Centre dedocumentation
scientifique

An automatic approach for tree species detection and profile estimation of urban street trees using deep learning and Google street view images / Kwanghun Choi in ISPRS Journal of photogrammetry and remote sensing, vol 190 (August 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 190 (August 2022) . - pp 165 - 180 Titre : An automatic approach for tree species detection and profile estimation of urban street trees using deep learning and Google street view images Type de document : Article/Communication Auteurs : Kwanghun Choi, Auteur ; Wontaek LIM, Auteur ; Byungwoo Chang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 165 - 180 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] arbre urbain [Termes IGN] détection automatique [Termes IGN] détection d'arbres [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] gestion forestière durable [Termes IGN] image Streetview [Termes IGN] inventaire de la végétation [Termes IGN] segmentation sémantique [Termes IGN] Séoul Résumé : (auteur) Tree species and canopy structural profile (‘tree profile’) are among the most critical environmental factors in determining urban ecosystem services such as climate and air quality control from urban trees. To accurately characterize a tree profile, the tree diameter, height, crown width, and height to the lowest live branch must be all measured, which is an expensive and time-consuming procedure. Recent advances in artificial intelligence aids to efficiently and accurately measure the aforementioned tree profile parameters. This can be particularly helpful if spatially extensive and accurate street-level images provided by Google (‘streetview’) or Kakao (‘roadview’) are utilized. We focused on street trees in Seoul, the capital city of South Korea, and suggested a novel approach to create a tree profile and inventory based on deep learning algorithms. We classified urban tree species using the YOLO (You Only Look Once), one of the most popular deep learning object detection algorithms, which provides an uncomplicated method of creating datasets with custom classes. We further utilized semantic segmentation algorithm and graphical analysis to estimate tree profile parameters by determining the relative location of the interface of tree and ground surface. We evaluated the performance of the model by comparing the estimated tree heights, diameters, and locations from the model with the field measurements as ground truth. The results are promising and demonstrate the potential of the method for creating urban street tree profile inventory. In terms of tree species classification, the method showed the mean average precision (mAP) of 0.564. When we used the ideal tree images, the method also reported the normalized root mean squared error (NRMSE) for the tree height, diameter at breast height (DBH), and distances from the camera to the trees as 0.24, 0.44, and 0.41. Numéro de notice : A2022-503 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.06.004 Date de publication en ligne : 22/06/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.06.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101001 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2022081	SL	Revue	Centre de documentation	Revues en salle	Disponible
081-2022083	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2022082	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Green infrastructure planning through EO and GIS analysis: the canopy plan of Liège, Belgium, to mitigate its urban heat island / Benjamin Beaumont in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-4-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-4-2022 (2022 edition) . - pp 243 - 250 Titre : Green infrastructure planning through EO and GIS analysis: the canopy plan of Liège, Belgium, to mitigate its urban heat island Type de document : Article/Communication Auteurs : Benjamin Beaumont, Auteur ; Yasmina Loozen, Auteur ; Thibault Castin, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 243 - 250 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Analyse spatiale [Termes IGN] arbre urbain [Termes IGN] ilot thermique urbain [Termes IGN] image aérienne [Termes IGN] Liège [Termes IGN] planification urbaine [Termes IGN] plantation forestière Résumé : (auteur) As a place to live, work and play, urban spaces are the nerve centers of human activity. The urban spaces, which are becoming increasingly extensive and dense, are particularly sensitive to the effects of climate change. Greening cities has been identified as one of the most effective ways to mitigate one of these effects, the urban heat island. In this context, the city of Liège, Belgium, has adopted a greening plan, called “Plan canopée”, to increase the tree canopy area at city level. The aim of this study is to present the methodology used to objectivize and prioritize the selection of potential planting sites. This research proposes the production of a series of spatial indicators allowing, on the one hand, the precise mapping of urban surfaces ready for planting, and on the other hand, the objective prioritization of city districts to be vegetated. The research integrates airborne image classification, urban heat island modeling and a series of reference geodata combinations. The set of data produced provides a transparent decision support tool to the authorities for the operational planning of tree plantations. These results contribute to the development of a planting strategy that maximizes the chances of ownership by the citizens, and consequently the sustainable and effective impact of the achievements. Numéro de notice : A2022-423 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.5194/isprs-annals-V-4-2022-243-2022 Date de publication en ligne : 18/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-4-2022-243-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100727 [article]

Effects of climate and drought on stem diameter growth of urban tree species / Vjosa Dervishi in Forests, vol 13 n° 5 (May 2022)  

Public [article]  inForests > vol 13 n° 5 (May 2022) . - n° 641 Titre : Effects of climate and drought on stem diameter growth of urban tree species Type de document : Article/Communication Auteurs : Vjosa Dervishi, Auteur ; Werner Poschenrieder, Auteur ; Thomas Rötzer, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 641 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Aesculus hippocastanum [Termes IGN] Allemagne [Termes IGN] arbre urbain [Termes IGN] changement climatique [Termes IGN] croissance des arbres [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] Paris (75) [Termes IGN] Platanus ×hispanica [Termes IGN] Quercus nigra [Termes IGN] Quercus pedunculata [Termes IGN] Robinia pseudoacacia [Termes IGN] sécheresse [Termes IGN] Tilia cordata [Termes IGN] zone urbaine [Vedettes matières IGN] Végétation et changement climatique Résumé : (auteur) Urbanization and climate change are two inevitable megatrends of this century. Knowledge about the growth responses of urban trees to climate is of utmost importance towards future management of green infrastructure with the aim of a sustainable provision of the environmental ecosystem services. Using tree-ring records, this study analyzed growth response to climate by stem diameter at breast height (DBH) of 1178 trees in seven large cities worldwide, including Aesculus hippocastanum L. in Munich; Platanus × hispanica Münchh. in Paris; Quercus nigra L. in Houston; Quercus robur L. in Cape Town; Robinia pseudoacacia L. in Santiago de Chile, Munich, and Würzburg; and Tilia cordata Mill. in Berlin, Munich, and Würzburg. Climate was characterized following the de Martonne aridity index (DMI). Overall, trees showed an 8.3% lower DBH under arid than humid climate at the age of 100. Drought-tolerant tree species were overall not affected by climate. However, R. pseudoacacia showed a lower diameter when growing in semi-dry than humid climate. In contrast, drought-sensitive tree species were negatively affected by arid climate. Moreover, the effect of drought years on annual diameter increment was assessed. P. × hispanica and R. pseudoacacia appeared as the most drought-resistant species. The highest sensitivity to drought was detected in T. cordata and Q. robur. A. hippocastanum and Q. nigra showed a lower diameter growth during drought events, followed by a fast recovery. This study’s findings may contribute to a better understanding of urban tree growth reactions to climate, aiming for sustainable planning and management of urban trees. Numéro de notice : A2022-348 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.3390/f13050641 En ligne : https://doi.org/10.3390/f13050641 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100534 [article]

Procedural urban forestry / Till Niese in ACM Transactions on Graphics, TOG, Vol 41 n° 2 (April 2022)  

Public [article]  inACM Transactions on Graphics, TOG > Vol 41 n° 2 (April 2022) . - pp 1 - 18 Titre : Procedural urban forestry Type de document : Article/Communication Auteurs : Till Niese, Auteur ; Sören Pirk,, Auteur ; Matthias Albrecht,, Auteur Année de publication : 2022 Article en page(s) : pp 1 - 18 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] arbre urbain [Termes IGN] paysage urbain [Termes IGN] placement automatique des objets [Termes IGN] scène urbaine [Termes IGN] scène virtuelle Résumé : (auteur) The placement of vegetation plays a central role in the realism of virtual scenes. We introduce procedural placement models (PPMs) for vegetation in urban layouts. PPMs are environmentally sensitive to city geometry and allow identifying plausible plant positions based on structural and functional zones in an urban layout. PPMs can either be directly used by defining their parameters or learned from satellite images and land register data. This allows us to populate urban landscapes with complex 3D vegetation and enhance existing approaches for generating urban landscapes. Our framework’s effectiveness is shown through examples of large-scale city scenes and close-ups of individually grown tree models. We validate the results generated with our framework with a perceptual user study and its usability based on urban scene design sessions with expert users. Numéro de notice : A2022-152 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1145/3502220 En ligne : https://doi.org/10.1145/3502220 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100371 [article]

Comparison of UAV-based LiDAR and digital aerial photogrammetry for measuring crown-level canopy height in the urban environment / Longfei Zhou in Urban Forestry & Urban Greening, vol 69 (March 2022)  

Public [article]  inUrban Forestry & Urban Greening > vol 69 (March 2022) . - n° 127489 Titre : Comparison of UAV-based LiDAR and digital aerial photogrammetry for measuring crown-level canopy height in the urban environment Type de document : Article/Communication Auteurs : Longfei Zhou, Auteur ; Ran Meng, Auteur ; Yiyang Tan, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 127489 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] analyse comparative [Termes IGN] arbre urbain [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] forêt urbaine [Termes IGN] hauteur des arbres [Termes IGN] houppier [Termes IGN] image captée par drone [Termes IGN] modèle numérique de terrain [Termes IGN] structure-from-motion Résumé : (auteur) Spatial information on urban forest canopy height (FCH) is fundamental for urban forest monitoring and assisting urban planning and management. Traditionally, ground-based canopy height measurements are time-consuming and laborious, making it challenging for periodic inventory of urban FCH at crown level. Airborne-light detection and ranging (LiDAR) sensor can efficiently measure crown-level FCH; however, the high cost of airborne-LiDAR data collection over large scales hinders its wide applications at a high temporal resolution. Previous studies have shown that in some cases, the Unmanned Aerial Vehicle (UAV)-digital aerial photogrammetry (DAP) approach (i.e., UAV-based structure from motion algorithm) is equivalent to or even outperform airborne-LiDAR in measuring forest structure, but few studies have evaluated their performances in measuring FCH in more complex urban environment, across non-ground coverage (including both canopy and building coverage) and topographical slope gradients. Also, the contribution of multi-angle measurement technique from UAV-DAP to FCH estimation accuracy has rarely been explored in the urban environment. Here, we compared the performances of UAV-LiDAR and UAV-DAP approaches on measuring thousands of crown-level FCH at different non-ground coverage and topographical slope areas in an urban environment. Specifically, UAV-LiDAR-based spatial measurements of crown-level FCH were used as the reference after ground-based validation (R2 = 0.88, RMSE = 2.36 m). The accuracy of UAV-DAP approach with/without multi-angle measurement in different non-ground coverage and topographical slope areas were then analyzed. The results showed that although the DAP multi-angle-based approach can improve the accuracy of spatial measurement for crown-level FCH in some cases, non-ground coverage (including both canopy and building coverage) was still the main factor affecting the broad applications of DAP approach in measuring urban FCH: at areas where non-ground coverage 0.95, except for the case of flat areas (i.e., topographical slope 0.95, can significantly improve the accuracy of UAV-DAP approach in measuring crown-level FCH (R2 = 0.91, RMSE =1.61 m). Our study thus provides a complete guidance on the usage of cost-effective UAV-DAP approach for measuring crown-level FCH in the urban environment, which will be helpful for precise urban forest management and improving the efficiency of urban environmental planning. Numéro de notice : A2022-318 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.ufug.2022.127489 Date de publication en ligne : 26/01/2022 En ligne : https://doi.org/10.1016/j.ufug.2022.127489 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100424 [article]

Generating 2m fine-scale urban tree cover product over 34 metropolises in China based on deep context-aware sub-pixel mapping network / Da He in International journal of applied Earth observation and geoinformation, vol 106 (February 2022)  

Permalink

Quantifying the shape of urban street trees and evaluating its influence on their aesthetic functions based on mobile lidar data / Tianyu Hu in ISPRS Journal of photogrammetry and remote sensing, vol 184 (February 2022)  

Permalink

Geospatial assessment of urban ecosystem disservices: An example of poisonous urban trees in Berlin, Germany / Peer von Döhren in Urban Forestry & Urban Greening, vol 67 (January 2022)  

Permalink

Classification of tree species in a heterogeneous urban environment using object-based ensemble analysis and World View-2 satellite imagery / Simbarashe Jombo in Applied geomatics, vol 13 n° 3 (September 2021)  

Permalink

Numerical modelling for analysis of the effect of different urban green spaces on urban heat load patterns in the present and in the future / Tamás Gál in Computers, Environment and Urban Systems, vol 87 (May 2021)  

Permalink

Automated street tree inventory using mobile LiDAR point clouds based on Hough transform and active contours / Amir Hossein Safaie in ISPRS Journal of photogrammetry and remote sensing, vol 174 (April 2021)  

Permalink

Détection et reconstruction 3D d’arbres urbains par segmentation de nuages de points : apport de l’apprentissage profond / Victor Alteirac (2021)  

Permalink

Learning to map street-side objects using multiple views / Ahmed Samy Nassar (2021)  

Permalink

Proposition d’un référentiel de description et de détection de la végétation dans une agglomération / Mathilde Segaud (2021) 

Permalink

A novel intelligent classification method for urban green space based on high-resolution remote sensing images / Zhiyu Xu in Remote sensing, vol 12 n° 22 (December-1 2020)  

Permalink