forum.hugin.com
User Forums => HUGIN GUI Discussion => Topic started by: Raymond Blum on July 08, 2019, 14:53:18
-
As part of a larger project I have images from a Ricoh Theta that I would like to apply (TensorFlow Lite implemented) Object Detection to and then slice vertically for display.
I've found this HOWTO topic https://community.theta360.guide/t/hugin-howto-convert-360-image-to-cropped-flat-panoramic-image/1271
...but I confess that I've not been able to successfully flatten an image.
Assuming that this HOWTO is applicable, When I run the batch and produce my output file (.tif by default, not JPEG) the image I end up with is just a crop of the "distorted" or "fisheye" photosphere, whereas I expected/wanted to produce an image normalized so that there was no fisheye effect.
1) Is what I expected feasible?
2) Is this an applicable HOWTO?
3a) If not, is there a more appropriate one?
3b) If so, what am I missing?
Thanks
-
Hello Raymond,
I assume that you by now have realised that "our" HUGIN is a tool for probabilistic graphical models and not images.
Sorry for the belated reply.
Anders