Question about depth estimation

pntt3011 / mediapipe_face_iris_cpp

Real-time Face and Iris Landmarks Detection using C++

GNU General Public License v3.0

81 stars 15 forks source link

Question about depth estimation #10

Open DavitMob opened 2 years ago

DavitMob commented 2 years ago

I see in code comments that I can get depth estimation from the model output inside getEyeLandmarkAt by float _d = model->getOutputData(isIris)[index * 3 + 2];. Can you please say what kind of postprocessing needs to be done on this output? Seems there should be some postprocessing, because by printing the value I get also negtaive values.

pntt3011 commented 2 years ago

I just found this part of a repo, which is written in Python but can be easily mapped to C++. I'm sorry that I'm very busy right now so I can't help you much.

DavitMob commented 2 years ago

Thank you very much @pntt3011 for the reply. I will take a look.