°ÇÃ൵½Ã°ø°£¿¬±¸¼Ò

Architecture & Urban Research Institute

pdf¿ø¹®º¸±â ¿¡·¯ ÇØ°á¹æ¹ý ¹Ù·Î°¡±â



¹®ÇåȨ > ¿¬±¸³í¹® > »ó¼¼

[¿ø¹®º¸±â½Ã ¼ÒºñµÇ´Â Æ÷ÀÎÆ® : 100 Æ÷ÀÎÆ®] ¹Ì¸®º¸±â Àοë

Çѱ¹°Ç¼³°ü¸®ÇÐȸ|³í¹®Áý 2024³â 3¿ù

³í¹®¸í Edge ºÐ¼®°ú ROI ±â¹ýÀ» Ȱ¿ëÇÑ ÄÜÅ©¸®Æ® ±Õ¿­ ºÐ¼® - Edge¿Í ROI¸¦ Àû¿ëÇÑ ÄÜÅ©¸®Æ® ±Õ¿­ ºÐ¼® ¹× °Ë»ç - / Edge Detection and ROI-Based Concrete Crack Detection
ÀúÀÚ¸í ¹ÚÈñ¿ø(Park, Heewon)½Äº°ÀúÀÚ ; À̵¿Àº(Lee, Dong-Eun)
¹ßÇà»ç Çѱ¹°Ç¼³°ü¸®ÇÐȸ
¼ö·Ï»çÇ× Çѱ¹°Ç¼³°ü¸®ÇÐȸ ³í¹®Áý, Vol.25 No.2 (2024-03)
ÆäÀÌÁö ½ÃÀÛÆäÀÌÁö(36) ÃÑÆäÀÌÁö(9)
ISSN 2005-6095
ÁÖÁ¦ºÐ·ù ½Ã°ø(Àû»ê)
ÁÖÁ¦¾î ÇÕ¼º°ö ½Å°æ¸Á; ÄÜÅ©¸®Æ® ±Õ¿­; °ü½É¿µ¿ª; ¿¡Áö ¼¼±×¸àÅ×À̼Ç; ¼öµ¿ °Ë»ç ; CNN; Concrete Crack; ROI; Edge Segmentation; Manual Inspection
¿ä¾à1 º» ³í¹®¿¡¼­´Â ÇÕ¼º°ö½Å°æ¸Á°ú ROI±â¹ýÀ» ÀÌ¿ëÇÑ ÄÜÅ©¸®Æ® ±Õ¿­ ºÐ¼®¿¡ °üÇØ ¼Ò°³ÇÑ´Ù. ÄÜÅ©¸®Æ® Ç¥¸é, ºö°ú °°Àº ±¸Á¶¹°Àº ÇÇ·Î ÀÀ·Â, Áֱ⠺ÎÇÏ¿¡ ³ëÃâµÇ¸ç, ÀÌ´Â ÀϹÝÀûÀ¸·Î ±¸Á¶¹°ÀÇ Ç¥¸é¿¡¼­ ¹Ì¼¼ÇÑ ¼öÁØ¿¡¼­ ½ÃÀ۵Ǵ ±Õ¿­À» ¾ß±âÇÑ´Ù. ±¸Á¶¹°ÀÇ ±Õ¿­Àº ¾ÈÁ¤¼ºÀ» ÀúÇϽÃŰ°í ±¸Á¶¹°ÀÇ °ß°íÇÔÀ» °¨¼Ò½ÃŲ´Ù. Á¶±â ¹ß°ßÀ» ÅëÇØ ¼Õ»ó ¹× °íÀå °¡´É¼ºÀ» ¹æÁöÇϱâ À§ÇÑ ¿¹¹æ Á¶Ä¡¸¦ ÃëÇÒ ¼ö ÀÖ´Ù. ÀϹÝÀûÀ¸·Î ¼öµ¿ °Ë»ç °á°ú´Â ǰÁúÀÌ ÁÁÁö ¾Ê°í, ´ë±Ô¸ð ±â¹Ý ½Ã¼³ÀÇ °æ¿ì Á¢±ÙÀÌ ¾î·Á¿ì¸ç, ±Õ¿­À» Á¤È®ÇÏ°Ô °¨ÁöÇÏ±â ¾î·Æ´Ù. ÀÌ·¯ÇÑ ¼öµ¿°Ë»çÀÇ ÀÚµ¿È­´Â ±âÁ¸ ¹æ½ÄÀÇ ÇѰ踦 ÇØ°áÇÒ ¼ö Àֱ⠶§¹®¿¡ ÄÄÇ»ÅÍ ºñÀü ±â¹ÝÀÇ ¿¬±¸µéÀÌ ¼öÇàµÇ¾ú´Ù. ÇÏÁö¸¸ ´Ù¾çÇÑ À¯ÇüÀÇ ±Õ¿­À̳ª, ¿­È­»ó Ä«¸Þ¶ó µîÀ» ÀÌ¿ëÇÑ ¿¬±¸µéÀº ºÎÁ·ÇÑ »óÅÂÀÌ´Ù. µû¶ó¼­ º» ¿¬¿¡¼­´Â ÄÜÅ©¸®Æ® º®ÀÇ ±Õ¿­À» ÀÚµ¿À¸·Î °¨ÁöÇÏ´Â ¹æ¹ý·ÐÀ» °³¹ßÇÏ¿© Á¦½ÃÇϸç, ´ÙÀ½°ú °°Àº ¿¬±¸ ³»¿ëÀ» ¸ñÇ¥·Î ÇÑ´Ù. ù°, ±Õ¿­ °¨Áö À̹ÌÁö ±â¹Ý ºÐ¼®ÀÇ ÁÖ¿ä ÀåÁ¡ÀÎ À̹ÌÁö ó¸® ±â¼úÀ» »ç¿ëÇÏ¿© ±âÁ¸ÀÇ ¼öµ¿ ¹æ¹ý°ú ºñ±³ÇÏ¿© Á¤È®µµ°¡ Çâ»óµÈ °á°ú ¹× Á¤º¸¸¦ Á¦°øÇÑ´Ù. µÑ°, °­È­µÈ Sobel edge segmentation ±â¼ú ¹× ROI ±â¹ý ±â¹ÝÀÇ ¾Ë°í¸®ÁòÀ» °³¹ßÇÏ¿© ºñÆÄ±« ½ÃÇèÀ» À§ÇÑ ÀÚµ¿ ±Õ¿­ °¨Áö ±â¼úÀ» ±¸ÇöÇÑ´Ù.
¿ä¾à2 This paper presents the application of Convolutional Neural Networks (CNNs) and Region of Interest (ROI) techniques for concrete crack analysis. Surfaces of concrete structures, such as beams, etc., are exposed to fatigue stress and cyclic loads, typically resulting in the initiation of cracks at a microscopic level on the structure's surface. Early detection enables preventative measures to mitigate potential damage and failures. Conventional manual inspections often yield subpar results, especially for large-scale infrastructure where access is challenging and detecting cracks can be difficult. This paper presents data collection, edge segmentation and ROI techniques application, and analysis of concrete cracks using Convolutional Neural Networks. This paper aims to achieve the following objectives: Firstly, achieving improved accuracy in crack detection using image-based technology compared to traditional manual inspection methods. Secondly, developing an algorithm that utilizes enhanced Sobel edge segmentation and ROI techniques. The algorithm provides automated crack detection capabilities for non-destructive testing.
¼ÒÀåó Çѱ¹°Ç¼³°ü¸®ÇÐȸ
¾ð¾î Çѱ¹¾î
DOI https://dx.doi.org/10.6106/KJCEM.2024.25.2.036
¡á Á¦ 1 ÀúÀÚÀÇ ´Ù¸¥ ¹®Çå ½Äº°ÀúÀÚ´õº¸±â
[Çмú±â»ç] ºôµù¿¡ ÀÛ¿ëÇÏ´Â °ø·Â Ư¼ºÀÇ Åë°è ºÐ¼®
¹ÚÈñ¿ø(Park Heewon) ; À¯¹Ù¶óÁö³ªÅ¸¶óÀÜ(Yuvaraj Natarajan) ; ±è¹ý·Ä(Kim Bubryur) - Çѱ¹°ø°£±¸Á¶ÇÐȸÁö : Vol. 19, No. 4 (Åë±Ç 78È£) (201912)