• 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 :

ÇѱÛÁ¦¸ñ(Korean Title) Å°³ØÆ® ¼¾¼­ ±â¹Ý ½´Æà °ÔÀÓÀ» À§ÇÑ ÆÈ Á¦½ºÃ³ ÀνÄ
¿µ¹®Á¦¸ñ(English Title) Arm Gesture Recognition for Shooting Games based on Kinect Sensor
ÀúÀÚ(Author) Á¶¼±¿µ   º¯Çý¶õ   ÀÌÈñ°æ   Â÷ÁöÈÆ   Sunyoung Cho   Hyeran Byun   Hee Kyung Lee   Jihun Cha  
¿ø¹®¼ö·Ïó(Citation) VOL 39 NO. 10 PP. 0796 ~ 0805 (2012. 10)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â Å°³ØÆ® ¼¾¼­·ÎºÎÅÍ È¹µæµÈ °üÀý Á¤º¸¸¦ ÀÌ¿ëÇÏ¿© ÆÈ Á¦½ºÃ³¸¦ ÀνÄÇÏ´Â ¹æ¹ýÀ» ³ªÅ¸³»°í, À̸¦ ½´Æà °ÔÀÓ¿¡ Àû¿ëÇÑ´Ù. À̸¦ À§ÇØ Á¦¾ÈµÈ 2-°èÃþ ¸ðµ¨¿¡¼­ °èÃþ1Àº Á¦½ºÃ³¿Í ºñÁ¦½ºÃ³ ÆÐÅÏÀ» HMM(Hidden Markov Model)À¸·Î ¸ðµ¨¸µÇÏ°í, HMM ±â¹ÝÀÇ ÀûÀÀÀû ÀÓ°èÄ¡ ¸ðµ¨À» ÅëÇØ Á¦½ºÃ³/ºñÁ¦½ºÃ³ ±¸ºÐ ¹× Á¦½ºÃ³ÀÇ ½ÃÀÛ°ú ³¡ ÁöÁ¡À» °ËÃâÇÑ´Ù. °èÃþ2´Â °èÃþ1¿¡¼­ Á¦°øÇÏ´Â Á¦½ºÃ³ ÀûÃâ Á¤º¸¿¡ ´ëÇØ CRF(Conditional Random Field)¸ðµ¨ ±â¹ÝÀ¸·Î Á¦½ºÃ³ ÀνÄÀ» ¼öÇàÇÑ´Ù. ƯÈ÷ Á¦½ºÃ³ ÀνÄÀÇ ¼º´É Çâ»óÀ» À§ÇØ CRF ¸ðµ¨ÀÇ ´©ÀûµÈ ½ÃÄö½º ±â¹Ý È®·ü °ª¿¡ ´Ù¼ö ÅõÇ¥ ±â¹ýÀ» Àû¿ëÇÔÀ¸·Î½á, À߸øµÈ ÀûÃâ Á¤º¸³ª Á¦½ºÃ³ º¯Çü¿¡¼­ ¹ß»ýÇÏ´Â ÀÎ½Ä ¿À·ù¸¦ ÁÙÀÌ°í ÀÎ½Ä ¼º´ÉÀ» Çâ»óÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¼º´ÉÀ» Æò°¡Çϱâ À§ÇØ, ½ÇÁ¦ ½´Æà °ÔÀÓ¿¡¼­ »ç¿ëµÇ´Â ±â´É¿¡ ´ëÇÑ ÆÈ Á¦½ºÃ³¸¦ Á¤ÀÇÇÏ°í, Å°³ØÆ® ¼¾¼­¸¦ ÀÌ¿ëÇÏ¿© µ¥ÀÌÅͼÂÀ» ¼öÁýÇÏ¿´´Ù. ½ÇÇè °á°ú, Á¦¾ÈÇÏ´Â ¹æ¹ýÀº ¿¬¼ÓµÈ ÆÈ Á¦½ºÃ³ µ¥ÀÌÅÍ¿¡¼­ 97.54%ÀÇ ÀûÃâ·ü ¹× »çÀü¿¡ ÀûÃâµÈ ÆÈ Á¦½ºÃ³ µ¥ÀÌÅÍ¿¡¼­ 100%ÀÇ ³ôÀº ÀνķüÀ» º¸¿´´Ù. ¶ÇÇÑ, ±âÁ¸ÀÇ HMM ¹× CRF ¸ðµ¨°ú Á¦¾ÈÇÏ´Â ¸ðµ¨ÀÇ ÀÎ½Ä ¼º´ÉÀ» ºñ±³ÇÔÀ¸·Î½á, Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¿ì¼öÇÔÀ» ÀÔÁõÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper proposes a 2-layer gesture spotting and recognition model using data obtained from a kinect sensor and applies the model to the shooting game application. The layer1 models the gesture and non-gesture patterns using HMM and detects the start and end points of gesture using an adaptive threshold model based on HMM. Given a gesture segment from the layer1, the layer2 recognizes the gesture using CRF model. In particular, we propose the majority voting method for probabilities of accumulative sequences to reduce the errors and improve the recognition performance. To evaluate the performance of the proposed method, we define the arm gestures used in shooting game application and collect the dataset from a kinect sensor. The proposed method obtains the 97.54% spotting reliability and 100% recognition rate. We also compare the recognition rate between proposed model and HMM/CRF model to show the effectiveness of the proposed method.
Å°¿öµå(Keyword) ÆÈ Á¦½ºÃ³ ÀνĠ  2-°èÃþ Á¦½ºÃ³ ÀûÃâ ¹× ÀνĠ  Å°³ØÆ® ¼¾¼­   Arm gesture recognition   Two-layer gesture spotting and recognition   Kinect sensor  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå