• 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 : 5 / 17 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) ¿µ»ó±â¹Ý ÁÖÂ÷°ø°£ ºÐ·ù µö ¸ðµ¨À» À§ÇÑ µ¥ÀÌÅÍ Áõ°­±â¹ý
¿µ¹®Á¦¸ñ(English Title) Data Augmentation for Image based Parking Space Classification Deep Model
ÀúÀÚ(Author) Hojin Yoo   Kyungkoo Jun   À¯È£Áø   Àü°æ±¸  
¿ø¹®¼ö·Ïó(Citation) VOL 49 NO. 02 PP. 0126 ~ 0136 (2022. 02)
Çѱ۳»¿ë
(Korean Abstract)
ÃÊÀ½ÆÄ ¼¾¼­ ¶Ç´Â Ä«¸Þ¶ó¸¦ ÀÌ¿ëÇÑ ÁÖÂ÷ Á¡À¯»óÅ ÆÇ´Ü ½Ã½ºÅÛÀÌ ½Ç³» ÁÖÂ÷Àå À§ÁÖ·Î ¸¹ÀÌ »ç ¿ëµÇ°í ÀÖ´Ù. ±×·¯³ª ½Ç¿Ü ÁÖÂ÷ÀåÀÇ °æ¿ì, ÀÌ·¯ÇÑ ½Ã½ºÅÛµéÀÇ ³ôÀº ¼³Ä¡ ºñ¿ë°ú Á¤È®µµ ¹®Á¦·Î µµÀÔ¿¡ ÇÑ°è°¡ ÀÖ´Ù. ¶ÇÇÑ, Á¶¸í »óÅÂ, Ä«¸Þ¶ó À§Ä¡, ±×¸®°í ÁöÇüÁö¹°ÀÇ ´Ù¾ç¼ºÀ¸·Î ÀÎÇØ ´ëÇ¥¼ºÀ» °¡Áö´Â ÇнÀµ¥ÀÌÅÍ È®º¸¿¡ ¾î·Á¿òÀÌ ÀÖ¾î µö·¯´× Àû¿ëÀÌ Á¦ÇѵȴÙ. º» ³í¹®¿¡¼­´Â ÀÌ·¯ÇÑ µ¥ÀÌÅÍ ºÎÁ· »óȲ¿¡¼­ Áõ°­±â¹ýµéÀÌ ÁÖÂ÷»óÅ ºÐ·ù¸¦ À§ÇÑ µö ¸ðµ¨ ¼º´É¿¡ ¹ÌÄ¡´Â ¿µÇâÀ» ºÐ¼®ÇÑ´Ù. À̸¦ À§ÇØ, ÁÖÂ÷±¸¿ª ¿µ»óÀ» »óȲº°·Î ºÐ·ùÇÏ°í, ³× °¡Áö Áõ°­±â¹ýµéÀ» ResNet, EfficientNet ±×¸®°í MobileNetÀÇ ÇнÀ¿¡ Àû¿ëÇÏ¿´´Ù. ¼º´ÉÆò°¡ °á°ú, mixup, stopper, rescaling ¹æ¹ý¿¡¼­ °¢°¢ ÃÖ´ë 5.2, 8.67, 15.44% Æ÷ÀÎÆ® Á¤È®µµ°¡ Çâ»óµÇ¾ú´Ù. ¹Ý¸é¿¡, ´Ù¸¥ ¿¬±¸µé¿¡¼­ ¼º´É Çâ»ó È¿°ú°¡ ÀÖ¾ú´ø center cropÀÇ °æ¿ì Á¤È®µµ°¡ Æò±Õ 4.86% Æ÷ÀÎÆ® Ç϶ôÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
A parking occupancy state determination system using an ultrasonic sensor or a camera is mainly used in indoor parking lots. However, in the case of an outdoor parking lot, there is a limit to the introduction of these systems due to the high installation cost and accuracy problems. In addition, the application of deep learning is restricted because it is difficult to obtain representative learning data due to diverse lighting conditions, camera positions, and features. In this paper, we analyzed the effect of augmentation techniques on the performance of a deep model for parking status classification in such a data shortage situation. To this end, the parking area images were classified by situations. Four augmentation techniques were applied to the training of ResNet, EfficientNet, and MobileNet. Based on performance evaluation, the accuracy was improved by up to 5.2%, 8.67%, and 15.44%p in the case of mixup, stopper, and rescaling methods, respectively. On the other hand, in the case of center crop, which was known to have performance improvement in other studies, the accuracy decreased by an average of 4.86%p.
Å°¿öµå(Keyword) ¾ß¿Ü ÁÖÂ÷Àå   ÄÄÇ»ÅÍ ºñÀü   µö ¸ðµ¨   µ¥ÀÌÅÍ Áõ°­   outdoor parking   computer vision   deep model   data augmentation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå