Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
½Ã°¢Àå¾ÖÀÎ º¸Á¶¸¦ À§ÇÑ ¿µ»ó±â¹Ý ÈÞ¸Õ Çൿ ÀÎ½Ä ½Ã½ºÅÛ |
¿µ¹®Á¦¸ñ(English Title) |
Image Based Human Action Recognition System to Support the Blind |
ÀúÀÚ(Author) |
°íº´Ã¶
Ȳ¹Îö
³²Àç¿
ByoungChul Ko
Mincheol Hwang
Jae-Yeal Nam
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 42 NO. 01 PP. 0138 ~ 0143 (2015. 01) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ½Ã°¢Àå¾ÖÀÎÀÇ Àå¸éÀÎ½Ä º¸Á¶¸¦ À§ÇØ, ±Í°ÉÀÌ Çü ºí·çÅõ¼ö Ä«¸Þ¶ó¿Í ÇൿÀÎ½Ä ¼¹ö°£ÀÇ Åë½ÅÀ» ÅëÇØ ÈÞ¸ÕÀÇ ÇൿÀ» ÀνÄÇÏ´Â ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. ¸ÕÀú ½Ã°¢Àå¾ÖÀÎÀÌ ±Í°ÉÀÌ Çü ºí·çÅõ¼ö Ä«¸Þ¶ó¸¦ ÀÌ¿ëÇÏ¿© ¿øÇÏ´Â À§Ä¡ÀÇ Àå¸éÀ» ÃÔ¿µÇϸé, ÃÔ¿µµÈ ¿µ»óÀº Ä«¸Þ¶ó¿Í ¿¬µ¿µÈ ½º¸¶Æ® ÆùÀ» ÅëÇØ Àνļ¹ö·Î Àü¼ÛµÈ´Ù. ÀÎ½Ä ¼¹ö¿¡¼´Â ¿µ»ó ºÐ¼® ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÏ¿© ÈÞ¸Õ ¹× °´Ã¼¸¦ °ËÃâÇÏ°í ÈÞ¸ÕÀÇ Æ÷Á ºÐ¼®ÇÏ¿© ÈÞ¸Õ ÇൿÀ» ÀνÄÇÑ´Ù. ÀÎ½ÄµÈ ÈÞ¸Õ Çൿ Á¤º¸´Â ½º¸¶Æ® Æù¿¡ Àç Àü¼ÛµÇ°í »ç¿ëÀÚ´Â ½º¸¶Æ® ÆùÀ» ÅëÇØ text-to-speech (TTS)·Î Àνİá°ú¸¦ µè°Ô µÈ´Ù. º» ³í¹®¿¡¼ Á¦¾ÈÇÑ ½Ã½ºÅÛ¿¡¼´Â ½Ç³» ¿Ü¿¡¼ ÃÔ¿µµÈ ½ÇÇèµ¥ÀÌÅÍ¿¡ ´ëÇؼ 60.7%ÀÇ ÈÞ¸Õ Çൿ ÀÎ½Ä ¼º´ÉÀ» º¸¿© ÁÖ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In this paper we develop a novel human action recognition system based on communication between an ear-mounted Bluetooth camera and an action recognition server to aid scene recognition for the blind. First, if the blind capture an image of a specific location using theear-mounted camera, the captured image is transmitted to the recognition server using a smartphone that is synchronized with the camera. The recognition server sequentially performs human detection, object detection and action recognition by analyzing human poses . The recognized action information is retransmitted to the smartphone and the user can hear the action information through the text-to-speech (TTS). Experimental results using the proposed system showed a 60.7% action recognition performance on the test data captured in indoor and outdoor environments.
|
Å°¿öµå(Keyword) |
½Ã°¢Àå¾ÖÀÎ
ÈÞ¸Õ°ËÃâ
°´Ã¼ÀνÄ
ÇൿÀνÄ
The blind
human detection
object recognition
action recognition
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|