https://github.com/bradmontgomery/python-laser-tracker

A simple laser tracker using Python and OpenCV.
https://github.com/bradmontgomery/python-laser-tracker

opencv python

Last synced: 5 days ago
JSON representation

A simple laser tracker using Python and OpenCV.

• Host: GitHub
• URL: https://github.com/bradmontgomery/python-laser-tracker
• Owner: bradmontgomery
• License: mit
• Created: 2012-09-13T15:57:44.000Z (about 12 years ago)
• Default Branch: master
• Last Pushed: 2019-09-01T19:46:23.000Z (about 5 years ago)
• Last Synced: 2024-11-01T22:42:52.003Z (12 days ago)
• Topics: opencv, python
• Language: Python
• Homepage:
• Size: 34.2 KB
• Stars: 84
• Watchers: 14
• Forks: 38
• Open Issues: 4
• Metadata Files:
  • Readme: README.rst
  • License: LICENSE.txt

Awesome Lists containing this project

README

        
python laser tracker

====================

This is a OpenCV application that applies filters in order to track specific HSV ranges. By default, it tracks a red laser pointer, but it is modular and you can track about whatever you want.

Requirments

-----------

This requires Python2 and the Python wrapper for OpenCV.

It was tested on GNU/Linux distributions and Mac OS X.

Usage

-----

Run ``python laser_tracker/laser_tracker.py -h`` for help on the available command-line parameters.

Range for each HSV components:

    -   hue: [0, 180]

    -   saturation: [0, 255]

    -   value: [0, 255]

About the code

--------------

The code performs the following steps, and displays the results in several windows. The general idea is to:

1. Grab the video frame.

2. Convert it to HSV

3. Split the frame into individual components (separate images for H, S, and V)

4. Apply a threshold to each compenent (hopefully keeping just the dot from the laser)

5. Perform an AND operation on the 3 images (which "should" cut down on false positives)

6. Display the result.

The filtering part is done using successive `thresholding `_

.. image:: img/filtering.png

License

-------

This code is MIT-licensed. You can basically do whatever you want with it.

Contributing

------------

Any suggestions, bug reports, or pull requests are welcome! If there's

something I should be doing differently, here, feel free to open an Issue and

let me know.