Low Complexity, Hardware-Efficient Neighbor-Guided SGM Optical Flow for Low Power Mobile Vision Applications

Ziyun Li, Jiang Xiang, Luyao Gong, David Blaauw, Chaitali Chakrabarti, Hun Seok Kim

Research output: Contribution to journalArticle

1 Scopus citations

Abstract

Accurate, low-latency and energy-efficient optical flow estimation is a fundamental kernel function to enable several real-time vision applications on mobile platforms. This paper presents Neighbor-Guided Semi-Global Matching (NG-fSGM), a new low-complexity optical flow algorithm tailored for low power mobile applications. NG-fSGM obtains high accuracy optical flow by aggregating local matching costs over a semi-global region, successfully resolving local ambiguity in texture-less and occluded regions. Proposed NG-fSGM aggressively prunes the search space based on neighboring pixels’ information to significantly lower the algorithm complexity from the original fSGM. As a result, NG-fSGM achieves 17.9× reduction in the number of computations and 8.37× reduction in memory space compared to the original fSGM without compromising its algorithm accuracy. A multicore architecture for NG-fSGM is implemented in hardware to quantify algorithm complexity and power consumption. The proposed architecture realizes NG-fSGM with overlapping blocks processed in parallel to enhance throughput and to lower power consumption. The 8-core architecture achieves 20M pixel/s (66 frames / sec for VGA) throughput with 9.6mm2 area at 679.2mW power consumption in 28nm node.

Original languageEnglish (US)
JournalIEEE Transactions on Circuits and Systems for Video Technology
DOIs
StateAccepted/In press - Jul 8 2018

Keywords

  • Complexity theory
  • Estimation
  • Low power
  • Multi-core accelerator
  • Optical flow
  • Optical flow
  • Optimization
  • Power demand
  • Real-time systems
  • Semi-global matching
  • Transforms
  • VLSI

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Low Complexity, Hardware-Efficient Neighbor-Guided SGM Optical Flow for Low Power Mobile Vision Applications'. Together they form a unique fingerprint.

  • Cite this