Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding

© 2015 SPIE and IS and T. The progression toward spatially scalable video coding (SVC) solutions for ubiquitous endpoint systems introduces challenges to sustain real-time frame rates in downsampling high-resolution videos into multiple layers. In addressing these challenges, we put forward a hardwa...

Full description

Bibliographic Details
Main Authors: Buhari, A., Ling, Huo Chong, Baskaran, V., Wong, K.
Format: Journal Article
Published: S P I E - International Society for Optical Engineering 2015
Online Access:http://hdl.handle.net/20.500.11937/72593
_version_ 1848762791574372352
author Buhari, A.
Ling, Huo Chong
Baskaran, V.
Wong, K.
author_facet Buhari, A.
Ling, Huo Chong
Baskaran, V.
Wong, K.
author_sort Buhari, A.
building Curtin Institutional Repository
collection Online Access
description © 2015 SPIE and IS and T. The progression toward spatially scalable video coding (SVC) solutions for ubiquitous endpoint systems introduces challenges to sustain real-time frame rates in downsampling high-resolution videos into multiple layers. In addressing these challenges, we put forward a hardware accelerated downsampling algorithm on a parallel computing platform. First, we investigate the principal architecture of a serial downsampling algorithm in the Joint-Scalable-Video-Model reference software to identify the performance limitations for spatially SVC. Then, a parallel multicore-based downsampling algorithm is studied as a benchmark. Experimental results for this algorithm using an 8-core processor exhibit performance speedup of 5.25× against the serial algorithm in downsampling a quantum extended graphics array at 1536p video resolution into three lower resolution layers (i.e., Full-HD at 1080p, HD at 720p, and Quarter-HD at 540p). However, the achieved speedup here does not translate into the minimum required frame rate of 15 frames per second (fps) for real-time video processing. To improve the speedup, a many-core based downsampling algorithm using the compute unified device architecture parallel computing platform is proposed. The proposed algorithm increases the performance speedup to 26.14× against the serial algorithm. Crucially, the proposed algorithm exceeds the target frame rate of 15 fps, which in turn is advantageous to the overall performance of the video encoding process.
first_indexed 2025-11-14T10:53:11Z
format Journal Article
id curtin-20.500.11937-72593
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T10:53:11Z
publishDate 2015
publisher S P I E - International Society for Optical Engineering
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-725932018-12-13T09:33:20Z Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding Buhari, A. Ling, Huo Chong Baskaran, V. Wong, K. © 2015 SPIE and IS and T. The progression toward spatially scalable video coding (SVC) solutions for ubiquitous endpoint systems introduces challenges to sustain real-time frame rates in downsampling high-resolution videos into multiple layers. In addressing these challenges, we put forward a hardware accelerated downsampling algorithm on a parallel computing platform. First, we investigate the principal architecture of a serial downsampling algorithm in the Joint-Scalable-Video-Model reference software to identify the performance limitations for spatially SVC. Then, a parallel multicore-based downsampling algorithm is studied as a benchmark. Experimental results for this algorithm using an 8-core processor exhibit performance speedup of 5.25× against the serial algorithm in downsampling a quantum extended graphics array at 1536p video resolution into three lower resolution layers (i.e., Full-HD at 1080p, HD at 720p, and Quarter-HD at 540p). However, the achieved speedup here does not translate into the minimum required frame rate of 15 frames per second (fps) for real-time video processing. To improve the speedup, a many-core based downsampling algorithm using the compute unified device architecture parallel computing platform is proposed. The proposed algorithm increases the performance speedup to 26.14× against the serial algorithm. Crucially, the proposed algorithm exceeds the target frame rate of 15 fps, which in turn is advantageous to the overall performance of the video encoding process. 2015 Journal Article http://hdl.handle.net/20.500.11937/72593 10.1117/1.JEI.24.1.013025 S P I E - International Society for Optical Engineering restricted
spellingShingle Buhari, A.
Ling, Huo Chong
Baskaran, V.
Wong, K.
Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
title Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
title_full Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
title_fullStr Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
title_full_unstemmed Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
title_short Real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
title_sort real-time high-resolution downsampling algorithm on many-core processor for spatially scalable video coding
url http://hdl.handle.net/20.500.11937/72593