search

alicevision / CCTag

Detection of CCTag markers made up of concentric circles.
https://cctag.readthedocs.io
Mozilla Public License 2.0
351 stars 87 forks source link

Detect CCTag using Video Stream #198

Closed Akumar201 closed 1 year ago

Akumar201 commented 2 years ago

Describe the problem Greetings, I am new to the library. I was able to run the detection on CCTag images in sample folder. I would like to know how can I detect the printed CCTag on from live video stream. Please provide me with a detail changes or commands that I should use to detect the CCTag with live video stream.

Desktop (please complete the following and other pertinent information): Ubuntu 20.04

simogasp commented 2 years ago

if you used the detection application that comes with the library, you can just change the input parameter and provide an integer that refer to the camera you want to use. Normally, if you have a webcam attached via USB, you can just pass --input 0 and it will use the stream from that camera to process the images. see https://github.com/alicevision/CCTag/blob/develop/src/applications/detection/CmdLine.cpp#L27

Akumar201 commented 2 years ago

Thank you so much for your quick response. I would like to know how can I use it when I'll be making my own script in python or c++ ? Thank you

simogasp commented 2 years ago

In python you can call the binary but then you have to find a way to get the result. At the moment we don't have any python wrappers that enable to do the same thing as detection in a pure python code. In c++, just follow the code in the detection source code (main.cpp) and you see how the API is used

Akumar201 commented 2 years ago

Hello, thank you so much for your help. I would like to know is there a way I can use camera pose and distance estimation using your software. In addition to this I would like to know in future will there be pose estimation implementation of it ?

simogasp commented 2 years ago

no unfortunately that is not implemented at the moment. But it should not be difficult to do following the explanations in #63 It would be a nice contribution to add.