| ³í¹®¸í |
µå·Ð°ú À̹ÌÁö ºÐ¼®±â¹ýÀ» Ȱ¿ëÇÑ ±¸Á¶¹° ¿Ü°üÁ¡°Ë ±â¼ú ¿¬±¸ / Study on Structure Visual Inspection Technology using Drones and Image Analysis Techniques |
| ÀúÀÚ¸í |
±èÁ¾¿ì(Kim, Jong-Woo) ; Á¤¿µ¿ì(Jung, Young-Woo) ; ÀÓȫö(Rhim, Hong-Chul) |
| ¼ö·Ï»çÇ× |
Çѱ¹°ÇÃà½Ã°øÇÐȸ ³í¹®Áý, Vol.17 No.6 (2017-12) |
| ÆäÀÌÁö |
½ÃÀÛÆäÀÌÁö(545) ÃÑÆäÀÌÁö(13) |
| ÁÖÁ¦¾î |
±¸Á¶¹° ¿Ü°ü °Ë»ç ; µå·Ð ; ÀÚµ¿ºñÇàÇ×¹ý ; µö·¯´× À̹ÌÁö ºÐ¼® ; ¸ðÆú·ÎÁö ±â¹ý ; visual inspection ; drone ; automatic flight navigation ; deep learning image analysis ; morphology method |
| ¿ä¾à1 |
ÀÌ ¿¬±¸´Â »çȸ ±â¹Ý ±¸Á¶¹°ÀÇ ³ëÈÄÈ¿¡ ´ëÇÑ ¾ÈÀüÁ¡°Ë ±â¼úºÐ¾ß¿¡¼ ±¸Á¶¹° ¿Ü°üÁ¡°Ë ±â¼úÀÇ È¿À²Àû ´ë¾È¿¡ °üÇÑ ¿¬±¸ÀÌ´Ù. ±âÁ¸ À°¾ÈÁ¡°Ë ¹× Á¶»ç¸¦ ´ë½ÅÇÏ¿© »ê¾÷¿ë µå·Ð°ú µö ·¯´×±â¹ÝÀÇ À̹ÌÁö ºÐ¼® ±â¹ýÀ» Á¢¸ñÇÔÀ¸·Î½á ¸·´ëÇÑ Àη°ú ½Ã°£¼Ò¿ä ¹× ºñ¿ëÀ» Àý°¨ÇÏ°í ³ôÀº ±¸¿ª ¹× µ¼ ±¸Á¶¹°ÀÇ Á¢±Ù ÇѰ踦 ±Øº¹ÇϰíÀÚ ÇÏ¿´´Ù. ±¸Á¶¹°ÀÇ 0.3mm ÀÌ»óÀÇ ±Õ¿ ¼Õ»óÀ» °ËÁöÇÒ ¼ö ÀÖ´Â °í ÇØ»óµµ Ä«¸Þ¶ó¿Í ¶óÀÌ´Ù ¼¾¼, ÀÓº£µðµå À̹ÌÁö ÇÁ·Î¼¼¼ ¸ðµâ·Î ±¸¼ºµÈ žÀçü¸¦ Á¦ÀÛÇÏ¿© »ê¾÷¿ë µå·Ð¿¡ žÀçÇÏ¿´´Ù. À̸¦ ÇöÀå ½ÃÇè¿¡ Àû¿ëÇÏ¿© ÀÚµ¿ºñÇàÇ×¹ýÀ» ÅëÇØ ½ÃÆíÀÇ ¼Õ»ó À̹ÌÁö¸¦ ÃÔ¿µÇÏ¿´´Ù. ¶ÇÇÑ ±Õ¿°æÀ» ÀÌ¿ëÇÏ¿© ±âÁ¸ À°¾È Á¡°Ë ¹æ¹ýÀ¸·Î ¹éÅÂ, ¹Ú¸®¹Ú¶ô°ú °°Àº ¸éÀûÇü ¼Õ»ó°ú ¼±Çü ¼Õ»óÀÎ ±Õ¿ÀÇ Æø°ú ±æÀ̸¦ ÃøÁ¤ÇÏ¿© ÃÖÁ¾ À̹ÌÁöºÐ¼® °ËÃâ °á°ú¿Í ºñ±³ÇϰíÀÚ ÇÏ¿´´Ù. ÃÔ¿µµÈ À̹ÌÁö Áß 80ÀåÀÇ »ùÇÃÀ» °ñ¶ó À̹ÌÁö ºÐ¼® ±â¹ýÀ» Àû¿ëÇÏ¿© »çÀüó¸®ÀÛ¾÷(pre-processing)-ºÐ¸®ÀÛ¾÷(segmentation)-Ư¡Á¡ ÃßÃâÀÛ¾÷(feature extraction)-ºÐ·ù ÀÛ¾÷(Classification)-ÁöµµÇнÀÀÛ¾÷(supervised learning) µîÀÇ °úÁ¤À» °ÅÃÄ ¼Õ»óÀ» ºÐ¸®Çϰí, À̸¦ µö·¯´× ±â¹Ý Ç÷§ÆûÀ¸·Î ÁöµµÇнÀÇÏ¿© ºÐ¼® ÆÄ¶ó¹ÌÅ͸¦ ÃßÃâÇÏ¿´´Ù. ÁöµµÇнÀÀ» ¼öÇàÇÏÁö ¾ÊÀº ÀÓÀÇÀÇ À̹ÌÁö »ùÇà 60ÀåÀ» ½Å±Ô·Î Ãß°¡ÇÏ¿© ÃßÃâµÈ ÆÄ¶ó¹ÌÅ͸¦ ±â¹ÝÀ¸·Î À̹ÌÁö ºÐ¼®À» ¼öÇàÇÑ °á°ú, ¼Õ»ó °ËÃâÀ²ÀÇ 90.5%·Î ³ªÅ¸³µ´Ù. |
| ¿ä¾à2 |
The study is about the efficient alternative to concrete surface in the field of visual inspection technology for deteriorated infrastructure. By combining industrial drones and deep learning based image analysis techniques with traditional visual inspection and research, we tried to reduce manpowers, time requirements and costs, and to overcome the height and dome structures. On board device mounted on drones is consisting of a high resolution camera for detecting cracks of more than 0.3 mm, a lidar sensor and a embeded image processor module. It was mounted on an industrial drones, took sample images of damage from the site specimen through automatic flight navigation. In addition, the damege parts of the site specimen was used to measure not only the width and length of cracks but white rust also, and tried up compare them with the final image analysis detected results. Using the image analysis techniques, the damages of 54ea sample images were analyzed by the segmentation - feature extraction - decision making process, and extracted the analysis parameters using supervised mode of the deep learning platform. The image analysis of newly added non-supervised 60ea image samples was performed based on the extracted parameters. The result presented in 90.5 % of the damage detection rate. |