Centre dedocumentation
scientifique

Tree species classification using structural features derived from terrestrial laser scanning / Louise Terryn in ISPRS Journal of photogrammetry and remote sensing, vol 168 (October 2020)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 168 (October 2020) . - pp 170 - 181 Titre : Tree species classification using structural features derived from terrestrial laser scanning Type de document : Article/Communication Auteurs : Louise Terryn, Auteur ; Kim Calders, Auteur ; Mathias I. Disney, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 170 - 181 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] analyse comparative [Termes IGN] arbre (flore) [Termes IGN] classification barycentrique [Termes IGN] classification par régression logistique multinomiale [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] composition d'un peuplement forestier [Termes IGN] couvert forestier [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] espèce végétale [Termes IGN] extraction de traits caractéristiques [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] ombre [Termes IGN] semis de points Résumé : (auteur) Fast and automated collection of forest data, such as species composition information, is required to support climate mitigation actions. Recently, there have been significant advances in the use of terrestrial laser scanning (TLS) instruments, which facilitate the capture of detailed forest structure. However, for tree species recognition the structural information from TLS has mainly been used to complement spectral information. TLS-only classification studies have been limited in size and diversity of plot forest types. In this paper, we investigate the potential of TLS for tree species classification. We used quantitative structure models to determine 17 structural tree features. These features were computed for 758 trees of five tree species, including two understory species, of a 1.4 hectare mixed deciduous forest plot. Three classification methods were compared: k-nearest neighbours, multinomial logistic regression and support vector machine. We assessed the potential underlying causes for structural differences with principal component analysis. We obtained classification success rates of approximately 80%, however, with producer accuracies for three of the five species ranging from 0 to 60%. Low producer accuracies were the result of a high intra- and low inter-species variability. These effects were, respectively, caused by a high size-dependency of the structural features and a convergence of structural traits across species as a result of the individual tree position in the forest canopy and shade tolerance. Nevertheless, the producer accuracies could be improved through sensitivity vs. specificity trade-offs, with over 50% for all species being obtainable. The high intra -and low inter-species variability complicate the classification. Furthermore, the classification performance and best classification method greatly depend on its targeted application. In conclusion, this study proves the added value of TLS for tree species classification but also shows that TLS opens up potential for testing and further development of ecological theory. Numéro de notice : A2020-636 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.08.009 date de publication en ligne : 21/08/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.08.009 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96059 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2020101	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2020103	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2020102	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Improved supervised learning-based approach for leaf and wood classification from LiDAR point clouds of forests / Sruthi M. Krishna Moorthy in IEEE Transactions on geoscience and remote sensing, vol 58 n° 5 (May 2020)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 58 n° 5 (May 2020) . - pp 3057 - 3070 Titre : Improved supervised learning-based approach for leaf and wood classification from LiDAR point clouds of forests Type de document : Article/Communication Auteurs : Sruthi M. Krishna Moorthy, Auteur ; Kim Calders, Auteur ; Matheus B. Vicari, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 3057 - 3070 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage automatique [Termes IGN] apprentissage dirigé [Termes IGN] atmosphère terrestre [Termes IGN] canopée [Termes IGN] classification dirigée [Termes IGN] classification par forêts aléatoires [Termes IGN] données lidar [Termes IGN] faisceau laser [Termes IGN] feuille (végétation) [Termes IGN] foresterie [Termes IGN] forêt de feuillus [Termes IGN] forêt tropicale [Termes IGN] plus proche voisin (algorithme) [Termes IGN] précision de la classification [Termes IGN] Python (langage de programmation) [Termes IGN] semis de points [Termes IGN] transfert radiatif Résumé : (auteur) Accurately classifying 3-D point clouds into woody and leafy components has been an interest for applications in forestry and ecology including the better understanding of radiation transfer between canopy and atmosphere. The past decade has seen an increase in the methods attempting to classify leaves and wood in point clouds based on radiometric or geometric features. However, classification purely based on radiometric features is sensor-specific, and the method by which the local neighborhood of a point is defined affects the accuracy of classification based on geometric features. Here, we present a leaf-wood classification method combining geometrical features defined by radially bounded nearest neighbors at multiple spatial scales in a machine learning model. We compared the performance of three different machine learning models generated by the random forest (RF), XGBoost, and lightGBM algorithms. Using multiple spatial scales eliminates the need for an optimal neighborhood size selection and defining the local neighborhood by radially bounded nearest neighbors makes the method broadly applicable for point clouds of varying quality. We assessed the model performance at the individual tree- and plot-level on field data from tropical and deciduous forests, as well as on simulated point clouds. The method has an overall average accuracy of 94.2% on our data sets. For other data sets, the presented method outperformed the methods in literature in most cases without the need for additional postprocessing steps that are needed in most of the existing methods. We provide the entire framework as an open-source python package. Numéro de notice : A2020-232 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2019.2947198 date de publication en ligne : 31/10/2019 En ligne : https://doi.org/10.1109/TGRS.2019.2947198 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94970 [article]

Remote sensing technology applications in forestry and REDD+ / Kim Calders (2020)  

Public Titre : Remote sensing technology applications in forestry and REDD+ Type de document : Monographie Auteurs : Kim Calders, Éditeur scientifique ; Inge Jonckheere, Éditeur scientifique ; Mikko Vastaranta, Éditeur scientifique ; Joanne Nightingale, Éditeur scientifique Editeur : Bâle [Suisse] : Multidisciplinary Digital Publishing Institute MDPI Année de publication : 2020 Importance : 244 p. ISBN/ISSN/EAN : 978-3-03928-471-9 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] apprentissage automatique [Termes IGN] biomasse aérienne [Termes IGN] canopée [Termes IGN] cartographie des risques [Termes IGN] déboisement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] image Landsat [Termes IGN] image multibande [Termes IGN] image Sentinel [Termes IGN] Pinus massoniana [Termes IGN] polarimétrie radar [Termes IGN] télémétrie laser aéroporté [Termes IGN] télémétrie laser terrestre Résumé : (Editeur) Advances in close-range and remote sensing technologies are driving innovations in forest resource assessments and monitoring on varying scales. Data acquired with airborne and spaceborne platforms provide high(er) spatial resolution, more frequent coverage, and more spectral information. Recent developments in ground-based sensors have advanced 3D measurements, low-cost permanent systems, and community-based monitoring of forests. The UNFCCC REDD+ mechanism has advanced the remote sensing community and the development of forest geospatial products that can be used by countries for the international reporting and national forest monitoring. However, an urgent need remains to better understand the options and limitations of remote and close-range sensing techniques in the field of forest degradation and forest change. Therefore, we invite scientists working on remote sensing technologies, close-range sensing, and field data to contribute to this Special Issue. Topics of interest include: (1) novel remote sensing applications that can meet the needs of forest resource information and REDD+ MRV, (2) case studies of applying remote sensing data for REDD+ MRV, (3) timeseries algorithms and methodologies for forest resource assessment on different spatial scales varying from the tree to the national level, and (4) novel close-range sensing applications that can support sustainable forestry and REDD+ MRV. We particularly welcome submissions on data fusion. Numéro de notice : 26296 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Monographie DOI : 10.3390/books978-3-03928-471-9 date de publication en ligne : 07/04/2020 En ligne : https://doi.org/10.3390/books978-3-03928-471-9 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95009

Assessing the structural differences between tropical forest types using Terrestrial Laser Scanning / Mathieu Decuyper in Forest ecology and management, vol 429 (1 December 2018)  

Public [article]  inForest ecology and management > vol 429 (1 December 2018) . - pp 327 - 335 Titre : Assessing the structural differences between tropical forest types using Terrestrial Laser Scanning Type de document : Article/Communication Auteurs : Mathieu Decuyper, Auteur ; Kalkidan Ayele Mulatu, Auteur ; Benjamin Brede, Auteur ; Kim Calders, Auteur ; John Armston, Auteur ; et al., Auteur Année de publication : 2018 Article en page(s) : pp 327 - 335 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] canopée [Termes IGN] Coffea (genre) [Termes IGN] Coffea arabica [Termes IGN] données hétérogènes [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Ethiopie [Termes IGN] forêt tropicale [Termes IGN] structure d'un peuplement forestier [Termes IGN] sylvopastoralisme Résumé : (Auteur) Increasing anthropogenic pressure leads to loss of habitat through deforestation and degradation in tropical forests. While deforestation can be monitored relatively easily, forest management practices are often subtle processes, that are difficult to capture with for example satellite monitoring. Conventional measurements are well established and can be useful for management decisions, but it is believed that Terrestrial Laser Scanning (TLS) has a role in quantitative monitoring and continuous improvement of methods. In this study we used a combination of TLS and conventional forest inventory measures to estimate forest structural parameters in four different forest types in a tropical montane cloud forest in Kafa, Ethiopia. Here, the four forest types (intact forest, coffee forest, silvopasture, and plantations) are a result of specific management practices (e.g. clearance of understory in coffee forest), and not different forest communities or tree types. Both conventional and TLS derived parameters confirmed our assumptions that intact forest had the highest biomass, silvopasture had the largest canopy gaps, and plantations had the lowest canopy openness. Contrary to our expectations, coffee forest had higher canopy openness and similar biomass as silvopasture, indicating a significant loss of forest structure. The 3D vegetation structure (PAVD – Plant area vegetation density) was different between the forest types with the highest PAVD in intact forest and plantation canopy. Silvopasture was characterised by a low canopy but high understorey PAVD, indicating regeneration of the vegetation and infrequent fuelwood collection and/or non-intensive grazing. Coffee forest canopy had low PAVD, indicating that many trees had been removed, despite coffee needing canopy shade. These findings may advocate for more tangible criteria such as canopy openness thresholds in sustainable coffee certification schemes. TLS as tool for monitoring forest structure in plots with different forest types shows potential as it can capture the 3D position of the vegetation volume and open spaces at all heights in the forest. To quantify changes in different forest types, consistent monitoring of 3D structure is needed and here TLS is an add-on or an alternative to conventional forest structure monitoring. However, for the tropics, TLS-based automated segmentation of trees to derive DBH and biomass is not widely operational yet, nor is species richness determination in forest monitoring. Integration of data sources is needed to fully understand forest structural diversity and implications of forest management practices on different forest types. Numéro de notice : A2018-467 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.foreco.2018.07.032 date de publication en ligne : 23/07/2018 En ligne : https://doi.org/10.1016/j.foreco.2018.07.032 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91146 [article]

Evaluation of the range accuracy and the radiometric calibration of multiple terrestrial laser scanning instruments for data interoperability / Kim Calders in IEEE Transactions on geoscience and remote sensing, vol 55 n° 5 (May 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 5 (May 2017) . - pp 2716 - 2724 Titre : Evaluation of the range accuracy and the radiometric calibration of multiple terrestrial laser scanning instruments for data interoperability Type de document : Article/Communication Auteurs : Kim Calders, Auteur ; Mathias I. Disney, Auteur ; John Armston, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 2716 - 2724 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] acquisition de données [Termes IGN] analyse comparative [Termes IGN] étalonnage radiométrique [Termes IGN] évaluation des données [Termes IGN] interopérabilité sémantique [Termes IGN] précision métrique [Termes IGN] réflectance [Termes IGN] télémètre laser terrestre Résumé : (Auteur) Terrestrial laser scanning (TLS) data provide 3-D measurements of vegetation structure and have the potential to support the calibration and validation of satellite and airborne sensors. The increasing range of different commercial and scientific TLS instruments holds challenges for data and instrument interoperability. Using data from various TLS sources will be critical to upscale study areas or compare data. In this paper, we provide a general framework to compare the interoperability of TLS instruments. We compare three TLS instruments that are the same make and model, the RIEGL VZ-400. We compare the range accuracy and evaluate the manufacturer's radiometric calibration for the uncalibrated return intensities. Our results show that the range accuracy between instruments is comparable and within the manufacturer's specifications. This means that the spatial XYZ data of different instruments can be combined into a single data set. Our findings demonstrate that radiometric calibration is instrument specific and needs to be carried out for each instrument individually before including reflectance information in TLS analysis. We show that the residuals between the calibrated reflectance panels and the apparent reflectance measured by the instrument are greatest for highest reflectance panels (residuals ranging from 0.058 to 0.312). Numéro de notice : A2017-468 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://dx.doi.org/10.1109/TGRS.2017.2652721 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86391 [article]