Centre de documentation
scientifique

Instance segmentation of standing dead trees in dense forest from aerial imagery using deep learning / Aboubakar Sani-Mohammed in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 6 (December 2022)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 6 (December 2022) . - n° 100024 Titre : Instance segmentation of standing dead trees in dense forest from aerial imagery using deep learning Type de document : Article/Communication Auteurs : Aboubakar Sani-Mohammed, Auteur ; Wei Yao, Auteur ; Marco Heurich, Auteur Année de publication : 2022 Article en page(s) : n° 100024 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] arbre mort [Termes IGN] Bavière (Allemagne) [Termes IGN] bois sur pied [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection automatique [Termes IGN] gestion forestière durable [Termes IGN] image à haute résolution [Termes IGN] image aérienne [Termes IGN] image infrarouge couleur [Termes IGN] peuplement mélangé [Termes IGN] puits de carbone [Termes IGN] segmentation sémantique Résumé : (auteur) Mapping standing dead trees, especially, in natural forests is very important for evaluation of the forest's health status, and its capability for storing Carbon, and the conservation of biodiversity. Apparently, natural forests have larger areas which renders the classical field surveying method very challenging, time-consuming, labor-intensive, and unsustainable. Thus, for effective forest management, there is the need for an automated approach that would be cost-effective. With the advent of Machine Learning, Deep Learning has proven to successfully achieve excellent results. This study presents an adjusted Mask R-CNN Deep Learning approach for detecting and segmenting standing dead trees in a mixed dense forest from CIR aerial imagery using a limited (195 images) training dataset. First, transfer learning is considered coupled with the image augmentation technique to leverage the limitation of training datasets. Then, we strategically selected hyperparameters to suit appropriately our model's architecture that fits well with our type of data (dead trees in images). Finally, to assess the generalization capability of our model's performance, a test dataset that was not confronted to the deep neural network was used for comprehensive evaluation. Our model recorded promising results reaching a mean average precision, average recall, and average F1-Score of 0.85, 0.88, and 0.87 respectively, despite our relatively low resolution (20 cm) dataset. Consequently, our model could be used for automation in standing dead tree detection and segmentation for enhanced forest management. This is equally significant for biodiversity conservation, and forest Carbon storage estimation. Numéro de notice : A2022-871 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.ophoto.2022.100024 Date de publication en ligne : 10/11/2022 En ligne : https://doi.org/10.1016/j.ophoto.2022.100024 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102165 [article]

Wood decay detection in Norway spruce forests based on airborne hyperspectral and ALS data / Michele Dalponte in Remote sensing, vol 14 n° 8 (April-2 2022)  

Public [article]  inRemote sensing > vol 14 n° 8 (April-2 2022) . - n° 1892 Titre : Wood decay detection in Norway spruce forests based on airborne hyperspectral and ALS data Type de document : Article/Communication Auteurs : Michele Dalponte, Auteur ; Alvar J. I. Kallio, Auteur ; Hans Ole Ørka, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 1892 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] bois sur pied [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] dépérissement [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] données lidar [Termes IGN] image hyperspectrale [Termes IGN] image infrarouge [Termes IGN] Norvège [Termes IGN] Perceptron multicouche [Termes IGN] Picea abies [Termes IGN] régression linéaire [Termes IGN] régression logistique [Termes IGN] santé des forêts [Termes IGN] semis de points Résumé : (auteur) Wood decay caused by pathogenic fungi in Norway spruce forests causes severe economic losses in the forestry sector, and currently no efficient methods exist to detect infected trees. The detection of wood decay could potentially lead to improvements in forest management and could help in reducing economic losses. In this study, airborne hyperspectral data were used to detect the presence of wood decay in the trees in two forest areas located in Etnedal (dataset I) and Gran (dataset II) municipalities, in southern Norway. The hyperspectral data used consisted of images acquired by two sensors operating in the VNIR and SWIR parts of the spectrum. Corresponding ground reference data were collected in Etnedal using a cut-to-length harvester while in Gran, field measurements were collected manually. Airborne laser scanning (ALS) data were used to detect the individual tree crowns (ITCs) in both sites. Different approaches to deal with pixels inside each ITC were considered: in particular, pixels were either aggregated to a unique value per ITC (i.e., mean, weighted mean, median, centermost pixel) or analyzed in an unaggregated way. Multiple classification methods were explored to predict rot presence: logistic regression, feed forward neural networks, and convolutional neural networks. The results showed that wood decay could be detected, even if with accuracy varying among the two datasets. The best results on the Etnedal dataset were obtained using a convolution neural network with the first five components of a principal component analysis as input (OA = 65.5%), while on the Gran dataset, the best result was obtained using LASSO with logistic regression and data aggregated using the weighted mean (OA = 61.4%). In general, the differences among aggregated and unaggregated data were small. Numéro de notice : A2022-352 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.3390/rs14081892 Date de publication en ligne : 14/04/2022 En ligne : https://doi.org/10.3390/rs14081892 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100541 [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)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 4 (April 2022) . - n° 100012 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 bois Résumé : (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 [article]

Growing stock monitoring by European National Forest Inventories: Historical origins, current methods and harmonisation / Thomas Gschwantner in Forest ecology and management, vol 505 (February-1 2022)  

Public [article]  inForest ecology and management > vol 505 (February-1 2022) . - n° 119868 Titre : Growing stock monitoring by European National Forest Inventories: Historical origins, current methods and harmonisation Type de document : Article/Communication Auteurs : Thomas Gschwantner, Auteur ; Iciar A. Alberdi, Auteur ; Sébastien Bauwens, Auteur ; Susann Bender, Auteur ; Dragan Borota, Auteur ; Michal Bosela, Auteur ; Olivier Bouriaud , Auteur ; Johannes Breidenbach, Auteur ; Janis Donis, Auteur ; Christoph Fischer, Auteur ; Patrizia Gasparini, Auteur ; Luke Heffernan, Auteur ; Jean-Christophe Hervé (1961-2017) , Auteur ; László Kolozs, Auteur ; Kari T. Korhonen, Auteur ; Nikos Koutsias, Auteur ; Pál Kovácsevics, Auteur ; Miloš Kučera, Auteur ; Gintaras Kulbokas, Auteur ; Andrius Kuliesis, Auteur ; Adrian Lanz, Auteur ; Philippe Lejeune, Auteur ; Torgny Lind, Auteur ; Gheorghe Marin, Auteur ; François Morneau , Auteur ; Thomas Nord-Larsen, Auteur ; Leonia Nunes, Auteur ; Damjan Pantić, Auteur ; John Redmond, Auteur ; Francisco C. Rego, Auteur ; Thomas Riedel, Auteur ; Vladimir Šebeň, Auteur ; Allan Sims, Auteur ; Mitja Skudnik, Auteur ; Stein Michael Tomter, Auteur Année de publication : 2022 Projets : 1-Pas de projet / Article en page(s) : n° 119868 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] bois sur pied [Termes IGN] changement climatique [Termes IGN] Europe (géographie politique) [Termes IGN] gestion forestière durable [Termes IGN] harmonisation des données [Termes IGN] histoire [Termes IGN] inventaire forestier étranger (données) [Termes IGN] peuplement forestier [Termes IGN] ressources forestières [Termes IGN] volume en bois [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Wood resources have been essential for human welfare throughout history. Also nowadays, the volume of growing stock (GS) is considered one of the most important forest attributes monitored by National Forest Inventories (NFIs) to inform policy decisions and forest management planning. The origins of forest inventories closely relate to times of early wood shortage in Europe causing the need to explore and plan the utilisation of GS in the catchment areas of mines, saltworks and settlements. Over time, forest surveys became more detailed and their scope turned to larger areas, although they were still conceived as stand-wise inventories. In the 1920s, the first sample-based NFIs were introduced in the northern European countries. Since the earliest beginnings, GS monitoring approaches have considerably evolved. Current NFI methods differ due to country-specific conditions, inventory traditions, and information needs. Consequently, GS estimates were lacking international comparability and were therefore subject to recent harmonisation efforts to meet the increasing demand for consistent forest resource information at European level. As primary large-area monitoring programmes in most European countries, NFIs assess a multitude of variables, describing various aspects of sustainable forest management, including for example wood supply, carbon sequestration, and biodiversity. Many of these contemporary subject matters involve considerations about GS and its changes, at different geographic levels and time frames from past to future developments according to scenario simulations. Due to its historical, continued and currently increasing importance, we provide an up-to-date review focussing on large-area GS monitoring where we i) describe the origins and historical development of European NFIs, ii) address the terminology and present GS definitions of NFIs, iii) summarise the current methods of 23 European NFIs including sampling methods, tree measurements, volume models, estimators, uncertainty components, and the use of air- and space-borne data sources, iv) present the recent progress in NFI harmonisation in Europe, and v) provide an outlook under changing climate and forest-based bioeconomy objectives. Numéro de notice : A2022-040 Affiliation des auteurs : LIF+Ext (2020- ) Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2021.119868 Date de publication en ligne : 12/12/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.119868 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99386 [article]

Le mémento inventaire forestier, édition 2021 / Institut national de l'information géographique et forestière (2012 -) (2022)    

Public Titre : Le mémento inventaire forestier, édition 2021 Type de document : Rapport Auteurs : Institut national de l'information géographique et forestière (2012 -), Auteur Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN (2012-) Année de publication : 2022 Importance : 40 p. Format : 11 x 25 cm Langues : Français (fre) Descripteur : [Termes IGN] bois mort [Termes IGN] bois sur pied [Termes IGN] écosystème forestier [Termes IGN] France (administrative) [Termes IGN] France d'outre-mer [Termes IGN] inventaire forestier national (données France) [Termes IGN] ressources forestières [Vedettes matières IGN] Inventaire forestier Index. décimale : 48.20 Inventaire forestier Résumé : (Editeur) Le mémento de l’inventaire forestier – édition 2021 – rassemble dans 40 pages les principaux chiffres, cartes et informations sur la forêt française issus des campagnes d’inventaire 2016 à 2020 de l’IGN. Note de contenu : SURFACES FORESTIERES La forêt en Outre-Mer La forêt en France métropolitaine L'augmentation de la surface forestière Le taux de boisement À qui la forêt appartient-elle ? ECOSYSTEMES FORESTIERS La santé des forêts La diversité des peuplements La composition des peuplements Le bois mort sur pied Le bois mort au sol La répartition de quelques plantes RESSOURCES FORESTIERES Le bois vivant sur pied L'augmentation de la ressource Informations sur les principales essences La production biologique annuelle Les prélèvements de bois Quelques données régionales Numéro de notice : 17695 Affiliation des auteurs : IGN (2020- ) Thématique : FORET Nature : Rapport statistique nature-HAL : Rapport DOI : sans En ligne : https://inventaire-forestier.ign.fr/spip.php?article583= Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99508

Voir aussi

• Le mémento inventaire forestier, édition 2017 / Institut national de l'information géographique et forestière (2012 -) (2017)    
• Le mémento inventaire forestier, édition 2018 / Institut national de l'information géographique et forestière (2012 -) (2018)  
• Le mémento inventaire forestier, édition 2019 / Institut national de l'information géographique et forestière (2012 -) (2019)  
• Le mémento inventaire forestier, édition 2020 / Institut national de l'information géographique et forestière (2012 -) (2021)    
• Mémento 2022 / IGN (2022)    
• Mémento 2023 / IGN (2023)    
• Mémento 2024 / IGN (2024)    

Exemplaires(2)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
17695-01	48.20	Livre	Centre de documentation	Végétation - Forêt	Disponible
17695-02	48.20	Livre	Centre de documentation	Végétation - Forêt	Disponible

Documents numériques

peut être téléchargé mémento inventaire forestier, édition 2021 Adobe Acrobat PDF

Estimating timber volume loss due to storm damage in Carinthia, Austria, using ALS/TLS and spatial regression models / Arne Nothdurft in Forest ecology and management, vol 502 (December-15 2021)  

Permalink

Using electrical resistivity tomography to detect wetwood and estimate moisture content in silver fir (Abies alba Mill.) / Ludovic Martin in Annals of Forest Science, vol 78 n° 3 (September 2021)  

Permalink

Le mémento inventaire forestier, édition 2020 / Institut national de l'information géographique et forestière (2012 -) (2021)    

Permalink

Unprecedented pluri-decennial increase in the growing stock of French forests is persistent and dominated by private broadleaved forests / Jean-Daniel Bontemps in Annals of Forest Science, vol 77 n° 4 (December 2020)  

Permalink

Physical, chemical and mechanical wood properties of Pinus nigra growing in Portugal / Alexandra Dias in Annals of Forest Science, vol 77 n° 3 (September 2020)  

Permalink

Use of non-destructive test methods on Irish hardwood standing trees and small-diameter round timber for prediction of mechanical properties / Daniel F. Llana in Annals of Forest Science, vol 77 n° 3 (September 2020)  

Permalink

L’inventaire forestier national pour un suivi permanent, multi-échelles et multi-thématiques de la forêt française et des ressources bois mobilisables / Antoine Colin in Sciences, eaux & territoires, n° 33 (avril 2020)  

Permalink

Large-scale two-phase estimation of wood production by poplar plantations exploiting Sentinel-2 data as auxiliary information / Agnese Marcelli in Silva fennica, vol 54 n° 2 (March 2020)  

Permalink

European Forest Accounts - Années 2016-2017 : Rapport d’étude / Alexandra Niedzwiedz (2020)  

Permalink

Using a U-net convolutional neural network to map woody vegetation extent from high resolution satellite imagery across Queensland, Australia / Neil Flood in International journal of applied Earth observation and geoinformation, vol 82 (October 2019)  

Permalink