• 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¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Æ®·£½ºÆ÷¸Ó¸¦ ÀÌ¿ëÇÑ 1¡¿1 Ãʱ¤´ë¿ª ¹«¼± ½ÅÈ£ ±â¹Ý »ç¶÷ÀÇ ÀÚ¼¼ ÃßÁ¤
¿µ¹®Á¦¸ñ(English Title) 1¡¿1 UWB-based Human Pose Estimation Using Transformer
ÀúÀÚ(Author) ±è½ÂÇö   ä±ÙÈ«   ½Å½Âȯ   ±èÀ¯¼º   Seunghyun Kim   Keunhong Chae   Seunghwan Shin   Yusung Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 49 NO. 04 PP. 0298 ~ 0304 (2022. 04)
Çѱ۳»¿ë
(Korean Abstract)
ƯÁ¤ °ø°£¿¡¼­ »ç¶÷ÀÇ ÀÚ¼¼¸¦ ÃßÁ¤ÇÏ´Â ¹®Á¦´Â ÄÄÇ»ÅÍ ºñÀüÀÇ ÁÖ¿ä ºÐ¾ß Áß Çϳª·Î °ÔÀÓ, ÀÇ·á, Àç³­, ¼Ò¹æ º¸¾È, ±º»ç µî ´Ù¾çÇÑ ºÐ¾ß¿¡ È°¿ëµÉ ¼ö ÀÖ´Â Áß¿äÇÑ ±â¼úÀÌ´Ù. ÃÖ±Ù ±â°è ÇнÀ°ú Á¢¸ñÇÏ¿© ÀÚ¼¼ ÃßÁ¤ÀÇ Á¤È®µµ¸¦ Å©°Ô ³ôÀÏ ¼ö ÀÖ¾ú´Ù. ÇÏÁö¸¸ À̹ÌÁö ±â¹ÝÀÇ ¹æ½ÄÀº ½ÅüÀÇ ÀϺΠ¶Ç´Â Àüü°¡ Àå¾Ö¹°·Î °¡·ÁÁö°Å³ª Á¶¸íÀÌ ¾îµÎ¿î °æ¿ì ÀÚ¼¼ ÃßÁ¤ÀÌ ¾î·Æ´Ù´Â ÇÑ°è°¡ ÀÖ´Ù. ÃÖ±Ù¿¡´Â ¹«¼± ½ÅÈ£¸¦ »ç¿ëÇÏ¿© »ç¶÷ÀÇ ÀÚ¼¼¸¦ ÃßÁ¤ÇÏ´Â ¿¬±¸°¡ µîÀåÇÏ¿´À¸¸ç ÀÌ´Â Á¶¸íÀÇ ¹à±â¿¡ ¿µÇâÀ» ¹ÞÁö ¾Ê°í Àå¾Ö¹°À» Åõ°úÇÒ ¼ö ÀÖ´Ù´Â ÀåÁ¡À» °¡Áö°í ÀÖ´Ù. ¹«¼± ½ÅÈ£¸¦ ±â¹ÝÀ¸·Î ƯÁ¤ À§Ä¡¸¦ ÃßÁ¤Çϱâ À§Çؼ­´Â µÎ ½Ö ÀÌ»óÀÇ ¼Û¼ö½Å±â°¡ ÇÊ¿äÇÏ´Ù´Â °ÍÀÌ ±âÁ¸ÀÇ ÀνÄÀ̾ú´Ù. º» ³í¹®¿¡¼­´Â ÇÑ ½ÖÀÇ ¼Û¼ö½Å±â·Î ¼öÁýÇÑ 1¡¿1 Ãʱ¤´ë¿ª ¹«¼± ½ÅÈ£¸¸À¸·Î µö ·¯´×À» Àû¿ëÇÏ¿© »ç¶÷ÀÇ ÀÚ¼¼ ÃßÁ¤ ¹× ½Åü ¼¼±×¸àÅ×À̼ÇÀÌ °¡´ÉÇÔÀ» º¸ÀδÙ. ¶ÇÇÑ Æ®·£½ºÆ÷¸Ó ±â¹Ý ¸ðµ¨À» ÅëÇØ ÇÕ¼º°ö ½Å°æ¸ÁÀ» ´ëüÇÏ°í ´õ ³ªÀº ¼º´ÉÀ» º¸ÀÌ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
The problem of estimating a human¡¯s pose in specific space from an image is one of the main area of computer vision and is an important technology that can be used in various fields such as games, medical care, disaster, fire fighting, and the military. By combining with machine learning, the accuracy of pose estimation has been greatly improved. However, the image-based approach has a limitation in that it is difficult to estimate pose when part or whole of the body is occluded by obstacles or when the lighting is dark. Recently, studies have emerged to estimate a human pose using wireless signals, which have the advantage of penetrating obstacles without being affected by brightness. The previous stereotype was that two or more pairs of transceivers are required to estimate a specific location based on wireless signals. This paper shows that it is possible to estimate the human pose and to perform body segmentation by applying deep learning only with 1x1 ultra wide band signals collected by 1¡¿1 transceiver. We also propose a method of replacing convolution neural networks and showing better performance through transformer models.
Å°¿öµå(Keyword) Ãʱ¤´ë¿ª ¹«¼± ½ÅÈ£   1¡¿1   Æ®·£½ºÆ÷¸Ó   »ç¶÷ÀÇ ÀÚ¼¼ ÃßÁ¤   ½Åü ¼¼±×¸àÅ×À̼Ǡ  ultra wide band   1¡¿1   transformer   human pose estimation   body segmentation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå