• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document : 9 / 22 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) CNNÀ» ÀÌ¿ëÇÑ µö·¯´× ±â¹Ý Çϼö°ü ¼Õ»ó ŽÁö ºÐ·ù ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) Damage Detection and Classification System for Sewer Inspection using Convolutional Neural Networks based on Deep Learning
ÀúÀÚ(Author) ÀÓ¼öÇö   ¹Î°æº¹   ³²ÁØ¿µ   ¹®ÇöÁØ   Sh-hyeon Im   Kyung-bok Min   Jun-young Nam   Hyeon-joon Moon  
¿ø¹®¼ö·Ïó(Citation) VOL 22 NO. 03 PP. 0451 ~ 0457 (2018. 03)
Çѱ۳»¿ë
(Korean Abstract)
º» ¿¬±¸´Â ÀΰøÁö´É ºÐ¾ßÀÇ µö·¯´× ±â¼úÀ» ±â¹ÝÀ¸·Î ÇÑ Çϼö°ü ¼Õ»óÀÇ ÀÚµ¿ ŽÁö ºÐ·ù ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. ¼º´ÉÀÇ ÃÖÀûÈ­¸¦ À§ÇÏ¿© DB ȹµæ ½Ã ¹ß»ýµÈ Á¶µµ ¹× ±×¸²ÀÚ º¯È­¿Í °°Àº ´Ù¾çÇÑ È¯°æº¯È­¿¡ °­ÀÎÇÑ ½Ã½ºÅÛÀ» ±¸ÇöÇÏ¿´´Ù. Á¦¾ÈµÈ ½Ã½ºÅÛ¿¡¼­´Â Convolutional Neural Network(CNN) ±â¹ÝÀÇ ±Õ¿­ ŽÁö ¹× ¼Õ»ó ºÐ·ù ±â¹ýÀ» ±¸ÇöÇÏ¿´´Ù. ÃÖÀûÀÇ °á°ú¸¦ À§ÇÏ¿© 256 x 256 Çȼ¿ ÇØ»óµµÀÇ CCTV ¿µ»ó 9,941°³¸¦ ÀÌ¿ëÇÏ¿© CNN¸ðµ¨À» Àû¿ëÇÏ¿© ¼Õ»óºÎÀ§¿¡ ´ëÇÑ µö·¯´×À» ¼öÇàÇÏ¿´°í ±× °á°ú 98.76 %ÀÇ ÀνķüÀ» ȹµæÇÏ¿´´Ù. ±â°èÇнÀÀ» ÅëÇÑ µö·¯´× ¸ðµ¨À» ±â¹ÝÀ¸·Î ´Ù¾çÇÑ È¯°æÀÇ Çϼöµµ DB¿¡¼­ 720 x 480 Çȼ¿ ÇØ»óµµÀÇ 646°³ÀÇ À̹ÌÁö¸¦ ÃßÃâÇÏ¿© ¼º´É Æò°¡¸¦ ¼öÇà ÇÏ¿´´Ù. º» ½Ã½ºÅÛÀº ´Ù¾çÇÑ È¯°æ¿¡¼­ ±¸ÃàµÈ Çϼö°ü µ¥ÀÌÅͺ£À̽º ¿¡¼­ ¼Õ»ó À¯ÇüÀÇ ÀÚµ¿ ŽÁö ¹× ºÐ·ù¿¡ ÃÖÀûÈ­µÈ ÀνķüÀ» Á¦½ÃÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with 256 x 256 pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of 720 x 480 pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.
Å°¿öµå(Keyword) µö·¯´×   CNN   CCTVs   ÀΰøÁö´É   ¼Õ»ó ŽÁö   Çϼö°ü   Artificial Intelligence   CCTVs   CNN   Deep Learning   Demage Detection   Sewer Inspection  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå