Testing as "Augmented Autoencoder only" means there is no SSD detector used？

DLR-RM / AugmentedAutoencoder

Official Code: Implicit 3D Orientation Learning for 6D Object Detection from RGB Images

MIT License

338 stars 97 forks source link

Testing as "Augmented Autoencoder only" means there is no SSD detector used？ #37

Closed xiaomaoo closed 5 years ago

xiaomaoo commented 5 years ago

Testing as "Augmented Autoencoder only" means there is no SSD detector used and won't detect the object in the image or video ? and only calculate the 3D Orientation ? And I have to add my own detector model to the code (aae_webcam.py) ?

MartinSmeyer commented 5 years ago

Yes, exactly. However if you train
https://github.com/fizyr/keras-retinanet we provide a nice interface for the whole pipeline. See: https://github.com/DLR-RM/AugmentedAutoencoder#multi-object-rgb-based-6d-object-detection-from-a-webcam-stream