The Extraction Method of Major Articulation Points for 3D Interaction Games
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Action recognition technology has many application fields including gaming, human-computer interaction, security, virtual reality, etc. The technology has recently advanced and simplified by the introduction of real time depth cameras. The most famous depth camera, Kinect, has shown its success in human action recognitions by supervised learning methods. However, those method require a large number of motion capture data as the ground truth of each skeleton points. This paper proposes a human skeleton extraction method without using reference data. The method extracts the minimum number of articulation points instead of full skeleton data. The articulation points are used as an real-time interface for 3D interaction games.
Abstract
Action recognition technology has many application fields including gaming, human-computer interaction, security, virtual reality, etc. The technology has recently advanced and simplified by the introduction of real time depth cameras. The most famous depth camera, Kinect, has shown its success in human action recognitions by supervised learning methods. However, those method require a large number of motion capture data as the ground truth of each skeleton points. This paper proposes a human skeleton extraction method without using reference data. The method extracts the minimum number of articulation points instead of full skeleton data. The articulation points are used as an real-time interface for 3D interaction games.
참고문헌 (18)
- 윤현철, "Kinect 센서를 사용한 동작기반 게임 캐릭터 애니메이션", 한국컴퓨터게임학회논문지, 26(2), pp.147~153 (2013), (사)한국컴퓨터게임학회
- 박준석, "깊이 카메라를 이용한 상지 운동 게임", 한국컴퓨터게임학회논문지, 25(1), pp.61~66 (2012), (사)한국컴퓨터게임학회[DOI]
- 박영우, "키넥트 2.0을 활용한 게임 모션 라이브러리 툴 구축", 한국컴퓨터게임학회논문지, 28(2), pp.79~85 (2015), (사)한국컴퓨터게임학회
- Fengliang Xu, "Human Detection Using Depth and Gray Images", Proceedings of the IEEE Conference on Advanced Video and Signal Based Surveillance, pp.115~ (2003)
- A. Kar, "Skeletal tracking using Microsoft Kinect", ~ (2010)
- Shotton, Jamie, "Real-time human pose recognition in parts from single depth images", Communications of the ACM, 56(1), pp.116~124 (2013)
- Shotton, Jamie, "Efficient Human Pose Estimation from Single Depth Images", IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(12), pp.2821~2840 (2013)
- Sungphill Moon, "Multiple Kinect Sensor Fusion for Human Skeleton Tracking Using Kalman Filtering", International Journal of Advanced Robotic Systems, 13(65), pp.1~10 (2016)
- Wei Shen, "Unsupervised human skeleton extraction from Kinect depth images", Proceedings of the 4th International Conference on Internet Multimedia Computing and Service, pp.66~69 (2012)
- Du, Huan, "Digital Human Modeling. Applications in Health, Safety, Ergonomics and Risk Management", pp.15~23 (2014), Springer International Publishing
- Zhang, T. Y., "A fast parallel algorithm for thinning digital patterns", Communications of the ACM, 27(3), pp.236~239 (1984)
- Comaniciu, Dorin, "Mean shift: A robust approach toward feature space analysis", IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(5), pp.603~619 (2002)
- David Douglas, "Algorithms for the reduction of the number of points required to represent a digitized line or its caricature", The Canadian Cartographer, 10(2), pp.112~122 (1973)
- L. Breiman, "Random forests", Machine Learning, 45(1), pp.5~32 (2001)
- Bradski, Gary, "Learning OpenCV: Computer vision with the OpenCV library" (2008), O'Reilly Media, Inc
- "Kinect "Kinect SDK"" (2015)[URL]
- "Size Korea "Korean body"" (2015)[URL]
- "Web3D Consortium "h-anim"" (2015)[URL]