FPGA acceleration of Markov Random Field TRW-S inference for stereo matching

Jungwook Choi, Rob A. Rutenbar

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

Abstract

In this paper, we present our hardware accelerator for inference computations on Markov Random Fields (MRFs), which wins the "adjusted run time" category of MEMOCODE 2013 design contest. The contest problem is to accelerate the popular Belief Propagation (BP) algorithm for MRF stereo matching, but BP often suffers from non-convergence in its MRF inference. To overcome the drawbacks of BP, 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. We show how to implement TRW-S in FPGA hardware so that it exploits significant parallelism and memory bandwidth. Our FPGA implementation demonstrates superior MRF inference performance and comparable quality of stereo matching results on the provided stereo matching tasks compared to the reference BP software.

Original languageEnglish (US)
Title of host publication11th ACM/IEEE International Conference on Formal Methods and Models for Codesign, MEMOCODE 2013
PublisherIEEE Computer Society
Pages139-142
Number of pages4
ISBN (Print)9781479909032
StatePublished - 2013
Event11th ACM/IEEE International Conference on Formal Methods and Models for Codesign, MEMOCODE 2013 - Portland, OR, United States
Duration: Oct 18 2013Oct 20 2013

Other

Other11th ACM/IEEE International Conference on Formal Methods and Models for Codesign, MEMOCODE 2013
Country/TerritoryUnited States
CityPortland, OR
Period10/18/1310/20/13

Keywords

  • Belief propagation (BP)
  • FPGA implementation
  • Markov random field (MRF) inference
  • Sequential tree-reweighed message passing (TRW-S)
  • Stereo matching

ASJC Scopus subject areas

  • Logic
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'FPGA acceleration of Markov Random Field TRW-S inference for stereo matching'. Together they form a unique fingerprint.

Cite this