%0 Conference Proceedings
%T Instant First-Person Posture Estimation
%+ Graduate School of Science & Technology
%+ Faculty of Science and Engineering
%A Serizawa, Takafumi
%A Yanagida, Yasuyuki
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 9th International Conference on Entertainment Computing (ICEC)
%C Seoul, South Korea
%Y Hyun Seung Yang; Rainer Malaka; Junichi Hoshino; Jung Hyun Han
%I Springer
%3 Entertainment Computing - ICEC 2010
%V LNCS-6243
%P 508-510
%8 2010-09-08
%D 2010
%R 10.1007/978-3-642-15399-0_75
%K posture estimation
%K motion tracking
%K Marker-less
%K Calibration-free
%Z Computer Science [cs]/Digital Libraries [cs.DL]Conference papers
%X We propose an instant posture estimation technique, which can operate only by a stereo image with small (6 cm) baseline. It does not require a priori information of the target user, background information, and markers. This system allows cameras to move freely, because it operates only with a small stereo camera unit. Moreover, if the input image is replaced with a movie or real-time video, this system can be used as a real-time motion tracker. With our proposed technique, robots and computers will be able to non-verbally communicate with unspecified people as well as pre-registered people. Moreover, this system can output not only the posture but also the body size and clothes. Therefore, proposed technique can also be used as a calibration procedure for other motion tracking algorithms.
%G English
%2 https://inria.hal.science/hal-01055585/document
%2 https://inria.hal.science/hal-01055585/file/icec2010_submission_97.pdf
%L hal-01055585
%U https://inria.hal.science/hal-01055585
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-LNCS-6243
%~ IFIP-ICEC
%~ IFIP-2010