Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
»ö»óºÐÆ÷¿¡ ±â¹ÝÇÑ ÀûÀÀÇü »ùÇøµ ¹× 6Â÷¿ø ICP |
¿µ¹®Á¦¸ñ(English Title) |
6D ICP Based on Adaptive Sampling of Color Distribution |
ÀúÀÚ(Author) |
±èÀÀ¼ö
ÃÖ¼ºÀÎ
¹Ú¼ø¿ë
Eung-Su Kim
Sung-In Choi
Soon-Yong Park
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 05 NO. 09 PP. 0401 ~ 0410 (2016. 09) |
Çѱ۳»¿ë (Korean Abstract) |
3Â÷¿ø Á¤ÇÕÀ̶õ ´Ù½ÃÁ¡¿¡¼ ȹµæÇÑ 3Â÷¿ø Á¡±ºµéÀ» Á¤·ÄÇÏ´Â ±â¼ú·Î½á Áö³ ¼ö½Ê ³â°£ ¸¹Àº ¿¬±¸°¡ ÁøÇàµÇ°í ÀÖ´Â ºÐ¾ßÀÌ´Ù. ÀÌ·¯ÇÑ 3Â÷¿øÁ¤ÇÕÀº ICP(Iterative Closest Point) ¾Ë°í¸®ÁòÀ» ½ÃÀÛÀ¸·Î ¸¹Àº º¯Çü ICP°¡ ¼Ò°³µÇ°í ÀÖ´Ù. ÇÏÁö¸¸ ICP °è¿ÀÇ ¾Ë°í¸®ÁòµéÀº ÃÖ±ÙÁ¢Á¡À» ´ëÀÀÁ¡À¸·Î °£ÁÖÇÏ¿© ¾Ë°í¸®ÁòÀ» ¼öÇàÇÑ´Ù. ±×·¸±â ¶§¹®¿¡ 3Â÷¿ø Á¡±ºÀÇ Ãʱ⠿ÀÂ÷°¡ Å« °æ¿ì Á¤È®ÇÑ ´ëÀÀÁ¡ Ž»ö¿¡ ½ÇÆÐÇÒ ¼ö ÀÖ´Ù. ÀÌ·± ¹®Á¦Á¡À» ÇØ°áÇϱâ À§ÇØ º» ³í¹®¿¡¼´Â »ö»ó°ú 3Â÷¿ø °Å¸®°¡ À¶ÇÕµÈ 6Â÷¿ø °Å¸®¿Í »ö»óºÐÆ÷ À¯»çµµ¸¦ ÀÌ¿ëÇÑ´Ù. ´õ ³ª¾Æ°¡ »ö»ó ºÐÇÒ ±â¹Ý ÀûÀÀÇü »ùÇøµÀ» ÀÌ¿ëÇÏ¿© ¾Ë°í¸®Áò ¿¬»ê ¼Óµµ¸¦ °¨¼Ò½ÃÅ°°í ¼º´ÉÀ» Çâ»ó½ÃÅ°´Â °ÍÀ» ¸ñÇ¥·Î ÇÑ´Ù. ¸¶Áö¸·À¸·Î ½ÇÇèÀ» ÅëÇØ ±âÁ¸ÀÇ ¹æ¹ý°ú º» ³í¹®¿¡¼ Á¦¾ÈÇÏ´Â ¹æ¹ýÀÇ ¼º´ÉÀ» ºñ±³ÇÑ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
3D registration is a computer vision technique of aligning multi-view range images with respect to a reference coordinate system. Various 3D registration algorithms have been introduced in the past few decades. Iterative Closest Point (ICP) is one of the widely used 3D registration algorithms, where various modifications are available nowadays. In the ICP-based algorithms, the closest points are considered as the corresponding points. However, this assumption fails to find matching points accurately when the initial pose between point clouds is not sufficiently close. In this paper, we propose a new method to solve this problem using the 6D distance (3D color space and 3D Euclidean distances). Moreover, a color segmentation-based adaptive sampling technique is used to reduce the computational time and improve the registration accuracy. Several experiments are performed to evaluate the proposed method. Experimental results show that the proposed method yields better performance compared to the conventional methods.
|
Å°¿öµå(Keyword) |
Iterative Closest Point(ICP)
3Â÷¿ø Á¤ÇÕ
»ö»ó ºÐÇÒ
6Â÷¿ø °Å¸®
3D Registration
Color Segmentation
6D Distance
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|