Centre de documentation
scientifique

Fusion of 3D point clouds and hyperspectral data for the extraction of geometric and radiometric features of trees / Eduardo Alejandro Tusa Jumbo (2020)  

Public Titre : Fusion of 3D point clouds and hyperspectral data for the extraction of geometric and radiometric features of trees Type de document : Thèse/HDR Auteurs : Eduardo Alejandro Tusa Jumbo, Auteur ; Jocelyn Chanussot, Directeur de thèse ; Jean-Matthieu Monnet, Encadrant ; Mauro Dalla Mura, Encadrant ; Jean-Baptiste Barré, Encadrant Editeur : Grenoble : Université de Grenoble Année de publication : 2020 Importance : 153 p. Format : 21 x 30 cm Note générale : Bibliographie Thèse pour obtenir le grade de docteur de l'Université Grenoble Alpes, Signal image parole Telecoms Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] Alpes (France) [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] espèce végétale [Termes IGN] extraction de la végétation [Termes IGN] forêt alpestre [Termes IGN] fusion de données multisource [Termes IGN] image hyperspectrale [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] inventaire forestier local [Termes IGN] semis de points [Termes IGN] télédétection par lidar [Termes IGN] télédétection spatiale Index. décimale : THESE Thèses et HDR Résumé : (Auteur) Mountain forests provide environmental ecosystem services (EES) to communities: supplying of recreational landscapes, protection against natural hazards, supporting biodiversity conservation, among others. The preservation of these EES through space and time requires a good characterization of the resources. Especially in mountains, stands are very heterogeneous and timber harvesting is economically possible thanks to trees of higher value. This is why we want to be able to map each tree and estimate its characteristics, including quality, which is related to its shape and growth conditions. Field inventories are not able to provide a wall to wall cover of detailed tree-level information on a large scale. On the other hand, remote sensing tools seem to be a promising technology because of the time efficient and the affordable costs for studying forest areas. LiDAR data provide detailed information from the vertical distribution and location of the trees, but it is limited for mapping species. Hyperspectral data are associated to absorption features in the canopy reflectance spectrum, but is not effective for characterizing tree geometry. Hyperspectral and LiDAR systems provide independent and complementary data that are relevant for the assessment of biophysical and biochemical attributes of forest areas. This PhD thesis deals with the fusion of LiDAR and hyperspectral data to characterize individual forest trees. The leading idea is to improve methods to derive forest information at tree-level by extracting geometric and radiometric features. The contributions of this research work relies on: i) an updated review of data fusion methods of LiDAR and hyperspectral data for forest monitoring, ii) an improved 3D segmentation algorithm for delineating individual tree crowns based on Adaptive Mean Shift (AMS3D) and an ellipsoid crown shape model, iii) a criterion for feature selection based on random forests score, 5-fold cross validation and a cumulative error function for forest tree species classification. The two main methods used to derive forest information at tree level are tested with remote sensing data acquired in the French Alps. Note de contenu : 1 Introduction 1.1 Forest 1.2 Principles of remote sensing 1.3 Motivation 1.4 Objectives 1.5 Thesis structure 2. Data Fusion 15 2.1 Principles of fusion 2.2 Low-level 2.3 Medium-level 2.4 High-level 2.5 Applications 3. Material 32 3.1 Field data 3.2 Study areas 3.3 ALS and hyperspectral data 4 ITC Delineation 4.1 Introduction 4.2 MS segmentation 4.3 AMS3D based on crown shape model 4.4 Experimental analysis 4.5 Conclusion 5. Tree Species Classification 5.1 Introduction 5.2 Study area 5.3 Methodology 5.4 Results and discussion 5.5 Conclusions 6. Conclusion and work perspectives 6.1 How data processing methods are applied in each level of data fusion for forest monitoring? 6.2 How a crown shape model can improve the segmentation of individual tree crowns? 6.3 Which feature combination contribute to characterize the forest tree species composition? Numéro de notice : 26582 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Thèse française Note de thèse : Thèse de Doctorat : Signal image parole Telecoms : Grenoble : 2020 Organisme de stage : Grenoble Images Parole Signal Automatique GIPSA-lab nature-HAL : Thèse DOI : sans Date de publication en ligne : 30/07/2021 En ligne : https://tel.archives-ouvertes.fr/tel-03212453/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98403