Search Results

Now showing 1 - 5 of 5
  • Item
    User Interaction Feedback in a Hand-Controlled Interface for Robot Team Tele-operation Using Wearable Augmented Reality
    (The Eurographics Association, 2017) Cannavò, Alberto; Lamberti, Fabrizio; Andrea Giachetti and Paolo Pingi and Filippo Stanco
    Continuous advancements in the field of robotics and its increasing spread across heterogeneous application scenarios make the development of ever more effective user interfaces for human-robot interaction (HRI) an extremely relevant research topic. In particular, Natural User Interfaces (NUIs), e.g., based on hand and body gestures, proved to be an interesting technology to be exploited for designing intuitive interaction paradigms in the field of HRI. However, the more sophisticated the HRI interfaces become, the more important is to provide users with an accurate feedback about the state of the robot as well as of the interface itself. In this work, an Augmented Reality (AR)-based interface is deployed on a head-mounted display to enable tele-operation of a remote robot team using hand movements and gestures. A user study is performed to assess the advantages of wearable AR compared to desktop-based AR in the execution of specific tasks.
  • Item
    A 3 Cent Recognizer: Simple and Effective Retrieval and Classification of Mid-air Gestures from Single 3D Traces
    (The Eurographics Association, 2017) Caputo, Fabio Marco; Prebianca, Pietro; Carcangiu, Alessandro; Spano, Lucio D.; Giachetti, Andrea; Andrea Giachetti and Paolo Pingi and Filippo Stanco
    In this paper we present a simple 3D gesture recognizer based on trajectory matching, showing its good performances in classification and retrieval of command gestures based on single hand trajectories. We demonstrate that further simplifications in porting the classic "1 dollar" algorithm approach from the 2D to the 3D gesture recognition and retrieval problems can result in very high classification accuracy and retrieval scores even on datasets with a large number of different gestures executed by different users. Furthermore, recognition can be good even with heavily subsampled path traces and with incomplete gestures.
  • Item
    Data Painter: A Tool for Colormap Interaction
    (The Eurographics Association, 2017) Nagoor, Omniah H.; Borgo, Rita; Jones, Mark W.; Tao Ruan Wan and Franck Vidal
    The choice of a mapping from data to color should involve careful consideration in order to maximize the user understanding of the underlying data. It is desirable for features within the data to be visually separable and identifiable. Current practice involves selecting a mapping from predefined colormaps or coding specific colormaps using software such as MATLAB. The purposes of this paper are to introduce interactive operations for colormaps that enable users to create more visually distinguishable pixel based visualizations, and to describe our tool, Data Painter, that provides a fast, easy to use framework for defining these color mappings. We demonstrate the use of the tool to create colormaps for various application areas and compare to existing color mapping methods. We present a new objective measure to evaluate their efficacy
  • Item
    Single-Handed vs. Two Handed Manipulation in Virtual Reality: A Novel Metaphor and Experimental Comparisons
    (The Eurographics Association, 2017) Caputo, Fabio Marco; Emporio, Marco; Giachetti, Andrea; Andrea Giachetti and Paolo Pingi and Filippo Stanco
    In this paper we present a novel solution for single-handed deviceless object manipulation (e.g. picking/translating, rotating and scaling) in immersive visualization environments. The new method is based on degree of freedom (DOF) separation and on the idea of activating unambiguous gesture recognition when the hand is close to the object, giving visual feedback about gesture realization and available transitions. Furthermore, it introduces a novel metaphor, the "knob", to map hand rotation onto object rotation around selected axes. The solution was tested with users on a classical visualization task related to finding a point of interest in a 3D object and compared with the well known "Handlebar" metaphor. The metaphor shows a reasonable usability, even if not comparable with the bi- manual solution, particularly suited for the tested task. However, given the relevant improvements with task repetitions and the technical issues that can be solved improving the performances, the method seems to be a viable solution for deviceless single-hand manipulation.
  • Item
    Google Tango Outdoors. Augmented Reality for Underground Infrastructures
    (The Eurographics Association, 2017) Soria, Gregorio; Ortega, Lidia; Feito, Francisco R.; Fco. Javier Melero and Nuria Pelechano
    Underground infrastructures, which support much of the services provided to citizens, have the peculiarity of not being directly visible. This leads to problems when making incursions for maintenance or creating new installations. In this framework, new technologies related to augmented reality are of special interest. This work presents a virtual reality application using Google Tango in order to visualize underground infrastructures in situ, allowing also free navigation. The system works on a clientserver architecture. The client obtains the location point as well as the orientation of the device. The server returns the virtual visualization of infrastructure elements and buildings from this viewpoint, which will be superimposed over the actual view. The server maintains a spatial database with topological characteristics that allow this and other modes of interaction, as well as some analytical capacity. This article focuses on aspects such as the transformation of input data, the data model, the different methodologies for rapid and effective positioning, as well as the usability of the application.