperforms two reference DTM extraction algorithms in challenging areas. Numéro de notice : A2018-298 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.06.001 Date de publication en ligne : 15/06/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.06.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90410 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018081	RAB	Revue	Centre de documentation	En réserve L003	Disponible
081-2018083	DEP-EXM	Revue	LASTIG	Dépôt en unité	Exclu du prêt
081-2018082	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Study of a wide-angle laser ranging system for relative positioning of ground-based benchmarks with millimeter accuracy / Olivier Bock in Journal of geodesy, vol 72 n° 7-8 (July - August 1998)  

Permalink

Spécification d'un benchmark spatial / V. Oria in Revue internationale de géomatique, vol 7 n° 2 (juin – août 1997)

Permalink