Centre dedocumentation
scientifique

Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees / Hamid Hamraz in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 219 - 230 Titre : Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees Type de document : Article/Communication Auteurs : Hamid Hamraz, Auteur ; Nathan B. Jacobs, Auteur ; Marco A. Contreras, Auteur ; Chase H. Clark, Auteur Année de publication : 2019 Article en page(s) : pp 219 - 230 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] houppier [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] semis de points Résumé : (auteur) The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees segmented from airborne LiDAR data. To enable processing by a deep convolutional neural network (CNN), we designed two discrete representations using leaf-off and leaf-on LiDAR data: a digital surface model with four channels (DSM × 4) and a set of four 2D views (4 × 2D). A training dataset of tree crowns was generated via segmentation of tree crowns, followed by co-registration with field data. Potential mislabels due to GPS error or tree leaning were corrected using a statistical ensemble filtering procedure. Because the training data was heavily unbalanced (~8% conifers), we trained an ensemble of CNNs on random balanced sub-samples. Benchmarked against multiple traditional shallow learning methods using manually designed features, the CNNs improved accuracies up to 14%. The 4 × 2D representation yielded similar classification accuracies to the DSM × 4 representation (~82% coniferous and ~90% deciduous) while converging faster. Further experimentation showed that early/late fusion of the channels in the representations did not affect the accuracies in a significant way. The data augmentation that was used for the CNN training improved the classification accuracies, but more real training instances (especially coniferous) likely results in much stronger improvements. Leaf-off LiDAR data were the primary source of useful information, which is likely due to the perennial nature of coniferous foliage. LiDAR intensity values also proved to be useful, but normalization yielded no significant improvement. As we observed, large training data may compensate for the lack of a subset of important domain data. Lastly, the classification accuracies of overstory trees (~90%) were more balanced than those of understory trees (~90% deciduous and ~65% coniferous), which is likely due to the incomplete capture of understory tree crowns via airborne LiDAR. In domains like remote sensing and biomedical imaging, where the data contain a large amount of information and are not friendly to human visual system, human-designed features may become suboptimal. As exemplified by this study, automatic, objective derivation of optimal features via deep learning can improve prediction tasks in such domains. Numéro de notice : A2019-547 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.10.011 date de publication en ligne : 03/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.10.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94192 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019121	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2019123	DEP-RECP	Revue	MATIS	Dépôt en unité	Exclu du prêt
081-2019122	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Increasing precision for French forest inventory estimates using the k-NN technique with optical and photogrammetric data and model-assisted estimators / Dinesh Babu Irulappa Pillai Vijayakumar in Remote sensing, vol 11 n° 8 (August 2019)  

Public [article]  inRemote sensing > vol 11 n° 8 (August 2019) Titre : Increasing precision for French forest inventory estimates using the k-NN technique with optical and photogrammetric data and model-assisted estimators Type de document : Article/Communication Auteurs : Dinesh Babu Irulappa Pillai Vijayakumar, Auteur ; Jean-Pierre Renaud, Auteur ; François Morneau, Auteur ; Ronald E. McRoberts, Auteur ; Cédric Vega , Auteur Année de publication : 2019 Projets : DIABOLO / Packalen, Tuula Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] classification barycentrique [Termes descripteurs IGN] feuillu [Termes descripteurs IGN] image Landsat-8 [Termes descripteurs IGN] inférence statistique [Termes descripteurs IGN] inventaire forestier (techniques et méthodes) [Termes descripteurs IGN] inventaire forestier national (données France) [Termes descripteurs IGN] modèle numérique de surface de la canopée [Termes descripteurs IGN] Orléans, forêt d' (Loiret) [Termes descripteurs IGN] photogrammétrie numérique [Termes descripteurs IGN] Pinus pinaster [Termes descripteurs IGN] Pinus sylvestris [Termes descripteurs IGN] quercus pedunculata [Termes descripteurs IGN] quercus sessiliflora [Termes descripteurs IGN] Sologne (France) [Vedettes matières IGN] Inventaire forestier Résumé : (auteur) Multisource forest inventory methods were developed to improve the precision of national forest inventory estimates. These methods rely on the combination of inventory data and auxiliary information correlated with forest attributes of interest. As these methods have been predominantly tested over coniferous forests, the present study used this approach for heterogeneous and complex deciduous forests in the center of France. The auxiliary data considered included a forest type map, Landsat 8 spectral bands and derived vegetation indexes, and 3D variables derived from photogrammetric canopy height models. On a subset area, changes in canopy height estimated from two successive photogrammetric models were also used. A model-assisted inference framework, using a k nearest-neighbors approach, was used to predict 11 field inventory variables simultaneously. The results showed that among the auxiliary variables tested, 3D metrics improved the precision of dendrometric estimates more than other auxiliary variables. Relative efficiencies (RE) varying from 2.15 for volume to 1.04 for stand density were obtained using all auxiliary variables. Canopy height changes also increased RE from 3% to 26%. Our results confirmed the importance of 3D metrics as auxiliary variables and demonstrated the value of canopy change variables for increasing the precision of estimates of forest structural attributes such as density and quadratic mean diameter. Numéro de notice : A2019-382 Thématique : FORET/IMAGERIE/MATHEMATIQUE Nature : Article DOI : 10.3390/rs11080991 date de publication en ligne : 25/04/2019 En ligne : https://doi.org/10.3390/rs11080991 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93456 [article]

Potential of Sentinel-1 data for monitoring temperate mixed forest phenology / Pierre-Louis Frison in Remote sensing, vol 10 n° 12 (December 2018)  

Public [article]  inRemote sensing > vol 10 n° 12 (December 2018) Titre : Potential of Sentinel-1 data for monitoring temperate mixed forest phenology Type de document : Article/Communication Auteurs : Pierre-Louis Frison , Auteur ; Bénédicte Fruneau , Auteur ; Syrine Kmiha, Auteur ; Kamel Soudani, Auteur ; Eric Dufrêne, Auteur ; Thuy Le Toan, Auteur ; Thierry Koleck, Auteur ; Ludovic Villard, Auteur ; Eric Mougin, Auteur ; Jean-Paul Rudant , Auteur Année de publication : 2018 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] analyse diachronique [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] coefficient de rétrodiffusion [Termes descripteurs IGN] cohérence des données [Termes descripteurs IGN] données polarimétriques [Termes descripteurs IGN] Fontainebleau, forêt de [Termes descripteurs IGN] forêt tempérée [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] phénologie [Termes descripteurs IGN] signature spectrale [Termes descripteurs IGN] surveillance forestière Résumé : (auteur) In this study, the potential of Sentinel-1 data to seasonally monitor temperate forests was investigated by analyzing radar signatures observed from plots in the Fontainebleau Forest of the Ile de France region, France, for the period extending from March 2015 to January 2016. Radar backscattering coefficients, σ0 and the amplitude of temporal interferometric coherence profiles in relation to environmental variables are shown, such as in situ precipitation and air temperature. The high temporal frequency of Sentinel-1 acquisitions (i.e., twelve days, or six, if both Sentinel-1A and B are combined over Europe) and the dual polarization configuration (VV and VH over most land surfaces) made a significant contribution. In particular, the radar backscattering coefficient ratio of VV to VH polarization, σ0VV/σ0VH , showed a well-pronounced seasonality that was correlated with vegetation phenology, as confirmed in comparison to NDVI profiles derived from Landsat-8 (r = 0.77) over stands of deciduous trees. These results illustrate the high potential of Sentinel-1 data for monitoring vegetation, and as these data are not sensitive to the atmosphere, the phenology could be estimated with more accuracy than optical data. These observations will be quantitatively analyzed with the use of electromagnetic models in the near future. Numéro de notice : A2018-669 Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs10122049 date de publication en ligne : 17/12/2018 En ligne : https://doi.org/10.3390/rs10122049 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94271 [article]

Estimation of forest above-ground biomass by geographically weighted regression and machine learning with Sentinel imagery / Lin Chen in Forests, vol 9 n° 10 (October 2018)  

Public [article]  inForests > vol 9 n° 10 (October 2018) Titre : Estimation of forest above-ground biomass by geographically weighted regression and machine learning with Sentinel imagery Type de document : Article/Communication Auteurs : Lin Chen, Auteur ; Chunying Ren, Auteur ; Bai Zhang, Auteur ; Zongming Wang, Auteur ; Yanbiao Xi, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] biomasse aérienne [Termes descripteurs IGN] Changbai, massif du [Termes descripteurs IGN] Chine [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] classification par réseau neuronal [Termes descripteurs IGN] classification par séparateurs à vaste marge [Termes descripteurs IGN] image multibande [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] modèle de simulation [Termes descripteurs IGN] montagne [Termes descripteurs IGN] régression géographiquement pondérée [Termes descripteurs IGN] surveillance forestière [Termes descripteurs IGN] texture d'image [Termes descripteurs IGN] variable biophysique (végétation) Résumé : (Auteur) Accurate forest above-ground biomass (AGB) is crucial for sustaining forest management and mitigating climate change to support REDD+ (reducing emissions from deforestation and forest degradation, plus the sustainable management of forests, and the conservation and enhancement of forest carbon stocks) processes. Recently launched Sentinel imagery offers a new opportunity for forest AGB mapping and monitoring. In this study, texture characteristics and backscatter coefficients of Sentinel-1, in addition to multispectral bands, vegetation indices, and biophysical variables of Sentinal-2, based on 56 measured AGB samples in the center of the Changbai Mountains, China, were used to develop biomass prediction models through geographically weighted regression (GWR) and machine learning (ML) algorithms, such as the artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that texture characteristics and vegetation biophysical variables were the most important predictors. SVR was the best method for predicting and mapping the patterns of AGB in the study site with limited samples, whose mean error, mean absolute error, root mean square error, and correlation coefficient were 4 × 10−3, 0.07, 0.08 Mg·ha−1, and 1, respectively. Predicted values of AGB from four models ranged from 11.80 to 324.12 Mg·ha−1, and those for broadleaved deciduous forests were the most accurate, while those for AGB above 160 Mg·ha−1 were the least accurate. The study demonstrated encouraging results in forest AGB mapping of the normal vegetated area using the freely accessible and high-resolution Sentinel imagery, based on ML techniques. Numéro de notice : A2018-478 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/f9100582 date de publication en ligne : 20/09/2018 En ligne : https://doi.org/10.3390/f9100582 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91180 [article]

Strategies for climate-smart forest management in Austria / Robert Jandl in Forests, vol 9 n° 10 (October 2018)  

Public [article]  inForests > vol 9 n° 10 (October 2018) Titre : Strategies for climate-smart forest management in Austria Type de document : Article/Communication Auteurs : Robert Jandl, Auteur ; Thomas Ledermann, Auteur ; Georg Kindermann, Auteur ; Alexandra Freudenschuss, Auteur ; Thomas Gschwantner, Auteur ; Peter Weiss, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] Autriche [Termes descripteurs IGN] bioénergie [Termes descripteurs IGN] biomasse aérienne [Termes descripteurs IGN] changement climatique [Termes descripteurs IGN] gestion forestière durable [Termes descripteurs IGN] modèle de croissance [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] puits de carbone [Vedettes matières IGN] Végétation et changement climatique Résumé : (Auteur) We simulated Austrian forests under different sustainable management scenarios. A reference scenario was compared to scenarios focusing on the provision of bioenergy, enhancing the delivery of wood products, and reduced harvesting rates. The standing stock of the stem biomass, carbon in stems, and the soil carbon pool were calculated for the period 2010–2100. We used the forest growth model Câldis and the soil carbon model Yasso07. The wood demand of all scenarios could be satisfied within the simulation period. The reference scenario led to a small decrease of the stem biomass. Scenarios aiming at a supply of more timber decreased the standing stock to a greater extent. Emphasizing the production of bioenergy was successful for several decades but ultimately exhausted the available resources for fuel wood. Lower harvesting rates reduced the standing stock of coniferous and increased the standing stock of deciduous forests. The soil carbon pool was marginally changed by different management strategies. We conclude that the production of long-living wood products is the preferred implementation of climate-smart forestry. The accumulation of carbon in the standing biomass is risky in the case of disturbances. The production of bioenergy is suitable as a byproduct of high value forest products. Numéro de notice : A2018-474 Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/f9100592 date de publication en ligne : 22/09/2018 En ligne : https://doi.org/10.3390/f9100592 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91173 [article]

Multi-scale assessment of invasive plant species diversity using Pléiades 1A, RapidEye and Landsat-8 data / Siddhartha Khare in Geocarto international, vol 33 n° 7 (July 2018)  

Permalink

The German Forest Strategy 2020: Target achievement control using national forest inventory results / Martin Lorenz in Annals of forest research, vol 61 n° 2 (July - December 2018)  

Permalink

Vertical stratification of forest canopy for segmentation of understory trees within small-footprint airborne LiDAR point clouds / Hamid Hamraz in ISPRS Journal of photogrammetry and remote sensing, vol 130 (August 2017)  

Permalink

Total canopy transmittance estimated from small-footprint, full-waveform airborne LiDAR / Milutin Milenković in ISPRS Journal of photogrammetry and remote sensing, vol 128 (June 2017)  

Permalink

Le mémento inventaire forestier / IGN (2017)    

Permalink

La forêt en chiffres et en cartes / IGN (2016)    

Permalink

La forêt en chiffres et en cartes / IGN (2014)    

Permalink

La forêt en chiffres et en cartes / IGN (2013) 

Permalink

Vers une sylviculture économe / Laurent Dupayage in Forêt entreprise, n° 188 (2009/5)

Permalink