Centre dedocumentation
scientifique

Transfer learning from citizen science photographs enables plant species identification in UAV imagery / Salim Soltani in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 5 (August 2022)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 5 (August 2022) . - n° 100016 Titre : Transfer learning from citizen science photographs enables plant species identification in UAV imagery Type de document : Article/Communication Auteurs : Salim Soltani, Auteur ; Hannes Feilhauer, Auteur ; Robbert Duker, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 100016 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] base de données naturalistes [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] distribution spatiale [Termes IGN] données localisées des bénévoles [Termes IGN] espèce végétale [Termes IGN] filtrage de la végétation [Termes IGN] identification de plantes [Termes IGN] image captée par drone [Termes IGN] orthoimage couleur [Termes IGN] science citoyenne [Termes IGN] segmentation sémantique Résumé : (auteur) Accurate information on the spatial distribution of plant species and communities is in high demand for various fields of application, such as nature conservation, forestry, and agriculture. A series of studies has shown that Convolutional Neural Networks (CNNs) accurately predict plant species and communities in high-resolution remote sensing data, in particular with data at the centimeter scale acquired with Unoccupied Aerial Vehicles (UAV). However, such tasks often require ample training data, which is commonly generated in the field via geocoded in-situ observations or labeling remote sensing data through visual interpretation. Both approaches are laborious and can present a critical bottleneck for CNN applications. An alternative source of training data is given by using knowledge on the appearance of plants in the form of plant photographs from citizen science projects such as the iNaturalist database. Such crowd-sourced plant photographs typically exhibit very different perspectives and great heterogeneity in various aspects, yet the sheer volume of data could reveal great potential for application to bird’s eye views from remote sensing platforms. Here, we explore the potential of transfer learning from such a crowd-sourced data treasure to the remote sensing context. Therefore, we investigate firstly, if we can use crowd-sourced plant photographs for CNN training and subsequent mapping of plant species in high-resolution remote sensing imagery. Secondly, we test if the predictive performance can be increased by a priori selecting photographs that share a more similar perspective to the remote sensing data. We used two case studies to test our proposed approach with multiple RGB orthoimages acquired from UAV with the target plant species Fallopia japonica and Portulacaria afra respectively. Our results demonstrate that CNN models trained with heterogeneous, crowd-sourced plant photographs can indeed predict the target species in UAV orthoimages with surprising accuracy. Filtering the crowd-sourced photographs used for training by acquisition properties increased the predictive performance. This study demonstrates that citizen science data can effectively anticipate a common bottleneck for vegetation assessments and provides an example on how we can effectively harness the ever-increasing availability of crowd-sourced and big data for remote sensing applications. Numéro de notice : A2022-488 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.ophoto.2022.100016 Date de publication en ligne : 23/05/2022 En ligne : https://doi.org/10.1016/j.ophoto.2022.100016 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100956 [article]

Adaptive transfer of color from images to maps and visualizations / Mingguang Wu in Cartography and Geographic Information Science, Vol 49 n° 4 (July 2022)  

Public [article]  inCartography and Geographic Information Science > Vol 49 n° 4 (July 2022) . - pp 289 - 312 Titre : Adaptive transfer of color from images to maps and visualizations Type de document : Article/Communication Auteurs : Mingguang Wu, Auteur ; Yanjie Sun, Auteur ; Yaqian Li, Auteur Année de publication : 2022 Article en page(s) : pp 289 - 312 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] amélioration des couleurs [Termes IGN] couleur (rédaction cartographique) [Termes IGN] données vectorielles [Termes IGN] esthétique cartographique [Termes IGN] orthoimage couleur [Termes IGN] relation sémantique [Termes IGN] saillance [Termes IGN] visualisation cartographique [Vedettes matières IGN] Géovisualisation Résumé : (auteur) Because crafting attractive and effective colors from scratch is a high-effort and time-consuming process in map and visualization design, transferring color from an inspiration source to maps and visualizations is a promising technique for both novices and experts. To date, existing image-to-image color transfer methods suffer from ambiguities and inconsistencies; no computational approach is available to transfer color from arbitrary images to vector maps. To fill this gap, we propose a computational method that transfers color from arbitrary images to a vector map. First, we classify reference images into regions with measures of saliency. Second, we quantify the communicative quality and esthetics of colors in maps; we then transform the problem of color transfer into a dual-objective, multiple-constraint optimization problem. We also present a solution method that can create a series of optimal color suggestions and generate a communicative quality-esthetic compromise solution. We compare our method with an image-to-image method based on two sample maps and six reference images. The results indicate that our method is adaptive to mapping scales, themes, and regions. The evaluation also provides preliminary evidence that our method can achieve better communicative quality and harmony. Numéro de notice : A2022-478 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/15230406.2021.1982009 Date de publication en ligne : 10/11/2021 En ligne : https://doi.org/10.1080/15230406.2021.1982009 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100826 [article]

Effect of label noise in semantic segmentation of high resolution aerial images and height data / Arabinda Maiti in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 275 - 282 Titre : Effect of label noise in semantic segmentation of high resolution aerial images and height data Type de document : Article/Communication Auteurs : Arabinda Maiti, Auteur ; Sander J. Oude Elberink, Auteur ; M. George Vosselman, Auteur Année de publication : 2022 Article en page(s) : pp 275 - 282 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] bruit (théorie du signal) [Termes IGN] données altimétriques [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] image à très haute résolution [Termes IGN] image aérienne [Termes IGN] orthoimage [Termes IGN] segmentation sémantique Résumé : (auteur) The performance of deep learning models in semantic segmentation is dependent on the availability of a large amount of labeled data. However, the influence of label noise, in the form of incorrect annotations, on the performance is significant and mostly ignored. This is a big concern in remote sensing applications, wherein acquired datasets are spatially limited, labeling is done by domain experts with possible sources of high inter-and intra-observer variability leading to erroneous predictions. In this paper, we first simulate the label noise while conducting experiments on two different datasets with very high-resolution aerial images, height data, and inaccurate labels, responsible for the training of deep learning models. We then focus on the effect of these noises on the model performance. Different classes respond differently to the label noise. The typical size of an object belonging to a class is a crucial factor regarding the class-specific performance of the model trained with erroneous labels. Errors caused by relative shifts of labels are the most influential label errors. The model is generally more tolerant of the random label noise than other label errors. It has been observed that the accuracy gets reduced by at least 3% while 5% of label pixels are erroneous. In this regard, our study provides a new perspective of evaluating and quantifying the propagation of label noise in the model performance that is indeed important for adopting reliable semantic segmentation practices. Numéro de notice : A2022-434 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-275-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-275-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100741 [article]

Learning from the past: crowd-driven active transfer learning for semantic segmentation of multi-temporal 3D point clouds / Michael Kölle in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 259 - 266 Titre : Learning from the past: crowd-driven active transfer learning for semantic segmentation of multi-temporal 3D point clouds Type de document : Article/Communication Auteurs : Michael Kölle, Auteur ; Volker Walter, Auteur ; Uwe Soergel, Auteur Année de publication : 2022 Article en page(s) : pp 259 - 266 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] apprentissage automatique [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] données étiquetées d'entrainement [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] données multitemporelles [Termes IGN] orthoimage couleur [Termes IGN] production participative [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] traitement de données localisées Résumé : (auteur) The main bottleneck of machine learning systems, such as convolutional neural networks, is the availability of labeled training data. Hence, much effort (and thus cost) is caused by setting up proper training data sets. However, models trained on specific data sets often perform unsatisfactorily when used to derive predictions for another (yet related) data set. We aim to overcome this problem by employing active learning to iteratively adapt an existing classifier to another domain. Precisely, we are concerned with semantic segmentation of 3D point clouds of multiple epochs. We first establish a Random Forest classifier for the first epoch of our data set and adapt it for successful prediction to two more temporally disjoint point clouds of the same but extended area. The point clouds, which are part of the newly introduced Hessigheim 3D benchmark data set, incorporate different characteristics with respect to the acquisition date and sensor configuration. We demonstrate that our workflow for domain adaptation is designed in such a way that it i) offers the possibility to greatly reduce labeling effort compared to a passive learning baseline or to an active learning baseline trained from scratch, if the domain gap is small enough and ii) at least does not cause more expenses (compared to a newly initialized active learning loop), if the domain gap is severe. The latter is especially beneficial in scenarios where the similarity of two different domains is hard to assess. Numéro de notice : A2022-435 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-259-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-259-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100743 [article]

Hybrid georeferencing of images and LiDAR data for UAV-based point cloud collection at millimetre accuracy / Norbert Haala in ISPRS Open Journal of Photogrammetry and Remote Sensing, vol 4 (April 2022)  

Public [article]  inISPRS Open Journal of Photogrammetry and Remote Sensing > vol 4 (April 2022) . - n° 100014 Titre : Hybrid georeferencing of images and LiDAR data for UAV-based point cloud collection at millimetre accuracy Type de document : Article/Communication Auteurs : Norbert Haala, Auteur ; Michael Kölle, Auteur ; Michael Cramer, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 100014 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] aérotriangulation automatisée [Termes IGN] appariement d'images [Termes IGN] collecte de données [Termes IGN] compensation par faisceaux [Termes IGN] données lidar [Termes IGN] géoréférencement direct [Termes IGN] image captée par drone [Termes IGN] orthoimage [Termes IGN] précision millimétrique [Termes IGN] semis de points [Termes IGN] zone d'intérêt Résumé : (auteur) During the last two decades, UAV emerged as standard platform for photogrammetric data collection. Main motivation in that early phase was the cost effective airborne image collection at areas of limited size. This was already feasible by rather simple payloads like an off-the-shelf, compact camera and a navigation-grade GNSS sensor. Meanwhile, dedicated sensor systems enable applications that have not been feasible in the past. One example is the airborne collection of dense 3D point clouds at millimetre accuracies, which will be discussed in our paper. For this purpose, we collect both LiDAR and image data from a joint UAV platform and apply a so-called hybrid georeferencing. This process integrates photogrammetric bundle block adjustment with direct georeferencing of LiDAR point clouds. By these means georeferencing accuracy is improved for the LiDAR point cloud by an order of magnitude. We demonstrate the feasibility of our approach in the context of a project, which aims on monitoring of subsidence of about 10 mm/year. The respective area of interest is defined by a ship lock and its vicinity of mixed use. In that area, multiple UAV flights were captured and evaluated for a period of three years. As our main contribution, we demonstrate that 3D point accuracies at sub-centimetre level can be achieved. This is realized by joint orientation of laser scans and images in a hybrid adjustment framework, which enables accuracies corresponding to the GSD of the captured imagery. Numéro de notice : A2022-236 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.ophoto.2022.100014Get rights and content Date de publication en ligne : 16/03/2022 En ligne : https://doi.org/10.1016/j.ophoto.2022.100014Get rights and content Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100146 [article]

Comparaison des images satellite et aériennes dans le domaine de la détection d’obstacles à la navigation aérienne et de leur mise à jour / Olivier de Joinville in XYZ, n° 170 (mars 2022)

Permalink

Neural map style transfer exploration with GANs / Sidonie Christophe in International journal of cartography, vol 8 n° 1 (March 2022)  

Permalink

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

Permalink

Automatic extraction of damaged houses by earthquake based on improved YOLOv5: A case study in Yangbi / Yafei Jing in Remote sensing, vol 14 n° 2 (January-2 2022)  

Permalink

A 3D segments based algorithm for heterogeneous data registration / Rahima Djahel (2022)  

Permalink

Photogrammetric 3D mobile mapping of rail tracks / Philipp Glira in ISPRS Journal of photogrammetry and remote sensing, vol 183 (January 2022)  

Permalink

Building detection with convolutional networks trained with transfer learning / Simon Šanca in Geodetski vestnik, vol 65 n° 4 (December 2021 - February 2022)  

Permalink

Automatic tuning of segmentation parameters for tree crown delineation with VHR imagery / Camile Sothe in Geocarto international, vol 36 n° 19 ([01/11/2021])  

Permalink

Utilisation de l’apprentissage profond dans la modélisation 3D urbaine : partie 2, post-traitement et évaluation / Hamza Ben Addou in Géomatique expert, n° 136 (novembre - décembre 2021)

Permalink

Quantifying historical landscape change with repeat photography: an accuracy assessment of geospatial data obtained through monoplotting / Ulrike Bayr in International journal of geographical information science IJGIS, vol 35 n° 10 (October 2021)  

Permalink