Centre dedocumentation
scientifique

Attention mechanisms in computer vision: A survey / Meng-Hao Guo in Computational Visual Media, vol 8 n° 3 (September 2022)  

Public [article]  inComputational Visual Media > vol 8 n° 3 (September 2022) . - pp 331 - 368 Titre : Attention mechanisms in computer vision: A survey Type de document : Article/Communication Auteurs : Meng-Hao Guo, Auteur ; Tian-Xing Xu, Auteur ; Jiang-Jiang Liu, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 331 - 368 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] attention (apprentissage automatique) [Termes IGN] saillance [Termes IGN] scène Résumé : (auteur) Humans can naturally and effectively find salient regions in complex scenes. Motivated by this observation, attention mechanisms were introduced into computer vision with the aim of imitating this aspect of the human visual system. Such an attention mechanism can be regarded as a dynamic weight adjustment process based on features of the input image. Attention mechanisms have achieved great success in many visual tasks, including image classification, object detection, semantic segmentation, video understanding, image generation, 3D vision, multimodal tasks, and self-supervised learning. In this survey, we provide a comprehensive review of various attention mechanisms in computer vision and categorize them according to approach, such as channel attention, spatial attention, temporal attention, and branch attention; a related repository https://github.com/MenghaoGuo/Awesome-Vision-Attentions is dedicated to collecting related work. We also suggest future directions for attention mechanism research. Numéro de notice : A2022-329 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1007/s41095-022-0271-y Date de publication en ligne : 15/03/2022 En ligne : https://doi.org/10.1007/s41095-022-0271-y Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100601 [article]

DART-Lux: An unbiased and rapid Monte Carlo radiative transfer method for simulating remote sensing images / Yingjie Wang in Remote sensing of environment, vol 274 (June 2022)  

Public [article]  inRemote sensing of environment > vol 274 (June 2022) . - n° 112973 Titre : DART-Lux: An unbiased and rapid Monte Carlo radiative transfer method for simulating remote sensing images Type de document : Article/Communication Auteurs : Yingjie Wang, Auteur ; Abdelaziz Kallel, Auteur ; Xuebo Yang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 112973 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] bande spectrale [Termes IGN] distribution du coefficient de réflexion bidirectionnelle BRDF [Termes IGN] image à haute résolution [Termes IGN] méthode de Monte-Carlo [Termes IGN] modèle de transfert radiatif [Termes IGN] radiance [Termes IGN] réflectance directionnelle [Termes IGN] scène forestière [Termes IGN] scène urbaine Résumé : (auteur) Accurate and efficient simulation of remote sensing images is increasingly needed in order to better exploit remote sensing observations and to better design remote sensing missions. DART (Discrete Anisotropic Radiative Transfer), developed since 1992 based on the discrete ordinates method (i.e., standard mode DART-FT), is one of the most accurate and comprehensive 3D radiative transfer models to simulate the radiative budget and remote sensing observations of urban and natural landscapes. Recently, a new method, called DART-Lux, was integrated into DART model to address the requirements of massive remote sensing data simulation for large-scale and complex landscapes. It is developed based on efficient Monte Carlo light transport algorithms (i.e., bidirectional path tracing) and on DART model framework. DART-Lux can accurately and rapidly simulate the bidirectional reflectance factor (BRF) and spectral images of arbitrary landscapes. This paper presents its theory, implementation, and evaluation. Its accuracy, efficiency and advantages are also discussed. The comparison with standard DART-FT in a variety of scenarios shows that DART-Lux is consistent with DART-FT (relative differences Numéro de notice : A2022-398 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.rse.2022.112973 Date de publication en ligne : 26/03/2022 En ligne : https://doi.org/10.1016/j.rse.2022.112973 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100698 [article]

Application oriented quality evaluation of Gaofen-7 optical stereo satellite imagery / Jiaojiao Tian in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-1-2022 (2022 edition) . - pp 145 - 152 Titre : Application oriented quality evaluation of Gaofen-7 optical stereo satellite imagery Type de document : Article/Communication Auteurs : Jiaojiao Tian, Auteur ; Xiangyu Zhuo, Auteur ; Xiangtian Yuan, Auteur ; Corentin Henry, Auteur ; Pablo d' Angelo, Auteur ; Thomas Krauss, Auteur Année de publication : 2022 Article en page(s) : pp 145 - 152 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Allemagne [Termes IGN] détection du bâti [Termes IGN] extraction du réseau routier [Termes IGN] image Gaofen [Termes IGN] image optique [Termes IGN] orientation d'image [Termes IGN] reconstruction 3D [Termes IGN] scène urbaine [Termes IGN] segmentation Résumé : (auteur) GaoFen-7 (GF-7) satellite mission is further expanding the very high resolution 3D mapping application. Carrying the first civilian Chinese sub-meter resolution stereo satellite sensors, GF-7 satellite was launched on November 7, 2019. With 0.65 meter resolution on backward view and 0.8 meter resolution forward view, GF-7 has been designed to meet the demand of natural resource monitoring, land surveying, and other mapping applications in China. The use of GF-7 for 3D city reconstruction is unfortunately restricted by the fixed large stereo view angle of forward and backward cameras with +26 and −5 degrees respectively which is not optimal for dense stereo matching in urban regions. In this paper, we intensively evaluate the quality of the GF-7 datasets by performing a series of urban monitoring applications, including road detection, building extraction and 3D reconstruction. In addition, we propose a 3D reconstruction workflow which uses the land cover classification result to refine the stereo matching result. Six sub-urban regions are selected from the available datasets in the middle of Germany. The results show that basic elements in urban scenes like buildings and roads could be detected from GF-7 datasets with high accuracy. With the proposed workflow, a 3D city model with a visually observed good quality can be delivered. Numéro de notice : A2022-442 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-1-2022-145-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-1-2022-145-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100776 [article]

Cooperative image orientation considering dynamic objects / P. Trusheim in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-1-2022 (2022 edition) . - pp 169 - 177 Titre : Cooperative image orientation considering dynamic objects Type de document : Article/Communication Auteurs : P. Trusheim, Auteur ; Max Mehltretter, Auteur ; Franz Rottensteiner, Auteur ; Christian Heipke, Auteur Année de publication : 2022 Article en page(s) : pp 169 - 177 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] compensation par faisceaux [Termes IGN] orientation d'image [Termes IGN] point d'appui [Termes IGN] points homologues [Termes IGN] réseau neuronal artificiel [Termes IGN] scène urbaine [Termes IGN] séquence d'images Résumé : (auteur) In the context of image orientation, it is commonly assumed that the environment is completely static. This is why dynamic elements are typically filtered out using robust estimation procedures. Especially in urban areas, however, many such dynamic elements are present in the environment, which leads to a noticeable amount of errors that have to be detected via robust adjustment. This problem is even more evident in the case of cooperative image orientation using dynamic objects as ground control points (GCPs), because such dynamic objects carry the relevant information. One way to deal with this challenge is to detect these dynamic objects prior to the adjustment and to process the related image points separately. To do so, a novel methodology to distinguish dynamic and static image points in stereoscopic image sequences is introduced in this paper, using a neural network for the detection of potentially dynamic objects and additional checks via forward intersection. To investigate the effects of the consideration of dynamic points in the adjustment, an image sequence of an inner-city traffic scenario is used; image orientation, as well as the 3D coordinates of tie points, are calculated via a robust bundle adjustment. It is shown that compared to a solution without considering dynamic points, errors in the tie points are significantly reduced, while the median of the precision of all 3D coordinates of the tie points is improved. Numéro de notice : A2022-441 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.5194/isprs-annals-V-1-2022-169-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-1-2022-169-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100775 [article]

Railway lidar semantic segmentation with axially symmetrical convolutional learning / Antoine Manier in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Public [article]  inISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences > vol V-2-2022 (2022 edition) . - pp 135 - 142 Titre : Railway lidar semantic segmentation with axially symmetrical convolutional learning Type de document : Article/Communication Auteurs : Antoine Manier, Auteur ; Julien Moras, Auteur ; Jean-Christophe Michelin , Auteur ; Hélène Piet-Lahanier, Auteur Année de publication : 2022 Article en page(s) : pp 135 - 142 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Lasergrammétrie [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] scène 3D [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] voie ferrée Résumé : (auteur) This paper presents a new deep-learning-based method for 3D Point Cloud Semantic Segmentation specifically designed for processing real-world LIDAR railway scenes. The new approach relies on the use of spatial local point cloud transformations for convolutional learning. These transformations allow an increased robustness to varying point cloud densities while preserving metric information and a sufficient descriptive ability. The resulting performances are illustrated with results on railway data from two distinct LIDAR point cloud datasets acquired in industrial settings. The quality of the extraction of useful information for maintenance operations and topological analysis is pointed together with a noticeable robustness to point cloud variations in distribution and point redundancy. Numéro de notice : A2022-433 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.5194/isprs-annals-V-2-2022-135-2022 Date de publication en ligne : 17/05/2022 En ligne : https://doi.org/10.5194/isprs-annals-V-2-2022-135-2022 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100739 [article]

Semantic segmentation of urban textured meshes through point sampling / Grégoire Grzeczkowicz in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Permalink

Virtual laser scanning of dynamic scenes created from real 4D topographic point cloud data / Lukas Winiwarter in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-2-2022 (2022 edition)  

Permalink

Exploring the association between street built environment and street vitality using deep learning methods / Yunqin Li in Sustainable Cities and Society, vol 79 (April 2022)  

Permalink

Procedural urban forestry / Till Niese in ACM Transactions on Graphics, TOG, Vol 41 n° 2 (April 2022)  

Permalink

LiDAR-based method for analysing landmark visibility to pedestrians in cities: case study in Kraków, Poland / Krystian Pyka in International journal of geographical information science IJGIS, vol 36 n° 3 (March 2022)  

Permalink

Deep learning for radar data exploitation of autonomous vehicle / Arthur Ouaknine (2022)  

Permalink

Multi-view urban scene classification with a complementary-information learning model / Wanxuan Geng in Photogrammetric Engineering & Remote Sensing, PERS, vol 88 n° 1 (January 2022)  

Permalink

Automatic registration of mobile mapping system Lidar points and panoramic-image sequences by relative orientation model / Ningning Zhu in Photogrammetric Engineering & Remote Sensing, PERS, vol 87 n° 12 (December 2021)  

Permalink

Utility-pole detection based on interwoven column generation from terrestrial mobile Laser scanner data / Siamak Talebi Nahr in Photogrammetric record, Vol 36 n° 176 (December 2021)  

Permalink

Metaheuristics for the positioning of 3D objects based on image analysis of complementary 2D photographs / Arnaud Flori in Machine Vision and Applications, vol 32 n° 5 (September 2021)  

Permalink