Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
ÇѱÛÁ¦¸ñ(Korean Title) |
º¸Çà ¹æÇâ ¹× »óÅ ºÐ¼®À» À§ÇÑ º´·Ä °¡¿ì½º °úÁ¤ |
¿µ¹®Á¦¸ñ(English Title) |
Parallel Gaussian Processes for Gait and Phase Analysis |
ÀúÀÚ(Author) |
½ÅºÀ±â
Bong-Kee Sin
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 42 NO. 06 PP. 0748 ~ 0754 (2015. 06) |
Çѱ۳»¿ë (Korean Abstract) |
º» ¿¬±¸¿¡¼´Â ´ÙÁß »óÅ º¯¼öÀÇ Àμö HMMÀ» ÀϹÝÈÇÏ¿© ¿¬¼Ó Àº´Ð º¯¼ö¿Í ÀÌ»ê Àº´Ð º¯¼ö°¡ °áÇÕµÈ ¼øÂ÷ »óÅ ÃßÁ¤ ¸ðÇüÀ» Á¦¾ÈÇÏ°í ÀÌ¿¡ ±â¹ÝÇÑ º¸Çà µ¿ÀÛ ¸ðÇüÀ» ¼³°èÇÑ´Ù. À¯ÇÑ »óÅÂÀÇ ÀÌ»ê º¯¼ö´Â ¸¶¸£ÄÚÇÁ ¿¬¼â ±¸Á¶·Î º¸ÇàÀÇ µ¿¿ªÇÐÀû Ư¼ºÀ» Ç¥ÇöÇÏ°í °¢ ÀÌ»ê »óÅ¿¡ ´ëÇØ ¿¬¼Ó º¯¼ö¸¦ µ¶¸³ º¯¼ö·Î ÇÑ °¡¿ì½º °úÁ¤À» Á¤ÀÇÇÑ´Ù. ¸¶¸£ÄÚÇÁ »óÅ õÀÌ´Â ¿©·¯ °¡¿ì½º °úÁ¤ »çÀÌÀÇ ½ºÀ§ÄªÀ» Á¦¾îÇÏ¸ç °¢ °¡¿ì½º °úÁ¤Àº µ¿ÀÏÇÑ ÀÚ¼¼ÀÇ È¸Àü ¶Ç´Â ´Ù¾çÇÑ ½Ã°¢À» Ç¥ÇöÇÑ´Ù. ¿Â¶óÀÎ ÇÊÅ͸µ Ãß·ÐÀ» À§ÇØ ÀÔÀÚ ÇÊÅÍ ¹æ½ÄÀÇ Ãß·Ð ¾Ë°í¸®µëµµ Á¦½ÃÇÑ´Ù. ÀÌ ¾Ë°í¸®µëÀº ÀÔ·Â º¤ÅÍ ¿ÀÌ ÁÖ¾îÁ³À» ¶§ ÀÌµé º´·ÄÀû °¡¿ì½º °úÁ¤À» µ¿ÀûÀ¸·Î °¥¾ÆŸ´Â ½ºÀ§Äª ±ËÀûÀ» µðÄÚµù ÇØÁØ´Ù. ½ÇÇè °á°ú ºñ¼±ÇüÀû º¸ÇàÀÚ ºñµð¿À ¿µ»óÀ» º¸Çà ¹æÇâ°ú º¸Çà »óÅÂÀÇ ¿·Î ºÐ¸®ÇÏ¸ç ¸Å¿ì Á÷°üÀûÀÎ Çؼ®À» ÇÒ ¼ö ÀÖÀ½À» º¸¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
This paper proposes a sequential state estimation model consisting of continuous and discrete variables, as a way of generalizing all discrete-state factorial HMM, and gives a design of gait motion model based on the idea. The discrete state variable implements a Markov chain that models the gait dynamics, and for each state of the Markov chain, we created a Gaussian process over the space of the continuous variable. The Markov chain controls the switching among Gaussian processes, each of which models the rotation or various views of a gait state. Then a particle filter-based algorithm is presented to give an approximate filtering solution. Given an input vector sequence presented over time, this finds a trajectory that follows a Gaussian process and occasionally switches to another dynamically. Experimental results show that the proposed model can provide a very intuitive interpretation of video-based gait into a sequence of poses and a sequence of posture states.
|
Å°¿öµå(Keyword) |
º¸Çà µ¿ÀÛ ºÐ¼®
°¡¿ì½º °úÁ¤
¸¶¸£ÄÚÇÁ ¿¬¼â
ÀÔÀÚ ÇÊÅÍ
von Mises ºÐÆ÷
human gait analysis
Gaussian process
Markov chain
particle filter
von Mises distribution
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|