Computer Engineering and Applications ›› 2014, Vol. 50 ›› Issue (18): 44-49.
Previous Articles Next Articles
WANG Zhibin, YANG Wenmin, ZHANG Yuanpu, CHAI Zhilei
Online:
Published:
王芝斌,阳文敏,张圆蒲,柴志雷
Abstract: Techniques of optical flow computation are widely used in many video/image based applications such as motion detection, motion estimation and video analysis etc. However, high-quality optical flow algorithms are computationally intensive. Slow computation limits the applicability of optical flow computation in real-world applications, especially in embedded systems. In this paper, an implementation of Horn-Schunck optical flow algorithm based on Xilinx ZYNQ is presented. The High-Level Synthesis(HLS) language together with traditional hardware description language is used to describe optical flow accelerator in the software-hardware co-processing mode. Taking resolution 640×480 as instance, the result shows that FPGA-accelerated HS outperforms 34x than the pure software vision on ZYNQ. The execution time is decreased from 24.40 s to 0.71 s.
Key words: optical flow accelerator, ZYNQ, high-level synthesis language, software-hardware co-processing, Field-Programmable Gate Array(FPGA)
摘要: 光流法是计算机视觉中一个基础性的算法,可广泛应用于运动检测、运动估计、视频分析等领域。但光流法最大的问题是计算复杂、速度慢,限制了它在实际系统尤其是嵌入式系统中的应用。利用最新的高层综合(HLS)语言与传统的硬件描述语言相结合,在Xilinx的FPGA异构系统芯片(即ZYNQ)平台上,以软硬件协同的工作方式,设计了基于Horn-Schunck稠密光流法的硬件加速器。实验证明,对于640×480大小的图片,软硬件协同处理比纯软件处理的计算性能提高了34倍,执行时间从24.40 s降低到0.71 s。
关键词: 光流加速器, ZYNQ, 高层综合语言, 软硬件协同处理, 可编程器件
WANG Zhibin, YANG Wenmin, ZHANG Yuanpu, CHAI Zhilei. Dense optical flow software-hardware co-processing based on ZYNQ[J]. Computer Engineering and Applications, 2014, 50(18): 44-49.
王芝斌,阳文敏,张圆蒲,柴志雷. 基于ZYNQ的稠密光流法软硬件协同处理[J]. 计算机工程与应用, 2014, 50(18): 44-49.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/
http://cea.ceaj.org/EN/Y2014/V50/I18/44