Laboratoire d’Ingénierie des Systèmes Physiques Et Numériques (LISPEN)
http://hdl.handle.net/10985/177
2024-03-29T09:01:33Z3D Human Pose Estimation with a Catadioptric Sensor in Unconstrained Environments Using an Annealed Particle Filter
http://hdl.handle.net/10985/19775
3D Human Pose Estimation with a Catadioptric Sensor in Unconstrained Environments Using an Annealed Particle Filter
ABABSA, Fakhreddine; HADJ-ABDELKADER, Hicham; BOUI, Marouane
The purpose of this paper is to investigate the problem of 3D human tracking in complex environments using a particle filter with images captured by a catadioptric vision system. This issue has been widely studied in the literature on RGB images acquired from conventional perspective cameras, while omnidirectional images have seldom been used and published research works in this field remains limited. In this study, the Riemannian varieties was considered in order to compute the gradient on spherical images and generate a robust descriptor used along with an SVM classifier for human detection. Original likelihood functions associated with the particle filter are proposed, using both geodesic distances and overlapping regions between the silhouette detected in the images and the projected 3D human model. Our approach was experimentally evaluated on real data and showed favorable results compared to machine learning based techniques about the 3D pose accuracy. Thus, the Root Mean Square Error (RMSE) was measured by comparing estimated 3D poses and truth data, resulting in a mean error of 0.065 m when walking action was applied.
2020-01-01T00:00:00ZABABSA, FakhreddineHADJ-ABDELKADER, HichamBOUI, MarouaneThe purpose of this paper is to investigate the problem of 3D human tracking in complex environments using a particle filter with images captured by a catadioptric vision system. This issue has been widely studied in the literature on RGB images acquired from conventional perspective cameras, while omnidirectional images have seldom been used and published research works in this field remains limited. In this study, the Riemannian varieties was considered in order to compute the gradient on spherical images and generate a robust descriptor used along with an SVM classifier for human detection. Original likelihood functions associated with the particle filter are proposed, using both geodesic distances and overlapping regions between the silhouette detected in the images and the projected 3D human model. Our approach was experimentally evaluated on real data and showed favorable results compared to machine learning based techniques about the 3D pose accuracy. Thus, the Root Mean Square Error (RMSE) was measured by comparing estimated 3D poses and truth data, resulting in a mean error of 0.065 m when walking action was applied.Augmented Reality Application in Manufacturing Industry: Maintenance and Non-destructive Testing (NDT) Use Cases
http://hdl.handle.net/10985/19418
Augmented Reality Application in Manufacturing Industry: Maintenance and Non-destructive Testing (NDT) Use Cases
ABABSA, Fakhreddine
In recent years, a structural transformation of the manufacturing industry has been occurring as a result of the digital revolution. Thus, digital tools are now systematically used throughout the entire value chain, from design to production to marketing, especially virtual and augmented reality. Therefore, the purpose of this paper is to review, through concrete use cases, the progress of these novel technologies and their use in the manufacturing industry.
2020-01-01T00:00:00ZABABSA, FakhreddineIn recent years, a structural transformation of the manufacturing industry has been occurring as a result of the digital revolution. Thus, digital tools are now systematically used throughout the entire value chain, from design to production to marketing, especially virtual and augmented reality. Therefore, the purpose of this paper is to review, through concrete use cases, the progress of these novel technologies and their use in the manufacturing industry.3D Human Tracking with Catadioptric Omnidirectional Camera
http://hdl.handle.net/10985/16195
3D Human Tracking with Catadioptric Omnidirectional Camera
ABABSA, Fakhreddine; HADJ-ABDELKADER, Hicham; BOUI, Marouane
This paper deals with the problem of 3D human tracking in catadioptric images using particle-filtering framework. While traditional perspective images are well exploited, only a few methods have been developed for catadioptric vision, for the human detection or tracking problems. We propose to extend the 3D pose estimation in the case of perspective cameras to catadioptric sensors. In this paper, we develop an original likelihood functions based, on the one hand, on the geodetic distance in the spherical space SO3 and, on the other hand, on the mapping between the human silhouette in the images and the projected 3D model. These likelihood functions combined with a particle filter, whose propagation model is adapted to the spherical space, allow accurate 3D human tracking in omnidirectional images. Both visual and quantitative analysis of the experimental results demonstrate the effectiveness of our approach.
2019-01-01T00:00:00ZABABSA, FakhreddineHADJ-ABDELKADER, HichamBOUI, MarouaneThis paper deals with the problem of 3D human tracking in catadioptric images using particle-filtering framework. While traditional perspective images are well exploited, only a few methods have been developed for catadioptric vision, for the human detection or tracking problems. We propose to extend the 3D pose estimation in the case of perspective cameras to catadioptric sensors. In this paper, we develop an original likelihood functions based, on the one hand, on the geodetic distance in the spherical space SO3 and, on the other hand, on the mapping between the human silhouette in the images and the projected 3D model. These likelihood functions combined with a particle filter, whose propagation model is adapted to the spherical space, allow accurate 3D human tracking in omnidirectional images. Both visual and quantitative analysis of the experimental results demonstrate the effectiveness of our approach.Combining HoloLens and Leap-Motion for Free Hand-Based 3D Interaction in MR Environments
http://hdl.handle.net/10985/19485
Combining HoloLens and Leap-Motion for Free Hand-Based 3D Interaction in MR Environments
ABABSA, Fakhreddine; HE, Junhui; CHARDONNET, Jean-Rémy
The ability to interact with virtual objects using gestures would allow users to improve their experience in Mixed Reality (MR) environments, especially when they use AR headsets. Today, MR head-mounted displays like the HoloLens integrate hand gesture based interaction allowing users to take actions in MR environments. However, the proposed interactions remain limited. In this paper, we propose to combine a Leap Motion Controller (LMC) with a HoloLens in order to improve gesture interaction with virtual objects. Two main issues are presented: an interactive calibration procedure for the coupled HoloLens-LMC device and an intuitive hand-based interaction approach using LMC data in the HoloLens environment. A set of first experiments was carried out to evaluate the accuracy and the usability of the proposed approach.
2020-01-01T00:00:00ZABABSA, FakhreddineHE, JunhuiCHARDONNET, Jean-RémyThe ability to interact with virtual objects using gestures would allow users to improve their experience in Mixed Reality (MR) environments, especially when they use AR headsets. Today, MR head-mounted displays like the HoloLens integrate hand gesture based interaction allowing users to take actions in MR environments. However, the proposed interactions remain limited. In this paper, we propose to combine a Leap Motion Controller (LMC) with a HoloLens in order to improve gesture interaction with virtual objects. Two main issues are presented: an interactive calibration procedure for the coupled HoloLens-LMC device and an intuitive hand-based interaction approach using LMC data in the HoloLens environment. A set of first experiments was carried out to evaluate the accuracy and the usability of the proposed approach.Free Hand-Based 3D Interaction in Optical See-Through Augmented Reality Using Leap Motion
http://hdl.handle.net/10985/14475
Free Hand-Based 3D Interaction in Optical See-Through Augmented Reality Using Leap Motion
ABABSA, Fakhreddine; HE, Junhui; CHARDONNET, Jean-Rémy
In augmented reality environments, the natural hand interaction between a virtual object and the user is a major issue to manipulate a rendered object in a convenient way. Microsoft’s HoloLens (Microsoft 2018) is an innovative augmented reality (AR) device that has provided an impressive experience for the user. However, the gesture interactions offered to the user are very limited. HoloLens currently recognizes two core component gestures: Air tap and Bloom. To solve this issue, we propose to integrate a Leap Motion Controller (LMC) within the HoloLens device (Figure 1). We thus used 3D hand and finger tracking provided by the LMC to propose new free hand-based interaction more natural and intuitive. We implemented three fully 3D techniques for selection, translation and rotation manipulation. In this work, we first investigated how to combine the two devices to get them working together in real time, and then we evaluated the proposed 3D hand interactions.
2018-01-01T00:00:00ZABABSA, FakhreddineHE, JunhuiCHARDONNET, Jean-RémyIn augmented reality environments, the natural hand interaction between a virtual object and the user is a major issue to manipulate a rendered object in a convenient way. Microsoft’s HoloLens (Microsoft 2018) is an innovative augmented reality (AR) device that has provided an impressive experience for the user. However, the gesture interactions offered to the user are very limited. HoloLens currently recognizes two core component gestures: Air tap and Bloom. To solve this issue, we propose to integrate a Leap Motion Controller (LMC) within the HoloLens device (Figure 1). We thus used 3D hand and finger tracking provided by the LMC to propose new free hand-based interaction more natural and intuitive. We implemented three fully 3D techniques for selection, translation and rotation manipulation. In this work, we first investigated how to combine the two devices to get them working together in real time, and then we evaluated the proposed 3D hand interactions.Computation of dynamic transmission error for gear transmission systems using modal decomposition and Fourier series
http://hdl.handle.net/10985/22661
Computation of dynamic transmission error for gear transmission systems using modal decomposition and Fourier series
ABBOUD, Eddy; GROLET, Aurélien; MAHÉ, Hervé; THOMAS, Olivier
In this paper, a method for computing the dynamics of a geared system excited by its static transmission error is proposed. The method is based on the iterative spectral method (ISM) and on the harmonic balance method (HBM). It is shown that the dynamic transmission error (DTE) can be obtained in the frequency domain by solving a linear system of equations, which in turn allows the computation of the modal and physical coordinates of the system.
2021-11-01T00:00:00ZABBOUD, EddyGROLET, AurélienMAHÉ, HervéTHOMAS, OlivierIn this paper, a method for computing the dynamics of a geared system excited by its static transmission error is proposed. The method is based on the iterative spectral method (ISM) and on the harmonic balance method (HBM). It is shown that the dynamic transmission error (DTE) can be obtained in the frequency domain by solving a linear system of equations, which in turn allows the computation of the modal and physical coordinates of the system.Tabu Search Algorithm for Single and Multi-model Line Balancing Problems
http://hdl.handle.net/10985/20996
Tabu Search Algorithm for Single and Multi-model Line Balancing Problems
ABDELJAOUAD, Mohamed Amine; KLEMENT, Nathalie
This paper deals with the assembly line balancing issue. The considered objective is to minimize the weighted sum of products’ cycle times. The originality of this objective is that it is the generalization of the cycle time minimization used in single-model lines (SALBP) to the multi-model case (MALBP). An optimization algorithm made of a heuristic and a tabu-search method is presented and evaluated through an experimental study carried out on several and various randomly generated instances for both the single and multiproduct cases. The returned solutions are compared to optimal solutions given by a mathematical model from the literature and to a proposed lower bound inspired from the classical SALBP bound. The results show that the algorithm is high performing as the average relative gap between them is quite low for both problems.
2021-01-01T00:00:00ZABDELJAOUAD, Mohamed AmineKLEMENT, NathalieThis paper deals with the assembly line balancing issue. The considered objective is to minimize the weighted sum of products’ cycle times. The originality of this objective is that it is the generalization of the cycle time minimization used in single-model lines (SALBP) to the multi-model case (MALBP). An optimization algorithm made of a heuristic and a tabu-search method is presented and evaluated through an experimental study carried out on several and various randomly generated instances for both the single and multiproduct cases. The returned solutions are compared to optimal solutions given by a mathematical model from the literature and to a proposed lower bound inspired from the classical SALBP bound. The results show that the algorithm is high performing as the average relative gap between them is quite low for both problems.Towards a SLAM-based augmented reality application for the 3D annotation of rock art
http://hdl.handle.net/10985/17575
Towards a SLAM-based augmented reality application for the 3D annotation of rock art
ABERGEL, Violette; JACQUOT, Kévin; DE LUCA, Livio; VERON, Philippe
The digital technologies developed in recent decades have considerably enriched the survey and documentation practices in the field of cultural heritage. They now raise new issues and challenges, particularly in the management of multidimensional datasets, which require the development of new methods for the analysis, interpretation and sharing of heterogeneous data. In the case of rock art sites, additional challenges are added to this context, due to their nature and fragility. In many cases, digital data alone is not sufficient to meet contextualization, analysis or traceability needs.
 In this context, we propose to develop an application dedicated to rock art survey, allowing 3D annotation in augmented reality. This work is a part of an ongoing project about an information system dedicated to cultural heritage documentation. For this purpose, we propose a registration method based on a spatial resection calculation. We will also raise the perspectives that this opens up for heritage survey and documentation, in particular in terms of visualization enhancement.
2019-01-01T00:00:00ZABERGEL, VioletteJACQUOT, KévinDE LUCA, LivioVERON, PhilippeThe digital technologies developed in recent decades have considerably enriched the survey and documentation practices in the field of cultural heritage. They now raise new issues and challenges, particularly in the management of multidimensional datasets, which require the development of new methods for the analysis, interpretation and sharing of heterogeneous data. In the case of rock art sites, additional challenges are added to this context, due to their nature and fragility. In many cases, digital data alone is not sufficient to meet contextualization, analysis or traceability needs.
 In this context, we propose to develop an application dedicated to rock art survey, allowing 3D annotation in augmented reality. This work is a part of an ongoing project about an information system dedicated to cultural heritage documentation. For this purpose, we propose a registration method based on a spatial resection calculation. We will also raise the perspectives that this opens up for heritage survey and documentation, in particular in terms of visualization enhancement.Algorithmic Strategy for Simultaneous Optimization of Design and Maintenance of Multi-Component Industrial Systems
http://hdl.handle.net/10985/23286
Algorithmic Strategy for Simultaneous Optimization of Design and Maintenance of Multi-Component Industrial Systems
ADJOUL, Oussama; BENFRIHA, Khaled; EL ZANT, Chawki; AOUSSAT, Améziane
This article describes a new approach to simultaneous optimization of design and maintenance of large-scale multi-component industrial systems. This approach, in a form of an algorithm, aims to help designers in the search for solutions by characterizing the components and their architecture including maintenance issues. The aim is to improve the performance of the industrial systems by maximizing the Total Operational Reliability (TOR) at the lowest Life Cycle Cost (LCC). In the case of this research, the term "design" refers to the reliability properties of the components, possible redundancies, faulty component accessibility, and the ability to improve the component real-time monitoring architecture. The term “maintenance” refers to maintenance plan adapted to the opportunistic dynamic maintenance plan. Simultaneous optimization of design and maintenance is achieved by a two-level hybrid algorithm using evolutionary (genetic) algorithms. The first level identifies the optimal design solutions calculated relative to the TOR and the LCC. The second proposes a dynamic maintenance plan that maximizes the reliability of the system throughout its operating life.
2020-12-01T00:00:00ZADJOUL, OussamaBENFRIHA, KhaledEL ZANT, ChawkiAOUSSAT, AmézianeThis article describes a new approach to simultaneous optimization of design and maintenance of large-scale multi-component industrial systems. This approach, in a form of an algorithm, aims to help designers in the search for solutions by characterizing the components and their architecture including maintenance issues. The aim is to improve the performance of the industrial systems by maximizing the Total Operational Reliability (TOR) at the lowest Life Cycle Cost (LCC). In the case of this research, the term "design" refers to the reliability properties of the components, possible redundancies, faulty component accessibility, and the ability to improve the component real-time monitoring architecture. The term “maintenance” refers to maintenance plan adapted to the opportunistic dynamic maintenance plan. Simultaneous optimization of design and maintenance is achieved by a two-level hybrid algorithm using evolutionary (genetic) algorithms. The first level identifies the optimal design solutions calculated relative to the TOR and the LCC. The second proposes a dynamic maintenance plan that maximizes the reliability of the system throughout its operating life.Data aggregation architecture “Smart-Hub” for heterogeneous systems in industrial environment
http://hdl.handle.net/10985/16739
Data aggregation architecture “Smart-Hub” for heterogeneous systems in industrial environment
AHMED, Ahmed; GAUDY, Remy; LARAT, Bertrand; ROUCOULES, Lionel
Distributed systems spread widely in industrial environments. One of the key challenges is the exchange and the aggregation of data between these sys-tems. Although standards play an important role to solve data interoperability is-sues between systems, these standards do not completely address existing indus-trial problems. In fact, it is not granted to have an industrial environment that complies with a unique standard; therefore, ad-hoc solutions are used to solve this issue. In this article, the authors propose a generic architecture to address the in-teroperability between systems. This architecture is developed based on model-based techniques and principles. Besides, it reduces the need for human interven-tion and time by developing once and reusing the building blocks of the architec-ture. Finally, the architecture is described in its application to a case study.
2016-01-01T00:00:00ZAHMED, AhmedGAUDY, RemyLARAT, BertrandROUCOULES, LionelDistributed systems spread widely in industrial environments. One of the key challenges is the exchange and the aggregation of data between these sys-tems. Although standards play an important role to solve data interoperability is-sues between systems, these standards do not completely address existing indus-trial problems. In fact, it is not granted to have an industrial environment that complies with a unique standard; therefore, ad-hoc solutions are used to solve this issue. In this article, the authors propose a generic architecture to address the in-teroperability between systems. This architecture is developed based on model-based techniques and principles. Besides, it reduces the need for human interven-tion and time by developing once and reusing the building blocks of the architec-ture. Finally, the architecture is described in its application to a case study.