| ³í¹®¸í |
µö·¯´× ¹× ¿µ»óó¸® ±â¼úÀ» Ȱ¿ëÇÑ ÄÜÅ©¸®Æ® ±Õ¿ °ËÃâ ¹æ¹ý / A Method for Detecting Concrete Cracks using Deep-Learning and Image Processing |
| ÀúÀÚ¸í |
Á¤¼¿µ(Jung, Seo-Young) ; À̽½±â(Lee, Seul-Ki) ; ¹ÚÂùÀÏ(Park, Chan-Il) ; Á¶¼ö¿µ(Cho, Soo-Young) ; À¯Á¤È£(Yu, Jung-Ho) |
| ¼ö·Ï»çÇ× |
´ëÇѰÇÃàÇÐȸ³í¹®Áý ±¸Á¶°è, Vol.35 No.11 (2019-11) |
| ÆäÀÌÁö |
½ÃÀÛÆäÀÌÁö(163) ÃÑÆäÀÌÁö(8) |
| ÁÖÁ¦¾î |
ÄÜÅ©¸®Æ® ±Õ¿; ±Õ¿ °ËÃâ; µö·¯´×; ¿µ»óó¸®; ÇÕ¼º°ö½Å°æ¸Á ; Concrete Crack; Crack Detection; Deep Learning; Image Processing; CNN |
| ¿ä¾à1 |
ÇöÇà ±Õ¿Á¶»ç ¾÷¹«´Â À°¾ÈÁ¶»ç·Î ÀÌ·ç¾îÁö°í ÀÖ¾î Á¡°ËÀÚÀÇ ÁÖ°üÀÌ °³ÀԵǾî Á¡°Ë °á°ú¿¡ Â÷À̰¡ ¹ß»ýÇϰųª, ÃøÁ¤¿ÀÂ÷°¡ ¹ß»ýÇÒ ¿©Áö°¡ ÀÖ´Ù. ÀÌ¿¡ º» ¿¬±¸´Â ÄÜÅ©¸®Æ® ±Õ¿ Á¶»çÀÇ °´°ü¼º°ú È¿À²¼ºÀ» ³ôÀ̱â À§ÇÏ¿© µö·¯´× ³×Æ®¿öÅ© Áß ½Ç½Ã°£ ºÐ¼®ÀÌ °¡´ÉÇÑ YOLO v.2¸¦ Ȱ¿ëÇÏ¿© ±Õ¿À» ÀÎÁöÇϰí, ¿µ»óó¸® ±â¼úÀ» Ȱ¿ëÇÏ¿© ±Õ¿ÀÇ Æ¯¼ºÁ¤º¸¸¦ ÃßÃâÇÏ´Â ÇÁ·Î¼¼½º¸¦ Á¦½ÃÇÏ¿´´Ù. ½ÇÇè °á°ú, ½Ç½Ã°£ ºÐ¼®ÀÌ °¡´ÉÇÑ °ËÃâ¼Óµµ¿Í Á¤È®µµ¸¦ È®º¸ÇÒ ¼ö ÀÖ¾ú´Ù. º» ¿¬±¸ÀÇ °á°ú´Â ½Ã¼³¹° ÇÏÀÚÁø´Ü ÀÚµ¿È ½Ã½ºÅÛ °³¹ßÀÇ ±âÃÊÀÚ·á·Î Ȱ¿ëµÉ¼ö ÀÖÀ» °ÍÀÌ´Ù. |
| ¿ä¾à2 |
Most of the current crack investigation work consists of visual inspection using simple measuring equipment such as crack scale. These methods involve the subjection of the inspector, which may lead to differences in the inspection results prepared by the inspector, and may lead to a large number of measurement errors. So, this study proposes an image-based crack detection method to enhance objectivity and efficiency of concrete crack investigation. In this study, YOLOv2 was used to determine the presence of cracks in the image information to ensure the speed and accuracy of detection for real-time analysis. In addition, we extracted shapes of cracks and calculated quantitatively, such as width and length using various image processing techniques. The results of this study will be used as a basis for the development of image-based facility defect diagnosis automation system. |