Hello everyone,
I am thinking to use my observation output in the form of video format. I am aware that I need to have features and label in order to train the data. In order to do so, I've got to do some transcription towards the video to extract the features. However, that would not directly use a video format as a training data as it will need people transcription. Can anyone advise me on a proper way because I am newbies in the machine learning area.
Thanks in advance.