Descripteur
Termes IGN > sciences naturelles > physique > traitement d'image > analyse d'image numérique > analyse d'image orientée objet
analyse d'image orientée objetVoir aussi |
Documents disponibles dans cette catégorie (294)
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
Understanding the role of individual units in a deep neural network / David Bau in Proceedings of the National Academy of Sciences of the United States of America PNAS, vol 117 n° 48 (1 December 2020)
[article]
Titre : Understanding the role of individual units in a deep neural network Type de document : Article/Communication Auteurs : David Bau, Auteur ; Jun-Yan Zhu, Auteur ; Hendrik Strobelt, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : n° 30071-30078 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] cadre conceptuel
[Termes IGN] détection d'objet
[Termes IGN] réseau antagoniste génératif
[Termes IGN] réseau neuronal convolutif
[Termes IGN] scèneRésumé : (auteur) Deep neural networks excel at finding hierarchical representations that solve complex tasks over large datasets. How can we humans understand these learned representations? In this work, we present network dissection, an analytic framework to systematically identify the semantics of individual hidden units within image classification and image generation networks. First, we analyze a convolutional neural network (CNN) trained on scene classification and discover units that match a diverse set of object concepts. We find evidence that the network has learned many object classes that play crucial roles in classifying scene classes. Second, we use a similar analytic method to analyze a generative adversarial network (GAN) model trained to generate scenes. By analyzing changes made when small sets of units are activated or deactivated, we find that objects can be added and removed from the output scenes while adapting to the context. Finally, we apply our analytic framework to understanding adversarial attacks and to semantic image editing. Numéro de notice : A2020-864 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1073/pnas.1907375117 En ligne : https://doi.org/10.1073/pnas.1907375117 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=99086
in Proceedings of the National Academy of Sciences of the United States of America PNAS > vol 117 n° 48 (1 December 2020) . - n° 30071-30078[article]Unsupervised deep joint segmentation of multitemporal high-resolution images / Sudipan Saha in IEEE Transactions on geoscience and remote sensing, Vol 58 n° 12 (December 2020)
[article]
Titre : Unsupervised deep joint segmentation of multitemporal high-resolution images Type de document : Article/Communication Auteurs : Sudipan Saha, Auteur ; Lichao Mou, Auteur ; Chunping Qiu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 8780 - 8792 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 non dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] extraction de données
[Termes IGN] image à haute résolution
[Termes IGN] image à très haute résolution
[Termes IGN] image multitemporelle
[Termes IGN] itération
[Termes IGN] segmentation sémantiqueRésumé : (auteur) High/very-high-resolution (HR/VHR) multitemporal images are important in remote sensing to monitor the dynamics of the Earth’s surface. Unsupervised object-based image analysis provides an effective solution to analyze such images. Image semantic segmentation assigns pixel labels from meaningful object groups and has been extensively studied in the context of single-image analysis, however not explored for multitemporal one. In this article, we propose to extend supervised semantic segmentation to the unsupervised joint semantic segmentation of multitemporal images. We propose a novel method that processes multitemporal images by separately feeding to a deep network comprising of trainable convolutional layers. The training process does not involve any external label, and segmentation labels are obtained from the argmax classification of the final layer. A novel loss function is used to detect object segments from individual images as well as establish a correspondence between distinct multitemporal segments. Multitemporal semantic labels and weights of the trainable layers are jointly optimized in iterations. We tested the method on three different HR/VHR data sets from Munich, Paris, and Trento, which shows the method to be effective. We further extended the proposed joint segmentation method for change detection (CD) and tested on a VHR multisensor data set from Trento. Numéro de notice : A2020-744 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2990640 Date de publication en ligne : 11/05/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2990640 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96375
in IEEE Transactions on geoscience and remote sensing > Vol 58 n° 12 (December 2020) . - pp 8780 - 8792[article]Bayesian transfer learning for object detection in optical remote sensing images / Changsheng Zhou in IEEE Transactions on geoscience and remote sensing, vol 58 n° 11 (November 2020)
[article]
Titre : Bayesian transfer learning for object detection in optical remote sensing images Type de document : Article/Communication Auteurs : Changsheng Zhou, Auteur ; Jiangshe Zhang, Auteur ; Junmin Liu, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 7705 - 7719 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] apprentissage profond
[Termes IGN] chaîne de traitement
[Termes IGN] détection d'objet
[Termes IGN] distribution de Fisher
[Termes IGN] jeu de données localisées
[Termes IGN] théorème de BayesRésumé : (auteur) In the literature of object detection in optical remote sensing images, a popular pipeline is first modifying an off-the-shelf deep neural network, then initializing the modified network by pretrained weights on a source data set, and finally fine-tuning the network on a target data set. The procedure works well in practice but might not make full use of underlying knowledge implied by pretrained weights. In this article, we propose a novel method, referred to as Fisher regularization, for efficient knowledge transferring. Based on Bayes’ theorem, the method stores underlying knowledge into a Fisher information matrix and fine-tunes parameters based on the knowledge. The proposed method would not introduce extra parameters and is less sensitive to hyperparameters than classical weight decay. Experiments on NWPUVHR-10 and DOTA data sets show that the proposed method is effective and works well with different object detectors. Numéro de notice : A2020-679 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2020.2983201 Date de publication en ligne : 14/04/2020 En ligne : https://doi.org/10.1109/TGRS.2020.2983201 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96182
in IEEE Transactions on geoscience and remote sensing > vol 58 n° 11 (November 2020) . - pp 7705 - 7719[article]Bretagne, la végétation cartographiée / Marielle Mayo in Géomètre, n° 2185 (novembre 2020)
[article]
Titre : Bretagne, la végétation cartographiée Type de document : Article/Communication Auteurs : Marielle Mayo, Auteur Année de publication : 2020 Article en page(s) : pp 46 - 49 Langues : Français (fre) Descripteur : [Vedettes matières IGN] Cartographie thématique
[Termes IGN] 1:25.000
[Termes IGN] acquisition d'images
[Termes IGN] aménagement régional
[Termes IGN] ArcGIS
[Termes IGN] BD ortho
[Termes IGN] Bretagne
[Termes IGN] carte de la végétation
[Termes IGN] classification orientée objet
[Termes IGN] données localisées
[Termes IGN] données publiques
[Termes IGN] IGN cité
[Termes IGN] image infrarouge couleur
[Termes IGN] image proche infrarouge
[Termes IGN] modèle orienté objet
[Termes IGN] phytoécologieRésumé : (Auteur) Une cartographie inédite de la végétation de Bretagne sera accessible en totalité en ligne en décembre. Produite par télédétection grâce à une méthode semi-automatisée innovante, elle répond aux nouveaux besoins des acteurs de la biodiversité et de l'aménagement du territoire. Numéro de notice : A2020-707 Affiliation des auteurs : non IGN Thématique : BIODIVERSITE/FORET/IMAGERIE Nature : Article nature-HAL : ArtSansCL DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96281
in Géomètre > n° 2185 (novembre 2020) . - pp 46 - 49[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 063-2020101 RAB Revue Centre de documentation En réserve L003 Disponible Building change detection using a shape context similarity model for LiDAR data / Xuzhe Lyu in ISPRS International journal of geo-information, vol 9 n° 11 (November 2020)
[article]
Titre : Building change detection using a shape context similarity model for LiDAR data Type de document : Article/Communication Auteurs : Xuzhe Lyu, Auteur ; Ming Hao, Auteur ; Wenzhong Shi, Auteur Année de publication : 2020 Article en page(s) : n° 678 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes IGN] analyse d'image orientée objet
[Termes IGN] détection de changement
[Termes IGN] détection du bâti
[Termes IGN] données lidar
[Termes IGN] fusion d'images
[Termes IGN] modèle numérique de surface
[Termes IGN] reconnaissance de formes
[Termes IGN] segmentation d'image
[Termes IGN] semis de pointsRésumé : (auteur) In this paper, a novel building change detection approach is proposed using statistical region merging (SRM) and a shape context similarity model for Light Detection and Ranging (LiDAR) data. First, digital surface models (DSMs) are generated from LiDAR acquired at two different epochs, and the difference data D-DSM is created by difference processing. Second, to reduce the noise and registration error of the pixel-based method, the SRM algorithm is applied to segment the D-DSM, and multi-scale segmentation results are obtained under different scale values. Then, the shape context similarity model is used to calculate the shape similarity between the segmented objects and the buildings. Finally, the refined building change map is produced by the k-means clustering method based on shape context similarity and area-to-length ratio. The experimental results indicated that the proposed method could effectively improve the accuracy of building change detection compared with some popular change detection methods. Numéro de notice : A2020-732 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi9110678 Date de publication en ligne : 15/11/2020 En ligne : https://doi.org/10.3390/ijgi9110678 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96345
in ISPRS International journal of geo-information > vol 9 n° 11 (November 2020) . - n° 678[article]Urban tree species identification and carbon stock mapping for urban green planning and management / MD Abdul Choudhury in Forests, vol 11 n°11 (November 2020)PermalinkObject-based classification of mixed forest types in Mongolia / E. Nyamjargal in Geocarto international, vol 35 n° 14 ([15/10/2020])PermalinkApplication of convolutional and recurrent neural networks for buried threat detection using ground penetrating radar data / Mahdi Moalla in IEEE Transactions on geoscience and remote sensing, vol 58 n° 10 (October 2020)PermalinkExploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution / Vitor Martins in ISPRS Journal of photogrammetry and remote sensing, vol 168 (October 2020)PermalinkMapping wetland using the object-based stacked generalization method based on multi-temporal optical and SAR data / Yaotong Cai in International journal of applied Earth observation and geoinformation, vol 92 (October 2020)PermalinkApplication of UAV photogrammetry with LiDAR data to facilitate the estimation of tree locations and DBH values for high-value timber species in Northern Japanese mixed-wood forests / Kyaw Thu Moe in Remote sensing, vol 12 n° 17 (September-1 2020)PermalinkComparison of tree-based classification algorithms in mapping burned forest areas / Dilek Kucuk Matci in Geodetski vestnik, vol 64 n° 3 (September - November 2020)PermalinkCSVM architectures for pixel-wise object detection in high-resolution remote sensing images / Youyou Li in IEEE Transactions on geoscience and remote sensing, vol 58 n° 9 (September 2020)PermalinkDetecting classic Maya settlements with Lidar-derived relief visualizations / Amy E. Thompson in Remote sensing, vol 12 n° 17 (September-1 2020)PermalinkEvaluation of crop mapping on fragmented and complex slope farmlands through random forest and object-oriented analysis using unmanned aerial vehicles / Re-Yang Lee in Geocarto international, vol 35 n° 12 ([01/09/2020])Permalink