Publications of Abderrazzaq Kharroubi
Bookmark and Share    
Full Text
See detailPoint Cloud and GIS
Kharroubi, Abderrazzaq ULiege

Scientific conference (2021, November 19)

1. Notions 2. Applications et cas d’usages 3. Nuage de point et SIG  QGIS  PostGIS/pgpointcloud  Polyfit  CityGML et CityJSON 4. Mon sujet de recherche

Detailed reference viewed: 41 (5 ULiège)
Full Text
See detailMapping the change using LiDAR point clouds
Kharroubi, Abderrazzaq ULiege

Scientific conference (2021, October 26)

The rapid development of 3D data acquisition is enabling the collection of massive point clouds faster than ever before making them the future topographic core data for diverse applications. However, in a ... [more ▼]

The rapid development of 3D data acquisition is enabling the collection of massive point clouds faster than ever before making them the future topographic core data for diverse applications. However, in a dynamic world, everything is continuously changing, and the data needs to be updated, as well as used to detect the occurred change. The presentation focus on aspects related to the processing of multi-date point clouds for change detection, as well as the management of time in these massive data. [less ▲]

Detailed reference viewed: 47 (7 ULiège)
Full Text
See detailAn extension of CityJSON to support point clouds
Nys, Gilles-Antoine ULiege; Kharroubi, Abderrazzaq ULiege; Poux, Florent ULiege et al

in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2021, June 30), XLII-B4-2021

The combination between dense point clouds and 3D vector objects permits new cartographic representation of urban information. This paper proposes an extension for the CityJSON encoding to support point ... [more ▼]

The combination between dense point clouds and 3D vector objects permits new cartographic representation of urban information. This paper proposes an extension for the CityJSON encoding to support point clouds. Following the 3.0 CityGML specifications, attributes and features are added to the core module of v1.0.1 CityJSON. Two solutions are proposed: inline complex geometries and external link to a remote file. The extended schema can be illustrated in four scenarios: detailed features visualization, fall-back solution in features reconstruction processes, simulating urban climate represented as vector fields, and true-to-life representation solution for complex elements such as solitary vegetation objects. It permits 3D city modelers to handle points clouds in a native way reducing files size and avoiding redundancy. All developments and documentation are available open-source. [less ▲]

Detailed reference viewed: 48 (6 ULiège)
Full Text
See detailTESSERAE3D: A benchmark for tesserae semantic segmentation in 3D point clouds
Kharroubi, Abderrazzaq ULiege; Van Wersch, Line ULiege; Billen, Roland ULiege et al

in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2021, June 17), V-2-2021

3D point cloud of mosaic tesserae is used by heritage researchers, restorers, and archaeologists for digital investigations. Information extraction, pattern analysis, and semantic assignment are necessary ... [more ▼]

3D point cloud of mosaic tesserae is used by heritage researchers, restorers, and archaeologists for digital investigations. Information extraction, pattern analysis, and semantic assignment are necessary to complement geometric information. Automated processes that can speed up the task are highly sought after, especially new supervised approaches. However, the availability of labeled data necessary for training supervised learning models is a significant constraint. This paper introduces Tesserae3D, a 3D point cloud benchmark dataset for training and evaluating machine learning models, applied to mosaic tesserae segmentation. It is a publicly available, very high density and colored dataset, accompanied by a standard multi-class semantic segmentation baseline. It consists of about 502 million points and contains 11 semantic classes covering a wide range of tesserae types. We propose a semantic segmentation baseline building on radiometric and covariance features fed to ensemble learning methods. The results delineate an achievable 89% F1 score and are made available under https://github.com/akharroubi/Tesserae3D, providing a simple interface to improve the score based on feedback from the research community. [less ▲]

Detailed reference viewed: 39 (5 ULiège)
Full Text
See detailDes données LIDAR mobile au jumeau numérique: applications aux actifs ferroviaires
Kharroubi, Abderrazzaq ULiege

Conference given outside the academic context (2021)

La présentation répond à: Quels sont les concepts liés aux jumeaux numériques ? la différence entre digital model, digital shadow and digital twin ? le processus de création du jumeau numérique sur base ... [more ▼]

La présentation répond à: Quels sont les concepts liés aux jumeaux numériques ? la différence entre digital model, digital shadow and digital twin ? le processus de création du jumeau numérique sur base des données lidar mobile ? l'importance de la mise à jour et la gestion des données pour un digital twin ? avec une application dans le domaine ferroviaire. [less ▲]

Detailed reference viewed: 79 (20 ULiège)
See detailMapping the change: High-level understanding of dynamic in LiDAR point clouds
Kharroubi, Abderrazzaq ULiege

Scientific conference (2021, April 19)

C'est présentation traite le sujet de la détection de changement dans les nuages de points 3d acquissent par système de cartographie mobile sur train. Elle propose une nouvelle méthode de classification ... [more ▼]

C'est présentation traite le sujet de la détection de changement dans les nuages de points 3d acquissent par système de cartographie mobile sur train. Elle propose une nouvelle méthode de classification basée objet, suivie par un calcul de mouvement possible, afin de permettre une précise de décision. Le sujet traité porte une grande importance, surtout dans un domaine comme le ferroviaire. On envisage de réaliser des tests du travail réalisé sur divers scénarios principalement, l'estimation de la surcroissance de la végétation à coté des rails, la détection de mouvement/glissement de terrain voisin et aussi un déplacement possible dans les actifs ferroviaires. [less ▲]

Detailed reference viewed: 38 (10 ULiège)
Full Text
See detailMapping the change from LiDAR point clouds
Kharroubi, Abderrazzaq ULiege

Conference (2021, March 04)

Structuration de nuages de points multi-temporels et extraction de la sémantique pour la détection de changement

Detailed reference viewed: 45 (13 ULiège)
Full Text
See detailMARKER-LESS MOBILE AUGMENTED REALITY APPLICATION FOR MASSIVE 3D POINT CLOUDS AND SEMANTICS
Kharroubi, Abderrazzaq ULiege

Conference (2020, September 01)

Mobile Augmented Reality (MAR) attracts significant research and development efforts from both the industry and academia, but rarely integrate massive 3D dataset’s interactions. The emergence of dedicated ... [more ▼]

Mobile Augmented Reality (MAR) attracts significant research and development efforts from both the industry and academia, but rarely integrate massive 3D dataset’s interactions. The emergence of dedicated AR devices and powerful Software Development Kit (ARCore for android and ARKit for iOS) improves performance on mobile devices (Smartphones and tablets). This is aided by new sensor integration and advances in computer vision that fuels the development of MAR. In this paper, we propose a direct integration of massive 3D point clouds with semantics in a web-based marker-less mobile Augmented Reality (AR) application for real-time visualization. We specifically investigate challenges linked to point cloud data structure and semantic injection. Our solution consolidates some of the overarching principles of AR, of which pose estimation, registration and 3D tracking. The developed AR system is tested on mobile phones web-browsers providing clear insights on the performance of the system. Promising results highlight a number of frame per second varying between 27 and 60 for a real-time point budget of 4.3 million points. The point cloud tested is composed of 29 million points and shows how our indexation strategy permits the integration of massive point clouds aiming at the point budget. The results also gives research directions concerning the dependence and delay related to the quality of the network connection, and the battery consumption since portable sensors are used all the time. [less ▲]

Detailed reference viewed: 47 (6 ULiège)
Full Text
See detailMARKER-LESS MOBILE AUGMENTED REALITY APPLICATION FOR MASSIVE 3D POINT CLOUDS AND SEMANTICS
Kharroubi, Abderrazzaq ULiege; Billen, Roland ULiege; Poux, Florent ULiege

in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2020, August 12), XLIII(B2), 255261

Mobile Augmented Reality (MAR) attracts significant research and development efforts from both the industry and academia, but rarely integrate massive 3D dataset’s interactions. The emergence of dedicated ... [more ▼]

Mobile Augmented Reality (MAR) attracts significant research and development efforts from both the industry and academia, but rarely integrate massive 3D dataset’s interactions. The emergence of dedicated AR devices and powerful Software Development Kit (ARCore for android and ARKit for iOS) improves performance on mobile devices (Smartphones and tablets). This is aided by new sensor integration and advances in computer vision that fuels the development of MAR. In this paper, we propose a direct integration of massive 3D point clouds with semantics in a web-based marker-less mobile Augmented Reality (AR) application for real-time visualization. We specifically investigate challenges linked to point cloud data structure and semantic injection. Our solution consolidates some of the overarching principles of AR, of which pose estimation, registration and 3D tracking. The developed AR system is tested on mobile phones web-browsers providing clear insights on the performance of the system. Promising results highlight a number of frame per second varying between 27 and 60 for a real-time point budget of 4.3 million points. The point cloud tested is composed of 29 million points and shows how our indexation strategy permits the integration of massive point clouds aiming at the point budget. The results also gives research directions concerning the dependence and delay related to the quality of the network connection, and the battery consumption since portable sensors are used all the time. [less ▲]

Detailed reference viewed: 165 (12 ULiège)
Full Text
See detailRéalité mixte... Vers une formalisation de la Géo-visualisation 3D
Kharroubi, Abderrazzaq ULiege

Scientific conference (2020, June 24)

The representation of information is a fundamental theme in geomatics sciences. Over time, in addition to the question of the availability of data and their modes of acquisition (2D or 3D), the nature of ... [more ▼]

The representation of information is a fundamental theme in geomatics sciences. Over time, in addition to the question of the availability of data and their modes of acquisition (2D or 3D), the nature of the support and the mode of representation has evolved, from paper to digital, from 2D to 3D. The emergence of XR extended reality offers new possibilities for exploitation and cognitive perception. With this development, questions have arisen. Are the rules for the representation of geographic information, the way of handling and interacting evolving with XR? Are we witnessing a simple technological evolution or a radical change in the paradigm of representation? This research project aims to answer these questions by studying the impact of XR on the management, manipulation, and representation of 3D geographic data. This study will firstly be based on a multidisciplinary bibliographic analysis that should lead to identifying the rules of representation and the modes of interaction influenced by XR. Next, we study the possibility of establishing an XR-oriented geovisualization formalism, implemented in targeted application cases to be tested by users through immersive experiences. The analysis of the results obtained makes it possible to validate or not the rules of representation and the modes of interaction proposed and therefore to judge the nature and the depth of the impact of XR. [less ▲]

Detailed reference viewed: 51 (10 ULiège)
Full Text
See detailCLASSIFICATION AND INTEGRATION OF MASSIVE 3D POINTS CLOUDS IN A VIRTUAL REALITY (VR) ENVIRONMENT
Kharroubi, Abderrazzaq ULiege

Conference (2019, December 02)

With the increasing volume of 3D applications using immersive technologies such as virtual, augmented and mixed reality, it is very interesting to create better ways to integrate unstructured 3D data such ... [more ▼]

With the increasing volume of 3D applications using immersive technologies such as virtual, augmented and mixed reality, it is very interesting to create better ways to integrate unstructured 3D data such as point clouds as a source of data. Indeed, this can lead to an efficient workflow from 3D capture to 3D immersive environment creation without the need to derive 3D model, and lengthy optimization pipelines. In this paper, the main focus is on the direct classification and integration of massive 3D point clouds in a virtual reality (VR) environment. The emphasis is put on leveraging open-source frameworks for an easy replication of the findings. First, we develop a semi-automatic segmentation approach to provide semantic descriptors (mainly classes) to groups of points. We then build an octree data structure leveraged through out-of-core algorithms to load in real time and continuously only the points that are in the VR user's field of view. Then, we provide an open-source solution using Unity with a user interface for VR point cloud interaction and visualisation. Finally, we provide a full semantic VR data integration enhanced through developed shaders for future spatio-semantic queries. We tested our approach on several datasets of which a point cloud composed of 2.3 billion points, representing the heritage site of the castle of Jehay (Belgium). The results underline the efficiency and performance of the solution for visualizing classifieds massive point clouds in virtual environments with more than 100 frame per second. [less ▲]

Detailed reference viewed: 28 (4 ULiège)
Full Text
See detailCLASSIFICATION AND INTEGRATION OF MASSIVE 3D POINTS CLOUDS IN A VIRTUAL REALITY (VR) ENVIRONMENT
Kharroubi, Abderrazzaq ULiege; Hajji, Rafika; Billen, Roland ULiege et al

in International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2019, November 29), XLII-2(W17), 165-171

With the increasing volume of 3D applications using immersive technologies such as virtual, augmented and mixed reality, it is very interesting to create better ways to integrate unstructured 3D data such ... [more ▼]

With the increasing volume of 3D applications using immersive technologies such as virtual, augmented and mixed reality, it is very interesting to create better ways to integrate unstructured 3D data such as point clouds as a source of data. Indeed, this can lead to an efficient workflow from 3D capture to 3D immersive environment creation without the need to derive 3D model, and lengthy optimization pipelines. In this paper, the main focus is on the direct classification and integration of massive 3D point clouds in a virtual reality (VR) environment. The emphasis is put on leveraging open-source frameworks for an easy replication of the findings. First, we develop a semi-automatic segmentation approach to provide semantic descriptors (mainly classes) to groups of points. We then build an octree data structure leveraged through out-of-core algorithms to load in real time and continuously only the points that are in the VR user's field of view. Then, we provide an open-source solution using Unity with a user interface for VR point cloud interaction and visualisation. Finally, we provide a full semantic VR data integration enhanced through developed shaders for future spatio-semantic queries. We tested our approach on several datasets of which a point cloud composed of 2.3 billion points, representing the heritage site of the castle of Jehay (Belgium). The results underline the efficiency and performance of the solution for visualizing classifieds massive point clouds in virtual environments with more than 100 frame per second. [less ▲]

Detailed reference viewed: 465 (66 ULiège)
Full Text
See detailCLASSIFICATION ET INTEGRATION DES NUAGES DE POINTS 3D DANS UN ENVIRONNEMENT DE REALITE VIRTUELLE
Kharroubi, Abderrazzaq ULiege

Master's dissertation (2019)

Ce mémoire d’ingénieur en sciences géomatiques et ingénierie topographique propose une application de réalité virtuelle pour la visualisation et l’interaction avec les nuages de points massifs dans un ... [more ▼]

Ce mémoire d’ingénieur en sciences géomatiques et ingénierie topographique propose une application de réalité virtuelle pour la visualisation et l’interaction avec les nuages de points massifs dans un environnement virtuel. La solution s’inscrit dans un Framework global post classification s’appuyant sur des structures de données adaptées à la gestion des données massives en temps réel (plusieurs milliards de points). En général, les nuages de points constituent des données 3D de base pour le développement d’un bon nombre d’applications notamment celles liées à la réalité virtuelle. Cependant, ces données brutes n’intègrent pas d’information sémantique sur les objets qui composent une scène. Ainsi, les nuages de points nécessitent un prétraitement et une classification en vue d’une visualisation sémantique. À travers notre étude, nous présentons un processus de classification pour l’intégration de l’information sur le nuage de points. Ensuite, nous développons un système de rendu des nuages de points massifs en réalité virtuelle sous l’outil Unity. Dans ce travail, l’accent est principalement mis sur l’intégration de la classification dans un environnement virtuel et sur la gestion de ces nuages de points massifs, dépassant plusieurs milliards de points, ne pouvant pas être chargés directement dans la mémoire vive. Ainsi, une structure de données de type « Octree » est employée et des algorithmes « Out-of-Core » sont utilisés pour charger en temps réel et en continu, uniquement les points qui figurent dans le champ de vision de l’utilisateur. Nous proposons une solution de visualisation en réalité virtuelle avec une interface utilisateur permettant l’interaction avec le nuage de points et le changement des paramètres et des méthodes de rendu. Cette solution intégrée offre aussi un mode de déplacement dans le nuage de points afin de garantir à l’utilisateur une expérience immersive. [less ▲]

Detailed reference viewed: 159 (25 ULiège)