Closed fabolhak closed 3 years ago
For the Carolo Cup some signs are not in the database, to solve this problem we need other pictures.
Current status: We have a full synthetic environment generation, so this is superseded by that, however this would enable the generation of more realstic images.
The amount of hand-labeled data available to use is relatively high at this point though.
We could generate synthetic training data with GTRSB or other sign images. The images can be projected in our "environment" to create the synthetically labeled data. Based on the projection parameters we can obtain the bounding boxes easily.
Code lives here: https://github.com/tum-phoenix/drive_ml/tree/master/sign_recognition/utilities/data_augmentation
1st approach
problems:
2nd approach
code
possible processing steps