I am pleased to invite you to my PhD defense, entitled: "On Mobile Augmented Reality Applications based on Geolocation".
My defense will be held in Grand Amphi (A110) at Inria Grenoble on November 10, 2017 at 2 pm.
The PhD thesis has been directed by:
- Nabil Layaïda, Tyrex team, (thesis director, Inria)
- Pierre Genevès, Tyrex team, (co-supervisor, CNRS)
- Hassen Fourati, Necs team, (co-supervisor, Gipsa-Lab)
- Analysis and enhancement of an indoor and outdoor navigation system with a focus on attitude estimation for pedestrian navigation with smartphones. [MATLAB, PDR, Wifi, Barometer, GPS, Kalman Filter, Motion, Map-Matching]
- Working with OpenStreetMap client side. Parsing OSM Documents, projections, routing, UI (MapBox, MapsForge, OpenLayers...) [OSM, Android, OWP]
- Working with OpenStreetMap server side. Mount OSM Server: Postgis, Nominatim, Tilemill... Create WebApi access [Node.js, CentOS]
- Creation of an Augmented Reality and an Augmented Panorama Frameworks for Android. [Android, OpenGL ES, Sensors]
- Management of subprojects and creation of libraries for Venturi european project (immersiVe ENhancemenT of User-woRld Interactions). http://venturi.fbk.eu
IEEE International Conference on Pervasive Computing and Communications, Mar 2017, Kona, United States
We investigate the precision of attitude estimation algorithms in the particular context of pedestrian navigation with commodity smartphones and their inertial/magnetic sensors. We report on an extensive comparison and experimental analysis of existing algorithms. We focus on typical motions of smartphones when carried by pedestrians. We use a precise ground truth obtained from a motion capture system. We test state-of-the-art attitude estimation techniques with several smartphones, in the presence of magnetic perturbations typically found in buildings. We discuss the obtained results, analyze advantages and limits of current technologies for attitude estimation in this context. Furthermore, we propose a new technique for limiting the impact of magnetic perturbations with any attitude estimation algorithm used in this context. We show how our technique compares and improves over previous works.
[CONFERENCE] A Comparative Analysis of Attitude Estimation for Pedestrian Navigation with Smartphones [HAL, PDF, Abstract]Thibaud Michel, Hassen Fourati, Pierre Genevès, Nabil Layaïda
Indoor Positioning and Indoor Navigation, Oct 2015, Banff, Canada. pp.10, 2015, 2015 International Conference on Indoor Positioning and Indoor Navigation. 〈http://www.ucalgary.ca/ipin2015/〉. 〈10.1109/IPIN.2015.7346767〉
We investigate the precision of attitude estimation solutions in the context of Pedestrian Dead-Reckoning (PDR) with commodity smartphones and inertial/magnetic sensors. We propose a concise comparison and analysis of a number of attitude filtering methods in this setting. We conduct an experimental study with a precise ground truth obtained with a motion capture system. We precisely quantify the error in attitude estimation obtained with each filter which combines a 3-axis accelerometer, a 3-axis magnetometer and a 3-axis gyroscope measurements. We discuss the obtained results and analyse advantages and limitations of current technology for further PDR research.
[CONFERENCE] Personal Shopping Assistance and Navigator System for Visually Impaired People [HAL, PDF, Abstract]Paul Chippendale, Valeria Tomaselli, Viviana D'Alto, Giulio Urlini, Carla Maria Modena, Stefano Messelodi, Sebastiano Mauro Strano, Günter Alce, Klas Hermodsson, Mathieu Razafimahazo, Thibaud Michel, Maria Farinella Giovanni
ACVR2014: Second Workshop on Assistive Computer Vision and Robotics, Sep 2014, Zurich, Switzerland. 〈http://www.ino.it/ACVR2014/〉
In this paper, a personal assistant and navigator system for visually impaired people will be described. The showcase presented in-tends to demonstrate how partially sighted people could be aided by the technology in performing an ordinary activity, like going to a mall and moving inside it to find a specific product. We propose an Android ap-plication that integrates Pedestrian Dead Reckoning and Computer Vi-sion algorithms, using an off-the-shelf Smartphone connected to a Smart-watch. The detection, recognition and pose estimation of specific objects or features in the scene derive an estimate of user location with sub-meter accuracy when combined with a hardware-sensor pedometer. The pro-posed prototype interfaces with a user by means of Augmented Reality, exploring a variety of sensorial modalities other than just visual overlay, namely audio and haptic modalities, to create a seamless immersive user experience. The interface and interaction of the preliminary platform have been studied through specific evaluation methods. The feedback gathered will be taken into consideration to further improve the pro-posed system.
ERCIM News 98, 2014, ERCIM News 98, pp.45-46
Today, one of the main challenges in mobile augmented reality applications design is understanding how our perception of reality can be profitably augmented and how this augmentation can be made to fit seamlessly with the user’s interaction with the world. The European VENTURI project which began in 2011 is aiming to develop the first generation of ubiquitous augmented reality (AR) tools that meet real user needs and fit within the context they operate in.
[CONFERENCE] Mixed Reality Browsers and Pedestrian Navigation in Augmented Cities [HAL, PDF, Abstract]Jacques Lemordant, Thibaud Michel, Mathieu Razafinahazo
The Graphical Web Conference, Oct 2013, San Francisco, United States. 2013
In this paper, We use a declarative format for positional audio with synchronization between audio chunks using SMIL. This format has been specifically designed for the type of audio used in AR applications. The audio engine associated to this format is running on mobile platforms (iOS, Android). Our MRB browser called IXE use a format based on volunteered geographic information (OpenStreetMap) and OSM documents for IXE can be fully authored in side OSM editors like JOSM. This is in contrast with the other AR browsers like Layar, Juniao, Wikitude, which use a Point of Interest (POI) based format having no notion of ways. This introduces a fundamental difference and in some senses a duality relation between IXE and the other AR browsers. In IXE, Augmented Virtuality (AV) navigation along a route (composed of ways) is central and AR interaction with objects is delegated to associate 3D activities. In AR browsers, navigation along a route is delegated to associated map activities and AR interaction with objects is central. IXE supports multiple tracking technologies and therefore allows both indoor navigation in buildings and outdoor navigation at the level of sidewalks. A first android version of the IXE browser will be released at the end of 2013. Being based on volunteered geographic it will allow building accessible pedestrian networks in augmented cities.
Benchmarks Attitude on Smartphones
We investigate the precision of attitude estimation algorithms in the particular context of pedestrian navigation with commodity smartphones.
This android application records and store values from internal sensors.
Timelapse - Sony Camera
Take pictures with interval time in Wifi Mode for your Sony camera.
Venturi - Y3
Grenoble AR-Tour based on geolocation.