Title :
A Fast JPEG2000 Encoder That Preserves Coding Efficiency: The Split Arithmetic Encoder
Author :
Varma, Krishnaraj ; Damecharla, Hima B. ; Bell, Amy E. ; Carletta, Joan E. ; Back, Godmar V.
Author_Institution :
Hughes Network Syst., Germantown, MD
Abstract :
Embedded block coding, i.e., embedded block coder with optimal truncation (EBCOT) tier-1, is the most computationally intensive part of the JPEG2000 image coding standard. Past research on fast EBCOT tier-1 hardware implementations has concentrated on cycle-efficient context formation. These pass-parallel architectures require that JPEG2000´s three mode switches be turned on; thus, coding efficiency is sacrificed for improved throughput. In this paper, a new fast EBCOT tier-1 design is presented: It is called the split arithmetic encoder (SAE) process. The proposed process exploits concurrency to obtain improved throughput while preserving coding efficiency. The SAE process is evaluated using the following three methods: clock cycle estimation, multithreaded software implementation, and FPGA hardware implementation. All three methods achieve throughput improvement; the hardware implementation exhibits the largest speedup, as expected. The benefits of evaluating a proposed process (algorithm) from different perspectives are illustrated.
Keywords :
arithmetic codes; block codes; field programmable gate arrays; image coding; FPGA hardware implementation; JPEG2000 encoder; clock cycle estimation; coding efficiency; cycle-efficient context formation; embedded block coding; image coding standard; multithreaded software implementation; optimal truncation; split arithmetic encoder; split arithmetic encoder process; Context-state adaptation; EBCOT; FPGA; JPEG2000; MQ coder; context state adaptation; embedded block coder with optimal truncation (EBCOT); field-programmable gate array (FPGA); multithreading;
Journal_Title :
Circuits and Systems I: Regular Papers, IEEE Transactions on
DOI :
10.1109/TCSI.2008.927221