Capturing Basic Movements for Mobile Gaming Platforms Embedded with Motion Sensors

Capturing Basic Movements for Mobile Gaming Platforms Embedded with Motion Sensors

Aravind Kailas, Chia-Chin Chong
Copyright: © 2012 |Pages: 14
DOI: 10.4018/jehmc.2012100101
(Individual Articles)
No Current Special Offers


A novel experimental setup using accelerometer and gyroscope sensors embedded on a single board along with a distance-based pattern recognition algorithm is presented for accurately identifying basic movements for possible application in gaming using a mobile platform. As an example, the authors considered some basic step sequences in the popular dance game (e.g., dance dance revolution), and could detect these movements with a reasonably high probability. They envision that the experimental results presented in this paper will motivate future research in the world of mobile gaming applications using advanced smart phones with a dual module design.
Article Preview

1. Introduction: Evolution Of Mobile Gaming

Simply stated, a mobile game is a video game that is played on a mobile phone using the technologies present on the device itself. This classification does not include handheld video systems/products such as PlayStation Portable or Nintendo DS. Mobile games are applications that simply use the device platform to run the game software. These games maybe downloaded on the fly and installed while mobile, or onto the handset using a cable, or come pre-installed by the original equipment manufacturer (OEM) or by the cellular operator as applications or services. Mobile games are a growing market (Koivisto, 2006) and according to Gartner (2007), in 2010 the sales of smartphones is expected to suppress the laptops sales (Oliver, 2008). More than 10 million people worldwide play games on mobile phones and handheld devices (Soh & Tan, 2008), and the world-wide mobile gaming revenue is expected to reach $9.6 billion by 2011. These are very important motivations for game developers and designers to create blockbuster games for mobile platforms.

The contributions of the paper can be summarized as follows:

  • 1.

    Experimental Setup: A novel experimental setup using accelerometer and gyroscope sensors embedded on a single board (Block 2 in Figure 1);

  • 2.

    Data analysis and Feature Extraction: Our feature extraction using wavelet packet decomposition (WPD), thereby providing better resolution for analysis than the fast Fourier transform (FFT) (Block 3c in Figure 1);

  • 3.

    Algorithm Development: Pattern recognition-based algorithm based on the Maha- lanobis distance, which is based on the correlations between the data points (Block 4a in Figure 1);

  • 4.

    Pose Recognition: Reliable pose recognition using two sensor boards (i.e., accelerometer and gyro combination) for games with a lot of human movements (e.g., dance dance revolution (DDR), a very popular game), is demonstrated with a high probability of success (Block 4 in Figure 1) to motivate future research game changing phones with a dual module design such as the Fujitsu F-04B.

Figure 1.

Block diagram highlighting the main contributions of the paper


The rest of the paper is organized as follows. Section 2 described the prior works. Section 3 outlines the methodology and experiments conducted. Experimental results are discussed in Section 4 and conclusions are presented in Section 5.


2. Prior Works

Three axis accelerometers have been used to (1) monitor frail activity (Noury et al., 2004); (2) estimate energy expenditure (Wixted, Theil, Hahn, Gore, Pyne, & James, 2007); (3) track articulated human motion (Zhu & Zhou, 2004); (4) detect knee unlock (Veltink & Franken, 1996); (5) detect gesture awareness (Jang & Park, 2003); (6) analyze human motion (Luinge & Veltink, 2004); and (7) measure heart motion (Hoff, Elle, Grimmes, Halvorsen, Alker, & Fosse, 2004), to list a few. Combinations of accelerometers and gyroscope sensors have been used to (1) estimate human body orientation (Luinge, Veltink, & Baten, 1999); (2) detect human posture and walking speed (Motoi, Tanaka, Jang, & Kim, 2003); and (3) human recognition via gait recognition (Nowlan, 2009) to name a few. However, none of these implementations are for a portable device such as a mobile phone. Stated simply, the users need to wear some sensors on specific parts of their bodies, and the feature extraction is suitable only for a limited range of user context.

Complete Article List

Search this Journal:
Volume 15: 1 Issue (2024)
Volume 14: 1 Issue (2023)
Volume 13: 5 Issues (2022): 4 Released, 1 Forthcoming
Volume 12: 6 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing