Abstract
In this work, we present an unobtrusive and non-invasive perception framework based on the synergy between two main acquisition systems: the Touch-Me Pad, consisting of two electronic patches for physiological signal extraction and processing; and the Scene Analyzer, a visual-auditory perception system specifically designed for the detection of social and emotional cues. It will be explained how the information extracted by this specific kind of framework is particularly suitable for social robotics applications and how the system has been conceived in order to be used in human-robot interaction scenarios.
Highlights
Today, assessing the emotional state of a user can be considered one of the most important and challenging aims in human-computer interaction (HCI)
We will present a brief description of the Scene Analyzer, which is deeply discussed in a previous publication [39], while we will examine in depth the Touch-Me Pad, in terms of design, development, technical description and validation, as well as the ID (Identifier) tracking strategy, that represents the bridge between SA and TMP and gives the system the possibility to be used for long-term interactions
We present three experiments: the first one is an evaluation of the Touch-Me Pad, conducting a technical comparison with one of the best available device for physiological parameters acquisition; the second is about the presented ID Tracking Module (IDTm) module, is a demonstration of the capability of the system to keep track of the ID of subjects, even when they become undetectable for the vision system; the third and latter is the test of the overall architecture, included data integration, demonstrating the ability of our perception framework to gather data from both SA and TMP in a continuous session of acquisition
Summary
Today, assessing the emotional state of a user can be considered one of the most important and challenging aims in human-computer interaction (HCI). The simultaneous usage of multiple modalities for acquiring information about the users emotional state has proved to be a smart solution to the problem, especially when they involve computer vision and image processing [6] These audiovisual acquisition systems are focused on face detection [7,8], face recognition [9], facial expression analysis [10,11], vocal emotion [12,13], gesture recognition [14,15], human motion analysis [16,17,18], audiovisual automatic speech recognition [19], and eye tracking [20,21]. The integration of these acquisition modalities led to the development of many multimodal interfaces, so much to become an increasingly important research direction, defined by Turk et al as Perceptual Interfaces [24]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
