Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Faster R-CNN ±â¹ÝÀÇ ½Ç½Ã°£ ¹øÈ£ÆÇ °ËÃâ |
¿µ¹®Á¦¸ñ(English Title) |
Real-Time License Plate Detection Based on Faster R-CNN |
ÀúÀÚ(Author) |
À̵¿¼®
À±¼÷
ÀÌÀçȯ
¹Úµ¿¼±
Dongsuk Lee
Sook Yoon
Jaehwan Lee
Dong Sun Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 05 NO. 11 PP. 0511 ~ 0520 (2016. 11) |
Çѱ۳»¿ë (Korean Abstract) |
ÀÚµ¿Â÷ ¹øÈ£ÆÇ °ËÃâ ÀÚµ¿È(ALPD: Automatic License Plate Detection) ½Ã½ºÅÛÀº È¿À²ÀûÀÎ ±³Åë °üÁ¦¸¦ À§ÇÑ ÇÙ½É ±â¼úÀ̸ç, ÅëÇà·á ÁöºÒ½Ã½ºÅÛ, ÁÖÂ÷Àå ¹× ±³Åë °ü¸®¿Í °°Àº ¸¹Àº ÀÀ¿ë¿¡ »ç¿ëµÇ¾î ¾÷¹«ÀÇ È¿À²À» ³ôÀÌ°í ÀÖ´Ù. ÃÖ±Ù±îÁöÀÇ ALPD¿¡ °üÇÑ ¿¬±¸¿¡¼´Â ÁÖ·Î ¿µ»ó󸮸¦ À§ÇØ ¼³°èµÈ ±âÁ¸ÀÇ Æ¯Â¡µéÀ» ÃßÃâÇÏ¿© ¹øÈ£ÆÇ °ËÃâ¿¡ »ç¿ëÇØ¿Ô´Ù. ÀÌ·¯ÇÑ Á¾·¡ÀÇ ¹æ¹ýÀº ¼Óµµ¿¡ ÀÌÁ¡Àº ÀÖÀ¸³ª, ´Ù¾çÇÑ È¯°æ º¯È¿¡ µû¸¥ ¼º´É ÀúÇϸ¦ º¸¿´´Ù. º» ³í¹®¿¡¼´Â Àü¹ÝÀûÀÎ ¼º´ÉÀ» Çâ»ó½ÃÅ°±â À§ÇÏ¿© Faster R-CNN°ú CNNÀ¸·Î ±¸¼ºµÇ´Â µÎ ´Ü ±¸Á¶¸¦ È°¿ëÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. À̸¦ ÅëÇØ µ¿ÀÛ ¼Óµµ¸¦ Çâ»ó½ÃÅ°°í, ´Ù¾çÇÑ È¯°æº¯È¿¡ °ÀÎÇϵµ·Ï ±¸¼ºÇÏ¿´´Ù. ù ¹ø° ´Ü°è¿¡¼´Â Faster R-CNNÀ» Àû¿ëÇÏ¿© ¹øÈ£ÆÇ ¿µ¿ª Èĺ¸¿µ¿ªµéÀ» ¼±º°Çϸç, µÎ ¹ø° ´Ü¿¡¼ CNNÀ» È°¿ëÇÏ¿© Èĺ¸¿µ¿ªµé Áß¿¡¼ False Positives¸¦ Á¦°ÅÇÔÀ¸·Î½á °ËÃâ·üÀ» Çâ»ó½ÃÄ×´Ù. À̸¦ ÅëÇØ ZFNetÀ» ±â¹ÝÀ¸·Î ÇÏ¿© 99.94%ÀÇ °ËÃâ·üÀ» ´Þ¼ºÇÏ¿´´Ù. ¶ÇÇÑ Æò±Õ ¿î¿ë½Ã°£Àº 80ms/image·Î½á ºü¸£°í °ÀÎÇÑ ½Ç½Ã°£ ¹øÈ£ÆÇ °ËÃ⠽ýºÅÛÀ» ±¸ÇöÇÒ ¼ö ÀÖ¾ú´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
Automatic License Plate Detection (ALPD) is a key technology for a efficient traffic control. It is used to improve work efficiency in many applications such as toll payment systems and parking and traffic management. Until recently, the hand-crafted features made for image processing are used to detect license plates in most studies. It has the advantage in speed. but can degrade the detection rate with respect to various environmental changes. In this paper, we propose a way to utilize a Faster Region based Convolutional Neural Networks (Faster R-CNN) and a Conventional Convolutional Neural Networks (CNN), which improves the computational speed and is robust against changed environments. The module based on Faster R-CNN is used to detect license plate candidate regions from images and is followed by the module based on CNN to remove False Positives from the candidates. As a result, we achieved a detection rate of 99.94% from images captured under various environments. In addition, the average operating speed is 80ms/image. We implemented a fast and robust Real-Time License Plate Detection System.
|
Å°¿öµå(Keyword) |
ÀÚµ¿Â÷ ¹øÈ£ÆÇ
Deep Learning
ÄÁº¼·ç¼Ç ½Å°æ¸Á
Faster Region Based Convolutional Neural Networks
License Plate
Deep Learning
Convolutional Neural Network
Faster Region Based Convolutional Neural Network
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|