Àüü
ÀüÀÚ/Àü±â
Åë½Å
ÄÄÇ»ÅÍ
·Î±×ÀÎ
ȸ¿ø°¡ÀÔ
About Us
ÀÌ¿ë¾È³»
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
Æ÷Ä¿½ºiN
¿¬±¸ÀÚ Á¤º¸
¶óÀÌ¡½ºÅ¸
ÆÄ¿öiNÅͺä
¼¼ÁßÇÑ
¿¬±¸ÀÚ·á
¹®ÀÚ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñÁ¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
´Ý±â
»çÀÌÆ®¸Ê
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±³À°Á¤º¸
¿¬±¸ ù°ÉÀ½
ÇаúÁ¤º¸
°ÀÇÁ¤º¸
µ¿¿µ»óÁ¤º¸
E-Learning
¿Â¶óÀÎ Àú³Î
½ÉÈÁ¤º¸
¿¬±¸ ¹× ±â¼úµ¿Çâ
Áֿ俬±¸ÅäÇÈ
ÁÖ¿ä°úÁ¦ ¹× ±â°ü
Çؿܱâ°ü °ü·ÃÀÚ·á
¹ÙÀÌ¿À Á¤º¸±â¼ú
ÁÖ¿ä Archive Site
ÄÄÇ»ÅÍiN
¿¬±¸ÀÚ Á¤º¸
¿¬±¸ÀÚ·á
¹®ÀÚ DB
Ȧ·Î±×·¥ DB
¿ë¾î»çÀü
¾Ë¸²¸¶´ç
ºÎ½Ç ÇмúÈ°µ¿ ¿¹¹æ
³í¹®¸ðÁý
´ëȸ¾È³»
What's New
¿¬±¸ºñ Á¤º¸
±¸ÀÎÁ¤º¸
°øÁö»çÇ×
IT Daily
CSERIC ±¤Àå
Post-Conference
¿¬±¸ÀÚ Ä«Æä
ÀÚÀ¯°Ô½ÃÆÇ
Q&A
¼ºñ½º ¹Ù·Î°¡±â
¼³¹®Á¶»ç
¿¬±¸À±¸®
°ü·Ã±â°ü
Please wait....
¿¬±¸¹®Çå
±¹³» ³í¹®Áö
¿µ¹® ³í¹®Áö
±¹³» ÇÐȸÁö
Çмú´ëȸ ÇÁ·Î½Ãµù
±¹³» ÇÐÀ§ ³í¹®
³í¹®Á¤º¸
¹é¼
±¹³» ÇÐȸÁö
Ȩ > ¿¬±¸¹®Çå > ±¹³» ÇÐȸÁö >
µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)
µ¥ÀÌÅͺ£À̽º ¿¬±¸È¸Áö(SIGDB)
Current Result Document :
7
/ 7
ÀÌÀü°Ç
ÇѱÛÁ¦¸ñ(Korean Title)
Single Shot Multibox Detector¸¦ Àû¿ëÇÑ ½Ç½Ã°£ ¼±¹Ú °ËÃâ ¹× ºÐ·ù ½Ã½ºÅÛ °³¹ß
¿µ¹®Á¦¸ñ(English Title)
Development of Real-Time Ship Detection and Classification System Using Single Shot Multibox Detector
ÀúÀÚ(Author)
±è¿ëÇÑ
Yonghan Kim
ÇöÁ¤È¯
Jeonghwan Hyun
±ÇÁØÈ£
Joonho Kwon
¼Û±æÅÂ
Giltae Song
¿ø¹®¼ö·Ïó(Citation)
VOL 36 NO. 01 PP. 0093 ~ 0105 (2020. 04)
Çѱ۳»¿ë
(Korean Abstract)
¿µ»ó ±â¼úÀÇ ¹ßÀüÀº ÇØ»ó ȯ°æ¿¡¼ ÀÚÀ²¿îÇ×¼±¹Ú ½Ã½ºÅÛ ±¸Ãà¿¡ ´ëÇÑ °ü½ÉÀ¸·Î À̾îÁö°í ÀÖ´Ù. ÀÌ·¯ÇÑ ÀÚÀ²¿îÇ×¼±¹ÚÀ» ±¸ÇöÇϴµ¥ ÀÖ¾î ÁÖ¿äÇÑ ¹®Á¦ Áß Çϳª°¡ ½Ç½Ã°£ ¿µ»ó µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿© ÇØ»ó ¼±¹Ú°úÀÇ Ãæµ¹À» ÇÇÇϵµ·Ï ÇÏ´Â °ÍÀÌ´Ù. À̸¦ À§ÇØ Ä«¸Þ¶ó¸¦ ÅëÇØ ¼öÁýµÈ ¿µ»ó ¹× À̹ÌÁö µ¥ÀÌÅ͸¦ ºÐ¼®ÇÏ¿© ¼±¹ÚÀ» Á¤È®ÇÏ°Ô ½Ç½Ã°£À¸·Î °ËÃâÇÏ°í ºÐ·ùÇÏ´Â °ÍÀÌ ÇÊ¿äÇÏ´Ù. º» ³í¹®¿¡¼´Â ÀÚÀ²¿îÇ×¼±¹Ú ½Ã½ºÅÛ ±¸Çö¿¡ ÀÖ¾î ÇʼöÀûÀÎ ¿ä¼ÒÀÎ ¿µ»ó ¹× À̹ÌÁö µ¥ÀÌÅÍ ±â¹Ý ½Ç½Ã°£ ¼±¹Ú °ËÃâ ¹× ºÐ·ù¸¦ À§ÇÑ µö·¯´× ¼ÒÇÁÆ®¿þ¾î °³¹ßÀ» Á¦¾ÈÇÑ´Ù. À̸¦ À§ÇØ SSD (Single Shot Multibox Detector) ±¸Á¶ »ó¿¡ Inception ¸ðµ¨°ú MobileNet ¸ðµ¨À» º£À̽º ³×Æ®¿öÅ©·Î Àû¿ëÇÏ¿© ¿¬»ê·®À» °¨¼Ò½ÃÄÑ ½Ç½Ã°£¼ºÀ» ³ôÀÌ´Â ¼±¹Ú °ËÃâ ¹× ºÐ·ù ½Ã½ºÅÛÀ» ±¸ÇöÇÏ¿´´Ù. º» ³í¹®¿¡¼ °³¹ßµÈ ½Ã½ºÅÛ°ú ±âÁ¸ °³¹ßµÈ Faster R-CNN ±â¹Ý ¼±¹Ú °ËÃâ ¹× ºÐ·ù ½Ã½ºÅÛ°ú ºñ±³ÇÏ¿© ¼º´ÉÀ» °ËÁõÇÏ¿´´Ù. ±× °á°ú º» ³í¹®¿¡¼ Á¦¾ÈÇÑ ½Ã½ºÅÛÀÌ ±âÁ¸ Faster R-CNN ±â¹Ý ½Ã½ºÅÛº¸´Ù ´õ Á¤È®ÇÏ°í ºü¸¥ 󸮼ӵµ·Î ¼±¹ÚÀ» °ËÃâÇÏ°í ºÐ·ùÇÏ¿´´Ù. À̸¦ ÅëÇØ ½Ç½Ã°£ ¼±¹Ú ¿µ»ó µ¥ÀÌÅ͸¦ º¸´Ù Á¤È®ÇÏ°Ô ºÐ¼®ÇÒ ¼ö ÀÖ°Ô µÇ¾î ÀÚÀ²¿îÇ×¼±¹Ú ½Ã½ºÅÛ ½ÇÇöÀ» ´õ¿í ¾Õ´ç±æ ¼ö ÀÖÀ» °ÍÀ¸·Î ±â´ëµÈ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Advanced video technologies result in raising attention to the development of maritime autonomous surface ship. In such systems, it is one of major problems to prevent ships from colliding. To avoid the collisions among ships, it is required to detect and classify ships in real time using the collection of video data. In this paper, we propose a software system that detects and classifies ships in real time from video and images using a deep learning. We developed a system using the Inception model and MobileNet as the base network of the SSD (Single Shot Multibox Detector) structure, which reduces computations.. We evaluated these two models in terms of the speed of ship detections and the precision of classification using validation data. We compared our proposed methods with an existing method based on the Faster R-CNN. Our method outperformed in our performance evaluation. We expect that our system can contribute to develop the maritime autonomous surface ship via the accurate analysis of real time ship video data.
Å°¿öµå(Keyword)
¼±¹Ú ¿µ»ó ¹× À̹ÌÁö µ¥ÀÌÅÍ
¼±¹Ú °ËÃâ ¹× ºÐ·ù
Ship video and image data
Single shot multibox detector
Ship detection and classification
ÆÄÀÏ÷ºÎ
PDF ´Ù¿î·Îµå
¸ñ·Ï
Copyright(c)
Computer Science Engineering Research Information Center
. All rights reserved.