Abstract
While computing power and transmission bandwidth have both been steadily increasing over the last few years, bandwidth rather than processing power remains the primary bottleneck for many complex multimedia applications involving communication. Current video coding algorithms use intelligent encoding to yield higher compression ratios at the cost of additional computing requirements for encoding and decoding. The use of techniques from the fields of computer vision and robotics such as object recognition, scene interpretation, and tracking can further improve compression ratios as well as provide additional information about the video sequence being transmitted. We used a new face tracking system developed in the robotics area to normalize a video sequence to centered images of the face. The face-tracking allowed us to implement a compression scheme based on Principal Component Analysis (PCA), which we call Orthonormal Basis Coding (OBC). We designed and implemented the face tracker and video codecs entirely in software. Our current implementation of OBC operates on recorded video sequences, making it appropriate for applications such as video email.
This is a preview of subscription content, log in via an institution to check access.
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
T. S. Huang and R. Lopez, “Computer vision in next generation image and video coding,” Lecture Notes in Computer Science, vol. 0, no. 1035, pp. 13–22, 1996.
“La visioconférence sur IP selon PictureTel et Intel,” 01 Reseaux, pp. 64–65, January 1998.
J. L. Crowley, “Integration and control of reactive visual processes,” Robotics and Autonomous Systems, vol. 16, no. 1, pp. 17–28, 1995.
J. L. Crowley, “Vision for man-machine interaction,” Robotics and Autonomous Systems, vol. 19, no. 3–4, pp. 347–358, 1997.
J. L. Crowley, “Multi-modal tracking of faces for video communications,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 640–645, June 1997.
ITU-T Study Group XV, “Recommendation H.263: Video coding for low bit rate communication,” tech. rep., Telecommunication Standardization Sector of the International Telecommunication Union, Geneva, Switzerland, http://www.itu.ch, 1996.
“The GZIP home page,” http://www.gzip.org, May 1998.
ITU-T Study Group XV, “Recommendation H.261: Video codec for audiovisual services at px64 kbit/s,” tech. rep., Telecommunication Standardization Sector of the International Telecommunication Union, Geneva, Switzerland, http://www.itu.ch, 1993.
ISO/IEC 11172-2, “Information technology-coding of moving pictures and associated audio for digital storage media at up to about 1,5 mbit/s-part 2: Video,” tech. rep., International Organization of Standardization, Geneva, Switzerland, http://www.iso.ch/cate/d22411.html, 1993.
“Berkeley MPEG research,” http://bmrc.berkeley.edu/projects/mpeg, 1997.
M. J. Turk and A. Pentland, “Eigenfaces for recognition,” in IFIP Working Conference on Engineering for Human-Computer Interaction, vol. 3, pp. 71–86, 1991.
M. Kirby and L. Sirovich, “Application of the karhunen-loeve procedure for the characterization of human faces,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, pp. 103–108, 1990.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Vieux, W.E., Schwerdt, K., Crowley, J.L. (1999). Face-Tracking and Coding for Video Compression. In: Computer Vision Systems. ICVS 1999. Lecture Notes in Computer Science, vol 1542. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-49256-9_10
Download citation
DOI: https://doi.org/10.1007/3-540-49256-9_10
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-65459-9
Online ISBN: 978-3-540-49256-6
eBook Packages: Springer Book Archive