Skip to content

hamid-mp/IOU-tracker-pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 

Repository files navigation

IOU-tracker-pytorch

  • Pytorch implementation of simple IOU-tracker
    • Tracking is done per frame.

tips to get better result

  • IOU-tracker as its name suggests, is based on the intersection over union of the bounding boxes, so we want to compare one bbox of currenct frame with previous frame bboxes.
  • to get accurate tracking, the difference between frames should not be so far. so, try to capture frames in higher fps (frame per second) from your video.
  • it is better to have fps higher than 25, then you can choose higher IOU_threshold

About

Pytorch implementation of simple IOU-tracker

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages