I have a project where i'm supposed to find the distance and the height of a specific object in an image taken by a drone using one camera. I have looked into perspective transformation/correction but i couldn't find any solutions regarding the camera tilt. I have also tried using OpenCV's cv2.getPerspectiveTransform and cv2.warpPerspective but i was not able to transform the whole image as i need ( to be able to calculate the distance from the pixel count between objects). The image gets distorted by the perspective so i would like to be able to transform my image to eye bird view like image retrieving the lost pixels from the tilt and translating the pixel count to a real world measurement. How can i achieve this?

  • $\begingroup$ Hello. General programming questions are off-topic here, although this site is about artificial intelligence. Here we focus on theoretical aspects of AI. It seems that your problem is just how to use OpenCV to achieve a certain thing, so I think your post is off-topic. Try asking it on Stack Overflow. $\endgroup$ – nbro Nov 23 '20 at 17:08
  • $\begingroup$ Hi, Actually i'm interested in learning the math behind it more than the code itself i would like to train a model to learn the perspective shift at certain camera angel tilts so i'm trying to find the correct road to take here. Thanks for the advice thought i'll post it on stack overflow too. $\endgroup$ – Yunus Abdi Nov 23 '20 at 17:55

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.