Implementing Dense Optical Flow Computation on a Heterogeneous FPGA SoC in C

@article{Chen2016ImplementingDO,
  title={Implementing Dense Optical Flow Computation on a Heterogeneous FPGA SoC in C},
  author={Wenjie Chen and Zhenchang Wang and Qin Wu and Jiuzhen Liang and ZhiLei Chai},
  journal={TACO},
  year={2016},
  volume={13},
  pages={25:1-25:25}
}
High-quality optical flow computation algorithms are computationally intensive. The low computational speed of such algorithms causes difficulties for real-world applications. In this article, we propose an optimized implementation of the classical Combine-Brightness-Gradient (CBG) model on the Xilinx ZYNQ FPGA-SoC, by taking advantage of the inherent algorithmic parallelism and ZYNQ architecture. The execution time decreases to 0.82 second with a lower power consumption (1.881W). It is better… CONTINUE READING
4
Twitter Mentions

Similar Papers

Citations

Publications citing this paper.

SCOM: Spatiotemporal Constrained Optimization for Salient Object Detection

  • IEEE Transactions on Image Processing
  • 2018
VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 12 REFERENCES

The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields

  • Computer Vision and Image Understanding
  • 1996
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Altera SoCs: When architecture matters

Altera.
  • Retrieved April 21, 2016 from http://www.altera.com/ devices/processor/soc-fpga/overview/proc-soc-fpga.html.
  • 2015
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Large displacement optical flow

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Variational optic flow on the Sony PlayStation 3

  • Journal of Real-Time Image Processing
  • 2009
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Improving KLT in Embedded Systems by Processing Oversampling Video Sequence in Real-Time

  • 2011 International Conference on Reconfigurable Computing and FPGAs
  • 2011
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Optic Flow in Harmony

  • International Journal of Computer Vision
  • 2011
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL