Authors:
Lars Struyf
1
;
Stijn De Beugher
1
;
Dong Hoon Van Uytsel
2
;
Frans Kanters
3
and
Toon Goedemé
1
Affiliations:
1
KU Leuven, Belgium
;
2
eSATURNUS, Belgium
;
3
InViso, Netherlands
Keyword(s):
Computer Vision, Real-time, GPU, FPGA.
Related
Ontology
Subjects/Areas/Topics:
Digital Filter Design and Implementation
;
Digital Signal Processing
;
Embedded Communications Systems
;
Image and Multidimensional Signal Processing
;
Real-Time Systems
;
Telecommunications
Abstract:
This paper focuses on a thorough comparison of the two main hardware targets for real-time optimization of
a computer vision algorithm: GPU and FPGA. Based on a complex case study algorithm for threaded isle
detection, implementation on both hardware targets is compared in terms of resulting time performance, code
translation effort, hardware cost, power efficiency and integrateability. A real-life case study as described in
this paper is a very useful addition to discussions on a more theoretical level, going beyond artificial experiments.
In our experiments, we show the speed-up gained by porting our algorithm to FPGA using manually
written VHDL and to a heterogeneous GPU/CPU architecture with the OpenCL language. Also, issues and
problems occurring during the code porting are detailed.