I have geo-tagged images (i.e have the latitude and longitude from where the images were taken) from a truck every 20 feet.

I am trying to understand if it is possible to extract the latitude and longitude of the objects seen in the images.


You can try to georectify the images, however to do that you'll need more information than just the lat/lon that they were taken. If you know the exact orientation/tilt/elevation/field of view of the camera, then you can use geometry to transform the pixels from xy space into lon/lat. A big caveat -- it will only really work if you can assume the region you are rectifying is a flat plane. If there is actual topography, then I guess you would also need to know the topographic elevations in the field of view quite accurately.

Below is a reference for georectifying images, here used to map the flow of river ice. There is a toolbox available (for Matlab) that can be used when you don't know all the parameters, but can make reasonable guesses. In order for it to work though, you need to know the exact lon/lat of at least a few points in the scene (e.g. landmarks). I'm not aware of other software, but I haven't looked recently.


Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.