• 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 :

ÇѱÛÁ¦¸ñ(Korean Title) 3Â÷¿ø Àå¸é º¹¿øÀ» À§ÇÑ °­°ÇÇÑ ½Ç½Ã°£ ½Ã°¢ ÁÖÇà °Å¸® ÃøÁ¤
¿µ¹®Á¦¸ñ(English Title) Robust Real-Time Visual Odometry Estimation for 3D Scene Reconstruction
ÀúÀÚ(Author) ±èÁÖÈñ   ±èÀÎö   Joo-Hee Kim   In-Cheol Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 04 NO. 04 PP. 0187 ~ 0194 (2015. 04)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â RGB-D ÀÔ·Â ¿µ»óµé·ÎºÎÅÍ 3Â÷¿ø °ø°£À» ¿òÁ÷ÀÌ´Â Ä«¸Þ¶óÀÇ ½Ç½Ã°£ Æ÷Á È¿°úÀûÀ¸·Î ÃßÀûÇÒ ¼ö ÀÖ´Â ½Ã°¢ ÁÖÇà °Å¸® ÃøÁ¤±â¸¦ Á¦¾ÈÇÑ´Ù. º» ³í¹®¿¡¼­ Á¦¾ÈÇÏ´Â ½Ã°¢ ÁÖÇà °Å¸® ÃøÁ¤±â¿¡¼­´Â Ä÷¯ ¿µ»ó°ú ±íÀÌ ¿µ»óÀÇ Ç³ºÎÇÑ Á¤º¸¸¦ ÃæºÐÈ÷ È°¿ëÇϸ鼭µµ ½Ç½Ã°£ °è»ê·®À» ÁÙÀ̱â À§ÇØ, Ư¡ ±â¹ÝÀÇ Àú¹Ðµµ ÁÖÇà °Å¸® °è»ê ¹æ¹ýÀ» »ç¿ëÇÑ´Ù. º» ½Ã½ºÅÛ¿¡¼­´Â º¸´Ù Á¤È®ÇÑ ÁÖÇà °Å¸® ÃßÁ¤Ä¡¸¦ ¾ò±â À§ÇØ, Ä«¸Þ¶ó À̵¿ ÀÌÀü°ú À̵¿ ÀÌÈÄÀÇ ¿µ»ó¿¡¼­ ÃßÃâÇÑ Æ¯Â¡µéÀ» Á¤ÇÕÇÑ µÚ, Á¤ÇÕµÈ Æ¯Â¡µé¿¡ ´ëÇÑ Ãß°¡ÀûÀÎ Á¤»ó ÁýÇÕ Á¤Á¦ °úÁ¤°ú ÁÖÇà°Å¸® Á¤Á¦ ÀÛ¾÷À» ¹Ýº¹ÇÑ´Ù. ¶ÇÇÑ, Á¤Á¦ ÈÄ ÀÜ¿© Á¤»ó ÁýÇÕÀÇ Å©±â°¡ ÃæºÐÄ¡ ¾ÊÀº °æ¿ì¿¡µµ ÀÜ¿© Á¤»ó ÁýÇÕÀÇ Å©±â¿¡ ºñ·ÊÇØ ÃÖÁ¾ ÁÖÇà °Å¸®¸¦ °áÁ¤ÇÔÀ¸·Î½á, ÃßÀû ¼º°ø·üÀ» Å©°Ô Çâ»ó½ÃÄ×´Ù. TUM ´ëÇÐÀÇ º¥Ä¡¸¶Å© µ¥ÀÌÅÍ ÁýÇÕÀ» ÀÌ¿ëÇÑ ½ÇÇè°ú 3Â÷¿ø Àå¸é º¹¿ø ÀÀ¿ë ½Ã½ºÅÛÀÇ ±¸ÇöÀ» ÅëÇØ, º» ³í¹®¿¡¼­ Á¦¾ÈÇÏ´Â ½Ã°¢ ÁÖÇà °Å¸® ÃøÁ¤ ¹æ¹ýÀÇ ³ôÀº ¼º´ÉÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we present an effective visual odometry estimation system to track the real-time pose of a camera moving in 3D space. In order to meet the real-time requirement as well as to make full use of rich information from color and depth images, our system adopts a feature-based sparse odometry estimation method. After matching features extracted from across image frames, it repeats both the additional inlier set refinement and the motion refinement to get more accurate estimate of camera odometry. Moreover, even when the remaining inlier set is not sufficient, our system computes the final odometry estimate in proportion to the size of the inlier set, which improves the tracking success rate greatly. Through experiments with TUM benchmark datasets and implementation of the 3D scene reconstruction application, we confirmed the high performance of the proposed visual odometry estimation method.
Å°¿öµå(Keyword) RGB-D ¿µ»ó   ½Ã°¢ ÁÖÇà °Å¸® ÃøÁ¤   3Â÷¿ø Àå¸é º¹¿ø   Ư¡-±â¹Ý Àú¹Ðµµ ¹æ¹ý   RGB-D Images   Visual Odometry   3D Scene Reconstruction   Feature-Based Sparse Method  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå