A SAR image target recognition method based on denoising self-coding network

Abstract

The invention discloses a SAR image target recognition method based on a denoising self-coding network. The method comprises the following steps: denoising an image by using a three-dimensional modulematching algorithm (BM3D); for the original image and the denoised training image, the dense feature points are extracted by the sliding window and stored in pairs according to the corresponding positions, which are used for the input of the depth denoising encoder in the later training. Using the SIFT feature extracted from the denoised image as the original input x. The SIFT extracted from thecorresponding undenoised image is used as the noisy input to train the deep denoising self-coding network. The spatial pyramid model (SPM) is used to compute the image feature vector expression, and the maximum pooling (Max Pooling) is used to summarize the local features to obtain the final image description vector. A large number of dense SIFT features are used for deep network training, and thehigh-level representation of deep denoising and self-coding features is used for learning. Finally, the linear support vector machine is trained to classify and recognize the features instead of theinitial local features.

Description

technical field [0001] The invention belongs to the application field of synthetic aperture radar (SAR) images, and relates to a SAR image target recognition method, in particular to a SAR image target recognition method based on a denoising self-encoding network. Background technique [0002] Synthetic Aperture Radar (SAR), as an important remote sensing imaging sensor, has a very wide range of applications in the fields of environmental monitoring, resource exploration, national defense and military affairs. In the face of massive SAR data, how to identify targets automatically, quickly and accurately has become an important direction of SAR image processing research, and has attracted more and more attention and attention. [0003] In recent years, deep learning has been widely used in the fields of image processing and speech recognition. Its core idea is to construct a deep neural network structure with multiple hidden layers to extract high-level semantic information o...

AI Technical Summary

Problems solved by technology

On the other hand, the calculation process of sparse representation is complex, computationally intensive and time-consuming.

[0005] The currently proposed SAR image target recognition algorithms are not general enough, and due to the large amount of coherent speckle noise contained in SAR images, complex and time-consuming image preprocessing is generally required before target recognition; at the same time, the feature extraction of traditional optical images Insufficiently stable and robust in SAR image features

Images