Centre dedocumentation
scientifique

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)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 168 (October 2020) . - pp 56 - 73 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] squelettisation Résumé : (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 [article]

Réservation

Réserver ce document

Exemplaires (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

Simultaneous chain-forming and generalization of road networks / Susanne Wenzel in Photogrammetric Engineering & Remote Sensing, PERS, vol 85 n° 1 (January 2019)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 85 n° 1 (January 2019) . - pp 19 - 28 Titre : Simultaneous chain-forming and generalization of road networks Type de document : Article/Communication Auteurs : Susanne Wenzel, Auteur ; Dimitri Bulatov, Auteur Année de publication : 2019 Article en page(s) : pp 19 - 28 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes descripteurs IGN] algorithme de Douglas-Peucker [Termes descripteurs IGN] analyse de groupement [Termes descripteurs IGN] axe médian [Termes descripteurs IGN] classification bayesienne [Termes descripteurs IGN] extraction du réseau routier [Termes descripteurs IGN] Graz [Termes descripteurs IGN] itération [Termes descripteurs IGN] mise à jour automatique [Termes descripteurs IGN] Munich [Termes descripteurs IGN] objet géographique linéaire [Termes descripteurs IGN] orthoimage [Termes descripteurs IGN] polyligne [Termes descripteurs IGN] primitive géométrique [Termes descripteurs IGN] relation topologique [Termes descripteurs IGN] réseau routier [Termes descripteurs IGN] segmentation sémantique [Termes descripteurs IGN] squelettisation [Termes descripteurs IGN] zone urbaine [Vedettes matières IGN] Généralisation Résumé : (auteur) Streets are essential entities of urban terrain and their automatic extraction from airborne sensor data is cumbersome because of a complex interplay of geometric, topological, and semantic aspects. Given a binary image representing the road class, centerlines of road segments are extracted by means of skeletonization. The focus of this paper lies in a well-reasoned representation of these segments by means of geometric primitives, such as straight line segments as well as circle and ellipse arcs. Thereby, we aim at a fusion of raw segments to longer chains which better match to the intuitive perception of what a street is. We propose a two-step approach for simultaneous chain-forming and generalization. First, we obtain an over-segmentation of the raw polylines. Then, a model selection approach is applied to decide whether two neighboring segments should be fused to a new geometric entity. For this purpose, we propose an iterative greedy optimization procedure in order to find a strong minimum of a cost function based on a Bayesian information criterion. Starting at the given initial raw segments, we thus can obtain a set of chains describing long alleys and important roundabouts. Within the procedure, topological attributes, such as junctions and neighborhood structures, are consistently updated, in a way that for the greedy optimization procedure, accuracy, model complexity, and topology are considered simultaneously. The results on two challenging datasets indicate the benefits of the proposed procedure and provide ideas for future work. Numéro de notice : A2019-026 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.14358/PERS.85.1.19 date de publication en ligne : 01/01/2019 En ligne : https://doi.org/10.14358/PERS.85.1.19 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91962 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
105-2019011	SL	Revue	Centre de documentation	Revues en salle	Disponible

3D tree modeling from incomplete point clouds via optimization and L1-MST / Jie Mei in International journal of geographical information science IJGIS, vol 31 n° 5-6 (May-June 2017)  

Public [article]  inInternational journal of geographical information science IJGIS > vol 31 n° 5-6 (May-June 2017) . - pp 999 - 1021 Titre : 3D tree modeling from incomplete point clouds via optimization and L1-MST Type de document : Article/Communication Auteurs : Jie Mei, Auteur ; Liqiang Zhang, Auteur ; Shihao Wu, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 999 - 1021 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] algorithme STA [Termes descripteurs IGN] arbre (flore) [Termes descripteurs IGN] branche (arbre) [Termes descripteurs IGN] densité des points [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] méthode robuste [Termes descripteurs IGN] modèle numérique d'objet [Termes descripteurs IGN] optimisation (mathématiques) [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] semis de points clairsemés [Termes descripteurs IGN] squelettisation Résumé : (auteur) Reconstruction of 3D trees from incomplete point clouds is a challenging issue due to their large variety and natural geometric complexity. In this paper, we develop a novel method to effectively model trees from a single laser scan. First, coarse tree skeletons are extracted by utilizing the L1-median skeleton to compute the dominant direction of each point and the local point density of the point cloud. Then we propose a data completion scheme that guides the compensation for missing data. It is an iterative optimization process based on the dominant direction of each point and local point density. Finally, we present a L1-minimum spanning tree (MST) algorithm to refine tree skeletons from the optimized point cloud, which integrates the advantages of both L1-median skeleton and MST algorithms. The proposed method has been validated on various point clouds captured from single laser scans. The experiment results demonstrate the effectiveness and robustness of our method for coping with complex shapes of branching structures and occlusions. Numéro de notice : A2017-239 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/13658816.2016.1264075 En ligne : http://dx.doi.org/10.1080/13658816.2016.1264075 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85173 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
079-2017031	RAB	Revue	Centre de documentation	En réserve 3L	Disponible

Skeletal camera network embedded structure-from-motion for 3D scene reconstruction from UAV images / Zhihua Xua in ISPRS Journal of photogrammetry and remote sensing, vol 121 (November 2016)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 121 (November 2016) . - pp 113 - 127 Titre : Skeletal camera network embedded structure-from-motion for 3D scene reconstruction from UAV images Type de document : Article/Communication Auteurs : Zhihua Xua, Auteur ; Lixin Wud, Auteur ; Markus Gerke, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 113 - 127 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Acquisition d'image(s) et de donnée(s) [Termes descripteurs IGN] appariement de points [Termes descripteurs IGN] connexité (topologie) [Termes descripteurs IGN] drone [Termes descripteurs IGN] prise de vue aérienne [Termes descripteurs IGN] reconstruction 3D [Termes descripteurs IGN] squelettisation [Termes descripteurs IGN] structure-from-motion [Termes descripteurs IGN] topologie Résumé : (Auteur) Structure-from-Motion (SfM) techniques have been widely used for 3D scene reconstruction from multi-view images. However, due to the large computational costs of SfM methods there is a major challenge in processing highly overlapping images, e.g. images from unmanned aerial vehicles (UAV). This paper embeds a novel skeletal camera network (SCN) into SfM to enable efficient 3D scene reconstruction from a large set of UAV images. First, the flight control data are used within a weighted graph to construct a topologically connected camera network (TCN) to determine the spatial connections between UAV images. Second, the TCN is refined using a novel hierarchical degree bounded maximum spanning tree to generate a SCN, which contains a subset of edges from the TCN and ensures that each image is involved in at least a 3-view configuration. Third, the SCN is embedded into the SfM to produce a novel SCN-SfM method, which allows performing tie-point matching only for the actually connected image pairs. The proposed method was applied in three experiments with images from two fixed-wing UAVs and an octocopter UAV, respectively. In addition, the SCN-SfM method was compared to three other methods for image connectivity determination. The comparison shows a significant reduction in the number of matched images if our method is used, which leads to less computational costs. At the same time the achieved scene completeness and geometric accuracy are comparable. Numéro de notice : A2016--016 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2016.08.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83878 [article]

A local structure and direction-aware optimization approach for three-dimensional tree modeling / Zhen Wang in IEEE Transactions on geoscience and remote sensing, vol 54 n° 8 (August 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 8 (August 2016) . - pp 4749 - 4757 Titre : A local structure and direction-aware optimization approach for three-dimensional tree modeling Type de document : Article/Communication Auteurs : Zhen Wang, Auteur ; Liqiang Zhang, Auteur ; Tian Fang, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 4749 - 4757 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes descripteurs IGN] arbre (flore) [Termes descripteurs IGN] données lidar [Termes descripteurs IGN] données localisées 3D [Termes descripteurs IGN] optimisation (mathématiques) [Termes descripteurs IGN] reconstruction 3D [Termes descripteurs IGN] semis de points [Termes descripteurs IGN] squelettisation Résumé : (Auteur) Modeling 3-D trees from terrestrial laser scanning (TLS) point clouds remains a challenging task for several well-known reasons, including their complex structure and severe occlusions. In order to accurately reconstruct 3-D tree models from TLS point clouds that typically suffer from significant occlusions, in this paper, a novel local structure and direction-aware approach is presented to successfully complete missing structures of trees. In this method, we first extract the coarse tree skeleton from the input point cloud, and thus, the branch dominant direction and the point density of each branch are obtained. By a skeleton-based Laplacian algorithm, the point cloud is further shrunk into a skeleton point cloud to highlight the branch dominant direction of each branch. For obtaining even more accurate point densities, a dictionary-based algorithm is utilized to learn and reconstruct the local structure. Finally, the branch dominant direction and point density are integrated into an iterative optimization process to recover the missing data. Extensive experimental results have shown that the proposed method is very robust to incomplete data sets, and it is capable of accurately reconstructing 3-D trees, which are partially, or even to a large extent, missing from the input point cloud. Numéro de notice : A2016-890 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern En ligne : http://dx.doi.org/10.1109/TGRS.2016.2551286 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=83070 [article]

Crowd-sourced reconstruction of building interiors / Michael Peter (2016) 

Permalink

Pattern-mining approach for conflating crowdsourcing road networks with POIs / Bisheng Yang in International journal of geographical information science IJGIS, vol 29 n° 5 (May 2015)  

Permalink

Weighted straight skeletons in the plane / Therese Biedl in Computational Geometry : theory and applications, vol 48 n° 2 (February 2015)  

Permalink

3D tree reconstruction from simulated small footprint waveform lidar / Jiaying Wu in Photogrammetric Engineering & Remote Sensing, PERS, vol 79 n° 12 (December 2013)  

Permalink

Derivation of tree skeletons and error assessment using LiDAR point cloud data of varying quality / Magnus Bremer in ISPRS Journal of photogrammetry and remote sensing, vol 80 (June 2013)

Permalink

2D arrangement-based hierarchical spatial partitioning: an application to pedestrian network generation / Murat Yirci (2013)  

Permalink

Aerial image mosaicking with aid of vector roads / D. Wang in Photogrammetric Engineering & Remote Sensing, PERS, vol 78 n° 11 (November 2012)  

Permalink

Automated detection of branch dimensions in woody skeletons of fruit tree canopies / Alexander Bucksch in Photogrammetric Engineering & Remote Sensing, PERS, vol 77 n° 3 (March 2011)  

Permalink

Length-preserving thinning algorithm for line extraction from land cover data / J. Choi in Cartographica, vol 43 n° 4 (December 2008)

Permalink

CAMPINO, a skeletonization method for point cloud processing / Alexander Bucksch in ISPRS Journal of photogrammetry and remote sensing, vol 63 n° 1 (January - February 2008)

Permalink