Descripteur
Documents disponibles dans cette catégorie (1084)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Weakly supervised semantic segmentation of airborne laser scanning point clouds / Yaping Lin in ISPRS Journal of photogrammetry and remote sensing, vol 187 (May 2022)
[article]
Titre : Weakly supervised semantic segmentation of airborne laser scanning point clouds Type de document : Article/Communication Auteurs : Yaping Lin, Auteur ; M. George Vosselman, Auteur ; Michael Ying Yang, Auteur Année de publication : 2022 Article en page(s) : pp 79 - 100 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] apprentissage profond
[Termes IGN] chevauchement
[Termes IGN] classification dirigée
[Termes IGN] données étiquetées d'entrainement
[Termes IGN] données laser
[Termes IGN] données localisées 3D
[Termes IGN] hétérogénéité sémantique
[Termes IGN] segmentation sémantique
[Termes IGN] semis de pointsRésumé : (Auteur) While modern deep learning algorithms for semantic segmentation of airborne laser scanning (ALS) point clouds have achieved considerable success, the training process often requires a large number of labelled 3D points. Pointwise annotation of 3D point clouds, especially for large scale ALS datasets, is extremely time-consuming work. Weak supervision that only needs a few annotation efforts but can make networks achieve comparable performance is an alternative solution. Assigning a weak label to a subcloud, a group of points, is an efficient annotation strategy. With the supervision of subcloud labels, we first train a classification network that produces pseudo labels for the training data. Then the pseudo labels are taken as the input of a segmentation network which gives the final predictions on the testing data. As the quality of pseudo labels determines the performance of the segmentation network on testing data, we propose an overlap region loss and an elevation attention unit for the classification network to obtain more accurate pseudo labels. The overlap region loss that considers the nearby subcloud semantic information is introduced to enhance the awareness of the semantic heterogeneity within a subcloud. The elevation attention helps the classification network to encode more representative features for ALS point clouds. For the segmentation network, in order to effectively learn representative features from inaccurate pseudo labels, we adopt a supervised contrastive loss that uncovers the underlying correlations of class-specific features. Extensive experiments on three ALS datasets demonstrate the superior performance of our model to the baseline method (Wei et al., 2020). With the same amount of labelling efforts, for the ISPRS benchmark dataset, the Rotterdam dataset and the DFC2019 dataset, our method rises the overall accuracy by 0.062, 0.112 and 0.031, and the average F1 score by 0.09, 0.178 and 0.043 respectively. Our code is publicly available at ‘https://github.com/yaping222/Weak_ALS.git’. Numéro de notice : A2022-227 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.03.001 Date de publication en ligne : 11/03/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.03.001 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100197
in ISPRS Journal of photogrammetry and remote sensing > vol 187 (May 2022) . - pp 79 - 100[article]Exemplaires(3)
Code-barres Cote Support Localisation Section Disponibilité 081-2022051 SL Revue Centre de documentation Revues en salle Disponible 081-2022053 DEP-RECP Revue LASTIG Dépôt en unité Exclu du prêt 081-2022052 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt Assessing surface drainage conditions at the street and neighborhood scale: A computer vision and flow direction method applied to lidar data / Cheng-Chun Lee in Computers, Environment and Urban Systems, vol 93 (April 2022)
[article]
Titre : Assessing surface drainage conditions at the street and neighborhood scale: A computer vision and flow direction method applied to lidar data Type de document : Article/Communication Auteurs : Cheng-Chun Lee, Auteur ; Nasir G. Gharaibeh, Auteur Année de publication : 2022 Article en page(s) : n° 101755 Note générale : bibliogrphie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] drainage
[Termes IGN] écoulement des eaux
[Termes IGN] Houston (Texas)
[Termes IGN] inondation
[Termes IGN] lidar mobile
[Termes IGN] modèle numérique de surface
[Termes IGN] ruissellement
[Termes IGN] segmentation sémantiqueRésumé : (auteur) Surface drainage at the neighborhood and street scales plays an important role in conveying stormwater and mitigating urban flooding. Surface drainage at the local scale is often ignored due to the lack of up-to-date fine-scale topographical information. This paper addresses this issue by providing a novel method for evaluating surface drainage at the neighborhood and street scales based on mobile lidar (light detection and ranging) measurements. The developed method derives topographical properties and runoff accumulation by applying a semantic segmentation (SS) model (a computer vision technique) and a flow direction model (a hydrology technique) to lidar data. Fifty lidar images representing 50 street blocks were used to train, validate, and test the SS model. Based on the test dataset, the SS model has 80.3% IoU and 88.5% accuracy. The results suggest that the proposed method can effectively evaluate surface drainage conditions at both the neighborhood and street scales and identify problematic low points that could be susceptible to water ponding. Municipalities and property owners can use this information to take targeted corrective maintenance actions. Numéro de notice : A2022-120 Affiliation des auteurs : non IGN Thématique : IMAGERIE/URBANISME Nature : Article DOI : 10.1016/j.compenvurbsys.2021.101755 Date de publication en ligne : 13/01/2022 En ligne : https://doi.org/10.1016/j.compenvurbsys.2021.101755 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99661
in Computers, Environment and Urban Systems > vol 93 (April 2022) . - n° 101755[article]Characterizing stream morphological features important for fish habitat using airborne laser scanning data / Spencer Dakin Kuiper in Remote sensing of environment, vol 272 (April 2022)
[article]
Titre : Characterizing stream morphological features important for fish habitat using airborne laser scanning data Type de document : Article/Communication Auteurs : Spencer Dakin Kuiper, Auteur ; Nicholas C. Coops, Auteur ; Piotr Tompalski, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112948 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] bassin hydrographique
[Termes IGN] cours d'eau
[Termes IGN] données de terrain
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] écosystème forestier
[Termes IGN] forêt ripicole
[Termes IGN] géomorphologie locale
[Termes IGN] gestion forestière durable
[Termes IGN] habitat animal
[Termes IGN] modèle numérique de surface
[Termes IGN] poisson (faune aquatique)
[Termes IGN] semis de points
[Termes IGN] structure d'un peuplement forestier
[Termes IGN] Vancouver (Colombie britannique)Résumé : (auteur) Understanding changes in salmonid populations and their habitat is a critical issue given changing climate, their importance as a keystone species, and their cultural significance. Terrain features such as slope, gradient, and morphology, as well as forest structure attributes including canopy cover, height, and presence of on ground coarse wood, all influence the quality and quantity of salmonid habitat in forested ecosystems. The increasing availability of Airborne Laser Scanning (ALS) data for forest applications offers an opportunity to utilize these data for assessing the quality and quantity of habitat, which is often costly and difficult to characterize. ALS data provides detailed and accurate Digital Elevation Models (DEMs) under forest canopies, which in turn enable the characterization of detailed stream networks, as well as stream and terrain attributes important to salmonids. At the Nahmint watershed on Vancouver Island, British Columbia, Canada, we sampled six, 200 m long stream reaches, describing a range of terrain and stream features following standard data collection protocols. Our objective in this research was to use ALS data to estimate three attributes from the 3D point cloud and DEM that are known to be important for salmonids, including bankfull width,instream wood and discrete stream morphological units. Results indicate that ALS-based estimates had strong, significant, correlations with field-measured attributes (with Pearson's correlation of 0.80 and 0.81 for bankfull width and instream wood, respectively). Bankfull width was slightly underestimated using the ALS data (Bias = −1.01 m; MAD = 1.89 m; RMSD = 2.05 m) and 80% of instream wood pieces were detected. Using ALS-derived predictors in a Random Forest model, discrete stream morphological units (i.e. pools, riffles, glides, cascades) were classified with an overall accuracy of 85%, with pools having the highest user's class accuracy at 96%. Results presented herein indicate that ALS data can be used to provide a fine scale characterization of stream attributes that are required to identify salmonid habitat, providing critical information for sustainable forest management decision making, and providing a foundation for advanced salmonid habitat modeling. Numéro de notice : A2022-283 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2022.112948 Date de publication en ligne : 24/02/2022 En ligne : https://doi.org/10.1016/j.rse.2022.112948 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100301
in Remote sensing of environment > vol 272 (April 2022) . - n° 112948[article]Comparison of neural networks and k-nearest neighbors methods in forest stand variable estimation using airborne laser data / Andras Balazs in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 4 (April 2022)
[article]
Titre : Comparison of neural networks and k-nearest neighbors methods in forest stand variable estimation using airborne laser data Type de document : Article/Communication Auteurs : Andras Balazs, Auteur ; Eero Liski, Auteur ; Sakari Tuominen, Auteur Année de publication : 2022 Article en page(s) : n° 100012 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] algorithme génétique
[Termes IGN] bois sur pied
[Termes IGN] classification barycentrique
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] covariance
[Termes IGN] diamètre à hauteur de poitrine
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] Finlande
[Termes IGN] hauteur des arbres
[Termes IGN] inventaire forestier étranger (données)
[Termes IGN] peuplement forestier
[Termes IGN] réseau neuronal artificiel
[Termes IGN] semis de points
[Termes IGN] volume en boisRésumé : (auteur) In the remote sensing of forests, point cloud data from airborne laser scanning contains high-value information for predicting the volume of growing stock and the size of trees. At the same time, laser scanning data allows a very high number of potential features that can be extracted from the point cloud data for predicting the forest variables. In some methods, the features are first extracted by user-defined algorithms and the best features are selected based on supervised learning, whereas both tasks can be carried out automatically by deep learning methods typically based on deep neural networks. In this study we tested k-nearest neighbor method combined with genetic algorithm (k-NN), artificial neural network (ANN), 2-dimensional convolutional neural network (2D-CNN) and 3-dimensional CNN (3D-CNN) for estimating the following forest variables: volume of growing stock, stand mean height and mean diameter. The results indicate that there were no major differences in the accuracy of the tested methods, but the ANN and 3D-CNN generally resulted in the lowest RMSE values for the predicted forest variables and the highest R2 values between the predicted and observed forest variables. The lowest RMSE scores were 20.3% (3D-CNN), 6.4% (3D-CNN) and 11.2% (ANN) and the highest R2 results 0.90 (3D-CNN), 0.95 (3D-CNN) and 0.85 (ANN) for volume of growing stock, stand mean height and mean diameter, respectively. Covariances of all response variable combinations and all predictions methods were lower than corresponding covariances of the field observations. ANN predictions had the highest covariances for mean height vs. mean diameter and total growing stock vs. mean diameter combinations and 3D-CNN for mean height vs. total growing stock. CNNs have distinct theoretical advantage over the other methods in complex recognition or classification tasks, but the utilization of their full potential may possibly require higher point density clouds than applied here. Thus, the relatively low density of the point clouds data may have been a contributing factor to the somewhat inconclusive ranking of the methods in this study. The input data and computer codes are available at: https://github.com/balazsan/ALS_NNs. Numéro de notice : A2022-265 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.ophoto.2022.100012 Date de publication en ligne : 12/03/2022 En ligne : https://doi.org/10.1016/j.ophoto.2022.100012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100263
in ISPRS Open Journal of Photogrammetry and Remote Sensing > vol 4 (April 2022) . - n° 100012[article]Data assimilation of growing stock volume using a sequence of remote sensing data from different sensors / Niels Lindgren in Canadian journal of remote sensing, vol 48 n° 2 (April 2022)
[article]
Titre : Data assimilation of growing stock volume using a sequence of remote sensing data from different sensors Titre original : Assimilation de données de volume de bois à l’aide d’une séquence de données de télédétection provenant de différents capteurs Type de document : Article/Communication Auteurs : Niels Lindgren, Auteur ; Hakan Olsson, Auteur ; Kenneth Nyström, Auteur ; Mattias Nyström, Auteur ; Göran Stahl, Auteur Année de publication : 2022 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] Betula (genre)
[Termes IGN] capital sur pied
[Termes IGN] données lidar
[Termes IGN] données localisées 3D
[Termes IGN] étalonnage des données
[Termes IGN] filtre de Kalman
[Termes IGN] forêt boréale
[Termes IGN] Picea abies
[Termes IGN] Pinus sylvestris
[Termes IGN] Quercus (genre)
[Termes IGN] Suède
[Termes IGN] volume en boisRésumé : (auteur) Airborne Laser Scanning (ALS) has implied a disruptive transformation of how data are gathered for forest management planning in Nordic countries. We show in this study that the accuracy of ALS predictions of growing stock volume can be maintained and even improved over time if they are forecasted and assimilated with more frequent but less accurate remote sensing data sources like satellite images, digital photogrammetry, and InSAR. We obtained these results by introducing important methodological adaptations to data assimilation compared to previous forestry studies in Sweden. On a test site in the southwest of Sweden (58°27′N, 13°39′E), we evaluated the performance of the extended Kalman filter and a proposed modified filter that accounts for error correlations. We also applied classical calibration to the remote sensing predictions. We evaluated the developed methods using a dataset with nine different acquisitions of remotely sensed data from a mix of sensors over four years, starting and ending with ALS-based predictions of growing stock volume. The results showed that the modified filter and the calibrated predictions performed better than the standard extended Kalman filter and that at the endpoint the prediction based on data assimilation implied an improved accuracy (25.0% RMSE), compared to a new ALS-based prediction (27.5% RMSE). Numéro de notice : A2022-144 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1080/07038992.2021.1988542 Date de publication en ligne : 17/10/2021 En ligne : https://doi.org/10.1080/07038992.2021.1988542 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99985
in Canadian journal of remote sensing > vol 48 n° 2 (April 2022) . - pp[article]Deep learning for archaeological object detection on LiDAR: New evaluation measures and insights / Marco Fiorucci in Remote sensing, vol 14 n° 7 (April-1 2022)PermalinkDetermination of building flood risk maps from LiDAR mobile mapping data / Yu Feng in Computers, Environment and Urban Systems, vol 93 (April 2022)PermalinkEstimating forest attributes in airborne laser scanning based inventory using calibrated predictions from external models / Ana de Lera Garrido in Silva fennica, vol 56 n° 2 (April 2022)PermalinkGeoRec: Geometry-enhanced semantic 3D reconstruction of RGB-D indoor scenes / Linxi Huan in ISPRS Journal of photogrammetry and remote sensing, vol 186 (April 2022)PermalinkA graph attention network for road marking classification from mobile LiDAR point clouds / Lina Fang in International journal of applied Earth observation and geoinformation, vol 108 (April 2022)PermalinkComparison of UAV-based LiDAR and digital aerial photogrammetry for measuring crown-level canopy height in the urban environment / Longfei Zhou in Urban Forestry & Urban Greening, vol 69 (March 2022)PermalinkA cost-effective method for reconstructing city-building 3D models from sparse Lidar point clouds / Marek Kulawiak in Remote sensing, vol 14 n° 5 (March-1 2022)PermalinkEstimating aboveground biomass of urban forest trees with dual-source UAV acquired point clouds / Jiayuan Lin in Urban Forestry & Urban Greening, vol 69 (March 2022)PermalinkÉvaluation des apports de l’apprentissage profond au sein d’un service dédié à la numérisation du patrimoine / Maxime Mérizette in XYZ, n° 170 (mars 2022)PermalinkLiDAR-based method for analysing landmark visibility to pedestrians in cities: case study in Kraków, Poland / Krystian Pyka in International journal of geographical information science IJGIS, vol 36 n° 3 (March 2022)Permalink