Centre dedocumentation
scientifique

Improving deep learning on point cloud by maximizing mutual information across layers / Di Wang in Pattern recognition, vol 131 (November 2022)  

Public [article]  inPattern recognition > vol 131 (November 2022) . - n° 108892 Titre : Improving deep learning on point cloud by maximizing mutual information across layers Type de document : Article/Communication Auteurs : Di Wang, Auteur ; Lulu Tang, Auteur ; Xu Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 108892 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection d'objet [Termes IGN] entropie de Shannon [Termes IGN] information sémantique [Termes IGN] segmentation sémantique [Termes IGN] semis de points [Termes IGN] transformation géométrique [Termes IGN] vision par ordinateur [Termes IGN] visualisation 3D Résumé : (auteur) It is a fundamental and vital task to enhance the perception capability of the point cloud learning network in 3D machine vision applications. Most existing methods utilize feature fusion and geometric transformation to improve point cloud learning without paying enough attention to mining further intrinsic information across multiple network layers. Motivated to improve consistency between hierarchical features and strengthen the perception capability of the point cloud network, we propose exploring whether maximizing the mutual information (MI) across shallow and deep layers is beneficial to improve representation learning on point clouds. A novel design of Maximizing Mutual Information (MMI) Module is proposed, which assists the training process of the main network to capture discriminative features of the input point clouds. Specifically, the MMI-based loss function is employed to constrain the differences of semantic information in two hierarchical features extracted from the shallow and deep layers of the network. Extensive experiments show that our method is generally applicable to point cloud tasks, including classification, shape retrieval, indoor scene segmentation, 3D object detection, and completion, and illustrate the efficacy of our proposed method and its advantages over existing ones. Our source code is available at https://github.com/wendydidi/MMI.git. Numéro de notice : A2022-780 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : https://doi.org/10.1016/j.patcog.2022.108892 Date de publication en ligne : 08/07/2022 En ligne : https://doi.org/10.1016/j.patcog.2022.108892 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101859 [article]

Benchmarking laser scanning and terrestrial photogrammetry to extract forest inventory parameters in a complex temperate forest / Daniel Kükenbrink in International journal of applied Earth observation and geoinformation, vol 113 (September 2022)  

Public [article]  inInternational journal of applied Earth observation and geoinformation > vol 113 (September 2022) . - n° 102999 Titre : Benchmarking laser scanning and terrestrial photogrammetry to extract forest inventory parameters in a complex temperate forest Type de document : Article/Communication Auteurs : Daniel Kükenbrink, Auteur ; Mauro Marty, Auteur ; Ruedi Bösch, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : n° 102999 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques [Termes IGN] caméra à bas coût [Termes IGN] cartographie et localisation simultanées [Termes IGN] détection d'arbres [Termes IGN] diamètre à hauteur de poitrine [Termes IGN] données lidar [Termes IGN] données localisées 3D [Termes IGN] forêt tempérée [Termes IGN] inventaire forestier (techniques et méthodes) [Termes IGN] lidar mobile [Termes IGN] lidar topographique [Termes IGN] photogrammétrie terrestre [Termes IGN] semis de points [Termes IGN] série temporelle [Termes IGN] structure-from-motion [Termes IGN] Zurich (Suisse) Résumé : (auteur) National forest inventories (NFI) are important for the assessment of the state and development of forests. Traditional NFIs often rely on statistical sampling approaches as well as expert assessment which may suffer from observer bias and may lack robustness for time series analysis. Over the course of the last decade, close-range remote sensing techniques such as terrestrial and mobile laser scanning became ever more established for the assessment of three-dimensional (3D) forest structure. With the ongoing trend to make the systems smaller, easier to use and more efficient, the pathway is being opened for an operational inclusion of such devices within the framework of an NFI to support the traditional field assessment. Close-range remote sensing could potentially speed up field inventory work as well as increase the area in which certain parameters are assessed. Benchmarks are needed to evaluate the performance of different close-range remote sensing devices and approaches, both in terms of efficiency as well as accuracy. In this study we evaluate the performance of two terrestrial (TLS), one handheld mobile (PLS) and two drone based (UAVLS) laser scanning systems to detect trees and extract the diameter at breast height (DBH) in three plots with a steep gradient in tree and understorey vegetation density. As a novelty, we also tested the acquisition of 3D point-clouds using a low-cost action camera (GoPro) in conjunction with the Structure from Motion (SfM) technique and compared its performance with those of the more costly LiDAR devices. Among the many parameters evaluated in traditional NFIs, the focus of the performance evaluation of this study is set on the automatic tree detection and DBH extraction. The results showed that TLS delivers the highest tree detection rate (TDR) of up to 94.6% under leaf-off and up to 82% under leaf-on conditions and a relative RMSE (rRMSE) for the DBH extraction between 2.5 and 9%, depending on the undergrowth complexity. The tested PLS system (leaf-on) achieved a TDR of up to 80% with an rRMSE between 3.7 and 5.8%. The tested UAVLS systems showed lowest TDR of less than 77% under leaf-off and less than 37% under leaf-on conditions. The novel GoPro approach achieved a TDR of up to 53% under leaf-on conditions. The reduced TDR can be explained by the reduced area coverage due to the chosen circular acquisition path taken with the GoPro approach. The DBH extraction performance on the other hand is comparable to those of the LiDAR devices with an rRMSE between 2 and 9%. Further benchmarks are needed in order to fully assess the applicability of these systems in the framework of an NFI. Especially the robustness under varying forest conditions (seasonality) and over a broader range of forest types and canopy structure has to be evaluated. Numéro de notice : A2022-787 Affiliation des auteurs : IGN (1940-2011) Thématique : FORET/IMAGERIE Nature : Article DOI : 10.1016/j.jag.2022.102999 Date de publication en ligne : 05/09/2022 En ligne : https://doi.org/10.1016/j.jag.2022.102999 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101893 [article]

Deep image deblurring: A survey / Kaihao Zhang in International journal of computer vision, vol 130 n° 9 (September 2022)  

Public [article]  inInternational journal of computer vision > vol 130 n° 9 (September 2022) . - pp 2103 - 2130 Titre : Deep image deblurring: A survey Type de document : Article/Communication Auteurs : Kaihao Zhang, Auteur ; Wenqi Ren, Auteur ; Wenhan Luo, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2103 - 2130 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] accentuation d'image [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] déconvolution [Termes IGN] estimation par noyau [Termes IGN] filtrage du bruit [Termes IGN] image floue [Termes IGN] qualité d'image [Termes IGN] réseau antagoniste génératif [Termes IGN] taxinomie [Termes IGN] vision par ordinateur Résumé : (auteur) Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image. Advances in deep learning have led to significant progress in solving this problem, and a large number of deblurring networks have been proposed. This paper presents a comprehensive and timely survey of recently published deep-learning based image deblurring approaches, aiming to serve the community as a useful literature review. We start by discussing common causes of image blur, introduce benchmark datasets and performance metrics, and summarize different problem formulations. Next, we present a taxonomy of methods using convolutional neural networks (CNN) based on architecture, loss function, and application, offering a detailed review and comparison. In addition, we discuss some domain-specific deblurring applications including face images, text, and stereo image pairs. We conclude by discussing key challenges and future research directions. Numéro de notice : A2022-638 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-022-01633-5 Date de publication en ligne : 25/06/2022 En ligne : https://doi.org/10.1007/s11263-022-01633-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101444 [article]

Human perception evaluation system for urban streetscapes based on computer vision algorithms with attention mechanisms / Yunhao Li in Transactions in GIS, vol 26 n° 6 (September 2022)  

Public [article]  inTransactions in GIS > vol 26 n° 6 (September 2022) . - pp 2440 - 2454 Titre : Human perception evaluation system for urban streetscapes based on computer vision algorithms with attention mechanisms Type de document : Article/Communication Auteurs : Yunhao Li, Auteur ; Chunxiao Zhang, Auteur ; Chang Wang, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2440 - 2454 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] attention (apprentissage automatique) [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] détection de cible [Termes IGN] image virtuelle [Termes IGN] modèle 3D de l'espace urbain [Termes IGN] paysage urbain [Termes IGN] segmentation d'image [Termes IGN] vision [Termes IGN] vision par ordinateur Résumé : (auteur) Virtual 3D modeling is widely implemented in urban planning and design. To evaluate urban planning modeling, based on existing computer vision models, this article aims to improve performance in the field of human perception analysis for urban street views. In this study, the PSP module extracts detailed features from recognized objects of different sizes, an attention mechanism is applied to solve the problem of large information differences in pictures, and transfer learning technology is used to expand the model to the field of virtual 3D modeling to extract more representative and universal features, similar to how humans perceive street view information. Finally, we obtain a more objective, stable, and accurate neural network model that imitates human perception. This evaluation model converges within the correct interval on the training and validation datasets compared with an evaluation of virtual modeling by a large number of people. Numéro de notice : A2022-733 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1111/tgis.12882 Date de publication en ligne : 15/12/2021 En ligne : https://doi.org/10.1111/tgis.12882 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101698 [article]

PKS: A photogrammetric key-frame selection method for visual-inertial systems built on ORB-SLAM3 / Arash Azimi in ISPRS Journal of photogrammetry and remote sensing, vol 191 (September 2022)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 191 (September 2022) . - pp 18 - 32 Titre : PKS: A photogrammetric key-frame selection method for visual-inertial systems built on ORB-SLAM3 Type de document : Article/Communication Auteurs : Arash Azimi, Auteur ; Ali Hosseininaveh Ahmadabadian, Auteur ; Fabio Remondino, Auteur Année de publication : 2022 Article en page(s) : pp 18 - 32 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Photogrammétrie [Termes IGN] alignement [Termes IGN] cartographie et localisation simultanées [Termes IGN] centrale inertielle [Termes IGN] centre de gravité [Termes IGN] déformation d'image [Termes IGN] géoréférencement direct [Termes IGN] méthode heuristique [Termes IGN] semis de points [Termes IGN] seuillage d'image [Termes IGN] structure-from-motion [Termes IGN] vision par ordinateur Résumé : (auteur) Key-frame selection methods were developed in the past years to reduce the complexity of frame processing in visual odometry (VO) and visual simultaneous localization and mapping (VSLAM) algorithms. Key-frames help increasing algorithm's performances by sparsifying frames while maintaining its accuracy and robustness. Unlike current selection methods that rely on many heuristic thresholds to decide which key-frame should be selected, this paper proposes a photogrammetric-based key-frame selection method built upon ORB-SLAM3. The proposed algorithm, named Photogrammetric Key-frame Selection (PKS), replaces static heuristic thresholds with photogrammetric principles, ensuring algorithm’s robustness and better point cloud quality. A key-frame is chosen based on adaptive thresholds and the Equilibrium Of Center Of Gravity (ECOG) criteria as well as Inertial Measurement Unit (IMU) observations. To evaluate the proposed PKS method, the European Robotics Challenge (EuRoC) and an in-house datasets are used. Quantitative and qualitative evaluations are made by comparing trajectories, point clouds quality and completeness and Absolute Trajectory Error (ATE) in mono-inertial and stereo-inertial modes. Moreover, for the generated dense point clouds, extensive evaluations, including plane-fitting error, model deformation, model alignment error, and model density and quality, are performed. The results show that the proposed algorithm improves ORB-SLAM3 positioning accuracy by 18% in stereo-inertial mode and 20% in mono-inertial mode without the use of heuristic thresholds, as well as producing a more complete and accurate point cloud up to 50%. The open-source code of the presented method is available at https://github.com/arashazimi0032/PKS. Numéro de notice : A2022-664 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2022.07.003 Date de publication en ligne : 12/07/2022 En ligne : https://doi.org/10.1016/j.isprsjprs.2022.07.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=101525 [article]

Advancements in underground mine surveys by using SLAM-enabled handheld laser scanners / Artu Ellmann in Survey review, vol 54 n° 385 (July 2022)  

Permalink

Investigating the role of image retrieval for visual localization / Martin Humenberger in International journal of computer vision, vol 130 n° 7 (July 2022)  

Permalink

Spatial-temporal attentive LSTM for vehicle-trajectory prediction / Rui Jiang in ISPRS International journal of geo-information, vol 11 n° 7 (July 2022)  

Permalink

A method of vision aided GNSS positioning using semantic information in complex urban environment / Rui Zhai in Remote sensing, vol 14 n° 4 (February-2 2022)  

Permalink

3D stem modelling in tropical forest: towards improved biomass and biomass change estimates / Sébastien Bauwens (2022)  

Permalink

Analysis of pedestrian movements and gestures using an on-board camera to predict their intentions / Joseph Gesnouin (2022)  

Permalink

Deep learning based 2D and 3D object detection and tracking on monocular video in the context of autonomous vehicles / Zhujun Xu (2022)  

Permalink

Event-driven feature detection and tracking for visual SLAM / Ignacio Alzugaray (2022)  

Permalink

Exploring data fusion for multi-object detection for intelligent transportation systems using deep learning / Amira Mimouna (2022)  

Permalink

Learning to represent and reconstruct 3D deformable objects / Jan Bednarik (2022)  

Permalink