Centre dedocumentation
scientifique

Forest road extraction from orthophoto images by convolutional neural networks / Erhan Çalişkan in Geocarto international, vol 37 n° inconnu ([25/01/2022])  

Public [article]  inGeocarto international > vol 37 n° inconnu [25/01/2022] . - pp Titre : Forest road extraction from orthophoto images by convolutional neural networks Type de document : Article/Communication Auteurs : Erhan Çalişkan, Auteur ; Yusuf Sevim, Auteur Année de publication : 2022 Article en page(s) : pp Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] chemin forestier [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] extraction automatique [Termes IGN] orthoimage [Termes IGN] segmentation sémantique Résumé : (auteur) Continuous monitoring of the forest road infrastructure and keeping track of the changes occurred are important for forestry practices, map updating, forest fire and forest transport decision support systems. In this context, the most of up to date data can be obtained by automatic forest road extraction from satellite images via machine learning (ML). Acquiring sufficient data is one of the most important factors which affect the success of ML and deep learning (DL). DL architectures yield more consistent results for complex data sets compared with ML algorithms. In the present study, three different deep learning (Resnet-18, MobileNet-V2 and Xception) architectures with semantic segmentation architecture were compared for extracting the forest road network from high-resolution orthophoto images and the results were analyzed. The architectures were evaluated through a multiclass statistical analysis based precision, recall, F1 score, intersection over union and overall accuracy (OA). The results present significant values obtained by the Resnet-18 architecture, with 99.72% of OA and 98.87% of precision and by the MobileNet-V2 architecture, with 97.76% of OA and 98.28% of precision. Also the results show that Resnet-18, MobileNet-V2 semantic segmentation architectures can be used efficiently for forest road extraction. Numéro de notice : A2022-159 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1080/10106049.2022.2060319 Date de publication en ligne : 06/04/2022 En ligne : https://doi.org/10.1080/10106049.2022.2060319 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100380 [article]

An infrastructure perspective for enhancing multi-functionality of forests: A conceptual modeling approach / Mojtaba Houballah in Earth' future, vol 9 n° 1 (January 2021)  

Public [article]  inEarth' future > vol 9 n° 1 (January 2021) . - n° e2019EF001369 Titre : An infrastructure perspective for enhancing multi-functionality of forests: A conceptual modeling approach Type de document : Article/Communication Auteurs : Mojtaba Houballah, Auteur ; Jean-Denis Mathias, Auteur ; Thomas Cordonnier, Auteur Année de publication : 2021 Article en page(s) : n° e2019EF001369 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] chemin forestier [Termes IGN] conservation des ressources naturelles [Termes IGN] développement durable [Termes IGN] gestion forestière durable [Termes IGN] modèle conceptuel de données [Termes IGN] modèle mathématique [Termes IGN] production primaire brute [Termes IGN] service écosystémique [Termes IGN] tourisme [Vedettes matières IGN] Foresterie Résumé : (auteur) Many forest resource systems depend heavily on shared and coupled infrastructures in applying their management strategies. Addressing a question of sustainability for relevant contemporary social-ecological systems (SES) can be tackled by understanding how these shared infrastructures mediate the interaction between human and ecological environment. Shared infrastructures, which are mainly composed of roads (accessibility utilities), highlight the relation between the performance of ecosystem services and the multifunctional use of the forest. However, dilemmas associated with road provision pose some problems when applied in a forest multifunctional management context, because roads potentially diminish or enhance forest functions in a complex way. In this context, maintaining, fostering, and improving multifunctional management where the development of an ecosystem function can affect the performance of others is challenging. We propose to develop a mathematical model based on a recent study that links multifunctional forest management to the multifunctionality of forest roads by using the SES and robustness frameworks. With this model, we analyze the evolution of the forest system and three key forest functions (wood production, tourism, and nature conservation) when impacted by decisions of road provision. We then examine how governance provision strategies can affect the performance of functions and how these strategies can potentially foster forest multifunctionality. This approach allows us to derive conditions of sustainability in which decisions of shared infrastructure provisions can play an important role in the functionalities and performance of the forest. Numéro de notice : A2021-617 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1029/2019EF001369 Date de publication en ligne : 10/12/2020 En ligne : https://doi.org/10.1029/2019EF001369 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98581 [article]

Towards dynamic forest trafficability prediction using open spatial data, hydrological modelling and sensor technology / Aura Salmivaara in Forestry, an international journal of forest research, vol 93 n° 5 (October 2020)  

Public [article]  inForestry, an international journal of forest research > vol 93 n° 5 (October 2020) . - pp 662 - 674 Titre : Towards dynamic forest trafficability prediction using open spatial data, hydrological modelling and sensor technology Type de document : Article/Communication Auteurs : Aura Salmivaara, Auteur ; Samuli Launiainen, Auteur ; Jari Perttunen, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 662 - 674 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Environnement [Termes IGN] apprentissage automatique [Termes IGN] chemin forestier [Termes IGN] classification barycentrique [Termes IGN] dégradation des sols [Termes IGN] dommage [Termes IGN] données localisées libres [Termes IGN] exploitation forestière [Termes IGN] Finlande [Termes IGN] humidité du sol [Termes IGN] modèle dynamique [Termes IGN] modèle hydrographique Résumé : (auteur) Forest harvesting operations with heavy machinery can lead to significant soil rutting. Risks of rutting depend on the soil bearing capacity which has considerable spatial and temporal variability. Trafficability prediction is required in the selection of suitable operation sites for a given time window and conditions, and for on-site route optimization during the operation. Integrative tools are necessary to plan and carry out forest operations with minimal negative ecological and economic impacts. This study demonstrates a trafficability prediction framework that utilizes a spatial hydrological model and a wide range of spatial data. Trafficability was approached by producing a rut depth prediction map at a 16 × 16 m grid resolution, based on the outputs of a general linear mixed model developed using field data from Southern Finland, modelled daily soil moisture, spatial forest inventory and topography data, along with field measured rolling resistance and information on the mass transported through the grid cells. Dynamic rut depth prediction maps were produced by accounting for changing weather conditions through hydrological modelling. We also demonstrated a generalization of the rolling resistance coefficient, measured with harvester CAN-bus channel data. Future steps towards a nationwide prediction framework based on continuous data flow, process-based modelling and machine learning are discussed. Numéro de notice : A2020-790 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1093/forestry/cpaa010 Date de publication en ligne : 05/10/2020 En ligne : https://doi.org/10.1093/forestry/cpaa010 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96559 [article]

Improving drainage conditions of forest roads using the GIS and forest road simulator / Mehran Nasiri in Journal of forest science, vol 66 n° 9 (September 2020)  

Public [article]  inJournal of forest science > vol 66 n° 9 (September 2020) . - pp 361 - 367 Titre : Improving drainage conditions of forest roads using the GIS and forest road simulator Type de document : Article/Communication Auteurs : Mehran Nasiri, Auteur Année de publication : 2020 Article en page(s) : pp 361 - 367 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG [Termes IGN] chemin forestier [Termes IGN] drainage [Termes IGN] écoulement des eaux [Termes IGN] effondrement de terrain [Termes IGN] hydrologie [Termes IGN] Iran [Termes IGN] modèle numérique de surface [Termes IGN] réseau de drainage [Termes IGN] système d'information géographique Résumé : (auteur) In this study a new method of locating culverts is presented with the composition of achieved discharge from hydrological analysis and simulated forest roads in RoadEng 3D simulator to improve drainage condition. Locating culverts was performed on a small scale (1:20 000, using GIS) and large scale (1:2 000, road geometric design simulator). The small-scale study regarding the achieved discharge from streams shows that the installation of some culverts is not necessary. The large-scale study also showed that the geometric design of forest road has a significant effect on locating culverts and its accuracy. To improve drainage conditions 6 culverts and 2 waterfronts taking into account the geometric design of forest road, hydrological conditions and appropriate intervals (155 m) have been proposed. No installation or lack of accuracy to find the best location of culverts may result in the occurrence of creep and landslide, so the cost of destruction would be several times higher than the cost of technical buildings construction. Numéro de notice : A2020-693 Affiliation des auteurs : non IGN Thématique : FORET/GEOMATIQUE Nature : Article DOI : 10.17221/16/2020-JFS Date de publication en ligne : 01/09/2020 En ligne : https://doi.org/10.17221/16/2020-JFS Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96238 [article]

Large scale semi-automatic detection of forest roads from low density LiDAR data on steep terrain in Northern Spain / Convadonga Prendes in iForest, biogeosciences and forestry, vol 12 n° 4 (July 2019)  

Public [article]  iniForest, biogeosciences and forestry > vol 12 n° 4 (July 2019) . - pp 366 - 374 Titre : Large scale semi-automatic detection of forest roads from low density LiDAR data on steep terrain in Northern Spain Type de document : Article/Communication Auteurs : Convadonga Prendes, Auteur ; Sandra Bujan, Auteur ; Celestino Ordóñez, Auteur ; Elena Canga, Auteur Année de publication : 2019 Article en page(s) : pp 366 - 374 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] analyse d'image orientée objet [Termes IGN] axe médian [Termes IGN] chemin forestier [Termes IGN] classification pixellaire [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] Espagne [Termes IGN] montagne Résumé : (auteur) While forest roads are important to forest managers in terms of facilitating the exploitation of wood and timber, their role is far more multifunctional. They permit access to emergency services in the case of forest fires as well as acting as fire breaks, enhance biodiversity, and provide access to the public to enjoy recreational activities. Detailed maps of forest roads are an essential tool for better and more timely forest management and automatic/semi-automatic tools allow not only the creation of forest road databases, but also enable these to be updated. In Spain, LiDAR data for the entire national territory is freely available, and the capture of higher density data is planned in the next few years. As such, the development of a forest road detection methodology based on LiDAR data would allow maps of all forest roads to be developed and regularly updated. The general objective of this work was to establish a low density LiDAR data-based methodology for the semi-automatic detection of the centerline of forest roads on steep terrain with various types of canopy cover. Intensity and slope images were generated using the currently available LiDAR data of the study area (0.5 points m-2). Two image classification approaches were evaluated: pixel-based and object-oriented classification (OBIA). The LiDAR-derived centerlines obtained with the two approaches were compared with the real centerlines which had previously been digitized in the field. The road width, type of surface and type of vegetation cover were also recorded. The effectiveness of the two approaches was evaluated through three quality indicators: correctness, completeness and quality. In addition, the accuracy of the LiDAR-derived centerlines was also evaluated by combining GIS analysis and statistical methods. The pixel-based approach obtained higher values than OBIA for two of the three quality measures (correctness: 93% compared to 90%; and quality: 60% compared to 56%) as well as in terms of positional accuracy (± 5.5 m vs. ± 6.8 for OBIA). The results obtained in this study demonstrate that producing road maps is among the most valuable and easily attainable products of LiDAR data analysis. Numéro de notice : A2019-659 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.3832/ifor2989-012 Date de publication en ligne : 05/07/2019 En ligne : https://doi.org/10.3832/ifor2989-012 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98528 [article]

Routes forestières / Bernard Rérat in Forêts de France, n° 530 (janvier - février 2010)

Permalink

100 jeunes visiteurs pour la semaine du bois / Eric Sevrin in Notre forêt, n° 47 (juin 2009)

Permalink

Desservir une forêt : Pourquoi ? Comment ? / Pierre-Edmond Lelievre in Notre forêt, n° 46 (mars 2009)

Permalink

Desserte forestière : les bénéfices de l'action collective / Patrice Boiron in Le Bois International : l'officiel du bois [édition verte], vol 2008 n° 18 (17 mai 2008)

Permalink