Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)
ÇѱÛÁ¦¸ñ(Korean Title) |
CONDENSATION ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÑ ÀÔÀÚÇÊÅÍ ±â¹Ý µ¿ÀÛ ÀÎ½Ä ¿¬±¸ |
¿µ¹®Á¦¸ñ(English Title) |
A Study on the Gesture Recognition Based on the Particle Filter Using CONDENSATION Algorithm |
ÀúÀÚ(Author) |
À̾ç¿ø
Yang-Weon Lee
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 11 NO. 03 PP. 0584 ~ 0591 (2007. 03) |
Çѱ۳»¿ë (Korean Abstract) |
¿¬¼ÓµÇ´Â À̹ÌÁö Áß¿¡¼ Àΰ£ÀÇ µ¿ÀÛÀ» ÀνÄÇÏ´Â °ÍÀº Àΰ£°ú ÄÄÇ»ÅÍÀÇ »óÈ£ ÀÛ¿ë¿¡¼ ¸Å¿ì Áß¿äÇÏ°í µµÀüÇÒ ºÐ¾ßÀÌ´Ù. º» ³í¹®¿¡¼´Â CONDENSATION ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÏ¿© ÀÔÀÚ ÇÊÅÍ(particle filter)¿¡ ±â¹ÝÇÑ µ¿ÀÛ ÀÎ½Ä ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÑ´Ù. ÀÔÀÚ ÇÊÅÍ´Â Á¶°Ç È®·ü ÀüÆÄ ¸ðµ¨(Conditional Density Propagation)ÀÎ º£À̽þÈ(Bayesian) ÃßÁ¤ ±ÔÄ¢À» Àû¿ëÇÏ´Â ÃßÀû±¸Á¶¸¦ °®°í Àֱ⠶§¹®¿¡ ÀϹÝÀûÀ¸·Î ±âÁ¸ ÃßÀû ¾Ë°í¸®Áòº¸´Ù ¶Ù¾î³ ¼º´ÉÀ» °®´Â °æÇâÀÌ ÀÖ´Ù. º» ³í¹®¿¡¼´Â ¾Ë°í¸®ÁòÀÇ ¼º´É Æò°¡¸¦ À§Çؼ µÎ °³ÀÇ µ¿ÀÛ ¸ðµ¨À» °¡Á¤ÇÏ¿´°í, ¿µ»ó¿¡ ´ëÇÑ Àü󸮸¦ À§Çؼ´Â MATLAB¸¦ ÀÌ¿ëÇÏ¿´À¸¸ç ÀÔÀÚÇÊÅÍ´Â °í¼Ó 󸮸¦ À§ÇÏ¿© C ·Î ±¸ÇöÇÏ¿´´Ù. µÎ °³ÀÇ µ¿ÀÛ ½ÇÇè °á°ú¸¦ ÅëÇØ, µ¿ÀÛ ÀÎ½Ä ÀÔÀÚ ÇÊÅÍ°¡ ±ÙÁ¢ÇÑ µ¿ÀÛ È¯°æ ¼Ó¿¡¼ °ÀÎÇÑ ÃßÀû ¼º´ÉÀ» ³ªÅ¸³¿À» È®ÀÎÇÏ¿´´Ù. |
¿µ¹®³»¿ë (English Abstract) |
The recognition of human gestures in image sequences is an important and challenging problem that enables a host of human-computer interaction applications. This paper describes a gesture recognition algorithm based on the particle filters, namely CONDENSATION. The particle filter is more efficient than any other tracking algorithm because the tracking mechanism follows Bayesian estimation rule of conditional probability propagation. We used two models for the evaluation of particle filter and apply the MAILAB for the preprocessing of the image sequence. But we implement the particle filter using the C to get the high speed processing. In the experimental results, it is demonstrated that the proposed algorithm prove to be robust in the cluttered environment. |
Å°¿öµå(Keyword) |
Gesture recognition
particle filter
CONDENSATION
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|