Accelerating Viola-Jones Face Detection to FPGA-Level using GPUs

被引：49

作者：

Hefenbrock, Daniel ^{[1
]}

Oberg, Jason ^{[1
]}

Nhat Tan Nguyen Thanh ^{[1
]}

Kastner, Ryan ^{[1
]}

Baden, Scott B. ^{[1
]}

机构：

[1] Univ Calif San Diego, Dept Comp Sci & Engn, La Jolla, CA 92093 USA

来源：

2010 18TH IEEE ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM 2010) | 2010年

基金：

美国国家科学基金会;

关键词：

Graphical Processing Unit; Face Detection; Field Programmable Gate Array; Acceleration;

D O I：

10.1109/FCCM.2010.12

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

Face detection is an important aspect for biometrics, video surveillance and human computer interaction. We present a multi-GPU implementation of the Viola-Jones face detection algorithm that meets the performance of the fastest known FPGA implementation. The GPU design offers far lower development costs, but the FPGA implementation consumes less power. We discuss the performance programming required to realize our design, and describe future research directions.

引用

页码：11 / 18

页数：8

共 14 条

[1]

[Anonymous], CAT C SYNTH

[2]

[Anonymous], NCSA INT 64 TESL LIN

[3]

[Anonymous], NVIDIA PROD

[4]

[Anonymous], 2009, NVIDIA CUDA Programming Guide

[5]

[Anonymous], THESIS

[6]

[Anonymous], XIL PROD

[7]

[Anonymous], XPOWER EST

[8]

Cho J., 2009, FPGA 09, P103

[9] Parallelized Architecture of Multiple Classifiers for Face Detection [J].

Cho, Junguk ;

Benson, Bridget ;

Mirzaei, Shahnam ;

Kastner, Ryan .

2009 20TH IEEE INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS, 2009, :75-+

[10]

Gao CJ, 2008, I C FIELD PROG LOGIC, P372

← 1 2 →