https://github.com/apachecn-archive/edflow

https://github.com/apachecn-archive/edflow

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (8.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: apachecn-archive
  • Language: VHDL
  • Default Branch: master
  • Size: 91.8 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 3 years ago · Last pushed about 3 years ago
Metadata Files
Readme

README.md

EDFLOW

EDFLOW is the first Event Driven Optical Flow camera with integrated keypoint detection. It combines Adaptive Block Matching Optical Flow (ABMOF) and Slice FAST (SFAST) corner detector on FPGA. This repo includes the vivado project and Vivado HLS implementation of two core IPs (ABMOF and SFAST).

The purpose of this repo is for academic research. Commercial use is strictly forbidden.

Architecture

The platform of this project is called DAVIS346Zynq, its architecture is illustrated in the below figure. Hardware-Architecture-whole As shown in the figure, it is consists of 3 parts: daughter board, FPGA and USB PHY. There are several IPs are implemented on FPGA including DAVIS controller, SPI master, SFAST, ABMOF, output switch, VGA, USB, etc. The source code of all these IPs except DAVIS controller can be found in EDFLOWVivadoprj->IPs. DAVIS controller is a private IP from iniVation.

How to use it

It is very easy to restore the vivado project by simply running the script restoreEDFLOW.tcl in the EDFLOWVivado_prj folder. Detail steps are shown in that folder.

Website

Interested in this project, check https://sites.google.com/view/edflow21/home for videos and benchmarking code and data.

Citation

M. LIu and T. Delbruck, EDFLOW: Event Driven Optical Flow Camera with Keypoint Detection and Adaptive Block Matching, IEEE Trans. Circuits Syst. Video Technol., vol. (under review), 2022.

Please cite this paper if using data or code from this project.

Owner

  • Name: ApacheCN 归档
  • Login: apachecn-archive
  • Kind: organization
  • Email: wizard.z@qq.com

防止重要项目丢失而设立的归档

GitHub Events

Total
Last Year