• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Current Result Document : 8 / 10 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¹Ýº¹ ÃÖ±ÙÁ¢Á¡¿Í ÆÄƼŬ ÇÊÅ͸¦ ÀÌ¿ëÇÑ Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀû
¿µ¹®Á¦¸ñ(English Title) Human Body Motion Tracking Using ICP and Particle Filter
ÀúÀÚ(Author) ±è´ëȯ   ±èÈ¿Á¤   ±è´ëÁø   Daehwan Kim   Hyojung Kim   Daijin Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 36 NO. 12 PP. 0977 ~ 0985 (2009. 12)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº ºü¸£°Ô ¿òÁ÷ÀÌ´Â Àΰ£ ½Åü¸¦ ÃßÀûÇÒ ¼ö ÀÖ´Â ½Ç½Ã°£ Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀû ¾Ë°í¸®µëÀ» Á¦¾ÈÇÑ´Ù. ¹Ýº¹ ÃÖ±ÙÁ¢Á¡(Iterative closest point) ¾Ë°í¸®µëÀº È¿À²ÀûÀÌ°í °è»ê·®ÀÌ Àû¾î ½Ç½Ã°£ Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀû¿¡ ÀûÇÕÇÏÁö¸¸ À߸øµÈ ÃÖ±ÙÁ¢Á¡(Closest point) ¼±ÅÃÀ¸·Î ÀÎÇØ ±¹ºÎÀû ÃÖ¼ÒÁ¡(Local minimum)¿¡ ½±°Ô ºüÁö°Ô µÇ¾î Á¾Á¾ ÃßÀû¿¡ ½ÇÆÐÇÏ°Ô µÈ´Ù. À̸¦ ±Øº¹Çϱâ À§ÇØ, ¹Ýº¹ ÃÖ±ÙÁ¢Á¡ ¾Ë°í¸®µë¿¡ ¿òÁ÷ÀÓ ÀÌ·Â(Motion history) Á¤º¸¸¦ ±â¹ÝÀ¸·Î ÇÑ ÆÄƼŬ ÇÊÅÍ (Particle filter)¸¦ °áÇÕÇÑ´Ù. Á¦¾ÈÇÏ´Â Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀûÀº °èÃþÀû Æ®¸® ±¸Á¶¸¦ »ç¿ëÇÔÀ¸·Î½á ½Åü ÃßÀû °ø°£ Å©±â¸¦ ÁÙ¿©ÁÖ¸ç, ¿òÁ÷ÀÓ ÀÌ·Â Á¤º¸¸¦ ÀÌ¿ëÇÑ ¿òÁ÷ÀÓ ¿¹Ãø ¸ðµ¨À» »ç¿ëÇÔÀ¸·Î½á ºü¸¥ Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀûÀ» °¡´ÉÇÏ°Ô ÇÑ´Ù. ½ÇÇè °á°ú´Â Á¦¾ÈÇÏ´Â Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀûÀÌ Á¤È®ÇÑ ÃßÀû ¼º´É°ú ºü¸¥ ¼ö·Å ¼Óµµ¸¦ °¡Áø´Ù´Â °ÍÀ» º¸¿© ÁØ´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper proposes a real-time algorithm for tracking the fast moving human body. Although Iterative closest point (ICP) algorithm is suitable for real-time tracking due to its efficiency and low computational complexity, ICP often fails to converge when the human body moves fast because the closest point may be mistakenly selected and trapped in a local minimum. To overcome such limitation, we combine a particle filter based on a motion history information with the ICP. The proposed human body motion tracking algorithm reduces the search space for each limb by employing a hierarchical tree structure, and enables tracking of the fast moving human bodies by using the motion prediction based on the motion history. Experimental results show that the proposed human body motion tracking provides accurate tracking performance and fast convergence rate.
Å°¿öµå(Keyword) Àΰ£ ½Åü ¿òÁ÷ÀÓ ÃßÀû   ¹Ýº¹ÃÖ±ÙÁ¢Á¡   ÆÄƼŬ ÇÊÅÍ   ¿òÁ÷ÀÓ ÀÌ·Â Á¤º¸   Àΰ£ ½Åü ¸ðµ¨   Human body motion tracking   ICP   particle filter   motion history information   human body model  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå