A Few-Shot Polsar Image Classification Method Based on Fuzzy Label Semantic Prior

Abstract

The invention discloses a small-sample PolSAR image classification method based on the fuzzy label semantic prior, prepares the PolSAR image to be classified; then obtains the real-numbered polarization feature as the input data of the network; obtains the sampling matrix and Record the sampling label matrix of the pixel label information at the corresponding position; use the sampling label matrix to initialize the classification and build the full convolution network FCN; then send the real input data, sampling matrix, sampling label matrix and classification matrix into the built full convolution Train in the network FCN; update the classification matrix using the current state of the prediction results of the FCN, the sampling matrix, the sampling label matrix and the classification matrix; repeat the operation until the maximum number of iterations is met; output the final classification matrix; calculate the classification accuracy and classification result map Complete image classification. The invention performs alternate iterative training on deep full convolutional network parameters and label category variables, and solves the problem of low PolSAR classification accuracy under the problem of small samples.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a small-sample PolSAR image classification method based on fuzzy label semantic prior, which can be used for object classification or target recognition of PolSAR remote sensing images. Background technique [0002] Polarization synthetic aperture radar (PolSAR) is an active earth observation system. By measuring and recording the amplitude and phase difference information between the transmitted wave and the echo in different polarization states, it can perform full polarization measurement and imaging of the target. Compared with traditional optical, infrared and other passive imaging systems, it has all-weather and all-weather working capabilities, is not limited by conditions such as smog, cloud and rain, and observation distance, and has certain penetration capabilities. Therefore, the PolSAR system is widely used in disaster monitoring, ocean monitoring...

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide a small-sample PolSAR image classification method based on the fuzzy label semantic prior in view of the deficiencies in the above-mentioned prior art, and combine the classification network based on the depth full convolution and the semantic label prior Learning, through alternate iterative training of neural network and classification matrix, solves the problem of low classification accuracy of PolSAR under the problem of small samples

Images