Descripteur
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externesEtendre la recherche sur niveau(x) vers le bas
Exploring 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)
Titre : Exploring multiscale object-based convolutional neural network (multi-OCNN) for remote sensing image classification at high spatial resolution Type de document : Article/Communication Auteurs : Vitor Martins, Auteur ; Amy L. Kaleita, Auteur ; Brian K. Gelder, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 56 - 73 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] analyse d'image orientée objet
[Termes descripteurs IGN] apprentissage profond
[Termes descripteurs IGN] classification par réseau neuronal convolutif
[Termes descripteurs IGN] données multiéchelles
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] hétérogénéité environnementale
[Termes descripteurs IGN] image à haute résolution
[Termes descripteurs IGN] occupation du sol
[Termes descripteurs IGN] reconnaissance d'objets
[Termes descripteurs IGN] segmentation d'image
[Termes descripteurs IGN] squelettisationRésumé : (auteur) Convolutional Neural Network (CNN) has been increasingly used for land cover mapping of remotely sensed imagery. However, large-area classification using traditional CNN is computationally expensive and produces coarse maps using a sliding window approach. To address this problem, object-based CNN (OCNN) becomes an alternative solution to improve classification performance. However, previous studies were mainly focused on urban areas or small scenes, and implementation of OCNN method is still needed for large-area classification over heterogeneous landscape. Additionally, the massive labeling of segmented objects requires a practical approach for less computation, including object analysis and multiple CNNs. This study presents a new multiscale OCNN (multi-OCNN) framework for large-scale land cover classification at 1-m resolution over 145,740 km2. Our approach consists of three main steps: (i) image segmentation, (ii) object analysis with skeleton-based algorithm, and (iii) application of multiple CNNs for final classification. Also, we developed a large benchmark dataset, called IowaNet, with 1 million labeled images and 10 classes. In our approach, multiscale CNNs were trained to capture the best contextual information during the semantic labeling of objects. Meanwhile, skeletonization algorithm provided morphological representation (“medial axis”) of objects to support the selection of convolutional locations for CNN predictions. In general, proposed multi-OCNN presented better classification accuracy (overall accuracy ~87.2%) compared to traditional patch-based CNN (81.6%) and fixed-input OCNN (82%). In addition, the results showed that this framework is 8.1 and 111.5 times faster than traditional pixel-wise CNN16 or CNN256, respectively. Multiple CNNs and object analysis have proved to be essential for accurate and fast classification. While multi-OCNN produced a high-level of spatial details in the land cover product, misclassification was observed for some classes, such as road versus buildings or shadow versus lake. Despite these minor drawbacks, our results also demonstrated the benefits of IowaNet training dataset in the model performance; overfitting process reduces as the number of samples increases. The limitations of multi-OCNN are partially explained by segmentation quality and limited number of spectral bands in the aerial data. With the advance of deep learning methods, this study supports the claim of multi-OCNN benefits for operational large-scale land cover product at 1-m resolution. Numéro de notice : A2020-634 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.08.004 date de publication en ligne : 13/08/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.08.004 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=96057
in ISPRS Journal of photogrammetry and remote sensing > vol 168 (October 2020) . - pp 56 - 73[article]Réservation
Réserver ce documentExemplaires (3)
Code-barres Cote Support Localisation Section Disponibilité 081-2020101 SL Revue Centre de documentation Revues en salle Disponible 081-2020103 DEP-RECP Revue MATIS Dépôt en unité Exclu du prêt 081-2020102 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt
Titre : Unsupervised semantic and instance segmentation of forest point clouds Type de document : Article/Communication Auteurs : Di Wang, Auteur Année de publication : 2020 Article en page(s) : pp 86 - 97 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes descripteurs IGN] analyse de groupement
[Termes descripteurs IGN] classification non dirigée
[Termes descripteurs IGN] données lidar
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] hauteur des arbres
[Termes descripteurs IGN] houppier
[Termes descripteurs IGN] indice foliaire
[Termes descripteurs IGN] interprétation automatique
[Termes descripteurs IGN] segmentation sémantique
[Termes descripteurs IGN] semis de points
[Termes descripteurs IGN] télémètre laser terrestreRésumé : (auteur) Terrestrial Laser Scanning (TLS) has been increasingly used in forestry applications including forest inventory and plant ecology. Tree biophysical properties such as leaf area distributions and wood volumes can be accurately estimated from TLS point clouds. In these applications, a prerequisite is to properly understand the information content of large scale point clouds (i.e., semantic labelling of point clouds), so that tree-scale attributes can be retrieved. Currently, this requirement is undergoing laborious and time consuming manual works. In this work, we jointly address the problems of semantic and instance segmentation of forest point clouds. Specifically, we propose an unsupervised pipeline based on a structure called superpoint graph, to simultaneously perform two tasks: single tree isolation and leaf-wood classification. The proposed method is free from restricted assumptions of forest types. Validation using simulated data resulted in a mean Intersection over Union (mIoU) of 0.81 for single tree isolation, and an overall accuracy of 87.7% for leaf-wood classification. The single tree isolation led to a relative root mean square error (RMSE%) of 2.9% and 19.8% for tree height and crown diameter estimations, respectively. Comparisons with existing methods on other benchmark datasets showed state-of-the-art results of our method on both single tree isolation and leaf-wood classification tasks. We provide the entire framework as an open-source tool with an end-user interface. This study closes the gap for using TLS point clouds to quantify tree-scale properties in large areas, where automatic interpretation of the information content of TLS point clouds remains a crucial challenge. Numéro de notice : A2020-347 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.04.020 date de publication en ligne : 28/05/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.04.020 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95228
in ISPRS Journal of photogrammetry and remote sensing > vol 165 (July 2020) . - pp 86 - 97[article]Réservation
Réserver ce documentExemplaires (3)
Code-barres Cote Support Localisation Section Disponibilité 081-2020071 SL Revue Centre de documentation Revues en salle Disponible 081-2020073 DEP-RECP Revue MATIS Dépôt en unité Exclu du prêt 081-2020072 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt
Titre : Semantic signatures for large-scale visual localization Type de document : Article/Communication Auteurs : Li Weng Année de publication : 2020 Projets : THINGS2D0 / Gouet-Brunet, Valérie Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes descripteurs IGN] appariement sémantique
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] extraction de traits caractéristiques
[Termes descripteurs IGN] image numérique
[Termes descripteurs IGN] information sémantique
[Termes descripteurs IGN] recherche d'image basée sur le contenu
[Termes descripteurs IGN] zone urbaineRésumé : (auteur) Visual localization is a useful alternative to standard localization techniques. It works by utilizing cameras. In a typical scenario, features are extracted from captured images and compared with geo-referenced databases. Location information is then inferred from the matching results. Conventional schemes mainly use low-level visual features. These approaches offer good accuracy but suffer from scalability issues. In order to assist localization in large urban areas, this work explores a different path by utilizing high-level semantic information. It is found that object information in a street view can facilitate localization. A novel descriptor scheme called “semantic signature” is proposed to summarize this information. A semantic signature consists of type and angle information of visible objects at a spatial location. Several metrics and protocols are proposed for signature comparison and retrieval. They illustrate different trade-offs between accuracy and complexity. Extensive simulation results confirm the potential of the proposed scheme in large-scale applications. This paper is an extended version of a conference paper in CBMI’18. A more efficient retrieval protocol is presented with additional experiment results. Numéro de notice : A2020-367 Affiliation des auteurs : LaSTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11042-020-08992-6 date de publication en ligne : 07/05/2020 En ligne : https://doi.org/10.1007/s11042-020-08992-6 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95407
in Multimedia tools and applications > vol inconnu (2020)[article]
Titre : Directionally constrained fully convolutional neural network for airborne LiDAR point cloud classification Type de document : Article/Communication Auteurs : Congcong Wen, Auteur ; Lina Yang, Auteur ; Xiang Li, Auteur ; et al., Auteur Année de publication : 2020 Article en page(s) : pp 50 - 62 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie
[Termes descripteurs IGN] apprentissage automatique
[Termes descripteurs IGN] classification par réseau neuronal convolutif
[Termes descripteurs IGN] contrainte de direction
[Termes descripteurs IGN] données lidar
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] fusion de données
[Termes descripteurs IGN] plus proche voisin (algorithme)
[Termes descripteurs IGN] précision de la classification
[Termes descripteurs IGN] semis de points
[Termes descripteurs IGN] traitement de nuage de pointsRésumé : (auteur) Point cloud classification plays an important role in a wide range of airborne light detection and ranging (LiDAR) applications, such as topographic mapping, forest monitoring, power line detection, and road detection. However, due to the sensor noise, high redundancy, incompleteness, and complexity of airborne LiDAR systems, point cloud classification is challenging. Traditional point cloud classification methods mostly focus on the development of handcrafted point geometry features and employ machine learning-based classification models to conduct point classification. In recent years, the advances of deep learning models have caused researchers to shift their focus towards machine learning-based models, specifically deep neural networks, to classify airborne LiDAR point clouds. These learning-based methods start by transforming the unstructured 3D point sets to regular 2D representations, such as collections of feature images, and then employ a 2D CNN for point classification. Moreover, these methods usually need to calculate additional local geometry features, such as planarity, sphericity and roughness, to make use of the local structural information in the original 3D space. Nonetheless, the 3D to 2D conversion results in information loss. In this paper, we propose a directionally constrained fully convolutional neural network (D-FCN) that can take the original 3D coordinates and LiDAR intensity as input; thus, it can directly apply to unstructured 3D point clouds for semantic labeling. Specifically, we first introduce a novel directionally constrained point convolution (D-Conv) module to extract locally representative features of 3D point sets from the projected 2D receptive fields. To make full use of the orientation information of neighborhood points, the proposed D-Conv module performs convolution in an orientation-aware manner by using a directionally constrained nearest neighborhood search. Then, we design a multiscale fully convolutional neural network with downsampling and upsampling blocks to enable multiscale point feature learning. The proposed D-FCN model can therefore process input point cloud with arbitrary sizes and directly predict the semantic labels for all the input points in an end-to-end manner. Without involving additional geometry features as input, the proposed method demonstrates superior performance on the International Society for Photogrammetry and Remote Sensing (ISPRS) 3D labeling benchmark dataset. The results show that our model achieves a new state-of-the-art performance on powerline, car, and facade categories. Moreover, to demonstrate the generalization abilities of the proposed method, we conduct further experiments on the 2019 Data Fusion Contest Dataset. Our proposed method achieves superior performance than the comparing methods and accomplishes an overall accuracy of 95.6% and an average F1 score of 0.810. Numéro de notice : A2020-119 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2020.02.004 date de publication en ligne : 18/02/2020 En ligne : https://doi.org/10.1016/j.isprsjprs.2020.02.004 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94743
in ISPRS Journal of photogrammetry and remote sensing > vol 162 (April 2020) . - pp 50 - 62[article]
Titre : Modelling discontinuous terrain from DSMs using segment labelling, outlier removal and thin-plate splines Type de document : Article/Communication Auteurs : Kassel Hingee, Auteur ; Peter Caccetta, Auteur ; Louis Caccetta, Auteur Année de publication : 2019 Article en page(s) : pp 159 - 171 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes descripteurs IGN] Australie
[Termes descripteurs IGN] discontinuité
[Termes descripteurs IGN] étiquetage sémantique
[Termes descripteurs IGN] filtrage de points
[Termes descripteurs IGN] modèle numérique de surface
[Termes descripteurs IGN] modèle numérique de terrain
[Termes descripteurs IGN] valeur aberranteRésumé : (Auteur) Models of ground surface elevations are crucial to many applications of remotely sensed data, including estimates of the height relative to ground of non-ground objects, such as buildings and vegetation. In highly engineered regions, such as cities, there are many discontinuities in both the ground surface and the surface of non-ground objects. Sub-metre resolution elevation data for these regions are increasingly available. At these resolutions there is sufficient information and a growing need to improve model accuracies by incorporating discontinuities. Here we provide a new method for generating high resolution models of discontinuous ground surfaces from breakline data and digital surface models derived from remotely sensed data. The method uses segment based filtering, outlier removal and multiresolution thin-plate spline surface fitting. Breaklines are included in the fitted surface using partial derivatives and a breakline-aware method for transferring between different resolutions. We demonstrate our method using elevation data derived from photogrammetry for suburban regions of Perth, Western Australia, and Vaihingen, Germany. We produced ground surface models with noticeable qualitative and quantitative improvements when breaklines are included, at an increased computational cost of approximately 10% when all other parameters remained the same. For LiDAR derived elevations, we report our residual error against a number of other methods recorded using the ISPRS Ground Filtering Test Sites. Numéro de notice : A2019-314 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.isprsjprs.2019.07.004 date de publication en ligne : 24/07/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.07.004 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93340
in ISPRS Journal of photogrammetry and remote sensing > vol 155 (September 2019) . - pp 159 - 171[article]Réservation
Réserver ce documentExemplaires (3)
Code-barres Cote Support Localisation Section Disponibilité 081-2019091 RAB Revue Centre de documentation En réserve 3L Disponible 081-2019093 DEP-RECP Revue MATIS Dépôt en unité Exclu du prêt 081-2019092 DEP-RECF Revue Nancy Dépôt en unité Exclu du prêt PermalinkPermalinkPermalinkPermalinkPermalinkPermalink
