tj27-vkr / Monocular-Vehicle-Localization

Estimating the orientation and the relative dimensions of vehicles by producing a 3d bounding frame
33 stars 8 forks source link

Why you use the labels to generate the 3D centres? #3

Open deepmeng opened 5 years ago

deepmeng commented 5 years ago

I see the function " evaluate3d_detection()" in file “evaluation.py ”. And I find that you obtain the 3D centres based on the 2d labels. Also, the objects' 3D sizes are related to the samples' labels.

deepmeng commented 5 years ago

In file "predict.py", some preprocessing operatings which are before running the model for 3d prediction also refer to 2d labels.