• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ÄÄÇ»ÅÍ ¹× Åë½Å½Ã½ºÅÛ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) µö·¯´× ±â¹Ý ÄÁÅ×ÀÌ³Ê ÀûÀç Á¤·Ä »óÅ ¹× »ç°í À§Çèµµ °ËÃâ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Shipping Container Load State and Accident Risk Detection Techniques Based Deep Learning
ÀúÀÚ(Author) ¿¬Á¤Èì   ¼­¿ë¿í   ±è»ó¿ì   ¿À¼¼¿µ   Á¤ÁØÈ£   ºòÁøÈ¿   ±è¼ºÈñ   À±ÁÖ»ó   Yeon Jeong Hum   Seo Yong Uk   Kim Sang Woo   Oh Se Yeong   Jeong Jun Ho   Park Jin Hyo   Kim Sung-Hee   Youn Joosang  
¿ø¹®¼ö·Ïó(Citation) VOL 11 NO. 11 PP. 0411 ~ 0418 (2022. 11)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù Ç׸¸¿¡¼­´Â ºÎÁ¤È®ÇÑ ÄÁÅ×ÀÌ³Ê ÀûÀç·Î ÀÎÇØ ÄÁÅ×À̳ʰ¡ °­Ç³¿¡ ½±°Ô ¾²·¯Áö´Â ÄÁÅ×ÀÌ³Ê ºØ±« »ç°í°¡ ºó¹øÀÌ ¹ß»ýÇÏ°í ÀÖÀ¸¸ç ÀÌ´Â ¹°Àû ÇÇÇØ¿Í Ç׸¸ ½Ã½ºÅÛ ¸¶ºñ·Î À̾îÁö°í ÀÖ´Ù. º» ³í¹®¿¡¼­´Â ÀÌ·± »ç°í¸¦ ¹Ì¿¬¿¡ ¹æÁöÇϱâ À§ÇØ µö·¯´× ±â¹Ý ÄÁÅ×ÀÌ³Ê ÀûÀç »óÅ ¹× »ç°í À§Çèµµ °ËÃ⠽ýºÅÛÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈµÈ ½Ã½ºÅÛÀº darknet ±â¹Ý YOLO ¸ðµ¨À» È°¿ëÇÏ¿© ÄÁÅ×ÀÌ³Ê »óÇÏÀÇ ÄÚ³Êij½ºÆÃÀ» ÅëÇØ ÄÁÅ×ÀÌ³Ê Á¤·Ä »óŸ¦ ½Ç½Ã°£À¸·Î ÆľÇÇÏ°í °ü¸®ÀÚ¿¡°Ô »ç°í À§Çèµµ¸¦ ¾Ë¸®´Â ½Ã½ºÅÛÀÌ´Ù. Á¦¾ÈµÈ ½Ã½ºÅÛÀº Ãß·Ð ¼Óµµ, ºÐ·ù Á¤È®µµ, °ËÃâ Á¤È®µµ µîÀ» ¼º´É ÁöÇ¥¿Í ½ÇÁ¦ ±¸Çö ȯ°æ¿¡¼­ ÃÖÀûÀÇ ¼º´ÉÀ» º¸ÀÎ YOLOv4 ¸ðµ¨À» °´Ã¼ ÀÎ½Ä ¾Ë°í¸®Áò ¸ðµ¨·Î ¼±ÅÃÇÏ¿´´Ù. Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀÎ YOLOv4°¡ YOLOv3º¸´Ù Ã߷мӵµ¿Í FPSÀÇ ¼º´É Ãø¸é¿¡¼­ ³·Àº ¼º´ÉÀ» º¸À̱â´Â ÇßÁö¸¸, ºÐ·ù Á¤È®µµ¿Í °ËÃâ Á¤È®µµ¿¡¼­ °­·ÂÇÑ ¼º´ÉÀ» º¸ÀÓÀ» Áõ¸íÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
Incorrectly loaded containers can easily knock down by strong winds. Container collapse accidents can lead to material damage and paralysis of the port system. In this paper, We propose a deep learning-based container loading state and accident risk detection technique. Using Darknet-based YOLO, the container load status identifies in real-time through corner casting on the top and bottom of the container, and the risk of accidents notifies the manager. We present criteria for classifying container alignment states and select efficient learning algorithms based on inference speed, classification accuracy, detection accuracy, and FPS in real embedded devices in the same environment. The study found that YOLOv4 had a weaker inference speed and performance of FPS than YOLOv3, but showed strong performance in classification accuracy and detection accuracy.
Å°¿öµå(Keyword) ÄÁÅ×À̳ʠ  YOLOv4   µö·¯´×   °´Ã¼ÀνĠ  Shipping Container   YOLOv4   Deep Learning   Object Detection  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå