Improved bilateral filtering and clustered SAR based image change detection method

Abstract

The invention discloses an improved bilateral filtering and clustered SAR based image change detection method mainly for solving the problem of high speckle noise and low accuracy of the existing image change detection method. The image change detection method is implemented by the following steps: 1, inputting two to-be-detected images of the same size; 2, performing denoising pretreatment on the two images to configure an initial difference image; 3, performing median filtering on the initial difference image to obtain a final difference image; 4, performing clustering on the final difference image to obtain an unchanged type fuzzy membership matrix uu and a changed type fuzzy membership matrix uc; and 5, performing assignment and classification on the elements in the changed type fuzzy membership matrix uc to obtain a final change detection result image. According to the improved bilateral filtering and clustered SAR based image change detection method, the number of false detection and the speckle noise are reduced, more image information is kept, and the accuracy rate and the precision of the change detection are improved, so that the image change detection method can be used for evaluation of disaster situations, urban construction and forest change monitoring.

Description

technical field [0001] The invention belongs to the field of image processing, and relates to a SAR image change detection method, which can be used for disaster prediction, urban construction and forest change monitoring. Background technique [0002] With the continuous advancement of science and technology, the requirements for the acquired images are continuously improved, and the imaging of synthetic aperture radar SAR images is not affected by weather, atmosphere, temperature, and illumination, and has the characteristics of high resolution, which makes the changes of SAR images Detection has gradually become a research hotspot at home and abroad. Change detection of SAR images refers to the process of processing and analyzing two images acquired at different times and at the same place, and then obtaining change information. Due to the various advantages of SAR images, the change detection of SAR images has very important applications in many aspects. [0003] With ...

AI Technical Summary

Problems solved by technology

Because the fuzzy C-means clustering algorithm does not give a specific threshold when clustering, but uses the fuzzy membership matrix to represent the probability that each sample belongs to a certain set. Compared with the hard division, simply divide a certain sample It will be more accurate to a certain category, and it can better retain the original information of the image, but it does not take into account the spatial information of pixels, so it is very sensitive to speckle noise

[0004] S.KrinidisandV.Chatzis published the paper "Arobust fuzzy local information C-means clustering algorithm" on IEEETrans.ImageProcessing in May 2010. This paper improved the fuzzy C-means clustering algorithm and added a fuzzy factor to the objective function of the FCM algorithm. The fuzzy factor Taking spatial information into account can enhance the ability of the algorithm to suppress speckle noise to a certain extent, and also improve the image segmentation rate. Applying this method to change detection can get better change detection results, but because this method only It is a change detection for pixels, and does not make full use of the neighborhood information and regional features of the difference map, resulting in inaccurate change detection results

MaoguoGong et al. improved and published the paper "ChangeDetectioninSyntheticApertureRadarImagesbasedonImageFusionandFuzzyClustering" on IEEETrans.ImageProcessing in 2012. This paper fuses the images obtained by the mean ratio method and the logarithmic ratio method. Using the regional features in the difference map, the above method The fuzzy factor in has also been improved, so that the accuracy of change detection has been further improved, but the image obtained by the mean ratio and the logarithmic ratio is fused, and the neighborhood gray information of the difference map is not fully utilized. As a result, the results of change detection are not accurate enough.

Images