Descripteur
Documents disponibles dans cette catégorie (450)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Feature-selection high-resolution network with hypersphere embedding for semantic segmentation of VHR remote sensing images / Hanwen Xu in IEEE Transactions on geoscience and remote sensing, vol 60 n° 6 (June 2022)
[article]
Titre : Feature-selection high-resolution network with hypersphere embedding for semantic segmentation of VHR remote sensing images Type de document : Article/Communication Auteurs : Hanwen Xu, Auteur ; Xinming Tang, Auteur ; Bo Ai, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 4411915 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] architecture de réseau
[Termes IGN] attention (apprentissage automatique)
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] entropie
[Termes IGN] extraction de traits caractéristiques
[Termes IGN] image à très haute résolution
[Termes IGN] segmentation multi-échelle
[Termes IGN] segmentation sémantiqueRésumé : (auteur) Very-high-resolution (VHR) remote sensing images contain various multiscale objects, such as large-scale buildings and small-scale cars. However, these multiscale objects cannot be considered simultaneously in the widely used backbones with a large downsampling factor (e.g., VGG-like and ResNet-like), resulting in the appearance of various context aggregation approaches, such as fusing low-level features and attention-based modules. To alleviate this problem caused by backbones with a large downsampling factor, we propose a feature-selection high-resolution network (FSHRNet) based on an observation: if the features maintain high resolution throughout the network, a high precision segmentation result can be obtained by only using a 1× 1 convolution layer with no need for complex context aggregation modules. Specifically, the backbone of FSHRNet is a multibranch structure similar to HRNet where the high-resolution branch is the principal line. Then, a lightweight dynamic weight module, named the feature-selection convolution (FSConv) layer, is presented to fuse multiresolution features, allowing adaptively feature selection based on the characteristic of objects. Finally, a specially designed 1× 1 convolution layer derived from hypersphere embedding is used to produce the segmentation result. Experiments with other widely used methods show that the proposed FSHRNet obtains competitive performance on the ISPRS Vaihingen dataset, the ISPRS Potsdam dataset, and the iSAID dataset. Numéro de notice : A2022-559 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2022.3183144 En ligne : https://doi.org/10.1109/TGRS.2022.3183144 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101184
in IEEE Transactions on geoscience and remote sensing > vol 60 n° 6 (June 2022) . - n° 4411915[article]Large-scale automatic identification of urban vacant land using semantic segmentation of high-resolution remote sensing images / Lingdong Mao in Landscape and Urban Planning, vol 222 (June 2022)
[article]
Titre : Large-scale automatic identification of urban vacant land using semantic segmentation of high-resolution remote sensing images Type de document : Article/Communication Auteurs : Lingdong Mao, Auteur ; Zhe Zheng, Auteur ; Xiangfeng Meng, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 104384 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] Chine
[Termes IGN] détection d'objet
[Termes IGN] grande échelle
[Termes IGN] identification automatique
[Termes IGN] image à haute résolution
[Termes IGN] milieu urbain
[Termes IGN] occupation du sol
[Termes IGN] segmentation d'image
[Termes IGN] segmentation sémantiqueRésumé : (auteur) Urban vacant land is a growing issue worldwide. However, most of the existing research on urban vacant land has focused on small-scale city areas, while few studies have focused on large-scale national areas. Large-scale identification of urban vacant land is hindered by the disadvantage of high cost and high variability when using the conventional manual identification method. Criteria inconsistency in cross-domain identification is also a major challenge. To address these problems, we propose a large-scale automatic identification framework of urban vacant land based on semantic segmentation of high-resolution remote sensing images and select 36 major cities in China as study areas. The framework utilizes deep learning techniques to realize automatic identification and introduces the city stratification method to address the challenge of identification criteria inconsistency. The results of the case study on 36 major Chinese cities indicate two major conclusions. First, the proposed framework of vacant land identification can achieve over 90 percent accuracy of the level of professional auditors with much higher result stability and approximately 15 times higher efficiency compared to the manual identification method. Second, the framework has strong robustness and can maintain high performance in various cities. With the above advantages, the proposed framework provides a practical approach to large-scale vacant land identification in various countries and regions worldwide, which is of great significance for the academic development of urban vacant land and future urban development. Numéro de notice : A2022-267 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.landurbplan.2022.104384 Date de publication en ligne : 03/03/2022 En ligne : https://doi.org/10.1016/j.landurbplan.2022.104384 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100275
in Landscape and Urban Planning > vol 222 (June 2022) . - n° 104384[article]Application oriented quality evaluation of Gaofen-7 optical stereo satellite imagery / Jiaojiao Tian in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2022 (2022 edition)
[article]
Titre : Application oriented quality evaluation of Gaofen-7 optical stereo satellite imagery Type de document : Article/Communication Auteurs : Jiaojiao Tian, Auteur ; Xiangyu Zhuo, Auteur ; Xiangtian Yuan, Auteur ; Corentin Henry, Auteur ; Pablo d' Angelo, Auteur ; Thomas Krauss, Auteur Année de publication : 2022 Article en page(s) : pp 145 - 152 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] Allemagne
[Termes IGN] détection du bâti
[Termes IGN] extraction du réseau routier
[Termes IGN] image Gaofen
[Termes IGN] image optique
[Termes IGN] orientation d'image
[Termes IGN] reconstruction 3D
[Termes IGN] scène urbaine
[Termes IGN] segmentationRésumé : (auteur) GaoFen-7 (GF-7) satellite mission is further expanding the very high resolution 3D mapping application. Carrying the first civilian Chinese sub-meter resolution stereo satellite sensors, GF-7 satellite was launched on November 7, 2019. With 0.65 meter resolution on backward view and 0.8 meter resolution forward view, GF-7 has been designed to meet the demand of natural resource monitoring, land surveying, and other mapping applications in China. The use of GF-7 for 3D city reconstruction is unfortunately restricted by the fixed large stereo view angle of forward and backward cameras with +26 and −5 degrees respectively which is not optimal for dense stereo matching in urban regions. In this paper, we intensively evaluate the quality of the GF-7 datasets by performing a series of urban monitoring applications, including road detection, building extraction and 3D reconstruction. In addition, we propose a 3D reconstruction workflow which uses the land cover classification result to refine the stereo matching result. Six sub-urban regions are selected from the available datasets in the middle of Germany. The results show that basic elements in urban scenes like buildings and roads could be detected from GF-7 datasets with high accuracy. With the proposed workflow, a 3D city model with a visually observed good quality can be delivered. Numéro de notice : A2022-442 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-1-2022-145-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-1-2022-145-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100776
in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-1-2022 (2022 edition) . - pp 145 - 152[article]Automatic training data generation in deep learning-aided semantic segmentation of heritage buildings / Arnadi Murtiyoso in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)
[article]
Titre : Automatic training data generation in deep learning-aided semantic segmentation of heritage buildings Type de document : Article/Communication Auteurs : Arnadi Murtiyoso, Auteur ; Francesca Matrone, Auteur ; M.C. Martini, Auteur ; Andrea Lingua, Auteur ; Pierre Grussenmeyer, Auteur ; Roberto Pierdicca, Auteur Année de publication : 2022 Article en page(s) : pp 317 - 324 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] apprentissage profond
[Termes IGN] données d'entrainement (apprentissage automatique)
[Termes IGN] monument historique
[Termes IGN] segmentation sémantique
[Termes IGN] semis de pointsRésumé : (auteur) In the geomatics domain the use of deep learning, a subset of machine learning, is becoming more and more widespread. In this context, the 3D semantic segmentation of heritage point clouds presents an interesting and promising approach for modelling automation, in light of the heterogeneous nature of historical building styles and features. However, this heterogeneity also presents an obstacle in terms of generating the training data for use in deep learning, hitherto performed largely manually. The current generally low availability of labelled data also presents a motivation to aid the process of training data generation. In this paper, we propose the use of approaches based on geometric rules to automate to a certain degree this task. One object class will be discussed in this paper, namely the pillars class. Results show that the approach managed to extract pillars with satisfactory quality (98.5% of correctly detected pillars with the proposed algorithm). Tests were also performed to use the outputs in a deep learning segmentation setting, with a favourable outcome in terms of reducing the overall labelling time (−66.5%). Certain particularities were nevertheless observed, which also influence the result of the deep learning segmentation. Numéro de notice : A2022-430 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-317-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-317-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100736
in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 317 - 324[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)
[article]
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 sémantiqueRésumé : (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
in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 275 - 282[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)PermalinkRailway lidar semantic segmentation with axially symmetrical convolutional learning / Antoine Manier in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)PermalinkSemantic segmentation of urban textured meshes through point sampling / Grégoire Grzeczkowicz in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)PermalinkA voxel-based method for the three-dimensional modelling of heathland from lidar point clouds: first results / N. Homainejad in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-3-2022 (2022 edition)PermalinkWeakly supervised semantic segmentation of airborne laser scanning point clouds / Yaping Lin in ISPRS Journal of photogrammetry and remote sensing, vol 187 (May 2022)PermalinkAssessing surface drainage conditions at the street and neighborhood scale: A computer vision and flow direction method applied to lidar data / Cheng-Chun Lee in Computers, Environment and Urban Systems, vol 93 (April 2022)PermalinkClustering with implicit constraints: A novel approach to housing market segmentation / Xiaoqi Zhang in Transactions in GIS, vol 26 n° 2 (April 2022)PermalinkDetermination of building flood risk maps from LiDAR mobile mapping data / Yu Feng in Computers, Environment and Urban Systems, vol 93 (April 2022)PermalinkExploring the association between street built environment and street vitality using deep learning methods / Yunqin Li in Sustainable Cities and Society, vol 79 (April 2022)PermalinkGraph learning based on signal smoothness representation for homogeneous and heterogeneous change detection / David Alejandro Jimenez-Sierra in IEEE Transactions on geoscience and remote sensing, vol 60 n° 4 (April 2022)Permalink