Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)
ÇѱÛÁ¦¸ñ(Korean Title) |
´ÙÁß Å°³ØÆ® ¼¾¼ ±â¹ÝÀÇ ¿îµ¿ ÀÚ¼¼ ÃßÁ¤ ½Ã½ºÅÛ ¼³°è ¹× ±¸Çö |
¿µ¹®Á¦¸ñ(English Title) |
Design and Development of the Multiple Kinect Sensor-based Exercise Pose Estimation System |
ÀúÀÚ(Author) |
Á¶¿ëÁÖ
¹Ú°æ½Å
Yongjoo Cho
Kyoung Shin Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 21 NO. 03 PP. 0558 ~ 0567 (2017. 03) |
Çѱ۳»¿ë (Korean Abstract) |
º» ¿¬±¸¿¡¼´Â ´Ù¼öÀÇ Å°³ØÆ® ¼¾¼¸¦ ÀÌ¿ëÇÏ¿© È¿À²ÀûÀÎ ½Ç½Ã°£ ¿îµ¿ ÀÚ¼¼ ÃßÁ¤ ½Ã½ºÅÛÀ» ¼³°èÇÏ°í °³¹ßÇÏ¿´´Ù. ÀÌ ½Ã½ºÅÛÀº Á¤¸é°ú Ãø¸é¿¡ Å°³ØÆ® ¼¾¼¸¦ »ç¿ëÇÏ¿©, ÇÑ °³·Î ÃßÀûÀÌ ¾î·Á¿ü´ø »ç¿ëÀÚÀÇ Æ¯Á¤ ÀÚ¼¼ (¿¹¸¦ µé¾î, ¹«¸ Äà ¶Ç´Â ·±Áö)¸¦ º¸´Ù Á¤È®ÇÏ°Ô ÃøÁ¤ÇÏ°í ÀνÄÇÏ´Â °ÍÀ» ¸ñÀûÀ¸·Î ÇÑ´Ù. ±×¸®°í ÃßÈÄ ´Ù¾çÇÑ ÀÚ¼¼¸¦ Áö¿øÇÒ ¼ö ÀÖµµ·Ï È®Àå °¡´ÉÇÏ°í ¸ðµâÈ µÈ ¹æ¹ýÀ¸·Î ¼³°èµÇ¾ú´Ù. ÀÌ ½Ã½ºÅÛÀº ¿©·¯ Ŭ¶óÀ̾ðÆ®¿Í À¯´ÏƼ 3D ¼¹ö·Î ±¸¼ºµÈ´Ù. Ŭ¶óÀ̾ðÆ®´Â Å°³ØÆ® °ñ°Ý µ¥ÀÌÅ͸¦ ó¸®ÇÏ¿© ¼¹ö·Î Àü¼ÛÇÑ´Ù. ¼¹ö´Â ´ÙÁß Å°³ØÆ®¸¦ º¸Á¤ÇÏ°í, °¢µµ¿Í °Å¸®¸¦ ±â¹ÝÀ¸·Î ÇÑ Æ¯Â¡ °ª ÃßÃâÇÏ¸ç ¿©·¯ ´ëÀÇ Å°³ØÆ®·ÎºÎÅÍ °è»êµÈ Ư¡ °ªÀÇ °¡Áß Æò±ÕÀ» »ç¿ëÇÏ¿© ÀÚ¼¼ ÀÎ½Ä ¸ðµ¨À» ±â¹ÝÀ¸·Î ÀÚ¼¼ ÃßÁ¤ ¾Ë°í¸®ÁòÀ» Àû¿ëÇÑ´Ù. º» ³í¹®Àº ´ÙÁß Å°³ØÆ® ¼¾¼¸¦ ÀÌ¿ëÇÑ Àΰ£ ¿îµ¿ ÀÚ¼¼ ÃßÁ¤ ½Ã½ºÅÛÀÇ ¼³°è ¹× ±¸Çö ¹æ¹ýÀ» Á¦½ÃÇÏ°í, üÇèÇü À¯´ÏƼ 3D ¿îµ¿ °ÔÀÓ¿¡ Àû¿ëÇÑ ¿¹½Ã¸¦ ¼³¸íÇÑ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In this research, we developed an efficient real-time human exercise pose estimation system using multiple Kinects. The main objective of this system is to measure and recognize the user¡¯s posture (such as knee curl or lunge) more accurately by employing Kinects on the front and the sides. Especially it is designed as an extensible and modular method which enables to support various additional postures in the future. This system is configured as multiple clients and the Unity3D server. The client processes Kinect skeleton data and send to the server. The server performs the multiple-Kinect calibration process and then applies the pose estimation algorithm based on the Kinect-based posture recognition model using feature extractions and the weighted averaging of feature values for different Kinects. This paper presents the design and implementation of the human exercise pose estimation system using multiple Kinects and also describes how to build and execute an interactive Unity3D exergame.
|
Å°¿öµå(Keyword) |
¸ÖƼ Å°³ØÆ® ¼¾¼
¿îµ¿ ÀÚ¼¼ ÃßÁ¤
´ëÈÇü ¿îµ¿
¿îµ¿ ÀÀ¿ëÇÁ·Î±×·¥
Multiple Kinect sensors
Exercise Pose Estimation
Interactive Exercise
Fitness Applications
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|