• 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¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document : 1 / 2

ÇѱÛÁ¦¸ñ(Korean Title) µå·Ð°ú Áö»ó·Îº¿ °£ÀÇ Çù¾÷À» À§ÇÑ ±¤ÇÐÈ帧 ±â¹Ý ¸¶Ä¿ ÃßÀû¹æ¹ý
¿µ¹®Á¦¸ñ(English Title) Optical Flow-Based Marker Tracking Algorithm for Collaboration Between Drone and Ground Vehicle
ÀúÀÚ(Author) ¹éÁ¾È¯   ±è»óÈÆ   Jong-Hwan Beck   Sang-Hoon Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 07 NO. 03 PP. 0107 ~ 0112 (2018. 03)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â µå·Ð°ú Áö»ó ·Îº¿ °£ È¿°úÀûÀÎ Çù¾÷À» À§ÇÏ¿© ±¤ÇÐ È帧 ±â¼ú ±â¹ÝÀÇ Æ¯Â¡Á¡ ÃßÀû ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÏ¿´´Ù. µå·ÐÀÇ ºñÇà Áß ºü¸¥ ¿òÁ÷ÀÓ¿¡ ÀÇÇÏ¿© ¸¹Àº ¹®Á¦Á¡ÀÌ ¹ß»ýÇÏ¿© Áö»ó¹°Ã¼¸¦ ¼º°øÀûÀ¸·Î ÀνÄÇϱâ À§ÇØ Á÷°üÀûÀ̸鼭µµ ½Äº°ÀÚ¸¦ °¡Áö°í ÀÖ´Â ¸¶Ä¿¸¦ »ç¿ëÇß´Ù. Ư¡Á¡ ÃßÃâÀÌ ¿ì¼öÇÑ FAST¾Ë°í¸®Áò°ú ¿òÁ÷ÀÓ °¨Áö°¡ ¿ì¼öÇÑ ·çÄ«½º-Ä«³ªµ¥ ±¤ÇÐÈ帧 ¾Ë°í¸®ÁòÀÇ ÀåÁ¡µéÀ» È¥ÇÕÇÏ¿© ±âÁ¸ Ư¡Á¡-Ư¡·® ±â¹Ý °´Ã¼ ÃßÀû ¹æ¹ýº¸´Ù °³¼±µÈ ¼ÓµµÀÇ ½ÇÇè°á°ú¸¦ º¸¿©ÁØ´Ù. ¶ÇÇÑ Á¦¾ÈÇÑ ¸¶Ä¿ÀÇ °ËÃâ¹æ¹ý¿¡ ÀûÀýÇÑ ÀÌÁøÈ­ ¹æ¹ýÀ» Á¦¾ÈÇÏ¿© ÁÖ¾îÁø ¸¶Ä¿¿¡¼­ÀÇ °ËÃâ Á¤È®µµ¸¦ °³¼±ÇÏ¿´À¸¸ç, ÃßÀû¼Óµµ´Â À¯»çÇÑ È¯°æÀÇ ±âÁ¸¿¬±¸º¸´Ù 40% ÀÌ»ó °³¼±µÊÀ» È®ÀÎÇÏ¿´´Ù. ¶ÇÇÑ ºñÇàµå·ÐÀÇ °æ·®È­¿Í ¼Óµµ°³¼±¿¡ ¹®Á¦°¡ ¾øµµ·Ï ÃÖ¼ÒÇü °í¼º´ÉÀÇ ÀÓº£µðµå ȯ°æÀ» ¼±ÅÃÇÏ¿´À¸¸ç, Á¦ÇÑµÈ °³¹ßȯ°æ¿¡¼­µµ ¹°Ã¼°ËÃâ°ú ÃßÀû µî º¹ÀâÇÑ ¿¬»êÀÌ °¡´ÉÇϵµ·Ï µ¿ÀÛȯ°æ¿¡ ´ëÇÏ¿© ¿¬±¸ÇÏ¿´´Ù. ÇâÈÄ¿¡´Â ´Ù¸¥ ȯ°æ¿¡¼­ ºü¸£°Ô ¿òÁ÷ÀÌ´Â µÎ ·Îº¿ °£ÀÇ Çù¾÷ÀÇ Á¤È®µµ¸¦ Çâ»ó½ÃÅ°±â À§ÇØ Áö´ÉÀû ºñÀü±â´É¿¡ ´ëÇØ Ãß°¡ÇÒ ¿¹Á¤ÀÌ´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, optical flow based keypoint detection and tracking technique is proposed for the collaboration between flying drone with vision system and ground robots. There are many challenging problems in target detection research using moving vision system, so we combined the improved FAST algorithm and Lucas-Kanade method for adopting the better techniques in each feature detection and optical flow motion tracking, which results in 40% higher in processing speed than previous works. Also, proposed image binarization method which is appropriate for the given marker helped to improve the marker detection accuracy. We also studied how to optimize the embedded system which is operating complex computations for intelligent functions in a very limited resources while maintaining the drone¡¯s present weight and moving speed. In a future works, we are aiming to develop collaborating smarter robots by using the techniques of learning and recognizing targets even in a complex background.
Å°¿öµå(Keyword) ¸¶Ä¿ ÃßÀû   ±¤ÇÐ È帧   ·Îº¿ Çù¾÷   Ư¡Á¡ ÃßÃâ   Marker Tracking   Optical Flow   Robot Collaboration   Keypoint Detection  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå