Centre dedocumentation
scientifique

A hierarchical deformable deep neural network and an aerial image benchmark dataset for surface multiview stereo reconstruction / Jiayi Li in IEEE Transactions on geoscience and remote sensing, vol 61 n° 1 (January 2023)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 61 n° 1 (January 2023) . - n° 5600812 Titre : A hierarchical deformable deep neural network and an aerial image benchmark dataset for surface multiview stereo reconstruction Type de document : Article/Communication Auteurs : Jiayi Li, Auteur ; Xin Huang, Auteur ; Yujin Feng, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 5600812 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] approche hiérarchique [Termes IGN] carte de profondeur [Termes IGN] déformation d'objet [Termes IGN] effet de profondeur cinétique [Termes IGN] extraction de traits caractéristiques [Termes IGN] image aérienne [Termes IGN] jeu de données [Termes IGN] modèle numérique de surface [Termes IGN] modèle stéréoscopique [Termes IGN] reconstruction d'image [Termes IGN] réseau neuronal profond [Termes IGN] segmentation sémantique Résumé : (auteur) Multiview stereo (MVS) aerial image depth estimation is a research frontier in the remote sensing field. Recent deep learning-based advances in close-range object reconstruction have suggested the great potential of this approach. Meanwhile, the deformation problem and the scale variation issue are also worthy of attention. These characteristics of aerial images limit the applicability of the current methods for aerial image depth estimation. Moreover, there are few available benchmark datasets for aerial image depth estimation. In this regard, this article describes a new benchmark dataset called the LuoJia-MVS dataset ( https://irsip.whu.edu.cn/resources/resources_en_v2.php ), as well as a new deep neural network known as the hierarchical deformable cascade MVS network (HDC-MVSNet). The LuoJia-MVS dataset contains 7972 five-view images with a spatial resolution of 10 cm, pixel-wise depths, and precise camera parameters, and was generated from an accurate digital surface model (DSM) built from thousands of stereo aerial images. In the HDC-MVSNet network, a new full-scale feature pyramid extraction module, a hierarchical set of 3-D convolutional blocks, and “true 3-D” deformable 3-D convolutional layers are specifically designed by considering the aforementioned characteristics of aerial images. Overall and ablation experiments on the WHU and LuoJia-MVS datasets validated the superiority of HDC-MVSNet over the current state-of-the-art MVS depth estimation methods and confirmed that the newly built dataset can provide an effective benchmark. Numéro de notice : A2023-117 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2023.3234694 En ligne : https://doi.org/10.1109/TGRS.2023.3234694 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102488 [article]

Production of orthophoto map using mobile photogrammetry and comparative assessment of cost and accuracy with satellite imagery for corridor mapping: a case study in Manesar, Haryana, India / Manuj Dev in Annals of GIS, vol 29 n° 1 (January 2023)  

Public [article]  inAnnals of GIS > vol 29 n° 1 (January 2023) . - pp 163 - 176 Titre : Production of orthophoto map using mobile photogrammetry and comparative assessment of cost and accuracy with satellite imagery for corridor mapping: a case study in Manesar, Haryana, India Type de document : Article/Communication Auteurs : Manuj Dev, Auteur ; Shetru M. Veerabhadrappa, Auteur ; Ashutosh Kainthola, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : pp 163 - 176 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie [Termes IGN] aérotriangulation [Termes IGN] analyse comparative [Termes IGN] image panoramique [Termes IGN] image satellite [Termes IGN] modèle stéréoscopique [Termes IGN] orthoimage [Termes IGN] orthophotocarte [Termes IGN] point d'appui [Termes IGN] positionnement cinématique en temps réel [Termes IGN] système de numérisation mobile Résumé : (auteur) The study aims to find a low-cost alternate technology to get imagery, using mobile platform, and produce digital orthophoto for corridor mapping, with a higher degree of accuracy and which can reduce the lag time of acquisition of data. The present study uses digital single-lens reflex cameras, mounted on a mobile vehicle, and acquisition of data in the video format rather than still photographs, as traditionally used in mobile mapping systems. The videos are used to create a set of images and orthophotos. A widespread ground control points were recorded in the study area, using the global navigation satellite system receiver, which measured the control points in real-time kinematic mode. Generation of digital orthophoto has been completed using the captured mobile imagery and ground control point. Furthermore, procurement of satellite imagery and aerial triangulation using ground control points have been done. While comparing the planimetric accuracy of orthophoto against satellite imagery using the ground control points, the achieved root mean square error value of produced orthophoto is 0.171 m in X axis and 0.205 m in Y axis. However, for Cartosat -1 satellite imagery, the RMSE value for X is 1.22 m and for Y is 1.98 m. This research proposes the alternate low-cost mobile mapping method to capture the imagery for orthophoto production. The cost of orthophoto production from mobile image was found 77% cheaper than the orthophoto cost from fresh/latest satellite imagery procurement, while the overall production was 70% cost-effective than the orthophoto maps made from archived imagery. Numéro de notice : A2023-161 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/19475683.2022.2141853 Date de publication en ligne : 12/11/2022 En ligne : https://doi.org/10.1080/19475683.2022.2141853 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102864 [article]

A comparative study on deep-learning methods for dense image matching of multi-angle and multi-date remote sensing stereo-images / Hessah Albanwan in Photogrammetric record, vol 37 n° 180 (December 2022)  

Public [article]  inPhotogrammetric record > vol 37 n° 180 (December 2022) . - pp 385 - 409 Titre : A comparative study on deep-learning methods for dense image matching of multi-angle and multi-date remote sensing stereo-images Type de document : Article/Communication Auteurs : Hessah Albanwan, Auteur ; Rongjun Qin, Auteur Année de publication : 2022 Article en page(s) : pp 385 - 409 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] appariement d'images [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] couple stéréoscopique [Termes IGN] modèle stéréoscopique [Termes IGN] précision géométrique (imagerie) Résumé : (auteur) Deep-learning (DL) stereomatching methods gained great attention in remote sensing satellite datasets. However, most of these existing studies conclude assessments based only on a few/single stereo-images lacking a systematic evaluation on how robust DL methods are on satellite stereo-images with varying radiometric and geometric configurations. This paper provides an evaluation of four DL stereomatching methods through hundreds of multi-date multi-site satellite stereopairs with varying geometric configurations, against the traditional well-practiced Census-semi-global matching (SGM), to comprehensively understand their accuracy, robustness, generalisation capabilities, and their practical potential. The DL methods include a learning-based cost metric through convolutional neural networks (MC-CNN) followed by SGM, and three end-to-end (E2E) learning models using Geometry and Context Network (GCNet), Pyramid Stereo Matching Network (PSMNet), and LEAStereo. Our experiments show that E2E algorithms can achieve upper limits of geometric accuracies, while may not generalise well for unseen data. The learning-based cost metric and Census-SGM are rather robust and can consistently achieve acceptable results. All DL algorithms are robust to geometric configurations of stereopairs and are less sensitive in comparison to the Census-SGM, while learning-based cost metrics can generalise on satellite images when trained on different datasets (airborne or ground-view). Numéro de notice : A2022-938 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/phor.12430 Date de publication en ligne : 09/11/2022 En ligne : https://doi.org/10.1111/phor.12430 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102684 [article]

An approach to extracting digital elevation model for undulating and hilly terrain using de-noised stereo images of Cartosat-1 sensor / Litesh Bopche in Applied geomatics, vol 14 n° 1 (March 2022)  

Public [article]  inApplied geomatics > vol 14 n° 1 (March 2022) . - pp 39 - 55 Titre : An approach to extracting digital elevation model for undulating and hilly terrain using de-noised stereo images of Cartosat-1 sensor Type de document : Article/Communication Auteurs : Litesh Bopche, Auteur ; Priti P. Rege, Auteur Année de publication : 2022 Article en page(s) : pp 39 - 55 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] filtrage du bruit [Termes IGN] image ALOS [Termes IGN] image Cartosat-1 [Termes IGN] Inde [Termes IGN] MNS ASTER [Termes IGN] MNS SRTM [Termes IGN] modèle numérique de surface [Termes IGN] modèle par fonctions rationnelles [Termes IGN] modèle stéréoscopique [Termes IGN] points homologues Résumé : (auteur) A digital elevation model (DEM) is established as an essential geospatial dataset requisite for many topographical and environmental applications. The freely available DEMs have low spatial resolution (SR ≥ 30 m) and comprise considerable vertical errors. The vertical errors are worsened in the undulating and hilly or rugged terrain regions. In this research, we introduced a study to investigate the effect of the noise reduction filters on the accuracy and quality of the DEMs for undulating and hilly terrain regions. The main objectives are to extract a high-quality DEM without collecting physical data like ground control points. DEM generation using de-noised stereo images is carried out using Rational Polynomial Coefficients of Cartosat-1 sensor and Automated Tie Point (ATP) selection. The ATP selection and distribution on the stereo images play a significant role in the DEM accuracy. The present paper also provides information about the optimum number of ATPs used for different topographic conditions. The altitude value of extracted DEM through de-noised stereo images and freely accessible DEMs is compared with reference to the ground truth value of the study region. The 3-D surface profile map of the DEM is used for visual interpretation. Numéro de notice : A2022-216 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007/s12518-021-00412-0 Date de publication en ligne : 26/11/2021 En ligne : https://doi.org/10.1007/s12518-021-00412-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100086 [article]

Applications of multi-image remote sensing / Roger Mari Molas (2022)  

Public Titre : Applications of multi-image remote sensing Type de document : Thèse/HDR Auteurs : Roger Mari Molas, Auteur ; Gabriele Facciolo, Directeur de thèse ; Enric Meinhardt-Llopis, Directeur de thèse Editeur : Bures-sur-Yvette : Université Paris-Saclay Année de publication : 2022 Importance : 191 p. Format : 21 x 30 cm Note générale : Bibliographie Thèse de Doctorat de l’Université Paris-Saclay, spécialité Mathématiques Appliquées Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] compensation par faisceaux [Termes IGN] image satellite [Termes IGN] image Worldview [Termes IGN] modèle numérique de surface [Termes IGN] modèle par fonctions rationnelles [Termes IGN] modèle stéréoscopique [Termes IGN] Python (langage de programmation) [Termes IGN] reconstruction 3D Index. décimale : THESE Thèses et HDR Résumé : (auteur) This thesis studies the problem of 3D reconstruction from a collection of high-resolution satellite images. Satellite multi-view 3D reconstruction requires a very fine control of the acquisition geometry, in order to guarantee the consistency of altitude estimates obtained from different views. The first part of the thesis is therefore devoted to the optimization of the mathematical representation of the acquisition geometry, which usually takes the form of RPC camera models. We propose a bundle adjustment methodology that maximizes the geometric consistency between a set of satellite views and the associated RPC cameras. This methodology incorporates an RPC estimation algorithm that allows the direct composition of the original unrefined models with corrective transformations, without using approximate intermediate representations. The second part of the thesis presents different practical applications of multi-image remote sensing, most of which benefit from the consistency control of the acquisition geometry. The different methods concern the following topics: the detection of volume changes on the Earth's surface across different dates; the geometrically consistent generation of large-scale mosaics built from smaller satellite images; a neural rendering network (NeRF) capable of learning the geometry of a satellite scene in a self-supervised manner and also of synthesizing new realistic views, with the ability to distinguish shadows and transient objects from permanent structures; and a comparison between classic algorithms and supervised deep learning networks for dense stereo matching. As a result, this thesis describes a variety of cutting-edge ideas on the exploitation of optical satellite images that have the potential to improve activities related to large-scale land surface knowledge, such as surveillance, urban planning or natural resource management. The presented methods are evaluated with high-resolution images from the WorldView-3 and SkySat constellations. The implementation of most methods is also released as open-source Python code. Note de contenu : 1- Introduction 2- Introduction (en français) Part I. Geometric modeling of multi-view satellite imagery 3- Geolocation correction methods for satellite multi-view stereo 4- Bundle adjustment of RPC camera models 5- Robust RPC camera modeling Part II. Applications of multi-view satellite imagery 6- Automatic stockpile volume monitoring 7- Perfect sensor localization for push-frame image stitching 8- Satellite NeRF 9- Disparity estimation network 10- Conclusion Numéro de notice : 24100 Affiliation des auteurs : non IGN Thématique : IMAGERIE/MATHEMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Mathématiques Appliquées : Saclay : 2022 Organisme de stage : Centre Borelli (Saclay) DOI : sans En ligne : https://www.theses.fr/2022UPASM045 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102575

Deep learning based 3D reconstruction: supervision and representation / François Darmon (2022)  

Permalink

Global glacier mass change by spatiotemporal analysis of digital elevation models / Romain Hugonnet (2022)  

Permalink

A pipeline for automated processing of Corona KH-4 (1962-1972) stereo imagery / Sajid Ghuffar (2022)  

Permalink

Digital building-height preparation from satellite stereo images / P.S. Prakash in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 8 (August 2021)  

Permalink

Automated registration of SfM‐MVS multitemporal datasets using terrestrial and oblique aerial images / Luigi Parente in Photogrammetric record, vol 36 n° 173 (March 2021)  

Permalink

Activity recognition in residential spaces with Internet of things devices and thermal imaging / Kshirasagar Naik in Sensors, vol 21 n° 3 (February 2021)  

Permalink

Apport de la photogrammétrie satellite pour la modélisation du manteau neigeux / César Deschamps-Berger (2021)  

Permalink

Improving traffic sign recognition results in urban areas by overcoming the impact of scale and rotation / Roholah Yazdan in ISPRS Journal of photogrammetry and remote sensing, vol 171 (January 2021)  

Permalink

Operational monitoring of gravitational movements with image time series / Mathilde Desrues (2021)  

Permalink

Stereophotogrammetry for 2-D building deformation monitoring using Kalman Filter / J.O. Odumosu in Reports on geodesy and geoinformatics, vol 110 n° 1 (December 2020)  

Permalink