Real-Time Gesture Recognition Based On Motion Quality Analysis

Journal Title: EAI Endorsed Transactions on e-Learning - Year 2015, Vol 2, Issue 8

Abstract

This paper presents a robust and anticipative real-time gesture recognition and its motion quality analysis module. By utilizing a motion capture device, the system recognizes gestures performed by a human, where the recognition process is based on skeleton analysis and motion features computation. Gestures are collected from a single person. Skeleton joints are used to compute features which are stored in a reference database, and Principal Component Analysis (PCA) is computed to select the most important features, useful in discriminating gestures. During real-time recognition, using distance measures, real-time selected features are compared to the reference database to find the most similar gesture. Our evaluation results show that: i) recognition delay is similar to human recognition delay, ii) our module can recognize several gestures performed by different people and is morphology-independent, and iii) recognition rate is high: all gestures are recognized during gesture stroke. Results also show performance limits

Authors and Affiliations

Céline Jost, Igor Stankovic, Pierre De Loor, Alexis Nédélec, Elisabetta Bevacqua

Keywords

Related Articles

Engaging Our School Teachers: an Augmented Reality (AR) Approach to Continuous Professional Development

Currently, teachers in the UK learn about behaviour management strategies from theoretical perspectives when training, through discussions with mentors, and by trial and error at their schools. Existing literature mainly...

A survey of the benefits and issues arising from the deployment of physical artefacts in computer science teaching

This paper describes the introduction of the use of physical artefacts in the teaching of the curriculum in the Department of Computer Science at Middlesex University. The rationale for the change is discussed, together...

Automation of Algorithmic Tasks for Virtual Laboratories Based on Automata Theory.

In the work a description of an automata model of standard algorithm for constructing a correct solution of algorithmic tests is given. The described model allows a formal determination of the variant complexity of algor...

How Usable Are the Learning Management Systems? The Users Have their Say

E-learning is an innovative way of learning that is both symbolic and derivative of ‘the information age.’ When used as part of the learning process, it provides users with greater flexibility in terms of time and locati...

Integrating WeChat-based Mobile-Assisted Language Learning into College English Teaching

WeChat, one of the most popular social networking tools in China, has attracted attention of educators to its pedagogical value such as its support for interactivity and real-time communications. Based on the literature...

Download PDF file
  • EP ID EP45957
  • DOI http://dx.doi.org/10.4108/icst.intetain.2015.259608
  • Views 250
  • Downloads 0

How To Cite

Céline Jost, Igor Stankovic, Pierre De Loor, Alexis Nédélec, Elisabetta Bevacqua (2015). Real-Time Gesture Recognition Based On Motion Quality Analysis. EAI Endorsed Transactions on e-Learning, 2(8), -. https://europub.co.uk/articles/-A-45957