Centre de documentation
scientifique

Étude des outils permettant la classification d’un nuage de points LiDAR aérien et optimisation de la chaîne de traitement dans le cadre du programme national du LiDAR HD in XYZ, n° 179 (juin 2024)

Public [article]  inXYZ > n° 179 (juin 2024) . - pp. 35 - 42 Titre : Étude des outils permettant la classification d’un nuage de points LiDAR aérien et optimisation de la chaîne de traitement dans le cadre du programme national du LiDAR HD Type de document : Article/Communication Année de publication : 2024 Article en page(s) : pp. 35 - 42 Langues : Français (fre) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] classification [Termes IGN] image aérienne [Termes IGN] intelligence artificielle [Termes IGN] Lidar [Termes IGN] semis de points Résumé : Ce travail présente une étude portant sur la classification de nuages de points issus d’une acquisition aérienne, en se concentrant sur les données acquises dans le cadre du projet national LiDAR HD. Il réalise une analyse critique des outils proposés par Terrascan et des méthodes pa- ramétriques qui offrent un bon rapport temps/qualité, mais il subsiste des confusions qui demandent un temps de correction conséquent. De plus, les outils Terrascan sont limités à la classification du sol, des bâtiments et d’une partie de la végétation. Il n’est pas proposé de méthodes efficaces pour classifier des éléments de la classe du sursol pérenne, comme les pylônes électriques ou les éoliennes notamment. Pour y remédier, une autre méthode innovante, basée sur les descripteurs 3D est proposée. Cette méthode offre une meilleure détection des bâtiments et permet, en outre, de classifier des éléments du sursol pérenne. Enfin, il est étudié les synergies entre les différents outils testés. Puis les performances d’une IA sont introduites afin de discuter de l’avenir de la classification des nuages de points aériens. Numéro de notice : A2024-1792 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtSansCL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103658 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
112-2024021	RAB	Revue	Centre de documentation	En réserve L003	Exclu du prêt

Detailed cultural heritage recording produced with traditional methods and laser scanning / Ljubo Lah in Geodetski vestnik, vol 67 n° 4 (December 2023)  

Public [article]  inGeodetski vestnik > vol 67 n° 4 (December 2023) . - pp 442 - 458 Titre : Detailed cultural heritage recording produced with traditional methods and laser scanning Type de document : Article/Communication Auteurs : Ljubo Lah, Auteur ; Alain Guerreau, Auteur ; Mojca K. Fras, Auteur ; Tilen Urbančič, Auteur Année de publication : 2023 Article en page(s) : pp 442 - 458 Note générale : bibliographie Langues : Anglais (eng) Slovène (slv) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] analyse de données [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] église [Termes IGN] matrice orthogonale [Termes IGN] patrimoine culturel [Termes IGN] topométrie de précision Résumé : (auteur) Traditional measurement methods are still widely used for recording cultural heritage objects. On the other hand, geodetic surveying and modern technologies such as 3D laser scanning can provide more accurate, geometrically consistent and extremely detailed data that can be used as a basis for detailed vector maps or 3D models. The main aim of our research was to investigate the complementary approach, using both traditional and modern methods, in order to produce detailed vector maps of the Romanesque church of St. Martin in Chapaize, France, which are essential for further unveiling its historic development. Geometrically, this church is rather extensive and has many irregularities in its shape. Our approach to the documentation process is presented and evaluated in this paper. We applied the Procrustes analysis for the ground floor map, which gave us an objective accuracy assessment. Point clouds of the bell tower acquired by two different laser instruments have also been compared. Numéro de notice : A2023-240 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE/POSITIONNEMENT Nature : Article DOI : 10.15292/geodetski-vestnik.2023.04.442-458 Date de publication en ligne : 01/12/2023 En ligne : https://dx.doi.org/10.15292/geodetski-vestnik.2023.04.442-458 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103603 [article]

A Powerful Correspondence Selection Method for Point Cloud Registration Based on Machine Learning / Wuyong Tao in Photogrammetric Engineering & Remote Sensing, PERS, vol 89 n° 11 (November 2023)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 89 n° 11 (November 2023) . - pp 703 - 712 Titre : A Powerful Correspondence Selection Method for Point Cloud Registration Based on Machine Learning Type de document : Article/Communication Auteurs : Wuyong Tao, Auteur ; Dong Xu, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 703 - 712 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] appariement de points [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] semis de points Résumé : (auteur) Correspondence selection is an indispensable process in point cloud registration. The success of point cloud registration largely depends on a good correspondence selection method. For this purpose, a novel correspondence selection method is proposed in this paper. First, two geometric constraints, one of which is proposed in this paper, are used to compute the compatibility score between two correspondences. Then, the feature vectors of the correspondences are constructed according to the compatibility scores between the correspondence and others. A support vector machine classifier is trained to classify the correct and incorrect correspondences by using the feature vectors. The experimental results demonstrate that our method can choose the right correspondences well and get high precision and F-score performance. Also, our method has the best robustness to noise, pointdensity variation, and partial overlap compared to the other methods. Numéro de notice : A2023-237 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.23-00046R2 En ligne : https://doi.org/10.14358/PERS.23-00046R2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103597 [article]

Flood vulnerability assessment of urban buildings based on integrating high-resolution remote sensing and street view images / Ziyao Xing in Sustainable Cities and Society, vol 92 (May 2023)  

Public [article]  inSustainable Cities and Society > vol 92 (May 2023) . - n° 104467 Titre : Flood vulnerability assessment of urban buildings based on integrating high-resolution remote sensing and street view images Type de document : Article/Communication Auteurs : Ziyao Xing, Auteur ; Shuai Yang, Auteur ; Xuli Zan, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 104467 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] attention (apprentissage automatique) [Termes IGN] bâtiment [Termes IGN] Chine [Termes IGN] gestion des risques [Termes IGN] image Streetview [Termes IGN] inondation [Termes IGN] milieu urbain [Termes IGN] planification urbaine [Termes IGN] Quickbird [Termes IGN] segmentation sémantique [Termes IGN] vulnérabilité Résumé : (auteur) Urban flood risk management requires an extensive investigation of the vulnerability characteristics of buildings. Large-scale field surveys usually cost a lot of time and money, while satellite remote sensing and street view images can provide information on the tops and facades of buildings respectively. Thereupon, this paper develops a building vulnerability assessment framework using remote sensing and street view features. Specifically, a UNet-based semantic segmentation model, FSA-UNet (Fusion-Self-Attention-UNet) is proposed to integrate remote sensing and street view features and the vulnerability information contained in the images is fully exploited. And the building vulnerability index is generated to provide the spatial distribution characteristics of urban building vulnerability. The experiment shows that the mIoU of the proposed model can reach 82% for building vulnerability classification in Hefei, China, which is more accurate than the traditional semantic segmentation models. The results indicate that the integration of street view and remote sensing image features can improve the ability of building vulnerability assessment, and the model proposed in this study can better capture the correlation features of multi-angle images through the self-attention mechanism and combines hierarchy features and edge information to improve the classification effect. This study can support for disaster management and urban planning. Numéro de notice : A2023-152 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.scs.2023.104467 Date de publication en ligne : 23/02/2023 En ligne : https://doi.org/10.1016/j.scs.2023.104467 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102826 [article]

Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks / Sina Mohammadi in ISPRS Journal of photogrammetry and remote sensing, vol 198 (April 2023)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 198 (April 2023) . - pp 272 - 283 Titre : Improvement in crop mapping from satellite image time series by effectively supervising deep neural networks Type de document : Article/Communication Auteurs : Sina Mohammadi, Auteur ; Mariana Belgiu, Auteur ; Alfred Stein, Auteur Année de publication : 2023 Article en page(s) : pp 272 - 283 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] cultures [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-OLI [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] série temporelle Résumé : (auteur) Deep learning methods have achieved promising results in crop mapping using satellite image time series. A challenge still remains on how to better learn discriminative feature representations to detect crop types when the model is applied to unseen data. To address this challenge and reveal the importance of proper supervision of deep neural networks in improving performance, we propose to supervise intermediate layers of a designed 3D Fully Convolutional Neural Network (FCN) by employing two middle supervision methods: Cross-entropy loss Middle Supervision (CE-MidS) and a novel middle supervision method, namely Supervised Contrastive loss Middle Supervision (SupCon-MidS). This method pulls together features belonging to the same class in embedding space, while pushing apart features from different classes. We demonstrate that SupCon-MidS enhances feature discrimination and clustering throughout the network, thereby improving the network performance. In addition, we employ two output supervision methods, namely F1 loss and Intersection Over Union (IOU) loss. Our experiments on identifying corn, soybean, and the class Other from Landsat image time series in the U.S. corn belt show that the best set-up of our method, namely IOU+SupCon-MidS, is able to outperform the state-of-the-art methods by scores of 3.5% and 0.5% on average when testing its accuracy across a different year (local test) and different regions (spatial test), respectively. Further, adding SupCon-MidS to the output supervision methods improves scores by 1.2% and 7.6% on average in local and spatial tests, respectively. We conclude that proper supervision of deep neural networks plays a significant role in improving crop mapping performance. The code and data are available at: https://github.com/Sina-Mohammadi/CropSupervision. Numéro de notice : A2023-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2023.03.007 Date de publication en ligne : 29/03/2023 En ligne : https://doi.org/10.1016/j.isprsjprs.2023.03.007 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103105 [article]

Mapping the walk: A scalable computer vision approach for generating sidewalk network datasets from aerial imagery / Maryam Hosseini in Computers, Environment and Urban Systems, vol 101 (April 2023)  

Permalink

A network-constrained clustering method for bivariate origin-destination movement data / Wenkai Liu in International journal of geographical information science IJGIS, vol 37 n° 4 (April 2023)  

Permalink

Towards global scale segmentation with OpenStreetMap and remote sensing / Munazza Usmani in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 8 (April 2023)  

Permalink

Domain adaptation in segmenting historical maps: A weakly supervised approach through spatial co-occurrence / Sidi Wu in ISPRS Journal of photogrammetry and remote sensing, vol 197 (March 2023)  

Permalink

Point cloud data processing optimization in spectral and spatial dimensions based on multispectral Lidar for urban single-wood extraction / Shuo Shi in ISPRS International journal of geo-information, vol 12 n° 3 (March 2023)  

Permalink

Species distribution modelling under climate change scenarios for maritime pine (Pinus pinaster Aiton) in Portugal / Cristina Alegria in Forests, vol 14 n° 3 (March 2023)  

Permalink

The potential of combining satellite and airborne remote sensing data for habitat classification and monitoring in forest landscapes / Anna Iglseder in International journal of applied Earth observation and geoinformation, vol 117 (March 2023)  

Permalink

A unified attention paradigm for hyperspectral image classification / Qian Liu in IEEE Transactions on geoscience and remote sensing, vol 61 n° 3 (March 2023)  

Permalink

A spatial distribution: Principal component analysis (SD-PCA) model to assess pollution of heavy metals in soil / Jiawei Liu in Science of the total environment, vol 859 n° 1 (February 2023)  

Permalink

Comparative analysis of different CNN models for building segmentation from satellite and UAV images / Batuhan Sariturk in Photogrammetric Engineering & Remote Sensing, PERS, vol 89 n° 2 (February 2023)  

Permalink