Multi-pointing Method Using a Desk Lamp and Single Camera for Effective Human-Computer Interaction

Authors:
Taehoun Song;Thien Cong Pham;Soonmook Jung;Jihwan Park;Keyho Kwon;Jaewook Jeon
Affiliations:
School of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea;School of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea;School of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea;School of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea;School of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea;School of Information and Communication Engineering, Sungkyunkwan University, Suwon, Korea
Venue:
Proceedings of the 13th International Conference on Human-Computer Interaction. Part III: Ubiquitous and Intelligent Interaction
Year:
2009

Citing 3
Cited 0

User performance in relation to 3D input device design

ACM SIGGRAPH Computer Graphics
Skin Color-Based Video Segmentation under Time-Varying Illumination

IEEE Transactions on Pattern Analysis and Machine Intelligence
Dual hand extraction using skin color and stereo information

ROBIO '09 Proceedings of the 2008 IEEE International Conference on Robotics and Biomimetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-pointing has become an important research interest, and is used in many computer applications to allow users to interact effectively with a program. Multi-pointing is used as an input method, and can also be fun and very user-friendly. However, in order to use the method, a complex and expensive hardware configuration is required. This paper presents a new and low cost method of multi-pointing based on a simple hardware configuration. Our method uses dual hand recognition, a table lamp, and a single CMOS camera. The table lamp provides a steady illumination environment for image processing, and the CMOS camera is mounted to maintain good stability. A single camera is used for dual hand recognition to achieve multi-pointing. Therefore, image processing does not require intensive computing which allows us to use a stand-alone system (including a 32 bit RISK processor). The results of the proposed method show that effective control navigation of applications such as Google Earth or Google Maps can be achieved.