Abstract
In order to extract complex human motion precisely, multiple cameras are often used to capture the video sequences, then tracking and reconstruction of human motion can be achieved by virtue of the multi-view video sequences.[1] The self-occlusion problem that occurred during tracking can also be solved with the multi-view pattern. Multiple views mean that the same scene is captured with the same sampling rate from different viewpoints. According to the principle of vision, multiple corresponding image feature points are competent for reconstructing 3D coordinates of feature points accurately. Therefore, compared with monocular video sequence, 3D reconstruction is easier under multi-viewpoints. However, difficulties of feature correspondence and self-occlusion also exist in the tracking of multi-view video sequences. Especially, the automatic corresponding of multiple views is still a challenging issue. In this chapter, we intend to give readers more insight into the two-camera-based human motion capture as well as the VBHAS V3.0 (Video-based Human Animation).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kakadiaris A, Metaxas D. 3D human body model acquisition from multiple views. In: ICCV’95, pp. 618–623, IEEE Computer Society, 1995.
Liu X, Zhuang Y, Pan Y. Video based human animation technique. In: ACM Multimedia, pp. 353–362, ACM Press, 1999.
Bregler C, Malik J. Tracking people with twists and exponential maps. In: CVPR’98, pp. 8–15, IEEE Computer Society, 1998.
Fua P, Gruen A, Plankers R, Apuzzo N, Thalmann D. Human body modeling and motion analysis from video sequences. International Archives of Photogrammetry and Remote Sensing, 32(B5): 866–873, 1998.
Wren C, Azarbayejani A, Darrell T, Pentland A. Pfinder. real-time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7): 780–785, 1997.
Intille SS, Bobick AF. Closed world tracking. In: ICCV’95, pp. 672–678, IEEE Computer Society, 1995.
Rehg J, Kanade T. Model-based tracking of self-occluding articulated objects. In: ICCV’95, pp. 612–617, IEEE Computer Society, 1995.
Yonemoto S, Tsuruta N, Taniguchi R. Tracking of 3D multi-part objects using multiple viewpoint time-varying sequences. In: ICPR’98, pp. 490–494, IEEE Computer Society, 1998.
Sabel J. Optical 3D motion measurement. In: IEEE Instrumentation and Measurement Technology Conference, pp. 367–370, IEEE Computer Society, 1996.
Tsai RY. A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses. IEEE Journals of Robotics and Animation, RA-3 (4): 323–344, 1987.
More J. The Levenberg-Marquardt algorithm: implementation and theory. In: G. A. Waston ed., Lecture Notes in Mathematics 630: numerical analysis, Springer-Verlag, pp. 105–116, 1978.
Rights and permissions
Copyright information
© 2008 Zhejiang University Press, Hangzhou and Springer-Verlag GmbH Berlin Heidelberg
About this chapter
Cite this chapter
(2008). Two-camera-based Human Motion Capture. In: A Modern Approach to Intelligent Animation. Advanced Topics in Science and Technology in China. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73760-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-73760-5_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73759-9
Online ISBN: 978-3-540-73760-5
eBook Packages: Computer ScienceComputer Science (R0)