• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) µÅÁöÀÇ ºü¸¥ ÀÚ¼¼ °áÁ¤°ú ¸Ó¸® Á¦°Å¸¦ À§ÇÑ ¿µ»óó¸® ¹× µö·¯´× ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Image Processing and Deep Learning Techniques for Fast Pig¡¯s Posture Determining and Head Removal
ÀúÀÚ(Author) ¾ÈÇѼ¼   ÃÖ¿ø¼®   ¹Ú¼±È­   Á¤¿ëÈ­   ¹Ú´ëÈñ   Hanse Ahn   Wonseok Choi   Sunhwa Park   Yongwha Chung   Daihee Park  
¿ø¹®¼ö·Ïó(Citation) VOL 08 NO. 11 PP. 0457 ~ 0464 (2019. 11)
Çѱ۳»¿ë
(Korean Abstract)
¾çµ· ¾÷°è¿¡¼­ µÅÁöÀÇ ¹«°Ô´Â °Ç°­À̳ª ¼ºÀå »óÅÂ, ÃâÇÏ ¿©ºÎ, »çÀ° ȯ°æ, »ç·á ¹è±ÞÀ» °áÁ¤ÇÏ´Â ÁÖ¿ä ¿äÀÎ Áß ÇϳªÀ̸ç, µû¶ó¼­ µÅÁöÀÇ ¹«°Ô¸¦ ÃøÁ¤ÇÏ´Â °ÍÀº µÅÁöÀÇ »ý»ê¼º Ãø¸é¿¡¼­ Áß¿äÇÑ ¹®Á¦ÀÌ´Ù. Top-view Ä«¸Þ¶ó¿¡¼­ ȹµæÇÑ ¿µ»óÀ¸·ÎºÎÅÍ µÅÁöÀÇ Çȼ¿ ¼ö¸¦ ÀÌ¿ëÇÏ¿© µÅÁöÀÇ ¹«°Ô¸¦ ÃøÁ¤ÇÏ°íÀÚ ÇÒ ¶§, Á¤È®ÇÑ Çȼ¿ ¼ö ÃøÁ¤¿¡ ¿µÇâÀ» ÁÖ´Â µÅÁöÀÇ ÀÚ¼¼¸¦ °áÁ¤ÇÒ ÇÊ¿ä°¡ ÀÖÀ¸¸ç, Çȼ¿ ¼ö ÃøÁ¤¿¡ ¿µÇâÀ» ÁÖ´Â ¸Ó¸® ºÎºÐÀ» Á¦°ÅÇÒ ÇÊ¿ä°¡ ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ºü¸¥ ¿µ»óó¸® ±â¹ýÀ» ÀÌ¿ëÇÏ¿© µÅÁöÀÇ ÀÚ¼¼¸¦ ºü¸£°Ô °áÁ¤ÇÏ°í, µö·¯´× ±â¹ÝÀÇ ºü¸¥ °´Ã¼Å½Áö ±â¹ýÀÎ YOLO¸¦ ÀÌ¿ëÇÏ¿© µÅÁö ¸Ó¸® À§Ä¡¸¦ ÆľÇÇÑ ÈÄ, °æ·®È­µÈ ¿µ»óó¸® ±â¹ýÀ» ÀÌ¿ëÇÏ¿© µÅÁöÀÇ ¸Ó¸®¿Í ¸öÅë °æ°è¸¦ ȹµæÇÏ°í ¸Ó¸®¸¦ Á¦°ÅÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Áï, ºü¸¥ ¿µ»óó¸® ±â¹ýÀ¸·Î ÀÌÁøÈ­µÈ µÅÁöÀÇ ¿µ»ó µ¥ÀÌÅÍ¿¡¼­ µÅÁöÀÇ ¸öÅë Áß½ÉÁ¡À¸·ÎºÎÅÍ µÅÁöÀÇ ¿Ü°û¼±±îÁöÀÇ ±æÀ̸¦ ºñ±³ÇÏ¿© µÅÁöÀÇ ÀÚ¼¼¸¦ °áÁ¤ÇÑ´Ù. ¶ÇÇÑ, µÅÁöÀÇ ¸Ó¸® À§Ä¡¸¦ ŽÁöÇϱâ À§ÇÏ¿© YOLO¸¦ ÀÌ¿ëÇÏ¿© ¿µ»ó µ¥ÀÌÅÍ ³»ÀÇ µÅÁöÀÇ ¸Ó¸®, ¸öÅë, ¾ûµ¢ÀÌÀÇ À§Ä¡¸¦ ÇнÀ½ÃŲ ÈÄ °ðÀº ÀÚ¼¼ÀÇ µÅÁö ¸Ó¸® À§Ä¡¸¦ ȹµæÇÏ°í ¸Ó¸® ¹Ù±ù ¿µ¿ªÀ» Á¦°ÅÇÑ´Ù. ¸¶Áö¸·À¸·Î Convex-hullÀ» ÀÌ¿ëÇÏ¿© µÅÁöÀÇ ¸Ó¸®¿Í ¸öÅë °æ°è¸¦ ÃßÁ¤ÇÑ ÈÄ, ¸Ó¸®¸¦ Á¦°ÅÇÑ´Ù. ½ÇÇè °á°ú, 0.98ÀÇ Á¤È®µµ¿Í 250.00fpsÀÇ ¼öÇà¼Óµµ·Î µÅÁöÀÇ ÀÚ¼¼¸¦ °áÁ¤ÇÏ¿´À¸¸ç, 0.96ÀÇ Á¤È®µµ¿Í 48.97fpsÀÇ ¼öÇà¼Óµµ·Î µÅÁöÀÇ ¸Ó¸®Å½Áö ¹× Á¦°Å°¡ °¡´ÉÇÔÀ» È®ÀÎÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
The weight of pig is one of the main factors in determining the health and growth state of pigs, their shipment, the breeding environment, and the ration of feed, and thus measuring the pig¡¯s weight is an important issue in productivity perspective. In order to estimate the pig¡¯s weight by using the number of pig¡¯s pixels form images, acquired from a Top-view camera, the posture determining and the head removal from images are necessary to measure the accurate number of pixels. In this research, we propose the fast and accurate method to determine the pig¡¯s posture by using a fast image processing technique, find the head location by using a fast deep learning technique, and remove pig¡¯s head by using a fast image processing technique, find the head location by using a fast deep learning technique, and remove pig¡¯s head by using light weighted image processing technique. First, we determine the pig¡¯s posture by comparing the length from the center of the pig¡¯s body to the outline of the pig in the binary image. Then, we train the location of pig¡¯s head, body, and hip in images using YOLO(one of the fast deep learning based object detector), and then we obtain the location of pig¡¯s head and remove an outside area of head by using head location. Finally, we find the boundary of head and body by using Convex-hull, and we remove pig¡¯s head. In the Experiment result, we confirmed that the pig¡¯s posture was determined with and accuracy of 0.98 and a processing speed of 250.00fps, and the pig¡¯s head was removed with an accuracy of 0.96 and a processing speed of 48.97fps.
Å°¿öµå(Keyword) ½Ç½Ã°£ µÅÁö ¸ð´ÏÅ͸µ   ÀÚ¼¼ °áÁ¤   ¸Ó¸® Á¦°Å   ¿µ»ó󸮠  µö·¯´×   YOLO   Real-Time Pig Monitoring   Posture Determining   Head Removal   Image Processing   Deep Learning   YOLO  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå