Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
3Â÷¿ø Á¡±ºµ¥ÀÌÅÍÀÇ ±íÀÌ ¿µ»ó º¯È¯ ¹æ¹ý ¹× Çϵå¿þ¾î ±¸Çö |
¿µ¹®Á¦¸ñ(English Title) |
Conversion Method of 3D Point Cloud to Depth Image and Its Hardware Implementation |
ÀúÀÚ(Author) |
Àå°æÈÆ
Á¶±â»Ý
±è±ÙÁØ
°ºÀ¼ø
Kyounghoon Jang
Gippeum Jo
Geun-Jun Kim
Bongsoon Kang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 18 NO. 10 PP. 2443 ~ 2450 (2014. 10) |
Çѱ۳»¿ë (Korean Abstract) |
±íÀÌ ¿µ»óÀ» ÀÌ¿ëÇÑ µ¿ÀÛ ÀÎ½Ä ½Ã½ºÅÛ¿¡¼´Â È¿À²ÀûÀÎ ¾Ë°í¸®Áò Àû¿ëÀ» À§ÇÏ¿© ±íÀÌ ¿µ»óÀ» 3Â÷¿ø Á¡±º µ¥ÀÌÅÍ·Î ±¸¼ºµÇ´Â ½ÇÁ¦ °ø°£À¸·Î º¯È¯ÇÏ¿© ¾Ë°í¸®ÁòÀ» Àû¿ëÇÑ ÈÄ Åõ¿µ°ø°£À¸·Î º¯È¯ÇÏ¿© Ãâ·ÂÇÑ´Ù. ÇÏÁö¸¸ º¯È¯ °úÁ¤ Áß ¹Ý¿Ã¸² ¿ÀÂ÷¿Í Àû¿ëµÇ´Â ¾Ë°í¸®Áò¿¡ ÀÇÇÑ µ¥ÀÌÅÍ ¼Õ½ÇÀÌ ¹ß»ýÇÏ°Ô µÈ´Ù. º» ³í¹®¿¡¼´Â 3Â÷¿ø Á¡±º µ¥ÀÌÅÍ¿¡¼ ±íÀÌ ¿µ»óÀ¸·ÎÀÇ º¯È¯ ½Ã ¹Ý¿Ã¸² ¿ÀÂ÷¿Í ¿µ»óÀÇ Å©±â º¯È¿¡ µû¸¥ µ¥ÀÌÅÍ ¼Õ½ÇÀÌ ¹ß»ýÇÏÁö ¾Ê´Â È¿À²ÀûÀÎ ¹æ¹ý°ú À̸¦ Çϵå¿þ¾î·Î ±¸Çö ÇÏ´Â ¹æ¹ýÀ» Á¦¾È ÇÏ¿´´Ù. ÃÖÁ¾ÀûÀ¸·Î Á¦¾ÈµÈ ¾Ë°í¸®ÁòÀº OpenCV¿Í Window ÇÁ·Î±×·¥À» »ç¿ëÇÏ¿© ¼ÒÇÁÆ®¿þ¾îÀûÀ¸·Î ¾Ë°í¸®ÁòÀ» °ËÁõÇÏ¿´°í, Kinect¸¦ »ç¿ëÇÏ¿© ½Ç½Ã°£À¸·Î ¼º´ÉÀ» Å×½ºÆ®ÇÏ¿´´Ù. ¶ÇÇÑ, Verilog-HDLÀ» »ç¿ëÇÏ¿© Çϵå¿þ¾î ½Ã½ºÅÛÀ» ¼³°èÇÏ°í, Xilinx Zynq-7000 FPGA º¸µå¿¡ žÀçÇÏ¿© °ËÁõÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
In the motion recognition system using depth image, the depth image is converted to the real world formed 3D point cloud data for efficient algorithm apply. And then, output depth image is converted by the projective world after algorithm apply. However, when coordinate conversion, rounding error and data loss by applied algorithm are occurred. In this paper, when convert 3D point cloud data to depth image, we proposed efficient conversion method and its hardware implementation without rounding error and data loss according image size change. The proposed system make progress using the OpenCV and the window program, and we test a system using the Kinect in real time. In addition, designed using Verilog-HDL and verified through the Zynq-7000 FPGA Board of Xilinx.
|
Å°¿öµå(Keyword) |
µ¿ÀÛÀνÄ
±íÀÌ ¿µ»ó
3Â÷¿ø Á¡±º µ¥ÀÌÅÍ
ÁÂÇ¥ º¯È¯
Ȧ Á¦°Å
Motion Recognition
Depth Image
3D Point Cloud
Coordinate Conversion
Hole Filling
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|