Skip to content

cvlab-epfl/multiview_matching

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Blind matching of detections across multiple views using epipolar geometry and Integer Linear Programming (ILP).

This method blindly finds the set of correspondeces between multiple detections of the same objects acquire from multiple calibrated cameras. We leverge the epipolar geometry to find candidtaes matches betwene pair of views and Integer Linear Programming (ILP) to find the optimal solution considering all views.

Prerequisites

  • numpy
  • scipy
  • imageio
  • OpenCV

Installation

export PYTHONPATH="...parent folder...:$PYTHONPATH"

Usage

Compute intrinsic and extrinsics parameters of the cameras:

Have a look at the multiview_calib repository.

Find the correspondeces

Have a look at the example!

Benchmark

Benchmark

License

About

Blind matching of detections across multiple views

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages