Centre dedocumentation
scientifique

Feature detection and description for image matching: from hand-crafted design to deep learning / Lin Chen in Geo-spatial Information Science, vol 24 n° 1 (March 2021)  

Public [article]  inGeo-spatial Information Science > vol 24 n° 1 (March 2021) . - pp 58 - 74 Titre : Feature detection and description for image matching: from hand-crafted design to deep learning Type de document : Article/Communication Auteurs : Lin Chen, Auteur ; Franz Rottensteiner, Auteur ; Christian Heipke, Auteur Année de publication : 2021 Article en page(s) : pp 58 - 74 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement automatique [Termes IGN] appariement d'images [Termes IGN] appariement de formes [Termes IGN] apprentissage automatique [Termes IGN] apprentissage profond [Termes IGN] extraction de traits caractéristiques [Termes IGN] image aérienne oblique [Termes IGN] orientation d'image [Termes IGN] SIFT (algorithme) Résumé : (Auteur) In feature based image matching, distinctive features in images are detected and represented by feature descriptors. Matching is then carried out by assessing the similarity of the descriptors of potentially conjugate points. In this paper, we first shortly discuss the general framework. Then, we review feature detection as well as the determination of affine shape and orientation of local features, before analyzing feature description in more detail. In the feature description review, the general framework of local feature description is presented first. Then, the review discusses the evolution from hand-crafted feature descriptors, e.g. SIFT (Scale Invariant Feature Transform), to machine learning and deep learning based descriptors. The machine learning models, the training loss and the respective training data of learning-based algorithms are looked at in more detail; subsequently the various advantages and challenges of the different approaches are discussed. Finally, we present and assess some current research directions before concluding the paper. Numéro de notice : A2021-297 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10095020.2020.1843376 date de publication en ligne : 17/11/2020 En ligne : https://doi.org/10.1080/10095020.2020.1843376 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97379 [article]

Post‐filtering with surface orientation constraints for stereo dense image matching / Xu Huang in Photogrammetric record, vol 35 n° 171 (September 2020)  

Public [article]  inPhotogrammetric record > vol 35 n° 171 (September 2020) . - pp 375-401 Titre : Post‐filtering with surface orientation constraints for stereo dense image matching Type de document : Article/Communication Auteurs : Xu Huang, Auteur ; Rongjun Qin, Auteur Année de publication : 2020 Article en page(s) : pp 375-401 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement d'images [Termes IGN] corrélation automatique de points homologues [Termes IGN] corrélation d'images [Termes IGN] filtrage numérique d'image [Termes IGN] modèle numérique de surface [Termes IGN] modèle stéréoscopique [Termes IGN] orientation d'image Résumé : (Auteur) Dense image matching (DIM) is a critical technique when computing accurate 3D geometric information for many photogrammetric applications. Most DIM methods adopt first‐order regularisation priors for efficient matching, which often introduce stepped biases (also called fronto‐parallel biases) into the matching results. To remove these biases and compute more accurate matching results, this paper proposes a novel post‐filtering method by adjusting the surface orientation of each pixel in the matching process. The core algorithm formulates the post‐filtering as the optimisation of a global energy function with second‐order regularisation priors. A compromise solution of the energy function is computed by breaking the optimisation into a collection of sub‐optimisations of each pixel in a local adaptive window. The proposed method was compared with several state‐of‐the‐art post‐filtering methods on indoor, aerial and satellite datasets. The comparisons demonstrate that the proposed method obtains the highest post‐filtering accuracies on all datasets. Numéro de notice : A2020-437 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/phor.12333 date de publication en ligne : 20/09/2020 En ligne : https://doi.org/10.1111/phor.12333 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95843 [article]

Close-range photogrammetry and 3D imaging / Thomas Luhmann (2020)

Public Titre : Close-range photogrammetry and 3D imaging Type de document : Monographie Auteurs : Thomas Luhmann, Auteur ; Stuart Robson, Auteur ; Stephen Kyle, Auteur ; Jan Boehm, Auteur Editeur : Berlin, New York : Walter de Gruyter Année de publication : 2020 Importance : 822 p. Format : 17 x 24 cm ISBN/ISSN/EAN : 978-3-11-060724-6 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] analyse d'image numérique [Termes IGN] étalonnage [Termes IGN] image 3D [Termes IGN] instrument de photogrammétrie [Termes IGN] logiciel de photogrammétrie [Termes IGN] modélisation 3D [Termes IGN] orientation d'image [Termes IGN] photogrammétrie métrologique [Termes IGN] précision des mesures [Termes IGN] reconstruction 3D [Termes IGN] transformation mathématique Index. décimale : 33.30 Photogrammétrie numérique Résumé : (Editeur) This is the third edition of the well-known guide to close-range photogrammetry. It provides a thorough presentation of the methods, mathematics, systems and applications which comprise the subject of close-range photogrammetry, which uses accurate imaging techniques to analyse the three-dimensional shape of a wide range of manufactured and natural objects. Note de contenu : 1. Introduction 2. Mathematical fundamentals 3. Imaging technology 4. Analytical methods 5. Digital image analysis 6. Measuring tasks and systems 7. Measurement design and quality 8. Example applications Numéro de notice : 26341 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Monographie Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=95700

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
26341-01	33.30	Livre	Centre de documentation	Photogrammétrie - Lasergrammétrie	Disponible

Automatic sensor orientation using horizontal and vertical line feature constraints / Yanbiao Sun in ISPRS Journal of photogrammetry and remote sensing, vol 150 (April 2019)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 150 (April 2019) . - pp 172 - 184 Titre : Automatic sensor orientation using horizontal and vertical line feature constraints Type de document : Article/Communication Auteurs : Yanbiao Sun, Auteur ; Stuart Robson, Auteur ; Daniel Scott, Auteur ; et al., Auteur Année de publication : 2019 Article en page(s) : pp 172 - 184 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie numérique [Termes IGN] angle azimutal [Termes IGN] angle vertical [Termes IGN] compensation par faisceaux [Termes IGN] coordonnées horizontales [Termes IGN] extraction de traits caractéristiques [Termes IGN] forme linéaire [Termes IGN] image aérienne [Termes IGN] ligne caractéristique [Termes IGN] orientation d'image [Termes IGN] orientation du capteur [Termes IGN] point d'appui Résumé : (Auteur) To improve the accuracy of sensor orientation using calibrated aerial images, this paper proposes an automatic sensor orientation method utilizing horizontal and vertical constraints on human-engineered structures, addressing the limitations faced with sub-optimal number of Ground Control Points (GCPs) within a scene. Related state-of-the-art methods rely on structured building edges, and necessitate manual identification of end points. Our method makes use of line-segments but eliminates the need for these matched end points, thus eliminating the need for inefficient manual intervention. To achieve this, a 3D line in object space is represented by the intersection of two planes going through two camera centers. The normal vector of each plane can be written as a function of a pair of azimuth and elevations angles. The normal vector of the 3D line can be expressed by the cross product of these two plane’s normal vectors. Then, we create observation functions of horizontal and vertical line constraints based on the zero-vector cross-product and the dot-product of the normal vector of the 3D lines. The observation functions of the horizontal and vertical lines are then introduced into a hybrid Bundle Adjustment (BA) method as constraints, including observed image points as well as observed line segment projections. Finally, to assess the feasibility and effectiveness of the proposed method, simulated and real data are tested. The results demonstrate that, in cases with only 3 GCPs, the accuracy of the proposed method utilizing line features extracted automatically, is increased by 50%, compared to a BA using only point constraints. Numéro de notice : A2019-140 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2019.02.011 date de publication en ligne : 28/02/2019 En ligne : https://doi.org/10.1016/j.isprsjprs.2019.02.011 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=92478 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2019041	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2019043	DEP-RECP	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2019042	DEP-RECF	Revue	Nancy	Dépôt en unité	Exclu du prêt

A fully automatic approach to register mobile mapping and airborne imagery to support the correction of plateform trajectories in GNSS-denied urban areas / Phillipp Jende in ISPRS Journal of photogrammetry and remote sensing, vol 141 (July 2018)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 141 (July 2018) . - pp 86 - 99 Titre : A fully automatic approach to register mobile mapping and airborne imagery to support the correction of plateform trajectories in GNSS-denied urban areas Type de document : Article/Communication Auteurs : Phillipp Jende, Auteur ; Francesco Nex, Auteur ; Markus Gerke, Auteur ; M. George Vosselman, Auteur Année de publication : 2018 Article en page(s) : pp 86 - 99 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] appariement géométrique [Termes IGN] extraction de traits caractéristiques [Termes IGN] filtre de Wallis [Termes IGN] GNSS assisté pour la navigation [Termes IGN] image aérienne [Termes IGN] image terrestre [Termes IGN] orientation d'image [Termes IGN] orthoimage [Termes IGN] point d'appui [Termes IGN] précision décimétrique [Termes IGN] système de numérisation mobile [Termes IGN] zone urbaine Résumé : (Auteur) Mobile Mapping (MM) solutions have become a significant extension to traditional data acquisition methods over the last years. Independently from the sensor carried by a platform, may it be laser scanners or cameras, high-resolution data postings are opposing a poor absolute localisation accuracy in urban areas due to GNSS occlusions and multipath effects. Potentially inaccurate position estimations are propagated by IMUs which are furthermore prone to drift effects. Thus, reliable and accurate absolute positioning on a par with MM's high-quality data remains an open issue. Multiple and diverse approaches have shown promising potential to mitigate GNSS errors in urban areas, but cannot achieve decimetre accuracy, require manual effort, or have limitations with respect to costs and avail-ability. This paper presents a fully automatic approach to support the correction of MM imaging data based on correspondences with airborne nadir images. These correspondences can be employed to correct the MM plat-form's orientation by an adjustment solution. Unlike MM as such, aerial images do not suffer from GNSS oc-clusions, and their accuracy is usually verified by employing well-established methods using ground control points. However, a registration between MM and aerial images is a non-standard matching scenario, and requires several strategies to yield reliable and accurate correspondences. Scale, perspective and content strongly vary between both image sources, thus traditional feature matching methods may fail. To this end, the registration process is designed to focus on common and clearly distinguishable elements, such as road markings, manholes, or kerbstones. With a registration accuracy of about 98%, reliable tie information between MM and aerial data can be derived. Even though, the adjustment strategy is not covered in its entirety in this paper, accuracy results after adjustment will be presented. It will be shown that a decimetre accuracy is well achievable in a real data test scenari Numéro de notice : A2018-285 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2018.04.017 date de publication en ligne : 30/04/2018 En ligne : https://doi.org/10.1016/j.isprsjprs.2018.04.017 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90397 [article]

Réservation

Réserver ce document

Exemplaires (3)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2018071	RAB	Revue	Centre de documentation	En réserve 3L	Disponible
081-2018073	DEP-EXM	Revue	LaSTIG	Dépôt en unité	Exclu du prêt
081-2018072	DEP-EAF	Revue	Nancy	Dépôt en unité	Exclu du prêt

Second iteration of photogrammetric processing to refine image orientation with improved tie-points / Truong Giang Nguyen in Sensors, vol 18 n° 7 (July 2018)    

Permalink

Automatic measurement of control points for aerial image orientation / Adilson Berveglieri in Photogrammetric record, vol 32 n° 158 (June - july 2017)  

Permalink

Triangulating social multimedia content for event localization using Flickr and Twitter / George Panteras in Transactions in GIS, vol 19 n° 5 (October 2015)  

Permalink

Simultaneous registration of gnomonic projections and central perspectives / Luigi Barazzetti in Photogrammetric record, vol 29 n° 147 (September - November 2014)  

Permalink

Automatic orientation and 3D modelling from markerless rock art imagery / J. Lerma in ISPRS Journal of photogrammetry and remote sensing, vol 76 (February 2013)

Permalink

Reconnaissance de bâtiments et localisation de photographies au moyen d'un descripteur de texture / W. Suleiman in Revue internationale de géomatique, vol 22 n° 3 (septembre - novembre 2012)

Permalink

Fast AT: a simple procedure for quasi direct orientation / M. Blazquez in ISPRS Journal of photogrammetry and remote sensing, vol 71 (July 2012)

Permalink

Apero, an open source bundle adjusment software for automatic calibration and orientation of set of images / Marc Pierrot-Deseilligny (2011)  

Permalink

Photogrammetric image analysis PIA 11, Munich, Germany, October 5-7, 2011 / Uwe Stilla (2011)  

Permalink

Acquisition de nuages de points denses par photogrammétrie terrestre : Application à la mission d'archéologie de Kilwa, Arabie Saoudite / J.F. Hullo in XYZ, n° 122 (mars - mai 2010)

Permalink