CODEWITHSUNDEEP
python-3.xtensorflowdeep-learningobject-detection-api
Abdelouahid
Abdelouahid

Reputation: 11

How can I combine two fast R-CNN models for object detection?

I am working on object detection in video, and I want to train two fast R-CNN models on two different types of data (for example RGB and optical flow) then combine these models in one network.

I trained the model in one type of data, but I have no idea how can I combine the both type of data.

Any help would be great!

Upvotes: 1

Views: 360

Answers (1)

Tobias Senst
Tobias Senst

Reputation: 2830

What you are looking for are two-stream CNN architectures. As for example described by Peng and Schmid in Multi-region two-stream R-CNN for action detection. There is a large variaty of implementations but you will need to retrain your two-stream model with optical flow and image data.

Upvotes: 1

Related Questions