Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
AlphaPose¸¦ È°¿ëÇÑ LSTM(Long Short-Term Memory) ±â¹Ý ÀÌ»óÇൿÀÎ½Ä |
¿µ¹®Á¦¸ñ(English Title) |
LSTM(Long Short-Term Memory)-Based Abnormal Behavior Recognition Using AlphaPose |
ÀúÀÚ(Author) |
¹èÇöÀç
Àå±ÔÁø
±è¿µÈÆ
±èÁøÆò
Hyun-Jae Bae
Gyu-Jin Jang
Young-Hun Kim
Jin-Pyung Kim
À̺¸Çö
±è¸í
Bo Hyun Lee
Myung Kim
¹èÇöÀç
Àå±ÔÁø
±è¿µÈÆ
±èÁøÆò
Hyun-Jae Bae
Gyu-Jin Jang
Young-Hun Kim
Jin-Pyung Kim
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 10 NO. 05 PP. 0187 ~ 0194 (2021. 05) |
Çѱ۳»¿ë (Korean Abstract) |
»ç¶÷ÀÇ ÇൿÀνÄ(Action Recognition)Àº »ç¶÷ÀÇ °üÀý ¿òÁ÷ÀÓ¿¡ µû¶ó ¾î¶² ÇൿÀ» ÇÏ´ÂÁö ÀνÄÇÏ´Â °ÍÀÌ´Ù. À̸¦ À§Çؼ ¿µ»ó󸮿¡ È°¿ëµÇ´Â ÄÄÇ»ÅÍ ºñÀü ŽºÅ©¸¦ È°¿ëÇÏ¿´´Ù. »ç¶÷ÀÇ ÇൿÀνÄÀº µö·¯´×°ú CCTV¸¦ °áÇÕÇÑ ¾ÈÀü»ç°í ´ëÀÀ¼ºñ½º·Î¼ ¾ÈÀü°ü¸® ÇöÀå ³»¿¡¼µµ Àû¿ëµÉ ¼ö ÀÖ´Ù. ±âÁ¸¿¬±¸´Â µö·¯´×À» È°¿ëÇÏ¿© »ç¶÷ÀÇ °üÀý Å°Æ÷ÀÎÆ® ÃßÃâÀ» ÅëÇÑ ÇൿÀÎ½Ä ¿¬±¸°¡ »ó´ëÀûÀ¸·Î ºÎÁ·ÇÑ »óÅÂÀÌ´Ù. ¶ÇÇÑ ¾ÈÀü°ü¸® ÇöÀå¿¡¼ ÀÛ¾÷ÀÚ¸¦ Áö¼ÓÀûÀÌ°í ü°èÀûÀ¸·Î °ü¸®Çϱ⠾î·Á¿î ¹®Á¦Á¡µµ ÀÖ¾ú´Ù. º» ³í¹®¿¡¼´Â ÀÌ·¯ÇÑ ¹®Á¦Á¡µéÀ» ÇØ°áÇϱâ À§ÇØ °üÀý Å°Æ÷ÀÎÆ®¿Í °üÀý ¿òÁ÷ÀÓ Á¤º¸¸¸À» ÀÌ¿ëÇÏ¿© À§Çè ÇൿÀ» ÀνÄÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÏ°íÀÚ ÇÑ´Ù. ÀÚ¼¼ÃßÁ¤¹æ¹ý(Pose Estimation)ÀÇ ÇϳªÀÎ AlphaPose¸¦ È°¿ëÇÏ¿© ½Åü ºÎÀ§ÀÇ °üÀý Å°Æ÷ÀÎÆ®¸¦ ÃßÃâÇÏ¿´´Ù. ÃßÃâµÈ °üÀý Å°Æ÷ÀÎÆ®¸¦ LSTM(Long Short-Term Memory) ¸ðµ¨¿¡ ¼øÂ÷ÀûÀ¸·Î ÀÔ·ÂÇÏ¿© ¿¬¼ÓÀûÀÎ µ¥ÀÌÅÍ·Î ÇнÀÀ» ÇÏ¿´´Ù. ÇൿÀÎ½Ä Á¤È®·üÀ» È®ÀÎÇÑ °á°ú ¡°´©¿öÀÖ±â(Lying Down)¡± ÇൿÀÎ½Ä °á°úÀÇ Á¤È®µµ°¡ ³ôÀ½À» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
A person's behavioral recognition is the recognition of what a person does according to joint movements. To this end, we utilize computer vision tasks that are utilized in image processing. Human behavior recognition is a safety accident response service that combines deep learning and CCTV, and can be applied within the safety management site. Existing studies are relatively lacking in behavioral recognition studies through human joint keypoint extraction by utilizing deep learning. There were also problems that were difficult to manage workers continuously and systematically at safety management sites. In this paper, to address these problems, we propose a method to recognize risk behavior using only joint keypoints and joint motion information. AlphaPose, one of the pose estimation methods, was used to extract joint keypoints in the body part. The extracted joint keypoints were sequentially entered into the Long Short-Term Memory (LSTM) model to be learned with continuous data. After checking the behavioral recognition accuracy, it was confirmed that the accuracy of the "Lying Down" behavioral recognition results was high.
|
Å°¿öµå(Keyword) |
¾ÈÀü°ü¸®
ÇൿÀνÄ
Pose Estimation
LSTM
µö·¯´×
Safety Management
Action Recognition
Deep Learning
À½¾Ç °Ë»ö ¾Ë°í¸®Áò
½ÃÄö½ºÀÇ º¯°îÁ¡
½ÃÄö½º À¯»çµµ °è»ê
½ÃÄö½º ºñ±³
Music Search Algorithm
Sequence Similarity Calculation
Sequence Comparison
¾ÈÀü°ü¸®
ÇൿÀνÄ
Pose Estimation
LSTM
µö·¯´×
Safety Management
Action Recognition
Deep Learning
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|