Electroencephalogram emotion recognition method based on video level features

The invention relates to an electroencephalogram emotion recognition method based on video level features, and belongs to the field of emotion calculation. The method comprises the following steps: performing analysis and label processing on a data set electroencephalogram, organizing time domain, frequency domain and space domain information of electroencephalogram signals, constructing a channel attention volume accumulation network, training the channel attention volume accumulation network by using training set data, and inputting test set data into the trained network for emotion prediction. The method has the advantages that the electroencephalogram signals are converted into video-level electroencephalogram characteristics, and time domain, frequency domain and space domain information of the electroencephalogram signals is organized in a compact form, so that the electroencephalogram signals are further analyzed and understood; the channel attention volume accumulation network is a single-flow network