A Gesture Recognition Approach for Wheelchair Users in an Exergame

Author(s)

Szykman, Alexandre Greluk ; Brandao, Andre Luiz ; Gois, Joao Paulo ; IEEE

• Document type: Journal article
• Source: 2018 17TH BRAZILIAN SYMPOSIUM ON COMPUTER GAMES AND DIGITAL ENTERTAINMENT (SBGAMES 2018); v. N/A, p. 10-pg., 2018-01-01.

Abstract

Studies indicate that playing exergames, games that use technologies of gesture recognition to incentive exercising, can improve multiple skills of the players. However, when players are wheelchair users, interactive gesture recognition is an issue not sufficiently explored. There are already exergames explicitly developed for wheelchair users, but until 2016, as far as we know, there was no game that explored the users' gesture movements in the digital game characters. In this work, we present our approach for gesture recognition of wheelchair users. It uses a depth sensor to track specific movements from wheelchair users. We employ those movements to interact with the game character. Results suggest that our technique, despite its simplicity, provides interactive frame rates while being also efficient. (AU)

• FAPESP's process: 14/11067-1 - Development of methods for interactive modeling 2.5D Cartoon models with lighting support
• Grantee: João Paulo Gois
• Support Opportunities: Regular Research Grants