• 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¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) GAN ±â¹Ý ½ÃÁ¡ º¯È¯À» ÅëÇÑ Â÷·® ¿µ»ó µ¥ÀÌÅÍ È®Àå
¿µ¹®Á¦¸ñ(English Title) Vehicle Image Data Augmentation by GAN-based Viewpoint Transformation
ÀúÀÚ(Author) ¼±ÇÑ°á   À̸íÈñ   È«Âü±æ   ±èÀÎÁß   Hangyel Sun   Myeonghee Lee   Charmgil Hong   Injung Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 08 PP. 0885 ~ 0891 (2021. 08)
Çѱ۳»¿ë
(Korean Abstract)
GANÀ» ÀÌ¿ëÇØ ´Ù¾çÇÑ °¢µµ¿¡¼­ ÃÔ¿µµÈ Â÷·® ¿µ»óÀ» ƯÁ¤ °¢µµ¿¡¼­ ÃÔ¿µµÈ ÁÖÇà ¿µ»óÀ¸·Î º¯È¯ÇÏ´Â ¹æ¹ýÀ» ¼Ò°³ÇÑ´Ù. Â÷·® ¿µ»ó Àνı⸦ ÇнÀÇϱâ À§Çؼ­´Â ƯÁ¤ÇÑ °¢µµ¿¡¼­ ÃÔ¿µÇÑ ´Ù·®ÀÇ Â÷·® ¿µ»ó µ¥ÀÌÅÍ°¡ ¿ä±¸µÈ´Ù. ±×·¯³ª, ¸Å³â »õ·Î Ãâ½ÃµÇ´Â ´Ù¾çÇÑ Â÷Á¾¿¡ ´ëÇÏ¿© ±×·¯ÇÑ ÇнÀ µ¥ÀÌÅ͸¦ ¼öÁýÇÏ´Â °ÍÀº Çö½ÇÀûÀ¸·Î ¾î·Æ´Ù. µû¶ó¼­, ´Ù¾çÇÑ ½ÃÁ¡¿¡¼­ ÃÔ¿µµÈ Â÷·® ¿µ»óÀ» ƯÁ¤ ½ÃÁ¡¿¡¼­ ÃÔ¿µµÈ ¿µ»óÀ¸·Î º¯È¯ÇÔÀ¸·Î½á Â÷·® ¿µ»ó µ¥ÀÌÅ͸¦ È®ÀåÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ¹æ¹ýÀº ¸ÕÀú DRGANÀ» ÀÌ¿ëÇØ ÀÓÀÇÀÇ Â÷·® ¿µ»óÀ» Àü¸é »ó´Ü¿¡¼­ ÃÔ¿µÇÑ ¿µ»óÀ¸·Î º¯È¯ÇÑ ÈÄ DeblurGANÀ¸·Î È­ÁúÀ» °³¼±ÇÏ°í SRGANÀ» ÀÌ¿ëÇØ Çػ󵵸¦ °³¼±ÇÑ´Ù. ½ÇÇèÀ» ÅëÇØ Á¦¾ÈÇÏ´Â ¹æ¹ýÀÌ Á¿ì 45µµ À̳»ÀÇ ¹æÇâ¿¡¼­ ÃÔ¿µÇÑ ¿µ»óÀ» Àü¸é »ó´Ü ½ÃÁ¡ÀÇ ¿µ»óÀ¸·Î ¼º°øÀûÀ¸·Î º¯È¯Çϸç, ¿µ»óÀÇ È­Áú ¹× Çػ󵵸¦ °³¼±Çϴµ¥ È¿°úÀûÀÓÀ» º¸¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
We introduce a novel GAN-based image synthesis method that transforms vehicle images captured from arbitrary viewpoints into images taken from a specific viewpoint. Training a vehicle image recognizer requires a large number of vehicle images taken from a specific viewpoint. However, in practice, it is difficult to collect such training data, especially for newly released vehicles. Therefore, we propose a method of augmenting vehicle image data by converting a vehicle image from an arbitrary viewpoint into an image from a specific viewpoint. The proposed method first transforms a vehicle image from an arbitrary viewpoint to an image taken from the top-front view using DRGAN, then enhances the image quality with DeblurGAN, and finally, improves the resolution using SRGAN. The experimental results demonstrated that the proposed method successfully converted an image taken within 45 degrees left and right into an image from the top-frontal view and was effective in improving the image quality and resolution.
Å°¿öµå(Keyword) GAN   µ¥ÀÌÅÍ È®Àå   ½ÃÁ¡ º¯È¯   È­Áú °³¼±   ÇØ»óµµ °³¼±   Â÷·® ¿µ»ó ÀνĠ  GAN   data augmentation   viewpoint transformation   quality enhancement   super resolution   vehicle image recognition  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå