SAR image change detection method based on SPL and CCN

Abstract

The present invention discloses an SAR (Synthetic Aperture Radar) image change detection method based on an SPL (Self-Paced Learning) and a CCN (Convolutional Coupling Network). The problem is solvedthat a current technology is greatly influenced by nose and is not high in detection precision. The method comprises the steps of: (1) reading and processing data; (2) randomly selecting training samples; (3) constructing a convolutional coupling neural network; (4) training the convolutional coupling neural network; (5) employing the self-paced learning method to re-train the convolutional coupling neural network; (6) obtaining feature mapping; (7) employing a logarithm ratio method to obtain a difference chart; and (8) employing a threshold value method to obtain a change detection result map. Compared to the prior art, the SAR image change detection method filters part of training samples with large loss values, inhibits the influence of the noise on the change detection result, reducesthe generation of wrong classification points and improves the classification accuracy.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a synthetic aperture radar SAR (Synthetic Aperture Radar) based on self-paced learning SPL (Self-Paced Learning) and convolutional coupling neural network CCN (Convolutional Coupling Network) in the technical field of radar image processing Radar) image change detection method. The invention can be used to detect regional differences in two or more synthetic aperture radar SAR images from the same area in different time phases, so as to realize the monitoring of crop growth, urban planning layout, natural disasters and the like. Background technique [0002] As an active microwave sensor, synthetic aperture radar has the characteristics of high resolution, all-weather, all-weather work and strong penetration ability, which makes synthetic aperture radar SAR images widely used. The change detection of synthetic aperture radar SAR image is to identify the area that ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the deficiencies of the above-mentioned prior art, and propose a synthetic aperture radar SAR image change detection method based on self-paced learning SPL and convolutional coupling neural network CCN, which can effectively avoid the training process from falling into local optimum, At the same time, some pixels that are greatly affected by multiplicative speckle noise are filtered, which solves the problem in the prior art that the detection of synthetic aperture radar SAR image changes is greatly affected by noise.

Images