Highly efficient CAVLC encoder for MPEG-4 AVC/H.264

T. H. Tsai, S. P. Chang, T. L. Fang

Research output: Contribution to journalArticlepeer-review

9 Scopus citations


In dealing with high-resolution video information, encoding (or decoding) with an efficient context-based adaptive variable length code (CAVLC) encoder is important. A highly efficient CAVLC encoder is proposed for video coding application of MPEG-4 AVC/H.264. The main concept is to use block-based pipelining to speed up encoding efficiency and reduce the pipeline storage elements by using the associated input buffer. We also use zero-block detection to speed up encoding efficiency and eliminate the same codeword from all the tables to save the hardware cost. Simulation results show that our design can meet the real-time processing for 1920×1088 resolution with lower operation frequency. We also accomplish the higher encoding throughput with a more complete CAVLC design than others. The proposed design has been implemented and synthesised with TSMC 0.18m standard cell library. The synthesis result indicates that the gate count is 12125 with the clock constraint of 125MHz.

Original languageEnglish
Pages (from-to)116-124
Number of pages9
JournalIET Circuits, Devices and Systems
Issue number3
StatePublished - 2009


Dive into the research topics of 'Highly efficient CAVLC encoder for MPEG-4 AVC/H.264'. Together they form a unique fingerprint.

Cite this