Hardware implementation of MRF map inference on an FPGA platform

Jungwook Choi, Rob A. Rutenbar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we describe hardware for inference computations on Markov Random Fields (MRFs). MRFs are widely used in applications like computer vision, but conventional software solvers are slow. Belief Propagation (BP) solvers, which use patterns of local message passing on MRFs, have been studied in hardware, but their performance is unreliable. We show how a superior method - Sequential Tree-Reweighted message passing (TRW-S) - can be rendered in hardware. TRW-S has reliable convergence, guaranteed by its so-called "sequential" computation. Analysis reveals many opportunities for TRW-S hardware acceleration. We show how to implement TRW-S in FPGA hardware so that it exploits significant parallelism and memory bandwidth. Our implementation is capable of running a standard stereo vision benchmark at rates approaching 40 frames/sec; this represents the first time TRW-S methods have been accelerated to these speeds on an FPGA platform.

Original languageEnglish (US)
Title of host publicationProceedings - 22nd International Conference on Field Programmable Logic and Applications, FPL 2012
Pages209-216
Number of pages8
DOIs
StatePublished - 2012
Externally publishedYes
Event22nd International Conference on Field Programmable Logic and Applications, FPL 2012 - Oslo, Norway
Duration: Aug 29 2012Aug 31 2012

Publication series

NameProceedings - 22nd International Conference on Field Programmable Logic and Applications, FPL 2012

Other

Other22nd International Conference on Field Programmable Logic and Applications, FPL 2012
Country/TerritoryNorway
CityOslo
Period8/29/128/31/12

ASJC Scopus subject areas

  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Hardware implementation of MRF map inference on an FPGA platform'. Together they form a unique fingerprint.

Cite this