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» ³í¹®Áö
Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö >
Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö
>
Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)
Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)
Current Result Document :
1
/ 9
´ÙÀ½°Ç
ÇѱÛÁ¦¸ñ(Korean Title)
½Ç½Ã°£ ¾ß±¸ Á߰踦 À§ÇÑ CNN ±â¹Ý °í¼Ó ¾ß±¸ ¼±¼ö À§Ä¡ °ËÃ⠽ýºÅÛ
¿µ¹®Á¦¸ñ(English Title)
Fast Baseball Player Location Detection System using Convolutional Neural Networks for Real Time Broadcast
ÀúÀÚ(Author)
±èÀçÁØ
ÃÖÅ¿µ
Jaejun Kim
Tae-Young Choe
¿ø¹®¼ö·Ïó(Citation)
VOL 25 NO. 03 PP. 0171 ~ 0178 (2019. 03)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼´Â ¾ß±¸ °æ±â ¿µ»ó¿¡¼ µö ·¯´× ±â¹ýµé Áß ¿µ»ó ÀνĿ¡ ÀûÇÕÇÑ CNNÀ» »ç¿ëÇÏ¿© ¾ß±¸ ¼±¼öÀÇ À§Ä¡¸¦ °ËÃâÇÏ´Â ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. °´Ã¼ÀÇ À§Ä¡ °ËÃâÀ» À§ÇÑ ±âÁ¸ÀÇ ¿µ»ó ó¸® ±â¹ýµé Áß ´Ù¼ö´Â ¿µ»ó ÇÁ·¹ÀÓ »çÀÌÀÇ Â÷¿µ»óÀ̳ª °´Ã¼ÀÇ À±°ûÀ» ¾ò´Â ¹æ¹ýµéÀ» »ç¿ëÇØ¿ÔÁö¸¸, ¾ß±¸ Áß°è¿Í °°ÀÌ ´Ù¾çÇÑ ±âÈÄ¿Í ¹è°æÀ» ¸ðµÎ °í·ÁÇÏ¿© ½Ç¿ëÈÇϱ⿡´Â Ãß°¡ÀûÀÎ °ËÁõ °úÁ¤ÀÌ ÇÊ¿äÇÏ´Ù. º» ³í¹®¿¡¼´Â ´Ù¾çÇÑ °æ¿ì¿¡ ¿òÁ÷ÀÌ´Â °´Ã¼ÀÇ À§Ä¡¸¦ ºü¸£°Ô ÇнÀÇÏ°í °ËÃâÇϱâ À§ÇØ ÀÌÁø ºí·Ï ¿µ»óÀ» Àû¿ëÇÏ¿´°í ÇнÀ ¼º´ÉÀ» Çâ»ó½ÃÅ°±â À§ÇØ ÇнÀ ¿µ»óÀ» Ãß°¡·Î »ý¼ºÇÏ´Â µ¥ÀÌÅÍ Áõ° ±â¹ýÀ» »ç¿ëÇÏ¿´´Ù. ¼±¼ö À§Ä¡ÀÇ Á¤È®µµ Æò°¡ ôµµ´Â ¸ñÇ¥ °´Ã¼ÀÇ Áß½ÉÁ¡°ú Áö´É¸ÁÀ» ÅëÇØ °ËÃâµÈ È®·ü Á߽ɰúÀÇ °Å¸®¸¦ Æò°¡ ôµµ·Î Àû¿ëÇÏ¿´´Ù. ½ÇÇè °á°ú´Â Á¦¾ÈÇÑ ¹æ¹ýÀÇ Æò±Õ °Å¸®°¡ 2.92Çȼ¿·Î Faster R-CNNÀÇ Æò±Õ °Å¸®ÀÎ 3.35º¸´Ù 0.43Çȼ¿ÀÌ ³·¾Æ ¼±¼öÀÇ À§Ä¡ °ËÃâ Á¤È®µµ°¡ ³ôÀ¸¸ç, ¼öÇà ¼Óµµµµ Á¦¾ÈÇÑ ¹æ¹ýÀÌ Faster R-CNNº¸´Ù 69.93¹è ºü¸§À» º¸¿©ÁØ´Ù.
¿µ¹®³»¿ë
(English Abstract)
The paper proposes a player location detection system in a baseball game broadcast. Location detection system uses CNN (convolutional neural network) suitable for image processing among diverse deep learning systems. To train the location of a player faster and accurately, we choose binary block labeling instead of the commonly used edge detection methods. Data augmentation method, which generates additional training images was applied to increase the degree of accuracy. The distance between the center position of the target and the output position by neural network was used to measure performance. Experimental results indicated that the average pixel distances between center of target position and one of output are 2.92 and 3.35 in the case of the proposed method and Faster R-CNN, respectively. In addition, the execution time of the proposed method was established to be 69.93 times faster than that of Faster R-CNN.
Å°¿öµå(Keyword)
À̹ÌÁö À§Ä¡ °ËÃâ
µö·¯´×
CNN
¾ß±¸ °æ±â Áß°è
image detection algorithm
deep learning
CNN
baseball broadcasting
ÆÄÀÏ÷ºÎ
PDF ´Ù¿î·Îµå
¸ñ·Ï
Copyright(c)
Computer Science Engineering Research Information Center
. All rights reserved.