Abstract
The aim of this research to develop a real-time, robust, vision based hand-gesture control system capable of operating in different living room environments including low light conditions, and using inexpensive hardware components. The system is designed for remote control of a TV set-top box using a preset gesture vocabulary. A camera is located above a TV screen, across from the user. Gestures may be performed from anywhere within the sensors field of view, without the requirement that the operator obtain visual or auditory feedback. The system is capable of using either a near-IR or a visible color webcam. Hand tracking is based on a modified CAMShift algorithm with face detection and blocking. Gesture classification is based on a limited number of gesture motion trajectory features using a tree-based classifier ensemble, and a modified Longest Common Subsequence (LCS) method. Preliminary testing and evaluation of the systems real time operation is reported.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010 |
| Pages | 687-693 |
| Number of pages | 7 |
| Volume | 2 |
| State | Published - 1 Dec 2010 |
| Event | 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010 - Las Vegas, NV, United States Duration: 12 Jul 2010 → 15 Jul 2010 |
Conference
| Conference | 2010 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2010 |
|---|---|
| Country/Territory | United States |
| City | Las Vegas, NV |
| Period | 12/07/10 → 15/07/10 |
Keywords
- Gesture recognition
- Hand tracking
- LCS
- TV control
- Tree-based ensemble classifier
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Vision and Pattern Recognition