Small sample PolSAR image classification method based on fuzzy label semantic prior

Abstract

The invention discloses a small sample PolSAR image classification method based on fuzzy label semantic prior. The method comprises the steps of preparing a PolSAR image to be classified; obtaining real polarization characteristics as input data of the network; obtaining a sampling matrix for recording the position of the training sample and a sampling label matrix for recording pixel label information at the corresponding position; utilizing the sampling label matrix to initialize and classify to build a full convolutional network FCN; sending the real-number input data, the sampling matrix,the sampling label matrix and the classification matrix to a built full convolutional network FCN for training; updating the classification matrix by utilizing the prediction result of the FCN, the sampling matrix, the sampling label matrix and the current state of the classification matrix; repeating the operation until the maximum number of iterations is met; outputting the final classificationmatrix; and calculating classification accuracy and a classification result graph to complete image classification. According to the invention, alternate iteration training is carried out on the deepfull convolution network parameters and the label category variables, and the problem of low PolSAR classification precision under a small sample problem is solved.

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