Human-of-interest tracking system for natural interaction
- Authors
- Uhm, Taeyoung; Park, Hanhoon; Park, Jong-Il
- Issue Date
- Jan-2011
- Publisher
- IEEE
- Citation
- Digest of Technical Papers - IEEE International Conference on Consumer Electronics, pp.623 - 624
- Indexed
- SCOPUS
- Journal Title
- Digest of Technical Papers - IEEE International Conference on Consumer Electronics
- Start Page
- 623
- End Page
- 624
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/169229
- DOI
- 10.1109/ICCE.2011.5722775
- ISSN
- 0747-668X
- Abstract
- There have been considerable endeavors for robustly tracking human (his/her whole body's or body parts') gestures for achieving na tural human-computer interaction but it is still a challenging problem in vision-based research area. In particular, trackings electively o ne's-of-interest (or his/her body parts') gestures, which is necessary in multi-user applications, is more difficult and has been less developed. In this paper, we propose a simple yet effective method for human-of-interest tracking, which combines a background subtraction method using difference keying, a skin region detection method in YCbCr color space, a region-of-interest detection method using the depth information from infrared images, and a region classification method based on a set of Haar-like features and A daboost learning algorithm. Based on the proposed method, we built a proof-of-concept system. The system proved to be able to provide natural frontal-view interaction with one of interest in real-time and robustly in a cluttered indoor and multi-user environments. We expect that our interaction system can provide a practical solution for natural interaction with digital in formation display systems and interactive game or education systems.
- Files in This Item
-
Go to Link
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/169229)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.