NeuFlow: A Runtime Reconfigurable Dataflow Processor for Vision

Abstract

In this paper we present a scalable dataflow hardware architecture optimized for the computation of generalpurpose vision algorithms—neuFlow—and a dataflow compiler—luaFlow—that transforms high-level flow-graph representations of these algorithms into machine code for neuFlow. This system was designed with the goal of providing real-time detection, categorization and localization of objects in complex scenes, while consuming 10 Watts when implemented on a Xilinx Virtex 6 FPGA platform, or about ten times less than a laptop computer, and producing speedups of up to 100 times in real-world applications. We present an application of the system on street scene analysis, segmenting 20 categories on 500 × 375 frames at 12 frames per second on our custom hardware neuFlow.

Cite

Text

Farabet et al. "NeuFlow: A Runtime Reconfigurable Dataflow Processor for Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011. doi:10.1109/CVPRW.2011.5981829

Markdown

[Farabet et al. "NeuFlow: A Runtime Reconfigurable Dataflow Processor for Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2011.](https://mlanthology.org/cvprw/2011/farabet2011cvprw-neuflow/) doi:10.1109/CVPRW.2011.5981829

BibTeX

@inproceedings{farabet2011cvprw-neuflow,
  title     = {{NeuFlow: A Runtime Reconfigurable Dataflow Processor for Vision}},
  author    = {Farabet, Clément and Martini, Berin and Corda, B. and Akselrod, Polina and Culurciello, Eugenio and LeCun, Yann},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2011},
  pages     = {109-116},
  doi       = {10.1109/CVPRW.2011.5981829},
  url       = {https://mlanthology.org/cvprw/2011/farabet2011cvprw-neuflow/}
}