• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2017³â Ãß°èÇмú´ëȸ

2017³â Ãß°èÇмú´ëȸ

Current Result Document : 144 / 213 ÀÌÀü°Ç ÀÌÀü°Ç   ´ÙÀ½°Ç ´ÙÀ½°Ç

ÇѱÛÁ¦¸ñ(Korean Title) °í¼º´É ·çÇÁ³» ÇÊÅ͸¦ À§ÇÑ È¿À²ÀûÀÎ SAO Çϵå¿þ¾î ¼³°è
¿µ¹®Á¦¸ñ(English Title) Hardware Design of Efficient SAO for High Performance In-loop filters
ÀúÀÚ(Author) ¹Ú½Â¿ë   ·ù±¤±â   Seungyong Park   Kwangki Ryoo  
¿ø¹®¼ö·Ïó(Citation) VOL 21 NO. 02 PP. 0543 ~ 0545 (2017. 10)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â °í¼º´É ·çÇÁ³» ÇÊÅ͸¦ À§ÇÑ SAO Çϵå¿þ¾î ±¸Á¶ ¼³°è¿¡ ´ëÇØ ±â¼úÇÑ´Ù. SAO´Â ·çÇÁ³» ÇÊÅÍ ³»ºÎ ¸ðµâÀ̸ç, ºí·Ï ´ÜÀ§ ¿µ»ó ¾ÐÃà ¹× ¾çÀÚÈ­ µî¿¡¼­ ¹ß»ýÇÏ´Â Á¤º¸ÀÇ ¼Õ½ÇÀ» º¸»óÇÏ´Â ±â¼úÀÌ´Ù. ÇÏÁö¸¸, HEVCÀÇ SAO´Â Çȼ¿ ´ÜÀ§ ¿¬»êÀ» ¼öÇàÇϱ⠶§¹®¿¡ ³ôÀº ¿¬»ê ½Ã°£À» ¿ä±¸ÇÑ´Ù. µû¶ó¼­ º» ³í¹®¿¡¼­ Á¦¾ÈÇÏ´Â SAO Çϵå¿þ¾î ±¸Á¶´Â °í¼Ó¿¬»êÀ» À§ÇØ 4x4 ºí·Ï ¿¬»ê°ú 2´Ü ÆÄÀÌÇÁ ¶óÀÎ ±¸Á¶¸¦ ±â¹ÝÀ¸·Î ÇÑ´Ù. SAO ¿¬»êÀ» À§ÇÑ Á¤º¸»ý¼º ¹× offset ¿¬»ê±¸Á¶´Â º´·Ä±¸Á¶·Î ¼³°èÇÏ¿© ¿¬»ê½Ã°£À» ÃÖ¼ÒÈ­ ÇÏ¿´´Ù. Á¦¾ÈÇÏ´Â Çϵå¿þ¾î ±¸Á¶´Â Verilog HDL·Î ¼³°èÇÏ¿´À¸¸ç, TSMC Ĩ °øÁ¤130nm ¹× 65nm ¼¿ ¶óÀ̺귯¸®·Î ÇÕ¼ºÀ» ÁøÇàÇÏ¿´´Ù. 130nm¿¡¼­ ÃÖ´ë µ¿ÀÛ ÁÖÆļö´Â 476MHzÀÌ°í, Àüü °ÔÀÌÆ® ¼ö´Â 163kÀÌ´Ù. 65nm¿¡¼­ ÃÖ´ë µ¿ÀÛ ÁÖÆļö´Â 312.5MHzÀÌ°í, Àüü °ÔÀÌÆ® ¼ö´Â 193.6kÀÌ´Ù.
¿µ¹®³»¿ë
(English Abstract)
This paper describes the SAO hardware architecture design for high performance in-loop filters. SAO is an inner module of in-loop filter, which compensates for information loss caused by block-based image compression and quantization. However, HEVC's SAO requires a high computation time because it performs pixel-unit operations. Therefore, the SAO hardware architecture proposed in this paper is based on a 4x4 block operation and a 2-stage pipeline structure for high-speed operation. The information generation and offset computation structure for SAO computation is designed in a parallel structure to minimize computation time. The proposed hardware architecture was designed with Verilog HDL and synthesized with TSMC chip process 130nm and 65nm cell library. The proposed hardware design achieved a maximum frequency of 476MHz yielding 163k gates and 312.5MHz yielding 193.6k gates on the 130nm and 65nm processes respectively.
Å°¿öµå(Keyword) HEVC   In-loop filter   Sample Adaptive Offset   SAO  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå