Centre dedocumentation
scientifique

Fully automated pose estimation of historical images in the context of 4D geographic information systems utilizing machine learning methods / Ferdinand Maiwald in ISPRS International journal of geo-information, vol 10 n° 11 (November 2021)  

Public [article]  inISPRS International journal of geo-information > vol 10 n° 11 (November 2021) . - n° 748 Titre : Fully automated pose estimation of historical images in the context of 4D geographic information systems utilizing machine learning methods Type de document : Article/Communication Auteurs : Ferdinand Maiwald, Auteur ; Christoph Lehmann, Auteur ; Taras Lazariv, Auteur Année de publication : 2021 Article en page(s) : n° 748 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] apprentissage automatique [Termes IGN] chaîne de traitement [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] corrélation à l'aide de traits caractéristiques [Termes IGN] échelle de temps [Termes IGN] estimation de pose [Termes IGN] image ancienne [Termes IGN] image terrestre [Termes IGN] métadonnées [Termes IGN] modélisation 4D [Termes IGN] patrimoine culturel [Termes IGN] recherche d'image basée sur le contenu [Termes IGN] récupération de données [Termes IGN] structure-from-motion [Termes IGN] système d'information géographique Résumé : (auteur) The idea of virtual time machines in digital environments like hand-held virtual reality or four-dimensional (4D) geographic information systems requires an accurate positioning and orientation of urban historical images. The browsing of large repositories to retrieve historical images and their subsequent precise pose estimation is still a manual and time-consuming process in the field of Cultural Heritage. This contribution presents an end-to-end pipeline from finding relevant images with utilization of content-based image retrieval to photogrammetric pose estimation of large historical terrestrial image datasets. Image retrieval as well as pose estimation are challenging tasks and are subjects of current research. Thereby, research has a strong focus on contemporary images but the methods are not considered for a use on historical image material. The first part of the pipeline comprises the precise selection of many relevant historical images based on a few example images (so called query images) by using content-based image retrieval. Therefore, two different retrieval approaches based on convolutional neural networks (CNN) are tested, evaluated, and compared with conventional metadata search in repositories. Results show that image retrieval approaches outperform the metadata search and are a valuable strategy for finding images of interest. The second part of the pipeline uses techniques of photogrammetry to derive the camera position and orientation of the historical images identified by the image retrieval. Multiple feature matching methods are used on four different datasets, the scene is reconstructed in the Structure-from-Motion software COLMAP, and all experiments are evaluated on a newly generated historical benchmark dataset. A large number of oriented images, as well as low error measures for most of the datasets, show that the workflow can be successfully applied. Finally, the combination of a CNN-based image retrieval and the feature matching methods SuperGlue and DISK show very promising results to realize a fully automated workflow. Such an automated workflow of selection and pose estimation of historical terrestrial images enables the creation of large-scale 4D models. Numéro de notice : A2021-827 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi10110748 Date de publication en ligne : 04/11/2021 En ligne : https://doi.org/10.3390/ijgi10110748 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98964 [article]

Pose estimation and 3D reconstruction of vehicles from stereo-images using a subcategory-aware shape prior / Maximilian Alexander Coenen in ISPRS Journal of photogrammetry and remote sensing, Vol 181 (November 2021)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > Vol 181 (November 2021) . - pp 27 - 47 Titre : Pose estimation and 3D reconstruction of vehicles from stereo-images using a subcategory-aware shape prior Type de document : Article/Communication Auteurs : Maximilian Alexander Coenen, Auteur ; Franz Rottensteiner, Auteur Année de publication : 2021 Article en page(s) : pp 27 - 47 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] estimation de pose [Termes IGN] modèle stochastique [Termes IGN] problème inverse [Termes IGN] reconstruction 3D [Termes IGN] reconstruction d'objet [Termes IGN] robotique [Termes IGN] véhicule automobile [Termes IGN] vision par ordinateur Résumé : (auteur) The 3D reconstruction of objects is a prerequisite for many highly relevant applications of computer vision such as mobile robotics or autonomous driving. To deal with the inverse problem of reconstructing 3D objects from their 2D projections, a common strategy is to incorporate prior object knowledge into the reconstruction approach by establishing a 3D model and aligning it to the 2D image plane. However, current approaches are limited due to inadequate shape priors and the insufficiency of the derived image observations for a reliable alignment with the 3D model. The goal of this paper is to show how 3D object reconstruction can profit from a more sophisticated shape prior and from a combined incorporation of different observation types inferred from the images. We introduce a subcategory-aware deformable vehicle model that makes use of a prediction of the vehicle type for a more appropriate regularisation of the vehicle shape. A multi-branch CNN is presented to derive predictions of the vehicle type and orientation. This information is also introduced as prior information for model fitting. Furthermore, the CNN extracts vehicle keypoints and wireframes, which are well-suited for model-to-image association and model fitting. The task of pose estimation and reconstruction is addressed by a versatile probabilistic model. Extensive experiments are conducted using two challenging real-world data sets on both of which the benefit of the developed shape prior can be shown. A comparison to state-of-the-art methods for vehicle pose estimation shows that the proposed approach performs on par or better, confirming the suitability of the developed shape prior and probabilistic model for vehicle reconstruction. Numéro de notice : A2021-772 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2021.07.006 Date de publication en ligne : 14/09/2021 En ligne : https://doi.org/10.1016/j.isprsjprs.2021.07.006 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98829 [article]

Spherically optimized RANSAC aided by an IMU for Fisheye Image Matching / Anbang Liang in Remote sensing, vol 13 n°10 (May-2 2021)  

Public [article]  inRemote sensing > vol 13 n°10 (May-2 2021) . - n° 2017 Titre : Spherically optimized RANSAC aided by an IMU for Fisheye Image Matching Type de document : Article/Communication Auteurs : Anbang Liang, Auteur ; Qingquan Li, Auteur ; Zhipeng Chen, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 2017 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement d'images [Termes IGN] centrale inertielle [Termes IGN] coordonnées sphériques [Termes IGN] distorsion d'image [Termes IGN] estimation de pose [Termes IGN] étalonnage de chambre métrique [Termes IGN] géométrie épipolaire [Termes IGN] image hémisphérique [Termes IGN] Ransac (algorithme) Résumé : (auteur) Fisheye cameras are widely used in visual localization due to the advantage of the wide field of view. However, the severe distortion in fisheye images lead to feature matching difficulties. This paper proposes an IMU-assisted fisheye image matching method called spherically optimized random sample consensus (So-RANSAC). We converted the putative correspondences into fisheye spherical coordinates and then used an inertial measurement unit (IMU) to provide relative rotation angles to assist fisheye image epipolar constraints and improve the accuracy of pose estimation and mismatch removal. To verify the performance of So-RANSAC, experiments were performed on fisheye images of urban drainage pipes and public data sets. The experimental results showed that So-RANSAC can effectively improve the mismatch removal accuracy, and its performance was superior to the commonly used fisheye image matching methods in various experimental scenarios. Numéro de notice : A2021-416 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3390/rs13102017 Date de publication en ligne : 20/05/2021 En ligne : https://doi.org/10.3390/rs13102017 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97757 [article]

A skyline-based approach for mobile augmented reality / Mehdi Ayadi in The Visual Computer, vol 37 n° 4 (April 2021)  

Public [article]  inThe Visual Computer > vol 37 n° 4 (April 2021) . - pp 789 - 804 Titre : A skyline-based approach for mobile augmented reality Type de document : Article/Communication Auteurs : Mehdi Ayadi, Auteur ; Mihaela Scuturici, Auteur ; Chokri Ben Amar, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : pp 789 - 804 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] appariement géométrique [Termes IGN] base de données d'images [Termes IGN] CityGML [Termes IGN] détection de contours [Termes IGN] estimation de pose [Termes IGN] extraction de traits caractéristiques [Termes IGN] Lyon [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] paysage urbain [Termes IGN] réalité augmentée [Termes IGN] superposition d'images [Termes IGN] téléphone intelligent [Termes IGN] vision par ordinateur [Vedettes matières IGN] Géovisualisation Résumé : (auteur) This paper presents a skyline-based approach to enhance the visualization of a new construction project in augmented reality. We propose to process the video stream acquired with a mobile phone to register the real buildings with a 3D city model. We first combine the data acquired with the device’s instruments to estimate a rough user’s pose in the world coordinates system. Then, we use this estimated pose to generate a synthetic image of the user’s view from which we calculate a virtual skyline. In parallel, we extract a real skyline from the real-time video stream. Finally, we match these real and virtual skylines to correct the user’s pose (six degrees of freedom) and thus generate a more realistic augmented reality view. We evaluate the precision and the processing time of our approach using 2D and 3D registration algorithms, as well as with a novel double 2D strategy. Numéro de notice : A2021-342 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s00371-020-01830-8 Date de publication en ligne : 06/03/2020 En ligne : https://doi.org/10.1007/s00371-020-01830-8 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97581 [article]

Visual positioning in indoor environments using RGB-D images and improved vector of local aggregated descriptors / Longyu Zhang in ISPRS International journal of geo-information, vol 10 n° 4 (April 2021)  

Public [article]  inISPRS International journal of geo-information > vol 10 n° 4 (April 2021) . - n° 195 Titre : Visual positioning in indoor environments using RGB-D images and improved vector of local aggregated descriptors Type de document : Article/Communication Auteurs : Longyu Zhang, Auteur ; Hao Xia, Auteur ; Qingjun Liu, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 195 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification par nuées dynamiques [Termes IGN] estimation de pose [Termes IGN] extraction de traits caractéristiques [Termes IGN] image RVB [Termes IGN] modélisation 3D [Termes IGN] positionnement en intérieur [Termes IGN] Ransac (algorithme) [Termes IGN] scène intérieure [Termes IGN] SIFT (algorithme) [Termes IGN] SURF (algorithme) [Termes IGN] téléphone intelligent [Termes IGN] vision par ordinateur Résumé : (auteur) Positioning information has become one of the most important information for processing and displaying on smart mobile devices. In this paper, we propose a visual positioning method using RGB-D image on smart mobile devices. Firstly, the pose of each image in the training set is calculated through feature extraction and description, image registration, and pose map optimization. Then, in the image retrieval stage, the training set and the query set are clustered to generate the vector of local aggregated descriptors (VLAD) description vector. In order to overcome the problem that the description vector loses the image color information and improve the retrieval accuracy under different lighting conditions, the opponent color information and depth information are added to the description vector for retrieval. Finally, using the point cloud corresponding to the retrieval result image and its pose, the pose of the retrieved image is calculated by perspective-n-point (PnP) method. The results of indoor scene positioning under different illumination conditions show that the proposed method not only improves the positioning accuracy compared with the original VLAD and ORB-SLAM2, but also has high computational efficiency. Numéro de notice : A2021-481 Affiliation des auteurs : non IGN Thématique : IMAGERIE/POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi10040195 Date de publication en ligne : 24/03/2021 En ligne : https://doi.org/10.3390/ijgi10040195 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97425 [article]

Semi-supervised joint learning for hand gesture recognition from a single color image / Chi Xu in Sensors, vol 21 n° 3 (February 2021)  

Permalink

Apprentissage profond et IA pour l’amélioration de la robustesse des techniques de localisation par vision artificielle / Achref Elouni (2021)  

Permalink

Learning to map street-side objects using multiple views / Ahmed Samy Nassar (2021)  

Permalink

Robust and fast global image orientation / Xin Wang (2021)  

Permalink

How to spatialize geographical iconographic heritage / Emile Blettery (2021)    

Permalink

3D hand mesh reconstruction from a monocular RGB image / Hao Peng in The Visual Computer, vol 36 n° 10 - 12 (October 2020)  

Permalink

Guided feature matching for multi-epoch historical image blocks pose estimation / Lulin Zhang in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2 (August 2020)  

Permalink

Towards structureless bundle adjustment with two- and three-view structure approximation / Ewelina Rupnik in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-2 (August 2020)  

Permalink

Refractive two-view reconstruction for underwater 3D vision / François Chadebecq in International journal of computer vision, vol 128 n° 5 (May 2020)  

Permalink

Automatic scale estimation of structure from motion based 3D models using laser scalers in underwater scenarios / Klemen Istenič in ISPRS Journal of photogrammetry and remote sensing, vol 159 (January 2020)  

Permalink