Á¤º¸°úÇÐȸ ³í¹®Áö C : ÄÄÇ»ÆÃÀÇ ½ÇÁ¦
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
À̵¿Çü Á¤º¸ Áõ° ½Ã½ºÅÛÀ» À§ÇÑ ½Ç½Ã°£ Àå¼Ò ÀÎ½Ä |
¿µ¹®Á¦¸ñ(English Title) |
Real-Time Place Recognition for Augmented Mobile Information Systems |
ÀúÀÚ(Author) |
¿À¼öÁø
³²¾çÈñ
Sujin Oh
Yanghee Nam
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 14 NO. 05 PP. 0477 ~ 0481 (2008. 07) |
Çѱ۳»¿ë (Korean Abstract) |
À̵¿ Áß »ç¿ëÀÚ¿¡°Ô ÇÊ¿äÇÑ Á¤º¸¸¦ Á¦°øÇϱâ À§Çؼ´Â Àå¼Ò¸¦ ÀÎÁöÇÏ´Â ±â¼úÀÌ ÇÊ¿äÇÏ´Ù. º» ³í¹®¿¡¼´Â °Ç¹° ³»¿¡¼ À̵¿ÇÏ¸é¼ Ä«¸Þ¶ó¿¡ ÀÇÇØ Æ÷ÂøµÈ ¿µ»ó Á¤º¸¸¦ ºÐ¼®ÇÏ¿© ÇöÀç Àå¼Ò¸¦ ÆľÇÇÏ°í Ä«¸Þ¶ó ¿µ»ó¿¡ °ü·Ã Á¤º¸¸¦ Áõ°ÇÏ´Â ºñµð¿À ±â¹Ý ½Ç½Ã°£ Àå¼ÒÀÎ½Ä ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. ¿µ»óÀÇ Àü¿ªÀû Ư¡À» ÀÌ¿ëÇÑ ±âÁ¸ ¿¬±¸µéÀº Àå¸éÀÇ ºÎºÐÀûÀÎ Æó»öÀ̳ª ÀâÀ½¿¡ ¹Î°¨ÇÏ°í, ¹°Ã¼ÀνÄÀ» ÇàÇÏ´Â Áö¿ªÀû Ư¡ ÀÇÁ¸ ¹æ½ÄÀº °è»ê·®ÀÌ ¸¹¾Æ ½Ç½Ã°£ Àû¿ëÀÌ ¾î·Æ´Ù. ¶ÇÇÑ, ±×·¯ÇÑ Æ¯Â¡µé·ÎºÎÅÍ Àå¼ÒÀÎ½Ä °á°ú¸¦ µµÃâÇϱâ À§Çؼ´Â Åë°èÀû ±×·¡ÇÁ ±â¹Ý ¸ðµ¨À̳ª º£ÀÌ½Ã¾È ³×Æ®¿÷ µîÀÌ ÀÌ¿ëµÇ¾î ¿Ô´Âµ¥, ÀüÀÚÀÇ °æ¿ì Àå¼Ò À̵¿ÀÇ È®·üÀ» ¾ò±â À§ÇÑ ¸¹Àº Åë°è µ¥ÀÌŸ°¡ ÇÊ¿äÇϸç, ÈÄÀÚ´Â Àå¼Ò À̵¿ ¹®¸ÆÀ» È°¿ëÇÏÁö ¸øÇϹǷΠ¹°Ã¼ ÀÎ½Ä °á°ú¿¡¸¸ ÀÇÁ¸ÇÏ´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. º» ³í¹®¿¡¼´Â Àå¼Ò ¹®¸Æ Á¤º¸¸¦ È°¿ëÇÏ¸é¼ ¿µ»óÀÇ Áö¿ªÀû, Àü¿ªÀû Ư¡ÃßÃâ¹ýÀÇ °áÇÕÀ» ÅëÇØ ºÎºÐ Æó»ö ¹× ÀâÀ½¿¡ ´ëÇÑ Àü¿ªÀû ¹æ¹ýÀÇ ¹Î°¨¼ºÀ» º¸¿ÏÇÏ°í, Áö¿ªÀû ¹æ¹ýÀÇ ´À¸° 󸮼ӵµ¸¦ º¸¿ÏÇÑ ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈµÈ ¹æ¹ýÀ» °Ç¹° ³»ºÎ¸¦ À̵¿ÇÏ¸é¼ Àå¼Ò¿¡ ´ëÇÑ Á¤º¸¸¦ ¾ò´Â Á¤º¸Áõ° ½Ã½ºÅÛ¿¡ Àû¿ëÇÏ¿© ½Ç½Ã°£ ¼º´ÉÀ» È®ÀÎÇÏ¿´´Ù. |
¿µ¹®³»¿ë (English Abstract) |
Place recognition is necessary for a mobile user to be provided with place-dependent information. This paper proposes real-time video based place recognition system that identifies users' current place while moving in the building. As for the feature extraction of a scene, there have been existing methods based on global feature analysis that has drawback of sensitiveness for the case of partial occlusion and noises. There have also been local feature based methods that usually attempted object recognition which seemed hard to be applied in real-time system because of high computational cost. On the other hand, researches using statistical methods such as HMM(hidden Markov models) or bayesian networks have been used to derive place recognition result from the feature data. The former is, however, not practical because it requires huge amounts of efforts to gather the training data while the latter usually depends on object recognition only. This paper proposes a combined approach of global and local feature analysis for feature extraction to complement both approaches' drawbacks. The proposed method is applied to a mobile information system and shows real-time performance with competitive recognition result. |
Å°¿öµå(Keyword) |
Àå¼Ò ÀνÄ
À̵¿Çü Á¤º¸ Áõ° ½Ã½ºÅÛ
Àå¸é ºÐ·ù
º£ÀÌ½Ã¾È ºÐ·ù±â
¹é ¿ÀÇÁ Å°Æ÷ÀÎÆ®
place recognition
mobile system
scene classification
bayesian classifier
bag of keypoints
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|