Skip to content

This repository contains scripts to compare the accuracy and computational cost of event-based optical flow against standard frame-based optical flow.

Notifications You must be signed in to change notification settings

rbodo/eventbased_opticalflow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Event-based optical flow

This repository contains scripts to compare the accuracy and computational cost of event-based optical flow against standard frame-based optical flow.

The standard frame flow uses dense and sparse Lucas-Kanade variants implemented in opencv. (Some of the imports access the opencv sample scripts.)

The event-based flow samples were recorded with the DAVIS sensor, and processed using the jAER software. The flow algorithm for DVS input was implemented in jAER as described here.

For access to the dataset, please contact Bodo Rueckauer (rbodo).

About

This repository contains scripts to compare the accuracy and computational cost of event-based optical flow against standard frame-based optical flow.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published