Low-Latency H.264/AVC Encoder Hardware Design with Wavefront Parallelism on FPGA Platform

With network transmission delays reduced, video encoding latency emerges as a critical challenge for live video streaming. Nowadays, H.264/AVC remains the most popular video encoding standard in production due to its relatively low complexity. Therefore, an H.264 encoder with lower encoding latency and cost still has significant application value, but the fact that H.264 standard is not optimized for parallel processing has become a limitation to further reducing encoding latency. In this paper, we propose a dual-core hardware implementation of an H.264-based video encoder that performs wavefront parallelism on FPGA platform and provides full compatibility with the H.264 Baseline Profile. The main challenge is the maintenance of data dependencies of adjacent macroblock (MB) lines, introduced by the dual-core parallelism. To handle this problem, we propose a core scheduling mechanism and use a pair of single-input single-output (SISO) on-chip data channels to maintain data dependencies between adjacent MB lines. Furthermore, we combine the output from two sub-encoders to produce a bitstream compatible with a standard H.264 decoder. The encoder achieves 125fps for 1080p video and supports both intra and inter coding, providing real-time performance and flexibility in various live streaming scenarios. Results show that our design can reduce up to 49.4% of overall video encoding latency compared to MB serial processing without the loss of H.264 standard compatibility and rate-distortion performance.

Authors

Institutions

Publication Details

Published
2025-06-30
DOI
https://doi.org/10.1109/icmew68306.2025.11152256
Primary Topic
Video Coding and Compression Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Low-Latency H.264/AVC Encoder Hardware Design with Wavefront Parallelism on FPGA Platform

Linchen Xu, Jun Wang, Xin Liu, Fan Liang et al.
Video Coding and Compression Technologies
article

Low-Latency H.264/AVC Encoder Hardware Design with Wavefront Parallelism on FPGA Platform

Linchen Xu, Jun Wang, Xin Liu, Fan Liang, Zhibin Chen
article en

Abstract

With network transmission delays reduced, video encoding latency emerges as a critical challenge for live video streaming. Nowadays, H.264/AVC remains the most popular video encoding standard in production due to its relatively low complexity. Therefore, an H.264 encoder with lower encoding latency and cost still has significant application value, but the fact that H.264 standard is not optimized for parallel processing has become a limitation to further reducing encoding latency. In this paper, we propose a dual-core hardware implementation of an H.264-based video encoder that performs wavefront parallelism on FPGA platform and provides full compatibility with the H.264 Baseline Profile. The main challenge is the maintenance of data dependencies of adjacent macroblock (MB) lines, introduced by the dual-core parallelism. To handle this problem, we propose a core scheduling mechanism and use a pair of single-input single-output (SISO) on-chip data channels to maintain data dependencies between adjacent MB lines. Furthermore, we combine the output from two sub-encoders to produce a bitstream compatible with a standard H.264 decoder. The encoder achieves 125fps for 1080p video and supports both intra and inter coding, providing real-time performance and flexibility in various live streaming scenarios. Results show that our design can reduce up to 49.4% of overall video encoding latency compared to MB serial processing without the loss of H.264 standard compatibility and rate-distortion performance.

Sun Yat-sen University (CN), Zhuhai People's Hospital (CN), Taiwan Semiconductor Manufacturing Company (China) (CN), Zhuhai Institute of Advanced Technology (CN)
Openalex Percentile: Top 70%
Video Coding and Compression Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Low-Latency H.264/AVC Encoder Hardware Design with Wavefront Parallelism on FPGA Platform — Linchen Xu, Jun Wang, et al. · (2025) | TGRS Research Map | TGRS