Is it possible to map 2D orthomosaic pixels (x,y) values in the tiff image to the corresponding pixels (x,y) in the undistorted images?
I saw this answer (Matching pixels in orthomosaic to corresponding pixels in undistorted input images) and while I’m able to map a point from the point cloud to the undistorted images, I was wondering if there is a way to map a point in the orthomosaic to the point cloud or vice versa.
The goal is to use an object detection model on the orthophoto and extract the object from all undistorted images.
Thanks.