Paper Info
Title
High-quality real-time hardware stereo matching based on guided image filtering
Abstract
Stereo matching is a vital task in several emerging embedded vision applications requiring high-quality depth computation and real-time frame-rate. Although several stereo matching dedicated-hardware systems have been proposed in recent years, only few of them focus on balancing accuracy and speed. This paper proposes a hardware-based stereo matching architecture that aims to provide high accuracy and concurrently high performance in embedded vision applications. The proposed architecture integrates a compact and efficient design of the recently proposed guided image filter; an edge-preserving filter that reduces the hardware complexity of the implemented stereo algorithm, while at the same time maintains high-quality results. A prototype of the architecture has been implemented on a Kintex-7 FPGA board, achieving 60 fps for 720p resolution images. Moreover, the proposed design delivers leading accuracy when compared to state-of-the-art hardware implementations.
Year
DOI
Venue
2014
10.7873/DATE.2014.369
Design, Automation and Test in Europe Conference and Exhibition
Keywords
Field
DocType
high-quality real-time hardware stereo,efficient design,embedded vision application,stereo matching,stereo algorithm,hardware-based stereo,edge-preserving filter,concurrently high performance,high accuracy,proposed design,proposed architecture,field programmable gate arrays,embedded systems,algorithm design and analysis,fpgas,matched filters,accuracy,image resolution,hardware,computer architecture,real time systems
Template matching,Stereo cameras,Computer science,Real-time computing,Artificial intelligence,Computer hardware,Computation,Computer vision,Architecture,Field-programmable gate array,Filter (signal processing),Composite image filter,Image resolution
Conference
ISSN
Citations 
PageRank 
1530-1591
5
0.52
References 
Authors
12
2
Name
Order
Citations
PageRank
Christos Ttofis1625.90
Theocharis Theocharides220526.83