Target identification method, device and equipment based on HRRP spatial feature extraction

The invention relates to a target recognition method, device and equipment based on HRRP spatial feature extraction, and the method comprises the steps: carrying out the preprocessing of original one-dimensional range profile data, converting each one-dimensional range profile sequence of the preprocessed one-dimensional range profile data into a broken line graph without coordinates, and carrying out the recognition of the one-dimensional range profile. Splicing the broken line graphs according to a sequential arrangement mode to obtain a sparse two-dimensional image, and performing feature extraction on the sparse two-dimensional image by using a multi-scale convolutional network to obtain a plurality of feature graphs of different scales; and performing target identification according to the plurality of feature maps with different scales by using a classification network based on the multilayer perceptron to obtain a target identification result. By adopting the method, the recognition precision and robus