Target detection method for SAR (Synthetic Aperture Radar) image based on deep reinforcement learning

Abstract

The invention relates to a target detection method for an SAR (Synthetic Aperture Radar) image based on deep reinforcement learning, which comprises the steps of S1, setting the number of iterations,and sequentially processing images in a training set in each iteration process; S2, inputting an image from the training set, and generating training samples by using the Markov decision process; S3,randomly selecting a certain number of samples, training the Q-network by adopting a gradient descent method, obtaining the state of a reduced observation area, generating a next sample until a presettermination condition is met, and terminating the image processing process; S4, returning back to the step S2, continuing to input the next image from the training set until all images are completelyprocessed, and terminating the current iteration process; S5, continuing the next iteration process until the set number of iterations is met, and determining network parameters of the Q-network; andS6, performing target detection on an image in a test set through the trained Q-network, and outputting a detection result. The target detection method obtains good detection accuracy in target detection for the SAR image.

Description

technical field [0001] The invention belongs to the field of SAR image processing, and relates to a SAR image target detection method based on deep reinforcement learning. Background technique [0002] Synthetic Aperture Radar (SAR) is an active sensor using microwave perception, which is not limited by weather, light and other conditions. It can conduct all-weather and all-weather reconnaissance on targets of interest, and has been widely used in military and civilian fields. In the application field of SAR image interpretation, automatic target recognition (ATR) has always been the research focus and hotspot in this field. SAR image target detection is a key step in SAR image automatic target recognition. However, due to the complexity of the SAR imaging mechanism, the target is composed of fewer scattering points, and there is a lot of noise in the image, which increases the difficulty of target detection. [0003] The essence of SAR image target detection is to complete...

AI Technical Summary

Problems solved by technology

These traditional methods have achieved certain effects to a certain extent, but these methods require too much experience of experts to better extract the features of SAR image targets, thus limiting the detection accuracy

Images