| ³í¹®¸í |
ÄÄÇ»ÅÍ ºñÀü ±â¼úÀ» ÀÌ¿ëÇÑ °Ç¼³ ÀÛ¾÷ÀÚ º¸È£±¸ °ËÃâ Á¤È®µµ ºÐ¼® / Accuracy Analysis of Construction Worker¡¯s Protective Equipment Detection Using Computer Vision Technology |
| ÀúÀÚ¸í |
°¼º¿ø(Kang, Sungwon) ; À̱⼮(Lee, Kiseok) ; À¯À§¼º(Yoo, Wi Sung) ; ½ÅÀ±¼®(Shin, Yoonseok) ; ÀÌ¸íµµ(Lee, Myungdo) |
| ¼ö·Ï»çÇ× |
Çѱ¹°ÇÃà½Ã°øÇÐȸ ³í¹®Áý, Vol.23 No.1 (2023-02) |
| ÆäÀÌÁö |
½ÃÀÛÆäÀÌÁö(81) ÃÑÆäÀÌÁö(12) |
| ÁÖÁ¦¾î |
°Ç¼³¾ÈÀü°ü¸®; ÄÄÇ»ÅÍ ºñÀü; °³Àκ¸È£±¸ °ËÃâ ; construction safety management; computer vision; personal protective equipment detection |
| ¿ä¾à1 |
°Ç¼³¾÷ÀÇ »ç°í»ç¸ÁÀÚ ¼ö´Â Ÿ »ê¾÷¿¡ ºñÇØ ¸¹ÀÌ ¹ß»ýÇϰí ÀÖÀ¸¸ç, ±× Áß Ãß¶ôÀçÇØ·Î ÀÎÇÑ »ç°í°¡ Àý¹Ý ÀÌ»ó Â÷ÁöÇϰí ÀÖ´Ù. Á¤ºÎ´Â °Ç¼³ÇöÀåÀÇ »ç°í À§Çè ¿äÀεéÀ» ±ÙÀýÇϱâ À§ÇØ Ãß¶ô, ³¢ÀÓ ¹æÁöÁ¶Ä¡, °³Àκ¸È£±¸ Âø¿ë°ú °°Àº ¾ÈÀüÁ¶Ä¡¸¦ ÁýÁßÀûÀ¸·Î °ü¸®Çϰí ÀÖÀ¸³ª, °Ç¼³ÇöÀå ¾ÈÀü»ç°í´Â ²÷ÀÓ¾øÀÌ ¹ß»ýÇϰí ÀÖ´Ù. ÀÌ¿¡ º» ¿¬±¸´Â ÄÄÇ»ÅÍ ºñÀü ±â¼úÀ» Ȱ¿ëÇÏ¿© °Ç¼³ÇöÀå³» ÀÛ¾÷ÀÚÀÇ ¾ÈÀü¸ð, ¾ÈÀü´ë Âø¿ë »óŸ¦ °ËÃâÇÏ´Â ¸ðµ¨À» °³¹ßÇÏ¿´´Ù. º» ¿¬±¸´Â °Ç¼³ÇöÀå Àû¿ëÀ» À§ÇÑ Á¶°ÇµéÀ» ¼³Á¤ÇÏ¿©½ÇÇèÀ» ÁøÇàÇÏ¿´À¸¸ç, °á°ú ºÐ¼®À» ÅëÇØ °ËÃâ Á¤È®µµ ¹× ¸ðµ¨ ½ÇÇà ¼Óµµ ºÐ¼®ÇÏ¿´´Ù. ÀÌ´Â °á°úÀûÀ¸·Î °Ç¼³ÇöÀå °ü¸®ÀÚÀÇ Á¡°Ë, ¼øÂûÀÇ È¿À²À» Çâ»ó½Ãų ¼ö ÀÖÀ¸¸ç, ¾ÈÀü °ü¸® ¿ª·® ¼öÁØ °È¿¡ ±â¿©ÇÒ ¼ö ÀÖÀ» °ÍÀ¸·Î ±â´ëµÈ´Ù. |
| ¿ä¾à2 |
According to the 2020 industrial accident reports of the Ministry of Employment and Labor, thenumber of fatal accidents in the construction industry over the past 5 years has been higher than inother industries. Of these more than 50% of fatal accidents are initially caused by fall accidents. Thecentral government is intensively managing falling/jamming protection device and the use of personalprotective equipment to eradicate the inappropriate factors disrupting safety at construction sites. Inaddition, although efforts have been made to prevent safety accidents with the proposal of the SpecialAct on Construction Safety, fatalities on construction sites are constantly occurring. Therefore, thisstudy developed a model that automatically detects the wearing state of the worker¡¯s safety helmet andbelt using computer vision technology. In considerations of conditions occurring at construction sites,we suggest an optimization method, which has been verified in terms of the accuracy and operationspeed of the proposed model. As a result, it is possible to improve the efficiency of inspection and patrolby construction site managers, which is expected to contribute to reinforcing competency of safetymanagement. |