Centre dedocumentation
scientifique

Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees / Hamid Hamraz in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 219 - 230 Titre : Deep learning for conifer/deciduous classification of airborne LiDAR 3D point clouds representing individual trees Type de document : Article/Communication Auteurs : Hamid Hamraz, Auteur ; Nathan B. Jacobs, Auteur ; Marco A. Contreras, Auteur ; Chase H. Clark, Auteur Année de publication : 2019 Article en page(s) : pp 219 - 230 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] arbre caducifolié [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] données d'apprentissage [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] houppier [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] pinophyta [Termes descripteurs IGN] semis de points Résumé : (auteur) The purpose of this study was to investigate the use of deep learning for coniferous/deciduous classification of individual trees segmented from airborne LiDAR data. To enable processing by a deep convolutional neural network (CNN), we designed two discrete representations using leaf-off and leaf-on LiDAR data: a digital surface model with four channels (DSM × 4) and a set of four 2D views (4 × 2D). A training dataset of tree crowns was generated via segmentation of tree crowns, followed by co-registration with field data. Potential mislabels due to GPS error or tree leaning were corrected using a statistical ensemble filtering procedure. Because the training data was heavily unbalanced (~8% conifers), we trained an ensemble of CNNs on random balanced sub-samples. Benchmarked against multiple traditional shallow learning methods using manually designed features, the CNNs improved accuracies up to 14%. The 4 × 2D representation yielded similar classification accuracies to the DSM × 4 representation (~82% coniferous and ~90% deciduous) while converging faster. Further experimentation showed that early/late fusion of the channels in the representations did not affect the accuracies in a significant way. The data augmentation that was used for the CNN training improved the classification accuracies, but more real training instances (especially coniferous) likely results in much stronger improvements. Leaf-off LiDAR data were the primary source of useful information, which is likely due to the perennial nature of coniferous foliage. LiDAR intensity values also proved to be useful, but normalization yielded no significant improvement. As we observed, large training data may compensate for the lack of a subset of important domain data. Lastly, the classification accuracies of overstory trees (~90%) were more balanced than those of understory trees (~90% deciduous and ~65% coniferous), which is likely due to the incomplete capture of understory tree crowns via airborne LiDAR. In domains like remote sensing and biomedical imaging, where the data contain a large amount of information and are not friendly to human visual system, human-designed features may become suboptimal. As exemplified by this study, automatic, objective derivation of optimal features via deep learning can improve prediction tasks in such domains. Numéro de notice : A2019-547 Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.10.011 date de publication en ligne : 03/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.10.011 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94192 [article]

Extracting urban landmarks from geographical datasets using a random forests classifier / Yue Lin in International journal of geographical information science IJGIS, vol 33 n°12 (December 2019)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 33 n°12 (December 2019) . - pp 2406 - 2423 Titre : Extracting urban landmarks from geographical datasets using a random forests classifier Type de document : Article/Communication Auteurs : Yue Lin, Auteur ; Yuyang Cai, Auteur ; Yue Gong, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 2406 - 2423 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique [Termes descripteurs IGN] classification par forêts aléatoires [Termes descripteurs IGN] extraction automatique [Termes descripteurs IGN] gestion des itinéraires [Termes descripteurs IGN] jeu de données localisées [Termes descripteurs IGN] point de repère [Termes descripteurs IGN] précision de la classification [Termes descripteurs IGN] représentation mentale spatiale [Termes descripteurs IGN] saillance [Termes descripteurs IGN] Shenzhen [Termes descripteurs IGN] ville Résumé : (auteur) Urban landmarks are of significant importance to spatial cognition and route navigation. However, the current landmark extraction methods mainly focus on the visual salience of landmarks and are insufficient for obtaining high extraction accuracy when the size of the geographical dataset varies. This study introduces a random forests (RF) classifier combining with the synthetic minority oversampling technique (SMOTE) in urban landmark extraction. Both GIS and social sensing data are employed to quantify the structural and cognitive salience of the examined urban features, which are available from basic spatial databases or mainstream web service application programming interfaces (APIs). The results show that the SMOTE-RF model performs well in urban landmark extraction, with the values of recall, precision, F-measure and AUC reaching 0.851, 0.831, 0.841 and 0.841, respectively. Additionally, this method is suitable for both large and small geographical datasets. The ranking of variable importance given by this model further indicates that certain cognitive measures – such as feature class, Weibo popularity and Bing popularity – can serve as crucial factors for determining a landmark. The optimal variable combination for landmark extraction is also acquired, which might provide support for eliminating the variable selection requirement in other landmark extraction methods. Numéro de notice : A2019-426 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2019.1620238 date de publication en ligne : 28/05/2019 En ligne : https://doi.org/10.1080/13658816.2019.1620238 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93559 [article]

Matching of TerraSAR-X derived ground control points to optical image patches using deep learning / Tatjana Bürgmann in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 241 - 248 Titre : Matching of TerraSAR-X derived ground control points to optical image patches using deep learning Type de document : Article/Communication Auteurs : Tatjana Bürgmann, Auteur ; Wolfgang Koppe, Auteur ; Michael Schmitt, Auteur Année de publication : 2019 Article en page(s) : pp 241 - 248 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte [Termes descripteurs IGN] appariement d'images [Termes descripteurs IGN] apprentissage profond [Termes descripteurs IGN] classification par réseau neuronal convolutif [Termes descripteurs IGN] géolocalisation [Termes descripteurs IGN] image multicapteur [Termes descripteurs IGN] image optique [Termes descripteurs IGN] image Pléiades [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-MSI [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] image TerraSAR-X [Termes descripteurs IGN] point d'appui Résumé : (auteur) High resolution synthetic aperture radar (SAR) satellites like TerraSAR-X are capable of acquiring images exhibiting an absolute geolocation accuracy within a few centimeters, mainly because of the availability of precise orbit information and by compensating range delay errors due to atmospheric conditions. In contrast, satellite images from optical missions generally exhibit comparably low geolocation accuracies because of the propagation of errors in angular measurements over large distances. However, a variety of remote sensing applications, such as change detection, surface movement monitoring or ice flow measurements, require precisely geo-referenced and co-registered satellite images. By using Ground Control Points (GCPs) derived from TerraSAR-X, the absolute geolocation accuracy of optical satellite images can be improved. For this purpose, the corresponding matching points in the optical images need to be localized. In this paper, a deep learning based approach is investigated for an automated matching of SAR-derived GCPs to optical image elements. Therefore, a convolutional neural network is pretrained with medium resolution Sentinel-1 and Sentinel-2 imagery and fine-tuned on precisely co-registered TerraSAR-X and Pléiades training image pairs to learn a common descriptor representation. By using these descriptors, the similarity of SAR and optical image patches can be calculated. This similarity metric is then used in a sliding window approach to identify the matching points in the optical reference image. Subsequently, the derived points can be utilized for co-registration of the underlying images. The network is evaluated over nine study areas showing airports and their rural surroundings from several different countries around the world. The results show that based on TerraSAR-X-derived GCPs, corresponding points in the optical image can automatically and reliably be identified with a pixel-level localization accuracy. Numéro de notice : A2019-548 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.09.010 date de publication en ligne : 05/11/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.09.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94194 [article]

On the value of corner reflectors and surface models in InSAR precise point positioning / Mengshi Yang in ISPRS Journal of photogrammetry and remote sensing, Vol 158 (December 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 158 (December 2019) . - pp 113 - 122 Titre : On the value of corner reflectors and surface models in InSAR precise point positioning Type de document : Article/Communication Auteurs : Mengshi Yang, Auteur ; Paco Lopez-Dekker, Auteur ; Prabu Dheenathayalan, Auteur ; Mingsheng Liao, Auteur ; Ramon F. Hanssen, Auteur Année de publication : 2019 Article en page(s) : pp 113 - 122 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes descripteurs IGN] coin réflecteur [Termes descripteurs IGN] correction d'image [Termes descripteurs IGN] géolocalisation [Termes descripteurs IGN] image radar moirée [Termes descripteurs IGN] image Sentinel-SAR [Termes descripteurs IGN] image TerraSAR-X [Termes descripteurs IGN] interféromètrie par radar à antenne synthétique [Termes descripteurs IGN] MNS lidar [Termes descripteurs IGN] Pays-Bas [Termes descripteurs IGN] point d'appui [Termes descripteurs IGN] positionnement ponctuel précis Résumé : (auteur) To correctly interpret the estimated displacements in InSAR point clouds, especially in the built environment, these need to be linked to real-world structures. This requires the accurate and precise 3D positioning of each point. Artificial ground control points (GCPs), such as corner reflectors, serve this purpose, but since they require efforts and resources, there is a need for criteria to assess their usefulness. Here we evaluate the value and necessity of using GCPs for different scenarios, concerning the required efforts, and compare this to alternatives such as digital surface models (DSM) and advanced (geo) physical corrections. We consider single-epoch as well as multi-epoch GCP deployment, reflect on the number of GCPs required in relation to the number of SAR data acquisitions, and compare this with digital surface models of different quality levels. Analyzing the geolocation performance using TerraSAR-X and Sentinel-1 data, we evaluate the pros and cons of various deployment options and show that the multi-epoch deployment of a GCP yields optimal geolocalization results in terms of precision, accuracy, and reliability. Numéro de notice : A2019-546 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.10.006 date de publication en ligne : 25/10/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.10.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94191 [article]

Segmenting mangrove ecosystems drone images using SLIC superpixels / Edward Zimudzi in Geocarto international, vol 34 n° 14 ([30/10/2019])  

Public [article]  inGeocarto international > vol 34 n° 14 [30/10/2019] . - pp 1648 - 1662 Titre : Segmenting mangrove ecosystems drone images using SLIC superpixels Type de document : Article/Communication Auteurs : Edward Zimudzi, Auteur ; Ian Sanders, Auteur ; Nicholas Rollings, Auteur ; Christian Omlin, Auteur Année de publication : 2019 Article en page(s) : pp 1648 - 1662 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] algorithme de superpixels [Termes descripteurs IGN] classification par nuées dynamiques [Termes descripteurs IGN] classification pixellaire [Termes descripteurs IGN] écosystème [Termes descripteurs IGN] Fidji [Termes descripteurs IGN] image de drone [Termes descripteurs IGN] mangrove [Termes descripteurs IGN] modèle numérique de surface [Termes descripteurs IGN] orthophotoplan numérique [Termes descripteurs IGN] segmentation d'image [Termes descripteurs IGN] SLIC algorithm Résumé : (auteur) Mangrove ecosystems play a very important ecological role on land–ocean interfaces in tropical regions. These ecosystems comprise of various tree species and aquatic animals, protecting the environment and providing a habitat that supports many living organisms including humans. The identification of image regions in mangrove ecosystems plays a significant role in ecosystem monitoring and conservation. Recent studies have suggested oversegmentation of colour images using superpixels as a solution to the segmentation of image regions. This study used the SLIC superpixel algorithm and k-means clustering to segment images taken from a camera mounted on a drone from a mangrove ecosystem in Fiji. The SLIC superpixel algorithm performed well to demarcate image regions with similar colour and texture information into patches and to use k-means for the segmentation of the whole image. These results lend support to the use of superpixel algorithms for the segmentation of mangrove ecosystems. Understanding how superpixels can be used for the segmentation of drone images will assist conservation efforts in mangrove ecosystems. Numéro de notice : A2019-539 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1497093 date de publication en ligne : 22/10/2018 En ligne : https://doi.org/10.1080/10106049.2018.1497093 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94114 [article]

Estimating pasture biomass and canopy height in brazilian savanna using UAV photogrammetry / Juliana Batistoti in Remote sensing, Vol 11 n° 20 (2 October 2019)  

Permalink

A CNN-based subpixel level DSM generation approach via single image super-resolution / Yongjun Zhang in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 10 (October 2019)  

Permalink

Mapping dead forest cover using a deep convolutional neural network and digital aerial photography / Jean-Daniel Sylvain in ISPRS Journal of photogrammetry and remote sensing, vol 156 (October 2019)  

Permalink

Multiple-view geospatial comparison using web-based virtual globes / Liangfeng Zhu in ISPRS Journal of photogrammetry and remote sensing, vol 156 (October 2019)  

Permalink

Robust multisource remote sensing image registration method based on scene shape similarity / Ming Hao in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 10 (October 2019)  

Permalink

Unmanned aerial vehicles (UAVs) for monitoring macroalgal biodiversity: comparison of RGB and multispectral imaging sensors for biodiversity assessments / Leigh Tait in Remote sensing, vol 11 n° 19 (October 2019)  

Permalink

Mapping of forest tree distribution and estimation of forest biodiversity using Sentinel-2 imagery in the University Research Forest Taxiarchis in Chalkidiki, Greece / Maria Kampouri in Geocarto international, vol 34 n° 12 ([15/09/2019])  

Permalink

Comparison of filtering algorithms used for DTM production from airborne lidar data: a case study in Bergama, Turkey / Baris Suleymanoglu in Geodetski vestnik, vol 63 n° 3 (September - November 2019)  

Permalink

Delineation of vacant building land using orthophoto and lidar data object classification / Dejan Jenko in Geodetski vestnik, vol 63 n° 3 (September - November 2019)  

Permalink

Un demi-siècle de topographie à la SNCF / Pierre Lasseur in XYZ, n° 160 (septembre 2019)

Permalink