Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö B
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
¿¬¼Ó ¿µ»ó ±â¹Ý ½Ç½Ã°£ °´Ã¼ ºÐÇÒ |
¿µ¹®Á¦¸ñ(English Title) |
Real-Time Object Segmentation in Image Sequences |
ÀúÀÚ(Author) |
°ÀǼ±
À¯½ÂÈÆ
Eui-Seon Kang
Seung-Hun Yoo
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 18-B NO. 04 PP. 0173 ~ 0180 (2011. 08) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®Àº GPU(Graphics Processing Unit) ¿¡¼ CUDA(Compute Unified Device Architecture)¸¦ »ç¿ëÇÏ¿© ½Ç½Ã°£À¸·Î °´Ã¼¸¦ ºÐÇÒÇÏ´Â ¹æ¹ýÀ» ¼Ò°³ÇÑ´Ù. ÃÖ±Ù¿¡ °¨½Ã ½Ã½ºÅÛ, ¿ÀºêÁ§Æ® ÃßÀû, ¸ð¼Ç ºÐ¼® µîÀÇ ¸¹Àº ÀÀ¿ë ÇÁ·Î±×·¥µéÀº ½Ç½Ã°£ 󸮰¡ ¿ä±¸µÈ´Ù. ÀÌ·¯ÇÑ ´Ü°èÀÇ ¼±ÇàºÎºÐÀÎ °´Ã¼ ºÐÇÒ ±â¹ýÀº ±âÁ¸ CPU ±â¹ÝÀÇ ½Ã½ºÅÛÀ¸·Î´Â ½Ç½Ã°£ 󸮿¡ Á¦¾àÀÌ ¹ß»ýÇÑ´Ù. NVIDIA¿¡¼´Â Parallel Processing for General Computation À» À§ÇØ ±×·¡ÇÈ Çϵå¿þ¾î Á¦¾àÀ» °³¼±ÇÑ CUDA platformÀ» Á¦°øÇÏ°í ÀÖ´Ù. º» ³í¹®¿¡¼´Â °´Ã¼ ÃßÃâ ´Ü°è¿¡ ´ëÇ¥ÀûÀÎ ÀûÀÀÀû °¡¿ì½Ã¾È È¥ÇÕ ¹è°æ ¸ðµ¨¸µ(Adaptive Gaussian Mixture Background Modeling) ¾Ë°í¸®Áò°ú Classification ±â¹ýÀ¸·Î »ç¿ëµÇ´Â CCL (Connected Component Labeling) ¾Ë°í¸®ÁòÀ» Àû¿ëÇÏ¿´´Ù. º» ³í¹®Àº 2.4GHz¸¦ °®´Â Core2 Quad ÇÁ·Î¼¼¼¿Í ºñ±³ÇÏ¿© Æò°¡ÇÏ¿´°í ±× °á°ú 3~4¹è ÀÌ»óÀÇ ¼º´ÉÇâ»óÀ» È®ÀÎÇÒ ¼ö ÀÖ¾ú´Ù. |
¿µ¹®³»¿ë (English Abstract) |
This paper shows an approach for real-time object segmentation on GPU (Graphics Processing Unit) using CUDA (Compute Unified Device Architecture). Recently, many applications that is monitoring system, motion analysis, object tracking or etc require real-time processing. It is not suitable for object segmentation to procedure real-time in CPU. NVIDIA provide CUDA platform for Parallel Processing for General Computation to upgrade limit of Hardware Graphic. In this paper, we use adaptive Gaussian Mixture Background Modeling in the step of object extraction and CCL(Connected Component Labeling) for classification. The speed of GPU and CPU is compared and evaluated with implementation in Core2 Quad processor with 2.4GHz.The GPU version achieved a speedup of 3x-4x over the CPU version. |
Å°¿öµå(Keyword) |
GPU(Graphics Processing Unit)
CUDA(Compute Unified Device Architecture)
°´Ã¼ ºÐÇÒ
Object Segmentation
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|