Centre de documentation
scientifique

A hierarchical deep neural network with iterative features for semantic labeling of airborne LiDAR point clouds / Yetao Yang in Computers & geosciences, vol 157 (December 2021)  

Public [article]  inComputers & geosciences > vol 157 (December 2021) . - n° 104932 Titre : A hierarchical deep neural network with iterative features for semantic labeling of airborne LiDAR point clouds Type de document : Article/Communication Auteurs : Yetao Yang, Auteur ; Rongkui Tang, Auteur ; Jinglei Wang, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 104932 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage profond [Termes IGN] classification barycentrique [Termes IGN] classification par réseau neuronal [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] itération [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] structure hiérarchique de données Résumé : (auteur) Airborne LiDAR point clouds classification has been a challenging task due to the characteristics of point clouds and the complexity of the urban environment. Recently, methods that directly act on unordered point set have achieved satisfactory results in point clouds classification. However, the existing methods that directly consume point clouds pay little attention to the interaction between the deep layers, which makes the feature learning insufficient in complex environments. In this paper, we propose a deep neural network for semantic labeling task. It iteratively learns deep features in a hierarchical structure, and provides a simple but efficient way to make interactions between different hierarchical levels. Since iteration process will greatly increase the number of layers, we employ the residual network to improve the performance. In addition, we also introduce dilated k-nearest neighbors and multi-scale grouping to increase the receptive field. The experiments on both Vaihingen 3D dataset and Dayton Annotated LiDAR Earth Scan (DALES) dataset demonstrate the effectiveness of the proposed method in point cloud classification. Numéro de notice : A2021-867 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1016/j.cageo.2021.104932 Date de publication en ligne : 04/09/2021 En ligne : https://doi.org/10.1016/j.cageo.2021.104932 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99098 [article]

Geo-environment risk assessment in Zhengzhou City, China / Chuanming Ma in Geomatics, Natural Hazards and Risk, vol 11 n° 1 (2020)  

Public [article]  inGeomatics, Natural Hazards and Risk > vol 11 n° 1 (2020) . - pp 40 - 70 Titre : Geo-environment risk assessment in Zhengzhou City, China Type de document : Article/Communication Auteurs : Chuanming Ma, Auteur ; Wu Yan, Auteur ; Xinjie Hu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 40 - 70 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] cartographie des risques [Termes IGN] Chine [Termes IGN] effondrement de terrain [Termes IGN] évaluation des données [Termes IGN] gestion des risques [Termes IGN] pollution des eaux [Termes IGN] processus de hiérarchisation analytique [Termes IGN] risque environnemental [Termes IGN] séisme [Termes IGN] structure hiérarchique de données [Termes IGN] surveillance géologique [Termes IGN] urbanisme [Termes IGN] zone urbaine dense Résumé : (auteur) The urban geological environment risk assessment is based on the research and analysis of the main geological environmental problems of the city, comprehensively assessing the risk of urban geological environment problems and the possible losses, and studying the degree of matching between the natural and social attributes of the geological environment. According to the urban planning of Zhengzhou City, the different types of functional areas of the city were used as evaluation objects, and the analytic hierarchy-composite index model was used to evaluate the geological environment risk and social economic vulnerability. The risk assessment model was used to evaluate the geological environment risk of Zhengzhou City. The evaluation results show that the area of high-risk area in Zhengzhou accounts for 4.05%; the area of medium-high risk area accounts for 12.89%; the area of medium-low and low-risk area accounts for 83.06%. According to the assessment results, suggestions are put forward to provide service for the urban planning, development and risk management. Highlights: * An urban geo-environment risk assessment technique system combining with the AHP - composite index assessment model is proposed. * Different types of functional zones in Zhengzhou City are taken as assessment units. * Geo-environment risk in Zhengzhou City is qualitatively and quantitatively evaluated. Numéro de notice : A2020-565 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/19475705.2019.1701571 Date de publication en ligne : 27/12/2019 En ligne : https://doi.org/10.1080/19475705.2019.1701571 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95890 [article]

Small‐area patch‐merging method accounting for both local constraints and the overall area balance / Chengming Li in Transactions in GIS, Vol 24 n° 4 (August 2020)  

Public [article]  inTransactions in GIS > Vol 24 n° 4 (August 2020) . - 21 p. Titre : Small‐area patch‐merging method accounting for both local constraints and the overall area balance Type de document : Article/Communication Auteurs : Chengming Li, Auteur ; Yong Yin, Auteur ; Zhaoxin Dai, Auteur Année de publication : 2020 Article en page(s) : 21 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] contrainte relationnelle [Termes IGN] fusion (généralisation) [Termes IGN] itération [Termes IGN] Kouangtoung (Chine) [Termes IGN] parcelle agricole [Termes IGN] structure hiérarchique de données [Termes IGN] superficie [Termes IGN] Triangulated Irregular Network [Termes IGN] triangulation de Delaunay [Termes IGN] utilisation du sol [Vedettes matières IGN] Généralisation Résumé : (auteur) Small‐area patch merging is a common operation in land use data generalization. However, existing research on small‐area patch merging has mainly focused on local compatibility measures, which often lead to area imbalances among land use types from a global perspective. To address the shortcomings of previous studies by resolving local and global concerns simultaneously, this article proposes a merging method that considers both local constraints and the overall area balance. First, a local optimization model that considers three constraints—namely, the areas of neighboring patches, the lengths of shared arcs, and semantic similarity—is established. The areas of small patches are first pre‐allocated. Subsequently, in accordance with an area change threshold for individual land use types, land use types with area changes that exceed this threshold are identified. The patches corresponding to these land use types are subjected to iterative adjustments while considering the overall area balance. Based on their area splitting abilities, the split lines for small‐area patches are determined, and small‐area patches are merged. Finally, actual data from Guangdong Province are used for validation. The experimental results demonstrate that the proposed method is capable of preserving the local compatibility of patches while balancing the overall area associated with each land use type. Numéro de notice : A2020-672 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12634 Date de publication en ligne : 29/05/2020 En ligne : https://doi.org/10.1111/tgis.12634 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96157 [article]

A graph-based segmentation algorithm for tree crown extraction using airborne LiDAR data / Victor F. Strimbu in ISPRS Journal of photogrammetry and remote sensing, vol 104 (June 2015)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 104 (June 2015) . - pp 30 - 43 Titre : A graph-based segmentation algorithm for tree crown extraction using airborne LiDAR data Type de document : Article/Communication Auteurs : Victor F. Strimbu, Auteur ; Bogdan M. Strimbu, Auteur Année de publication : 2015 Article en page(s) : pp 30 - 43 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] données localisées 3D [Termes IGN] extraction de la végétation [Termes IGN] graphe [Termes IGN] houppier [Termes IGN] Louisiane (Etats-Unis) [Termes IGN] segmentation [Termes IGN] structure hiérarchique de données Résumé : (auteur) This work proposes a segmentation method that isolates individual tree crowns using airborne LiDAR data. The proposed approach captures the topological structure of the forest in hierarchical data structures, quantifies topological relationships of tree crown components in a weighted graph, and finally partitions the graph to separate individual tree crowns. This novel bottom-up segmentation strategy is based on several quantifiable cohesion criteria that act as a measure of belief on weather two crown components belong to the same tree. An added flexibility is provided by a set of weights that balance the contribution of each criterion, thus effectively allowing the algorithm to adjust to different forest structures. The LiDAR data used for testing was acquired in Louisiana, inside the Clear Creek Wildlife management area with a RIEGL LMS-Q680i airborne laser scanner. Three 1 ha forest areas of different conditions and increasing complexity were segmented and assessed in terms of an accuracy index (AI) accounting for both omission and commission. The three areas were segmented under optimum parameterization with an AI of 98.98%, 92.25% and 74.75% respectively, revealing the excellent potential of the algorithm. When segmentation parameters are optimized locally using plot references the AI drops to 98.23%, 89.24%, and 68.04% on average with plot sizes of 1000 m2 and 97.68%, 87.78% and 61.1% on average with plot sizes of 500 m2. More than introducing a segmentation algorithm, this paper proposes a powerful framework featuring flexibility to support a series of segmentation methods including some of those recurring in the tree segmentation literature. The segmentation method may extend its applications to any data of topological nature or data that has a topological equivalent. Numéro de notice : A2015-699 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2015.01.018 En ligne : https://doi.org/10.1016/j.isprsjprs.2015.01.018 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78335 [article]

A multiscale and hierarchical feature extraction method for terrestrial laser scanning point cloud classification / Z. Wang in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 53 n° 5 (mai 2015) . - pp 2409 - 2425 Titre : A multiscale and hierarchical feature extraction method for terrestrial laser scanning point cloud classification Type de document : Article/Communication Auteurs : Z. Wang, Auteur ; Liqiang Zhang, Auteur ; Tian Fang, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 2409 - 2425 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] classification orientée objet [Termes IGN] détection de piéton [Termes IGN] détection du bâti [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] extraction de traits caractéristiques [Termes IGN] lasergrammétrie [Termes IGN] objet mobile [Termes IGN] semis de points [Termes IGN] structure hiérarchique de données [Termes IGN] télémétrie laser terrestre [Termes IGN] zone urbaine dense Résumé : (Auteur) The effective extraction of shape features is an important requirement for the accurate and efficient classification of terrestrial laser scanning (TLS) point clouds. However, the challenge of how to obtain robust and discriminative features from noisy and varying density TLS point clouds remains. This paper introduces a novel multiscale and hierarchical framework, which describes the classification of TLS point clouds of cluttered urban scenes. In this framework, we propose multiscale and hierarchical point clusters (MHPCs). In MHPCs, point clouds are first resampled into different scales. Then, the resampled data set of each scale is aggregated into several hierarchical point clusters, where the point cloud of all scales in each level is termed a point-cluster set. This representation not only accounts for the multiscale properties of point clouds but also well captures their hierarchical structures. Based on the MHPCs, novel features of point clusters are constructed by employing the latent Dirichlet allocation (LDA). An LDA model is trained according to a training set. The LDA model then extracts a set of latent topics, i.e., a feature of topics, for a point cluster. Finally, to apply the introduced features for point-cluster classification, we train an AdaBoost classifier in each point-cluster set and obtain the corresponding classifiers to separate the TLS point clouds with varying point density and data missing into semantic regions. Compared with other methods, our features achieve the best classification results for buildings, trees, people, and cars from TLS point clouds, particularly for small and moving objects, such as people and cars. Numéro de notice : A2015-522 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2359951 En ligne : https://doi.org/10.1109/TGRS.2014.2359951 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=77533 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2015051	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Visualization of attributed hierarchical structures in a spatiotemporal context / S. Hadlak in International journal of geographical information science IJGIS, vol 24 n° 10 (october 2010)  

Permalink

A neural network-based method for solving "nested hierarchy" areal interpolation problems / D. Merwin in Cartography and Geographic Information Science, vol 36 n° 4 (October 2009)  

Permalink

A framework for the generalization of 3D city models / R. Guercke in Bulletin des sciences géographiques, n° 23 (juin 2009)

Permalink

Interoperability of functions in environmental models: a case study in hydrological modeling / S. Hu in International journal of geographical information science IJGIS, vol 23 n° 5 (may 2009)  

Permalink

Towards an integrated model of interoperability for Spatial Data Infrastructures / M.A. Manson in Transactions in GIS, vol 13 n° 1 (February 2009)  

Permalink

Efficiently computing and deriving topological relation matrices between complex regions with broad boundaries / S. Du in ISPRS Journal of photogrammetry and remote sensing, vol 63 n° 6 (November - December 2008)  

Permalink

Database requirements for generalisation and multiple representations / Sébastien Mustière (01/01/2007)

Permalink

A dynamic decision tree structure supporting urban road network automated generalization / W. Peng in Cartographic journal (the), vol 33 n° 1 (June 1996)  

Permalink

Agrégation et modélisation de données hiérarchiques sous le SIG Smallworld / Sylvie Gras (1994)

Permalink

Test d'implémentations de l'opérateur d'agrégation sur le SIG Smallworld pour un modèle hiérarchique de données traitant de zones végétales des Hautes-Alpes / Claudine Derrac (1994)

Permalink