Skip to content

balaganeshmohan/Key-frame-identifer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Key Frame Identifier

This is a tool that can identify key frames in a video. Can be used in machine learning pipelines to reduce data size or balance the dataset. The thresholding is important. The input is a float value between 0 and 1 which represents the percentage change between pixels of two consecute frames. The difference is calculated using OpenCV's absolute difference function. The scripts takes directory and threshold and returns a csv file with video name and key frames along with a plot of the difference of all frames.

Screenshot

Usage

python main.py --video directory --threshold

License

MIT

About

A tool to identify key frames in videos.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages