Centre dedocumentation
scientifique

Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data / Laura Elena Cué La Rosa in ISPRS Journal of photogrammetry and remote sensing, vol 179 (September 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 179 (September 2021) . - pp 35 - 49 Titre : Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data Type de document : Article/Communication Auteurs : Laura Elena Cué La Rosa, Auteur ; Camile Sothe, Auteur ; Raul Queiroz Feitosa, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 35 - 49 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Brésil [Termes IGN] carte de la végétation [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] densité de la végétation [Termes IGN] données d'apprentissage [Termes IGN] espèce végétale [Termes IGN] étiquetage sémantique [Termes IGN] forêt tropicale [Termes IGN] image captée par drone [Termes IGN] image hyperspectrale Résumé : (Auteur) This work proposes a multi-task fully convolutional architecture for tree species mapping in dense forests from sparse and scarce polygon-level annotations using hyperspectral UAV-borne data. Our model implements a partial loss function that enables dense tree semantic labeling outcomes from non-dense training samples, and a distance regression complementary task that enforces tree crown boundary constraints and substantially improves the model performance. Our multi-task architecture uses a shared backbone network that learns common representations for both tasks and two task-specific decoders, one for the semantic segmentation output and one for the distance map regression. We report that introducing the complementary task boosts the semantic segmentation performance compared to the single-task counterpart in up to 11% reaching an average user’s accuracy of 88.63% and an average producer’s accuracy of 88.59%, achieving state-of-art performance for tree species classification in tropical forests. Numéro de notice : A2021-575 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.07.001 Date de publication en ligne : 28/07/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.07.001 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98175 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2021091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2021093	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2021092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Target-based automated matching of multiple terrestrial laser scans for complex forest scenes / Xuming Ge in ISPRS Journal of photogrammetry and remote sensing, vol 179 (September 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 179 (September 2021) . - pp 1 - 13 Titre : Target-based automated matching of multiple terrestrial laser scans for complex forest scenes Type de document : Article/Communication Auteurs : Xuming Ge, Auteur ; Qing Zhu, Auteur Année de publication : 2021 Article en page(s) : pp 1 - 13 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] appariement de données localisées [Termes IGN] biomasse aérienne [Termes IGN] biomasse forestière [Termes IGN] densité de la végétation [Termes IGN] détection d'arbres [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] scène forestière [Termes IGN] semis de points Résumé : (Auteur) Terrestrial laser scanners are widely used to derive unbiased and non-destructive estimates of the vertical distribution of the plant area index and plant area volume density at plot-level scales, as well as the above-ground biomass, height, and diameter at breast height of individual trees. Multiple scans are often employed to capture and register data so that all of the stems can be detected and their complete forms can be analyzed. Researchers have traditionally preferred target-less strategies to register scans because of their low cost and convenience. However, in complex forest scenes, even state-of-the-art approaches cannot guarantee the success of any pairwise registration. In this study, we present an automated target-based processing approach for the registration of unordered scans in complex forest scenes. In contrast to previous studies, the proposed registration method automatically detects the artificial targets and builds a geometric network to judge their connectivity. A pose graph is then exploited to combine these data with the corresponding pairwise transformation, and then the scans are integrated into a unified coordinate system. This method is more robust and efficient than target-less approaches because it is independent of the characteristics of individual trees and does not require ground information. In an experimental scenario, we use an extremely complex wild bamboo forest scene to evaluate the performance of the proposed approach in terms of robustness, accuracy, and efficiency. Numéro de notice : A2021-573 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.06.019 Date de publication en ligne : 15/07/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.06.019 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98173 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2021091	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2021093	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2021092	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Comparison of two parameter recovery methods for the transformation of Pinus sylvestris yield tables into a diameter distribution model / Francisco Mauro in Annals of Forest Science [en ligne], vol 78 n° 1 (March 2021)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 78 n° 1 (March 2021) . - n° 12 Titre : Comparison of two parameter recovery methods for the transformation of Pinus sylvestris yield tables into a diameter distribution model Type de document : Article/Communication Auteurs : Francisco Mauro, Auteur ; Antonio Garcia-Abril, Auteur ; Esperanza Ayuga-Téllez, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 12 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] analyse comparative [Termes IGN] croissance des arbres [Termes IGN] densité de la végétation [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] diamètre des arbres [Termes IGN] distribution spatiale [Termes IGN] Espagne [Termes IGN] Pinus sylvestris [Termes IGN] structure d'un peuplement forestier [Vedettes matières IGN] Sylviculture Résumé : (auteur) Key message: We successfully transformed Pinus sylvestris yield tables into diameter distribution models. The best results were obtained with the parameter recovery method based on both mean and quadratic mean diameter, which explained 70% of the variability of frequencies by diameter classes and provided better results in the analysis of errors. On the other hand, the method based on stand density, dominant diameter and quadratic mean diameter explained less variability of frequencies by diameter classes (64.4%). Context: Old datasets used to develop yield table models can be recovered to transform those yield tables into diameter distribution models that provide a more detailed description of size variability and forest structure. Methods: We compared two different parameter recovery methods, one based on both mean and quadratic mean diameter and another one based on dominant diameter, stand density and quadratic mean diameter and used a set of 104 even aged plots to analyze the performance of the said methods for the transformation of Pinus sylvestris L yield tables in central Spain into a diameter distribution model. Results: The parameter recovery method based on both mean and quadratic mean diameter explained 70% of the variability of frequencies by diameter classes and provided better results than the method based on stand density, dominant diameter and quadratic mean diameter that explained 64.4% of the variability of frequencies by diameter classes. However, more important than the method itself were the errors that propagated from the models predicting the different variables used in the parameter recovery. Conclusion: Based on the results from the analysis of errors by diameter classes, the method using both mean and quadratic mean diameter outperformed the method using dominant diameter, stand density and quadratic mean diameter and is the best option to transform P. sylvestris yield tables into diameter distribution models. Numéro de notice : A2021-164 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-021-01028-5 Date de publication en ligne : 28/01/2021 En ligne : https://doi.org/10.1007/s13595-021-01028-5 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97094 [article]

Modeling size-density trajectories of even-aged ash (Fraxinus excelsior L.) stands in France. A baseline to assess the impact of Chalara ash dieback / Noël Le Goff in Annals of Forest Science [en ligne], vol 78 n° 1 (March 2021)  

Public [article]  inAnnals of Forest Science [en ligne] > vol 78 n° 1 (March 2021) . - n° 3 Titre : Modeling size-density trajectories of even-aged ash (Fraxinus excelsior L.) stands in France. A baseline to assess the impact of Chalara ash dieback Type de document : Article/Communication Auteurs : Noël Le Goff, Auteur ; François Ningre, Auteur ; Jean-Marc Ottorini, Auteur Année de publication : 2021 Article en page(s) : n° 3 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] densité de la végétation [Termes IGN] dépérissement [Termes IGN] éclaircie (sylviculture) [Termes IGN] foresterie [Termes IGN] France (administrative) [Termes IGN] Fraxinus excelsior [Termes IGN] Fungi [Termes IGN] maladie phytosanitaire [Termes IGN] modèle de croissance végétale [Termes IGN] mortalité [Vedettes matières IGN] Sylviculture Résumé : (auteur) Key message: A piecewise polynomial function already used to represent the size-density trajectories of pure even-aged stands of beech, oak, and Douglas-fir proved its ability to represent the size-density trajectories of a new species, ash. The widespread ash dieback caused departures from the expected size-density trajectories. These abnormalities can be used to detect an extra level of mortality due to infection by Hymenoscyphus fraxineus in pure even-aged ash stands. Context: The size-density trajectories allow quantifying more precisely the density of stands and can help the forest manager to decide of the opportunity of thinnings. This study helped to quantify extra mortality in pure even-aged stands by using the size-density trajectories established for stands evolving at maximum density. Aims: This study was conducted to establish size-density trajectories of pure even-aged ash stands and compare them with those recently established for beech and oak in France, in particular concerning the onset of density-dependent (regular) mortality. The additional effect of ash dieback on mortality was also an issue. Material and methods: We used permanent and semi-permanent unthinned ash plots installed in the north of France and where inventories of trees were performed at more or less regular intervals: measurements included tree status (dead or alive) and diameter or girth at breast height for all trees and total height for a sample of living trees. The size-density trajectories of plots describing the course of the number of living trees in relation with the mean stand girth, in logarithmic scales, were modeled with a piecewise polynomial function fitted with a mixed-effects model. A permanent sample of trees was also selected for ash dieback and extra mortality monitoring. Results: The piecewise polynomial function already used proved its ability to represent the size-density trajectories of even-aged ash stands of various initial densities and fertility levels. As for beech and oak, the trajectories were modeled so that mortality onset occurred at a constant relative density. This level appeared to be much higher for ash (RDI = 0.58), revealing that ash survived with less growing space than beech and oak and appeared to be more efficient. Ash dieback caused an additional mortality in the experimental ash stands studied, and this excess of mortality appeared predictable on the basis of observed departures from the expected size-density trajectories. Conclusion: A single parameter function family could be used to predict the size-density trajectories of even-aged ash stands, on the basis of the results obtained previously on oak and beech. Mortality onset and space requirements of ash could be compared with those of beech and oak and show that ash can survive at higher densities and is a more efficient species. Predicted size-density trajectories proved also useful to detect and quantify the excess of mortality due to H. fraxineus on ash. This approach could be extended to other diseases and species with predictable size-density trajectories. Numéro de notice : A2021-475 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-020-01005-4 Date de publication en ligne : 07/01/2021 En ligne : https://doi.org/10.1007/s13595-020-01005-4 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97095 [article]

A density-based algorithm for the detection of individual trees from LiDAR data / Melissa Latella in Remote sensing, Vol 13 n° 2 (January-2 2021)  

Public [article]  inRemote sensing > Vol 13 n° 2 (January-2 2021) . - n° 322 Titre : A density-based algorithm for the detection of individual trees from LiDAR data Type de document : Article/Communication Auteurs : Melissa Latella, Auteur ; Fabio Sola, Auteur ; Carlo Camporeal, Auteur Année de publication : 2021 Article en page(s) : n° 322 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] arbre (flore) [Termes IGN] comptage [Termes IGN] densité de la végétation [Termes IGN] détection d'arbres [Termes IGN] distribution spatiale [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] forêt de feuillus [Termes IGN] hauteur des arbres [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] semis de points [Termes IGN] sous-étage Résumé : (auteur) Nowadays, LiDAR is widely used for individual tree detection, usually providing higher accuracy in coniferous stands than in deciduous ones, where the rounded-crown, the presence of understory vegetation, and the random spatial tree distribution may affect the identification algorithms. In this work, we propose a novel algorithm that aims to overcome these difficulties and yield the coordinates and the height of the individual trees on the basis of the point density features of the input point cloud. The algorithm was tested on twelve deciduous areas, assessing its performance on both regular-patterned plantations and stands with randomly distributed trees. For all cases, the algorithm provides high accuracy tree count (F-score > 0.7) and satisfying stem locations (position error around 1.0 m). In comparison to other common tools, the algorithm is weakly sensitive to the parameter setup and can be applied with little knowledge of the study site, thus reducing the effort and cost of field campaigns. Furthermore, it demonstrates to require just 2 points·m−2 as minimum point density, allowing for the analysis of low-density point clouds. Despite its simplicity, it may set the basis for more complex tools, such as those for crown segmentation or biomass computation, with potential applications in forest modeling and management. Numéro de notice : A2021-196 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3390/rs13020322 Date de publication en ligne : 19/01/2021 En ligne : https://doi.org/10.3390/rs13020322 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97146 [article]

Competition overrides climate as trigger of growth decline in a mixed Fagaceae Mediterranean rear-edge forest / Alvaro Rubio-Cuadrado in Annals of Forest Science [en ligne], vol 77 n° 4 (December 2020)  

Permalink

Weighted spherical sampling of point clouds for forested scenes / Alex Fafard in Photogrammetric Engineering & Remote Sensing, PERS, vol 86 n° 10 (October 2020)  

Permalink

Local color and morphological image feature based vegetation identification and its application to human environment street view vegetation mapping, or how green is our county? / Istvan G. Lauko in Geo-spatial Information Science, vol 23 n° 3 (September 2020)  

Permalink

Decreasing stand density favors resistance, resilience, and recovery of Quercus petraea trees to a severe drought, particularly on dry sites / Anna Schmitt in Annals of Forest Science [en ligne], Vol 77 n° 2 (June 2020)  

Permalink

Size-class structure of the forests of Finland during 1921–2013: a recovery from centuries of exploitation, guided by forest policies / Helena M. Henttonen in European Journal of Forest Research, vol 139 n° 2 (April 2020)  

Permalink

Efficiency of post-stratification for a large-scale forest inventory : case Finnish NFI / Helena Haakana in Annals of Forest Science [en ligne], vol 76 n° 1 (March 2019)  

Permalink

When do dendrometric rules fail? Insights from 20 years of experimental thinnings on sessile oak in the GIS Coop network / Raphaël Trouvé in Forest ecology and management, vol 433 (15 February 2019)  

Permalink

TanDEM-X digital surface models in boreal forest above-ground biomass change detection / Kirsi Karila in ISPRS Journal of photogrammetry and remote sensing, vol 148 (February 2019)  

Permalink

Bridging the gap: toward a French MS-NFI for territories / Jean-Pierre Renaud (2019)

Permalink

Correcting for nondetection in estimating forest characteristics from single-scan terrestrial laser measurements / Mikko Kuronen in Canadian Journal of Forest Research, vol 49 n° 1 (janvier 2019)  

Permalink