Skip to content

Set of tools for processing camera images. It is a ROS wrapper for comonly used OpenCv techniques including deinterlace of analog images and filtering.

License

Notifications You must be signed in to change notification settings

denkrau/tud_img_prep

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

tud_img_prep

Set of tools for preprocessing a camera video feed using OpenCV.

Includes:

  • Deinterlacing of analog video signals, e.g. video feed acquired using an Easycap USB capture card. Different interlacing methods:
    • Half image
    • Interpolation (several interpolation methods)
  • Color format selection and conversion
  • Equalization of the images
    • Manual equalization using brighness and contrast controls
    • Automatic using OpenCV EqualizeHistogram function
  • Filtering
    • Median
    • Gaussian
    • Bilateral Filter

All the options can be changed in real time using Dynamic Reconfigure.

Installation

Clone repository in your catkin worskspace:

cd ~/catkin_ws/src
git clone https://github.com/raultron/tud_img_prep.git

Compile using catkin:

catkin build tud_img_prep

Usage

rosrun tud_img_prep img_prep

This package requires ROS camera topics properly published.

Default input topics:

/cam/image_raw
/cam/camera_info

Default output topics:

/prep/cam/image_raw
/prep/cam/camera_info

The default camera namespace can be changed using the parameter "camera_namespace" in a launch file or directly in the terminal.

For example, if you have a camera that publishes in:

/my_camera/image_raw
/my_camera/camera_info

Then the terminal command will be:

rosrun tud_img_prep img_prep _camera_namespace:=/my_camera

And the ouput topics will be

/prep/my_camera/image_raw
/prep/my_camera/camera_info

About

Set of tools for processing camera images. It is a ROS wrapper for comonly used OpenCv techniques including deinterlace of analog images and filtering.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 58.0%
  • CMake 28.9%
  • Python 13.1%