Which is the best way to classify videos in MATLAB?

Hi, everyone,

I need to classify videos, extracting frames from them. I think the best way to do this is using a 3D convolutional neural network, but i can't find official support for 3D ConvNets in MATLAB. There is a way to do this?

I can't handle frames as independent images because, of course, i need the time information too.

Thanks for the support and attention!

[Walter Roberson]

See https://www.mathworks.com/matlabcentral/answers/303635-hi-everyone-i-need-some-help-i-m-working-on-glcm-texture-features-i-want-to-know-which-classifier-gi#answer_235285

Answer 1

[Kenta]

One option is to use CNN and LSTM. The below is a demo of video classification which may relate to your study.

https://jp.mathworks.com/matlabcentral/fileexchange/74402-video-classification-using-lstm-lstm

The image features were extracted via a pre-trained network and the time-series features were classified using LSTM (Long Short Term Memory).