Hyperspectral classification detection method based on FPGA (Field Programmable Gate Array), storage medium and equipment

The invention discloses an FPGA-based hyperspectral classification detection method, a storage medium and equipment, and the method comprises the steps: collecting a to-be-classified and detected hyperspectral image, and carrying out the preprocessing of the to-be-classified and detected hyperspectral image; carrying out dimension reduction operation on the preprocessed hyperspectral image to be classified and detected, and carrying out depth edge filtering processing to obtain a training set; constructing a hyperspectral image classification detection network; inputting the training set into the hyperspectral image classification detection network for training until the network loss function value is less than 0.3, and completing the training of the hyperspectral image classification detection network; and loading the trained hyperspectral image classification detection network into the FPGA, collecting hyperspectral images to be subjected to classification detection in real time, and inputting the hyperspec