• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document : 11 / 22 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¸ð³ë Ä«¸Þ¶ó ¿µ»ó±â¹Ý ½Ã°£ °£°Ý À©µµ¿ì¸¦ ÀÌ¿ëÇÑ ±¤¿ª ¹× Áö¿ª Ư¡ º¤ÅÍ Àû¿ë AdaBoost±â¹Ý Á¦½ºÃ³ ÀνÄ
¿µ¹®Á¦¸ñ(English Title) AdaBoost-based Gesture Recognition Using Time Interval Window Applied Global and Local Feature Vectors with Mono Camera
ÀúÀÚ(Author) Ȳ½ÂÁØ   °íÇÏÀ±   ¹éÁßȯ   Seung-Jun Hwang   Ha-Yoon Ko   Joong-Hwan Baek  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 03 PP. 0471 ~ 0479 (2018. 03)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù ¾Èµå·ÎÀ̵å, iOS µîÀÇ ¼ÂÅé¹Ú½º ±â¹ÝÀÇ ½º¸¶Æ® TV¿¡ ´ëÇÑ º¸±Þ¿¡ µû¶ó Á¦½ºÃ³·Î TV¸¦ ÄÁÆ®·Ñ ÇÒ ¼ö ÀÖ´Â »õ·Î¿î Á¢±ÙÀ» Á¦¾ÈÇÑ´Ù. º» ³í¹®¿¡¼­´Â ¸ð³ë Ä«¸Þ¶ó ¼¾¼­¸¦ ÀÌ¿ëÇÑ AdaBoost ±â¹Ý Á¦½ºÃ³ ÀνĿ¡ °üÇÑ ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÑ´Ù. ¿ì¼±, ½Åü ÁÂÇ¥ ÃßÃâÀ» À§ÇØ °¡¿ì½Ã¾È ¹è°æ Á¦°Å ¹× Camshift ±â¹Ý ÀÚ¼¼ ÃßÀû ¹× ÃßÁ¤ ¾Ë°í¸®ÁòÀ» »ç¿ëÇÑ´Ù. AdaBoost ÇнÀ ¸ðµ¨À» ½Åü Á¤±ÔÈ­µÈ ±¤¿ª ¹× Áö¿ª Ư¡ º¤ÅÍÀÇ ÁýÇÕÀ» Ư¡ ÆÐÅÏÀ¸·Î ÇÏ¿©, ¼Óµµ°¡ ´Ù¸¥ µ¿ÀÛµéÀ» ÀνÄÇÒ ¼ö ÀÖµµ·Ï ÇÏ¿´´Ù. ¶ÇÇÑ ¼Óµµ°¡ ´Ù¸¥ ´Ù¾çÇÑ Á¦½ºÃ³¸¦ ÀνÄÇϱâ À§ÇØ ´ÙÁß AdaBoost ¾Ë°í¸®ÁòÀ» Àû¿ëÇÏ¿´´Ù. CART ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÏ¿© ¼º°øÀûÀÎ Áß¿ä Ư¡ º¤Å͸¦ È®ÀÎÇÏ°í Áß¿äµµ°¡ ³·Àº Ư¡º¤Å͸¦ Á¦°ÅÇÏ´Â ¹æ½ÄÀ» Àû¿ëÇϸ鼭 ºÐ·ù ¼º°ø·üÀÌ ³ôÀº ÃÖÀûÀÇ Æ¯Â¡ º¤Å͸¦ Ž»öÇÏ¿´´Ù. ±× °á°ú 24°³ÀÇ ÁÖ¼ººÐ Ư¡ º¤Å͸¦ ã¾ÒÀ¸¸ç, ±âÁ¸ ¾Ë°í¸®Áò¿¡ ºñÇØ ³·Àº ¿ÀºÐ·ùÀ²(3.73%)°ú ³ôÀº Àνķü(95.17%)À» Áö´Ñ Ư¡ º¤ÅÍ ¹× ºÐ·ù±â¸¦ ¼³°èÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Recently, the spread of smart TV based Android iOS Set Top box has become common. This paper propose a new approach to control the TV using gestures away from the era of controlling the TV using remote control. In this paper, the AdaBoost algorithm is applied to gesture recognition by using a mono camera. First, we use Camshift-based Body tracking and estimation algorithm based on Gaussian background removal for body coordinate extraction. Using global and local feature vectors, we recognized gestures with speed change. By tracking the time interval trajectories of hand and wrist, the AdaBoost algorithm with CART algorithm is used to train and classify gestures. The principal component feature vector with high classification success rate is searched using CART algorithm. As a result, 24 optimal feature vectors were found, which showed lower error rate (3.73%) and higher accuracy rate (95.17%) than the existing algorithm.
Å°¿öµå(Keyword) 3D Á¦½ºÃ³ ÀνĠ  ÆÐÅÏ ÀνĠ  ±â°è ÇнÀ   AdaBoost ¾Ë°í¸®Áò   ½Åü ºÐÇÒ   3D Gesture Recognition   Pattern Recognition   Machine Learning   AdaBoost   Body Segmentation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå