Centre dedocumentation
scientifique

Mask R-CNN-based building extraction from VHR satellite data in operational humanitarian action: An example related to Covid-19 response in Khartoum, Sudan / Dirk Tiede in Transactions in GIS, Vol 25 n° 3 (June 2021)  

Public [article]  inTransactions in GIS > Vol 25 n° 3 (June 2021) . - pp 1213-1227 Titre : Mask R-CNN-based building extraction from VHR satellite data in operational humanitarian action: An example related to Covid-19 response in Khartoum, Sudan Type de document : Article/Communication Auteurs : Dirk Tiede, Auteur ; Gina Schwendemann, Auteur ; Ahmad Alobaidi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 1213-1227 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection du bâti [Termes IGN] échantillonnage [Termes IGN] épidémie [Termes IGN] gestion de crise [Termes IGN] HRV (capteur) [Termes IGN] image à très haute résolution [Termes IGN] image Pléiades-HR [Termes IGN] itération [Termes IGN] Soudan Résumé : Auteur) Within the constraints of operational work supporting humanitarian organizations in their response to the Covid-19 pandemic, we conducted building extraction for Khartoum, Sudan. We extracted approximately 1.2 million dwellings and buildings, using a Mask R-CNN deep learning approach from a Pléiades very high-resolution satellite image with 0.5 m pixel resolution. Starting from an untrained network, we digitized a few hundred samples and iteratively increased the number of samples by validating initial classification results and adding them to the sample collection. We were able to strike a balance between the need for timely information and the accuracy of the result by combining the output from three different models, each aiming at distinctive types of buildings, in a post-processing workflow. We obtained a recall of 0.78, precision of 0.77 and F1 score of 0.78, and were able to deliver first results in only 10 days after the initial request. The procedure shows the great potential of convolutional neural network frameworks in combination with GIS routines for dwelling extraction even in an operational setting. Numéro de notice : A2021-464 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12766 date de publication en ligne : 06/05/2021 En ligne : https://doi.org/10.1111/tgis.12766 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98060 [article]

Mixture effect on radial stem and shoot growth differs and varies with temperature / Maude Toïgo in Forest ecology and management, vol 488 (15 May 2021)  

Public [article]  inForest ecology and management > vol 488 (15 May 2021) . - n° 119046 Titre : Mixture effect on radial stem and shoot growth differs and varies with temperature Type de document : Article/Communication Auteurs : Maude Toïgo, Auteur ; Gaël Ledoux, Auteur ; Soline Martin-Blangy, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 119046 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Abies alba [Termes IGN] Alpes (France) [Termes IGN] climat [Termes IGN] croissance des arbres [Termes IGN] diamètre des arbres [Termes IGN] échantillonnage [Termes IGN] Fagus sylvatica [Termes IGN] forêt tempérée [Termes IGN] houppier [Termes IGN] indice de stress [Termes IGN] peuplement mélangé [Termes IGN] Quercus pubescens [Termes IGN] température [Vedettes matières IGN] Sylviculture Résumé : (auteur) The effect of species diversity on forest productivity and its temporal stability is known to be species-, climate- and site- dependent and is mostly apprehended through stem diameter. Therefore, it remains largely unknown whether the mixture effect on the growth of tree crowns is similar to its effect on the growth of tree diameter. However, it is commonly accepted that changes in crown architecture are an important component of tree response to tree species diversity. Moreover, the mixture effect on species is often asymmetric, i.e. the effect of a species A on a species B is not equal to the effect of species B on A. It then appears that considering the effects of both species mixture and climate on shoot growth could contrast the results coming mainly from stem growth. We studied the effects of tree species mixture and temperature on the annual growth of shoots and basal area of stems in Fagus sylvatica-Quercus pubescens and Fagus sylvatica-Abies alba stands along a Mediterranean-Alpine gradient, for four years in five sites. The sample design was organized in 10 triplets: four triplets of mono- and bi-specific plots of Quercus pubescens and Fagus sylvatica and six triplets of mono- and bi-specific plots of Abies alba and Fagus sylvatica along an altitudinal gradient ranging from 725 m to 1431 m. We found that the mixture effect on annual shoot volume increment (SVI) and on basal area increment (BAI) was asymmetrical in seven out of 10 cases and not significant in the three remaining cases. Mixture effect on SVI ranked from −56% to 157% and on BAI it ranked from −40% to 252%. Eventually we found that mixture effect was dependent on the type of limiting factor for growth, with at the driest sites a predominance of competition effects and at the coldest site a positive mixture effect on the two species studied. Branch growth appears as a variable that can be at least as informative as radial growth regarding the tree response to species interactions. This implies that considering only stem diameter in the diversity-productivity relationship can lead to biased conclusions on the global mixture effect on tree growth, which calls for a comprehensive approach of the tree response to tree species diversity. Our results are discussed in the light of the species stress tolerances and strategies to cope with competition. Numéro de notice : A2021-357 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1016/j.foreco.2021.119046 date de publication en ligne : 26/02/2021 En ligne : https://doi.org/10.1016/j.foreco.2021.119046 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97615 [article]

Performance evaluation of artificial neural networks for natural terrain classification / Perpetual Hope Akwensi in Applied geomatics, vol 13 n° 1 (May 2021)  

Public [article]  inApplied geomatics > vol 13 n° 1 (May 2021) Titre : Performance evaluation of artificial neural networks for natural terrain classification Type de document : Article/Communication Auteurs : Perpetual Hope Akwensi, Auteur ; Eric Thompson Brantson, Auteur ; Johanna Ngula Niipele, Auteur ; et al., Auteur Année de publication : 2021 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Afrique occidentale [Termes IGN] classification par nuées dynamiques [Termes IGN] échantillonnage [Termes IGN] fonction de base radiale [Termes IGN] image Landsat-OLI [Termes IGN] image multibande [Termes IGN] inventaire de la végétation [Termes IGN] réalité de terrain [Termes IGN] regroupement de données [Termes IGN] réseau neuronal artificiel [Termes IGN] segmentation d'image Résumé : (auteur) Remotely sensed image segmentation and classification form a very important part of remote sensing which involves geo-data processing and analysis. Artificial neural networks (ANNs) are powerful machine learning approaches that have been successfully implemented in numerous fields of study. There exist many kinds of neural networks and there is no single efficient approach for resolving all geospatial problems. Therefore, this research aims at investigating and evaluating the efficiency of three ANN approaches, namely, backpropagation neural network (BPNN), radial basis function neural network (RBFNN), and Elman backpropagation recurrent neural network (EBPRNN) using multi-spectral satellite images for terrain feature classification. Additionally, there has been close to no application of EBPRNN in modeling multi-spectral satellite images even though they also contain patterns. The efficiency of the three tested approaches is presented using the kappa coefficient, user’s accuracy, producer’s accuracy, overall accuracy, classification error, and computational simulation time. The study demonstrated that all the three ANN models achieved the aim of pattern identification, segmentation, and classification. This paper also discusses the observations of increasing sample sizes as inputs in the various ANN models. It was concluded that RBFNN’s computational time increases with increasing sample size and consequently increasing the number of hidden neurons; BPNN on overall attained the highest accuracy compared to the other models; EBPRNN’s accuracy increases with increasing sample size, hence a promising and perhaps an alternative choice to BPNN and RBFNN if very large datasets are involved. Based on the performance metrics used in this study, BPNN is the best model out of the three evaluated ANN models. Numéro de notice : A2021-223 Affiliation des auteurs : non IGN Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12518-021-00360-9 date de publication en ligne : 13/02/2021 En ligne : https://doi.org/10.1007/s12518-021-00360-9 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97194 [article]

Sensitivity of voxel-based estimations of leaf area density with terrestrial LiDAR to vegetation structure and sampling limitations: A simulation experiment / Maxime Soma in Remote sensing of environment, vol 257 (May 2021)  

Public [article]  inRemote sensing of environment > vol 257 (May 2021) . - n° 112354 Titre : Sensitivity of voxel-based estimations of leaf area density with terrestrial LiDAR to vegetation structure and sampling limitations: A simulation experiment Type de document : Article/Communication Auteurs : Maxime Soma, Auteur ; François Pimont, Auteur ; Jean-Luc Dupuy, Auteur Année de publication : 2021 Article en page(s) : n° 112354 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] analyse de sensibilité [Termes IGN] densité du feuillage [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] échantillonnage [Termes IGN] Leaf Area Index [Termes IGN] Leaf Mass per Area [Termes IGN] semis de points [Termes IGN] structure de la végétation [Termes IGN] voxel Résumé : (auteur) The need for fine scale description of vegetation structure is increasing as Leaf Area Density (LAD, m2/m3) becomes a critical parameter to understand ecosystem functioning and energy and mass fluxes in heterogeneous ecosystems. Terrestrial Laser Scanning (TLS) has shown great potential for retrieving the foliage area at stand, plant or voxel scales. Several sources of measurement errors have been identified and corrected over the past years. However, measurements remain sensitive to several factors, including, 1) voxel size and vegetation structure within voxels, 2) heterogeneity in sampling from TLS instrument (occlusion and shooting pattern), the consequences of which have been seldom analyzed at the scale of forest plots. In the present paper, we aimed at disentangling biases and errors in plot-scale measurements of LAD with TLS in a simulated vegetation scene. Two negative biases were formerly attributed to (i) the unsampled voxels and to (ii) the subgrid vegetation heterogeneity (i.e. clumping effect), and then quantified, thanks to a the simulation experiment providing known LAD references at voxel scale, vegetation manipulations and unbiased point estimators. We used confidence intervals to evaluate voxel-scale measurement accuracy. Numéro de notice : A2021-278 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.rse.2021.112354 date de publication en ligne : 18/02/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112354 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97371 [article]

A stacked dense denoising–segmentation network for undersampled tomograms and knowledge transfer using synthetic tomograms / Dimitrios Bellos in Machine Vision and Applications, vol 32 n° 3 (May 2021)  

Public [article]  inMachine Vision and Applications > vol 32 n° 3 (May 2021) . - n° 75 Titre : A stacked dense denoising–segmentation network for undersampled tomograms and knowledge transfer using synthetic tomograms Type de document : Article/Communication Auteurs : Dimitrios Bellos, Auteur ; Mark Basham, Auteur ; Tony Pridmore, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 75 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] acquisition de connaissances [Termes IGN] apprentissage profond [Termes IGN] échantillonnage [Termes IGN] filtrage du bruit [Termes IGN] rapport signal sur bruit [Termes IGN] rayon X [Termes IGN] reconstruction d'image [Termes IGN] segmentation sémantique [Termes IGN] série temporelle [Termes IGN] tomographie Résumé : (auteur) Over recent years, many approaches have been proposed for the denoising or semantic segmentation of X-ray computed tomography (CT) scans. In most cases, high-quality CT reconstructions are used; however, such reconstructions are not always available. When the X-ray exposure time has to be limited, undersampled tomograms (in terms of their component projections) are attained. This low number of projections offers low-quality reconstructions that are difficult to segment. Here, we consider CT time-series (i.e. 4D data), where the limited time for capturing fast-occurring temporal events results in the time-series tomograms being necessarily undersampled. Fortunately, in these collections, it is common practice to obtain representative highly sampled tomograms before or after the time-critical portion of the experiment. In this paper, we propose an end-to-end network that can learn to denoise and segment the time-series’ undersampled CTs, by training with the earlier highly sampled representative CTs. Our single network can offer two desired outputs while only training once, with the denoised output improving the accuracy of the final segmentation. Our method is able to outperform state-of-the-art methods in the task of semantic segmentation and offer comparable results in regard to denoising. Additionally, we propose a knowledge transfer scheme using synthetic tomograms. This not only allows accurate segmentation and denoising using less real-world data, but also increases segmentation accuracy. Finally, we make our datasets, as well as the code, publicly available. Numéro de notice : A2021-456 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s00138-021-01196-4 date de publication en ligne : 27/04/2021 En ligne : https://doi.org/10.1007/s00138-021-01196-4 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97902 [article]

Estimation of some stand parameters from textural features from WorldView-2 satellite image using the artificial neural network and multiple regression methods: a case study from Turkey / Alkan Günlü in Geocarto international, vol 36 n° 8 ([15/04/2021])  

Permalink

Forest fragmentation assessment using field-based sampling data from forest inventories / Habib Ramezani in Scandinavian journal of forest research, vol 36 n° 4 ([01/04/2021])  

Permalink

Robust unsupervised small area change detection from SAR imagery using deep learning / Xinzheng Zhang in ISPRS Journal of photogrammetry and remote sensing, vol 173 (March 2021)  

Permalink

Variations in temperate forest biomass ratio along three environmental gradients are dominated by interspecific differences in wood density / Baptiste Kerfriden in Plant ecology, vol 222 n° 3 (March 2021)  

Permalink

Developing a site index model for P. Pinaster stands in NW Spain by combining bi-temporal ALS data and environmental data / Juan Guerra-Hernández in Forest ecology and management, vol 481 (February 2021)  

Permalink

A regional spatiotemporal analysis of large magnitude snow avalanches using tree rings / Erich Peitzsch in Natural Hazards and Earth System Sciences, Vol 21 n° 2 (February 2021)  

Permalink

From local to global: A transfer learning-based approach for mapping poplar plantations at national scale using Sentinel-2 / Yousra Hamrouni in ISPRS Journal of photogrammetry and remote sensing, vol 171 (January 2021)  

Permalink

Is field-measured tree height as reliable as believed – Part II, A comparison study of tree height estimates from conventional field measurement and low-cost close-range remote sensing in a deciduous forest / Luka Jurjević in ISPRS Journal of photogrammetry and remote sensing, vol 169 (November 2020)  

Permalink

From small sets of GPS trajectories to detailed movement profiles: quantifying personalized trip-dependent movement diversity / Elham Naghizade in International journal of geographical information science IJGIS, vol 34 n° 10 (October 2020)  

Permalink

Towards an optimization of sample plot size and scanner position layout for terrestrial laser scanning in multi-scan mode / Tim Ritter in Forests, vol 11 n° 10 (October 2020)  

Permalink