So I promised to protoype a model that would do object detection trained on my own labeled videos; in real time on full HD video @25 fps. I have spent quite some time learning Mask R-CNN, but realized just now that this library is too slow for my usage.
I have googled OpenCV, browsed through LearnOpenCV, searched these forums, peaked at the tutorials at opencv.org etc. I understand that using the DNN module with C++ will let me train my own model and do object detection at some frame rate.
Which OpenCV based method would you choose for training an object detection model to work @25 fps, full HD?