• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Àü¹æ Â÷·® ¿òÁ÷ÀÓ ÃßÁ¤ ¾Ë°í¸®Áò
¿µ¹®Á¦¸ñ(English Title) Forward Vehicle Movement Estimation Algorithm
ÀúÀÚ(Author) ¹ÚÇѵ¿   ¿ÀÁ¤¼ö   Han-dong Park   Jeong-su Oh  
¿ø¹®¼ö·Ïó(Citation) VOL 21 NO. 09 PP. 1697 ~ 1702 (2017. 09)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®Àº ¿µ»ó ±â¹Ý Àü¹æ Ãßµ¹ °æ°í¸¦ À§ÇÑ Àü¹æ Â÷·® ¿òÁ÷ÀÓ ÃßÁ¤ ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÑ´Ù. »çÀü¿¡ ÃëµæµÈ ¿µ»ó¿¡¼­ Â÷µµ ¿µ¿ªÀÌ °ü½É ¿µ¿ªÀ¸·Î ÁöÁ¤µÇ°í °Å¸® ÂüÁ¶Ç¥°¡ »ý¼ºµÈ´Ù. °Å¸® ÂüÁ¶Ç¥´Â ½ÇÇè Â÷·® À§Ä¡ÀÎ ±âÁØ È­¼Ò¿¡¼­ °ü½É¿µ¿ª »ó Â÷·® À§Ä¡ÀÎ ÀÓÀÇ È­¼Ò±îÁö ¼öÆò°ú ¼öÁ÷ ½ÇÁ¦ °Å¸®¸¦ º¸¿©ÁÖ´Ù. Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀº °ü½É¿µ¿ª¿¡¼­ Â÷·®µéÀ» °ËÃâÇÏ°í, °ËÃâµÈ Â÷·®µé¿¡°Ô ·¹À̺íÀ» ÁöÁ¤ÇÏ°í, °Å¸® ÂüÁ¶Ç¥¸¦ ÀÌ¿ëÇØ ±×µéÀÇ °Å¸® Á¤º¸¸¦ ÀúÀåÇÑ´Ù. ±×¸®°í ³ª¼­ Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀº ÇÁ·¹ÀÓ°£ °Å¸® º¯È­¸¦ ÀÌ¿ëÇØ Á¢±Ù °Å¸®, Ãø¹æ Á¢±Ù ¼Óµµ, Àü¹æ Á¢±Ù ¼Óµµ °°Àº Â÷·® ¿òÁ÷ÀÓµéÀ» ÃßÁ¤ÇÑ´Ù. µµ·Î ÁÖÇà µ¿¿µ»óµéÀ» ÀÌ¿ëÇÑ Àü¹æ Â÷·® ¿òÁ÷ÀÓ ÃßÁ¤ ½ÇÇè¿¡¼­ Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀº Â÷·® ¿òÁ÷Àӵ鿡 ´ëÇØ °¢°¢ Æò±Õ 98.7%, 95.9%, 94.3%¸¦ À¯È¿ÇÏ°Ô ÃßÁ¤ÇÏ°í ÀÖ´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper proposes a forward vehicle movement estimation algorithm for the image-based forward collision warning. The road region in the acquired image is designated as a region of interest (ROI) and a distance look up table (LUT) is made in advance. The distance LUT shows horizontal and vertical real distances from a reference pixel as a test vehicle position to any pixel as a position of a vehicle on the ROI. The proposed algorithm detects vehicles in the ROI, assigns labels to them, and saves their distance information using the distance LUT. And then the proposed algorithm estimates the vehicle movements such as approach distance, side-approaching and front-approaching velocities using distance changes between frames. In forward vehicle movement estimation test using road driving videos, the proposed algorithm makes the valid estimation of average 98.7%, 95.9%, 94.3% in the vehicle movements, respectively.
Å°¿öµå(Keyword) ¿òÁ÷ÀÓ ÃßÁ¤   °Å¸® ÂüÁ¶Ç¥   Â÷·® °ËÃâ   Àü¹æ Ãßµ¹   top-view º¯È¯   Movement estimation   Distance LUT   Vehicle detection   Forward collision   Top-view transform  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå