SAR image ship target identification method based on pulse neural network

Abstract

The invention provides an SAR image ship target identification method based on a pulse neural network, and the method employs a visual saliency map extraction method based on a visual attention mechanism, can enhance the image features, removes the noise influence of speckles, and improves the generalization capability and robustness of a model; then, pulse coding with the step length being T is carried out on the visual saliency map through a Poisson encoder, and a discrete pulse time sequence is obtained so that information can be transmitted by a subsequent network conveniently; then, a convolutional neural network and LIF spiking neurons are utilized to construct a spiking neural network model, better biological characteristics are given to the neural network, and then the information transmission process of the brain can be simulated more accurately; and finally, by using a substitution gradient training method, the problem that the pulse neural network model is difficult to optimize by using gradient descent and back propagation is solved. The method can accurately identify the ship target, and has the advantages of high efficiency and energy conservation.

Description

technical field [0001] The invention relates to the field of image target recognition, and more particularly, relates to a SAR image ship target recognition method based on a pulse neural network. Background technique [0002] Synthetic Aperture Radar (SAR) is a high-resolution imaging radar with imaging characteristics such as all-weather, all-time, and weather-free. Dynamic and real-time observation of land and ocean has become an important part of the observation system of the earth and the sea, and is currently the research focus of remote sensing technology. It is not only widely used in national economic construction, ecological environment protection and other fields, but also plays an increasingly important role in national security and military fields. With the launch of Gaofen-3 and other satellites, more and more high-resolution SAR images are provided, which further promotes the development and application of SAR image interpretation technology. [0003] In rec...

AI Technical Summary

Problems solved by technology

[0006] The invention provides a SAR image ship target recognition method based on a pulse neural network, which overcomes the technical problems of the existing SAR image ship target recognition neural network with huge parameters and high energy consumption.

Images