decadenza / DirectStereoRectification

"Rectifying Homographies for Stereo Vision: Analytical Solution for Minimal Distortion": algorithm to compute the optimal rectifying homographies that minimise perspective distortion.
GNU General Public License v3.0
27 stars 5 forks source link

Extended 'example.py' to include OpenCV chessboard calibration #3

Closed KevinCain closed 2 years ago

KevinCain commented 2 years ago

I've updated example.py to include chessboard calibration from (provided) photos as per this recent issue.

Please don't accept this merge request quite yet as the rectification results aren't usable.

Any suggestions are welcome!

KevinCain commented 2 years ago

While the chessboard detection and calibration looks reasonable, my rectification results with the example code in the branch are bad. I've experimented with additional chessboard calibration in case the trouble was not having enough calibration coverage in Z-depth, but the results are equally unusable.

Are there any glaring errors to identify in the 'example.py' in this branch?

decadenza commented 2 years ago

Hi. I had a quick look. You may want to check the following in your fork:

Please note that I have to cancel your pull request. My repository is intended to be only an example of rectification to support our paper on rectification. The full library is soon to be released as separate repository.

Happy to help if you have other questions.

decadenza commented 2 years ago

For full library, including calibration, please go https://github.com/decadenza/SimpleStereo