Malik Mallem | Evry University - CNRS - Genopole (original) (raw)

Papers by Malik Mallem

2012 5th Workshop on Software Engineering and Architectures for Realtime Interactive Systems (SEARIS), 2012

ABSTRACT Nowadays, many Augmented Reality (AR) frameworks are using a component based approach. I... more ABSTRACT Nowadays, many Augmented Reality (AR) frameworks are using a component based approach. It ensures that the non functional requirements of AR such as extensibility, configurability and modularity are handled. One of the challenge the AR application designer have to face is the problem of the integration of multiple technologies that could be provided by different component systems that do not cover the same issues. In this paper, we will see how our AR component based framework, named ARCS (Augmented Reality Component System), is intended to integrate other components from exogenous component systems and how it could be integrated into other software. At the same time, we also tackle the issues that may arise in multi-threaded environments by using a specific heuristic in order to monitor components. We also explain how we implement the networking non functional requirement using a proxy desing pattern. Then, we discuss and study the impact such genericity has on performances of our system. Finally, our approach will be exposed and validated through different examples of different sizes.

This work focuses on 3D interaction assistance by adding adaptivity depending on the tasks, the o... more This work focuses on 3D interaction assistance by adding adaptivity depending on the tasks, the objectives, and the general interaction context. An engine to reach context-awareness has been implemented in Prolog+CG which uses Conceptual Graphs (CGs) based on an ontology. CGs descriptions of the available sensors and actuators in our scene manager (Virtools) allow the engine to take decisions and send them through Open Sound Control (OSC). Measurements and adaptations corresponding to specific tools uses are decided from rules handled by the engine. This project is a step towards Intelligent Virtual Environments, which proposes a hybrid solution by adding a separate semantic reasoning to classic environments. The first experiment automatically manages few modalities depending on the distance to objects, user movement, available tools, etc. Gestures are used both as an engine direct control and as an interpretation of user activity.

Proceedings of the 18th ACM symposium on Virtual reality software and technology - VRST '12, 2012

ABSTRACT We propose a semantic reasoning engine for context-awareness in classic VR environments.... more ABSTRACT We propose a semantic reasoning engine for context-awareness in classic VR environments. It is currently used to automatically detect user's interests and manage visual enhancements depending on the user's movement.

2013 10th IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL (ICNSC), 2013

ABSTRACT Humanoid robots are not easy to program, it's a challenging task, even if they c... more ABSTRACT Humanoid robots are not easy to program, it's a challenging task, even if they come with an advanced high level programming interfaces, such as drag-and-drop applications, which are indeed less complex and save a lot of time, it still needs an experienced user to produce a high quality motion, especially for the natural human-like motions which are very hard to reproduce. This paper introduces a new technique to fully imitate the human body motion on a humanoid robot NAO in real time using the Kinect Depth Camera, OpenNI Framework and the Robot Operating System (ROS).

ETFA 2001. 8th International Conference on Emerging Technologies and Factory Automation. Proceedings (Cat. No.01TH8597), 2001

The described problem is a diagnostic task which must be solved for high-velocity industrial mach... more The described problem is a diagnostic task which must be solved for high-velocity industrial machine tools. Due to environmentally degraded conditions, direct measurements are not possible. Due to the rapidity of the machine, human intervention is not possible in case it causes positional faults. So, an oriented vision solution is proposed. The degraded conditions are vibrations, projections of water and

IMTC/99. Proceedings of the 16th IEEE Instrumentation and Measurement Technology Conference (Cat. No.99CH36309), 1999

Abstract-MCIT -Multimedia Control Interface for Telerobotics-is an augmented reality system we ar... more Abstract-MCIT -Multimedia Control Interface for Telerobotics-is an augmented reality system we are working on in our lab. MCIT sensing devices consist of a camera, allowing the operator an indirect view of a scene (real world), proprioceptive and exteroceptive sensors, ...

Proceedings of the 17th international ACM Sigsoft symposium on Component-based software engineering - CBSE '14, 2014

ABSTRACT When programming software applications, developers have to deal with many functional and... more ABSTRACT When programming software applications, developers have to deal with many functional and non-functional requirements. During the last decade, especially in the augmented reality field of research, many frameworks have been developed using a component-based approach in order to fulfil the non-functional requirements. In this paper, we focus on such a specific requirement: race conditions issues in component-based systems. We present a heuristic that analyses data flows and detects components that may be subject to race conditions. A toy example introducing the problem and the solution is developed and implemented under the ARCS (for Augmented Reality Component System) framework. We also show the results of our algorithm on real size applications using up to 70 components and compare those results with some obtained by developers who had to make exactly the same work by hand.

2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA), 2012

ABSTRACT This work studies, implements and evaluates a gestures recognition module based on discr... more ABSTRACT This work studies, implements and evaluates a gestures recognition module based on discrete Hidden Markov Models. The module is implemented on Matlab and used from Virtools. It can be used with different inputs therefore serves different recognition purposes. We focus on the 3D positions, our devices common information, as inputs for gesture recognition. Experiments are realized with an infra-red tracked flystick. Finally, the recognition rate is more than 90% with a personalized learning base. Otherwise, the results are beyond 70%, for an evaluation of 8 users on a real time mini-game. The rates are basically 80% for simple gestures and 60% for complex ones.

Third IEEE and ACM International Symposium on Mixed and Augmented Reality, 2004

One of the key problems in augmented reality systems is registration, that is to say the synchron... more One of the key problems in augmented reality systems is registration, that is to say the synchronization of real and virtual world. Augmented reality uses a lot of different sensors in order to estimate camera or operator&amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;amp;#x27;s point of view. These sensors could provide samples faster than mixing of virtual and real information could be displayed. We expose here a

1995 IEEE International Conference on Systems, Man and Cybernetics. Intelligent Systems for the 21st Century, 1995

The paper deals with the updating of environment's geometric database in telerobotics. It... more The paper deals with the updating of environment's geometric database in telerobotics. It concerns the pose determination of known objects using 2D clues obtained through video images. A two step algorithm is implemented and assessed. The first step is available in case of object large motion, it is a geometric algorithm, which doesn't use redundant data; it provides a first

Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications - VRCIA '06, 2006

Object recognition supported by user interaction for service robots, 2002

This paper presents a new method for an automatic matching between a free form 3D objects and a s... more This paper presents a new method for an automatic matching between a free form 3D objects and a single image. This matching could be used for object recognition and/or object 3D recovering. This kind of problem has raised a tremendous amount of interest in research fields such as Computer Vision and more specifically in Augmented Reality. The original idea brought by our method is to use a photoclinometric framework (such as Shape from Shading) in order to extract normal vectors information from the image. Our interest is focused on the distribution of angles between surface normal vectors and incident light vector. This information is discriminate for free form objects without symmetries, and one can show that it could be used to match between the image and the model by using an aspect graph featuring this distribution.

Proceedings of the ACM symposium on Virtual reality software and technology - VRST '06, 2006

This paper presents a robust line tracking approach for camera pose estimation which is based on ... more This paper presents a robust line tracking approach for camera pose estimation which is based on particle filtering framework. Particle filters are sequential Monte Carlo methods based on point mass (or &amp;amp;amp;amp;amp;amp;amp;amp;amp;quot;particle&amp;amp;amp;amp;amp;amp;amp;amp;amp;quot;) representations of probability densities, which can be applied to any state-space model. Their ability to deal with non-linearities and non-Gaussian statistics allows to improve robustness comparing to existing

Lecture Notes in Computer Science, 2009

This paper presents a new robust and reliable marker less camera tracking system for outdoor augm... more This paper presents a new robust and reliable marker less camera tracking system for outdoor augmented reality using only a mobile handheld camera. The proposed method is particularly efficient for partially known 3D scenes where only an incomplete 3D model of the outdoor environment is available. Indeed, the system combines an edge-based tracker with a sparse 3D reconstruction of the

Proceedings of the 2004 ACM SIGGRAPH international conference on Virtual Reality continuum and its applications in industry - VRCAI '04, 2004

Augmented reality (AR) deals with the problem of dynamically and accurately align virtual objects... more Augmented reality (AR) deals with the problem of dynamically and accurately align virtual objects with the real world. Among the used methods, vision-based techniques have advantages for AR applications, their registration can be very accurate, and there is no delay between the motion of real and virtual scenes. However, the downfall of these approaches is their high computational cost and lack of robustness. To address these shortcomings we propose a robust camera pose estimation method based on tracking calibrated fiducials in a known 3D environment, the camera location is dynamically computed by the Orthogonal Iteration Algorithm. Experimental results show the robustness and the effectiveness of our approach in the context of real-time AR tracking.

Proceedings of the 2008 ACM symposium on Virtual reality software and technology - VRST '08, 2008

In mobile outdoor augmented reality applications, accurate localization is critical to register v... more In mobile outdoor augmented reality applications, accurate localization is critical to register virtual augmentations over a real scene. Vision-based approaches provide accurate localization estimates but are still too sensitive to outdoor conditions (brightness changes, occlusions, etc.). This drawback can be overcome by adding other types of sensors. In this work, we combine a GPS and an inertial sensor with a camera to provide accurate localization. We will present the calibration process and we will discuss how to quantify the 3D localization accuracy. Experimental results on real data are presented.

Virtual Reality, 2014

ABSTRACT The equilibrium of complex systems often depends on a set of constraints. Thus, credible... more ABSTRACT The equilibrium of complex systems often depends on a set of constraints. Thus, credible virtual reality modeling of these systems must respect these constraints, in particular for 3D interactions. In this paper, we propose a generic framework for designing assistance to 3D user interaction in constraints-based virtual environment that associates constraints, interaction tasks and assistance tools, such as virtual fixtures (VFs). This framework is applied to design assistance tools for molecular biology analysis. Evaluation shows that VF designed using our framework improve effectiveness of the manipulation task.

IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004, 2004

... SIR PARTICLE FILTER I. Set t=O, generates N samples @E, from the initial ... We used a SIRpar... more ... SIR PARTICLE FILTER I. Set t=O, generates N samples @E, from the initial ... We used a SIRparticle filter as fusion filter [12,13,21,22] to estimate the head pose parameters of (IO) from the measurements of the vision and inertial sensors. Iv. RESULTS ...

Proceedings of the 5th International Conference on Communication System Software and Middleware - COMSWARE '11, 2011

This paper describes the design and implementation of a middleware for a framework dedicated to A... more This paper describes the design and implementation of a middleware for a framework dedicated to Augmented Reality / Mixed Reality (AR/MR) applications. The goal is to offer an environment for the development of distributed applications running on mobile devices (wearable computers and/or smartphones). The paper first presents the main needs of an AR application and introduces the necessity of distribution in this field. Then we make a quick overview of existing distributed AR frameworks. The goal of this overview is to extract main features and strengths of each framework's architecture based on a set of defined criteria. This comparison being meant as a starting point to extend our own framework (ARCS: Augmented Reality Component System), the last section is about the design and implementation of our own software infrastructure for transparent distributed Augmented Reality taking in consideration our own goals and constraints and taking profit of the strengths of the studied existing frameworks.

Proceedings of the 2005 IEEE International Conference on Robotics and Automation, 2005

Climbing robots can perform many tasks inaccessible to other robots or humans such as inspection,... more Climbing robots can perform many tasks inaccessible to other robots or humans such as inspection, repair, cleaning, surveillance, and exploration. This paper presents and discusses the design, fabrication, and evaluation of two novel bio-inspired climbing robots. Both are inspired by the locomotion of Geckos, a highly skilled natural climber. They are developed for terrestrial and extra-terrestrial environments, and their kinematics is inspired by the Geckos' gait. The first relatively large robot actuated by conventional motors is designed to operate at both in Earth and space scenarios. The second robot, whose motion is controlled using shape memory alloy actuators and size can be miniaturized to few centimeters scale, is designed for terrestrial applications. Preliminary prototypes of these robots are developed, demonstrated, and evaluated by steep and flat acrylic surface climbing tests. Current robots can successfully climb up to 65° slopes at 2 cm/sec speeds.