Polarized SAR target detection method based on fcn-crf master-slave network

Abstract

The invention discloses a polarimetric SAR target detection method based on FCN-CRF master-slave network. The polarimetric SAR image to be detected is input, and the polarimetric coherent matrix T of the polarimetric SAR image is filtered by refined polarization Lee filtering. coherent noise, to obtain the filtered coherence matrix, wherein each element in the filtered coherence matrix is ​​a 3×3 matrix, which is equivalent to a 9-dimensional feature for each pixel, and the present invention expands the image block feature into a pixel-level feature , the training samples selected through the matching of pixels in the region of interest are more relevant and more effective, and the number of pixels in the region of interest is less than 50% of the feature matrix blocks of the entire block, which will no longer participate in subsequent operations, to a great extent Reduce the amount of calculation and improve the detection efficiency; use Lee filter to preprocess the original polarimetric SAR, effectively reduce the coherent speckle noise, improve the image quality and detection performance; use Yamaguchi decomposition to get the spiral scattering that mainly corresponds to urban buildings components, effectively extracting the features of polarimetric SAR man-made targets, and increasing the detection accuracy of man-made targets.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a polarization SAR target detection method based on an FCN-CRF master-slave network. Background technique [0002] Polarization SAR has the advantages of all-weather, all-time, high resolution, side-view imaging, etc. It can obtain the fine features and geometric features of the target. It is very urgent to make fast and accurate detection of man-made targets in military and civilian applications. The efficient use of convolutional network in image feature extraction makes it have important theoretical value and broad application prospects in solving the problem of polarimetric SAR artificial target detection. [0003] Traditional convolutional networks such as CNN use image blocks as input for training and prediction to implement a pixel category detection task, which not only increases storage space, but also has low computational efficiency, and the size ...

AI Technical Summary

Problems solved by technology

[0003] Traditional convolutional networks such as CNN use image blocks as input for training and prediction to implement a pixel category detection task, which not only increases storage space, but also has low computational efficiency, and the size of image blocks is much smaller than the entire image. Lead to the loss of some features, thus limiting the detection performance

[0004] In 2015, in response to the problems existing in CNN, Jonathan Long et al. proposed Fully Convolutional Networks, referred to as FCN. This network extends the category detection task from the image level to the pixel level, thereby detecting the region of interest, but the FCN detection result is not fine enough. It is easy to ignore the image details, and the pixel-level detection fails to fully consider the spatial neighborhood information

Images