Gesture recognition with a wiimote (english version)

[english version]

Gesture recognition with a wiimote

Originally designed as a 3D peripheral, the wii remote is dedicated to gesture recognition for wii games.
Indeed, on 10/12/2006, AiLive commercialized LiveMove : A Gesture recognition library for game developpers of the Nintendo Wii .

[extract from LiveMoe features]

Vidéo 1 :

[LiveMove Uploaded by dkr- extract from Dailymotion Video]

This application was commercialized, with agreement of Nintendo, for game developers. Excepted this business, several open-source solutions are existing . Furthermore, several researchers are interested by the subject :

Logo	Comment	Type
	wiigee is a Java-based library (min. Java 1.5) for gesture recognition. Wigee can be integrated with Java's GUI. It uses enhanced algorithms as hidden markov models. (The following video illustrate how it works : Wiimote Gesture Recognition with Wiigee) The Project is maintained by Benjamin Poppinga	Applic- ation
AGR (Accelerometer Gesture Recognizer)	Accelerometer Gesture Recognizer AGR (Accelerometer Gesture Recogniser) is a library aimed to helps gesture recognition using an accelerometer device, like the Nintendo Wii remote controller. Project maintained by (pseudo) Ruffi.	Applic- ation
	Gesture recognition Site from Hubert Wassner, Professor at french engineering school/university ESIEA. Here, gesture recognition is based on neural computing . [Neural computing with a wiimote] The website describes several applications of neural computing and other reengineered softwares for the wiimote. There is not any current open-source but some videos are available. Moreover, some Practise courses involving wiimote and neural computing are presented! [Exrtact from practise course - recorded data from the wiimote and for a movment] See videos 2 and 3	Group
Wii Write Group	Wii Write Group : Gesture Recognition The purpose of this study is to introduce a novel approach for defining certain writing motions using gestural-lexical analysis from the acceleration and position values obtained from the Wii controllers. The major focus of this work is to be able to interpret the unique signatures each person makes when writing on air. (abstract)	Group

Video 2 :

Reconnaissance de mouvements 1/2

Uploaded by esieaLabs

[gesture recognition 1/2]

Video 3 :

Reconnaissance de mouvements 2/2
Uploaded by esieaLabs

[Gesture recognition [2/2]

Then, some articles related to gesture recognition with the wiimote :

Object [Title] Location	Article – [Wiizards : 3D gesture recognition for game play input ] / Drexel University, Philadelphia, PA U.S.A
WWW	Reference : LINK -Document (registering needed) : PDF
Author (date)	Louis Kratz, Matthew Smith , Frank J. Lee (2007/11)	Lang. : English
Abstract	"... The use of gestures provides intuitive and natural input mechanics for games, presenting an easy to learn yet richly immersive experience. In Wiizards, we explore the use of 3D accelerometer gestures in a multiplayer, zero sum game. Hidden Markov models are constructed for gesture recognition, providing increased flexibility and fluid tolerance. ..." (from abstract)
Comment	This article focuses on result of experimentation and on performance of the algorithm . The bigger movements steps for one gesture are, the longer learning step is.	Interest wwwww

Object [Title] Location	Article – [Gesture recognition with a Wii controller] / University of Oldenburg, Germany
WWW	Reference : LINK - Document (registering needed) : PDF
Author (date)	Thomas Schlömer, Benjamin Poppinga, Niels Henze, Susanne Boll (2008)	Lang. : English
Abstract	" We use the Wiimote's acceleration sensor independent of the gaming console for gesture recognition. The system allows the training of arbitrary gestures by users which can then be recalled for interacting with systems like photo browsing on a home TV. The developed library exploits Wii-sensor data and employs a hidden Markov model for training and recognizing user-chosen gestures. Our evaluation shows that we can already recognize gestures with a small number of training samples. In addition to the gesture recognition we also present our experiences with the Wii-controller and the implementation of the gesture recognition. ..." (from abstract)
Comment	This article focuses on implementation : filtering, quantization, HMM estimation and classification. Here, Wiigee is used.	Interest wwwww

Object [Title] Location	Article – [Exploring the Use of Tangible User Interfaces for Human-Robot Interaction: A Comparative Study] / University of Calgary, Canada
WWW	Reference : LINK - Document : PDF
Author (date)	Cheng Guo and Ehud Sharlin (2008)	Lang. : English
Abstract	"In this paper we suggest the use of tangible user interfaces (TUIs) for human-robot interaction (HRI) applications. We discuss the potential benefits of this approach while focusing on low-level of autonomy tasks. We present an experimental robotic interaction test bed to support our investigation. We use the test bed to explore two HRI-related task-sets: robotic navigation control and robotic posture control. We discuss the implementation of these two task-sets using an AIBO" robot dog..." (from abstract)
Comment	Analysis in progress	Interest wwwww

Finally, this video illustrates gesture recognition with 2 wii controllers :

Video 4 :

[YouTube : "Wiimote Gesture recognition" from (pseudo) BespokeSoftware]

Other readings around the web :

- Paul Taele's Blog on Gesture Recognition

- YouTube Video from (pseudo) oskeucew34 : "Wii-Based Gesture Recognition"

- The Nintendo Wii controller as an adaptive assistive device (Workshop Technical report from Steven Battersby (Nottingham Trent University, Nottingham, UK))