High-resolution SAR image segmentation method of improving FCM through multi-stage cooperation

Abstract

According to a high-resolution SAR image segmentation method for improving the FCM through multi-stage cooperation, the theoretical basis of an FCM clustering algorithm and the limitation of the FCM clustering algorithm for high-resolution SAR image segmentation are analyzed, weighted median filtering improvement is conducted on the FCM in combination with the spatial neighborhood relation of pixels, aiming at the limitation that a current FCM segmentation result is prone to falling into local optimum, SA is improved to further optimize the FCM, the effectiveness of the improved and optimized algorithm is verified through experiments, finally, the segmentation result of the improved and optimized FCM clustering algorithm is used as the initial segmentation of maximum posterior probability superposition re-segmentation, the maximum posterior probability superposition SAR re-segmentation is adopted to segment the image, qualitative and quantitative comparative analysis is carried out on the segmentation results of the above methods to obtain a series of improvements, the SAR segmentation quality is obviously improved, details and contours of image edge areas are clear, segmentation is accurate, robustness and reliability are good, meanwhile, the resistance of the algorithm is enhanced, and the SAR segmentation quality and efficiency are greatly improved.

Description

technical field [0001] The invention relates to an improved FCM high-resolution SAR image segmentation method, in particular to a multi-level cooperative improved FCM high-resolution SAR image segmentation method, which belongs to the technical field of high-resolution SAR image segmentation. Background technique [0002] In the research and application of images, people are often only interested in a certain area (target or background) on the image. To extract this part of information separately, digital image segmentation is needed. Image segmentation plays a pivotal role in image engineering, but subject to the current level of technological development, image segmentation results are far from meeting application requirements. All images have essential properties that can be used to distinguish them. This essential property is a feature, which includes both statistical and visual aspects. Statistical features are some intrinsic properties of an image, which can only be o...

AI Technical Summary

Problems solved by technology

[0007] First, there are relatively few methods for segmenting SAR images, because SAR is a microwave imaging image, which is very different from other types of images, which brings many difficulties to the segmentation of SAR images. The prior art SAR image segmentation The difficulties include: first, the problem of resolution, which is one of the important parameters to describe the quality of SAR images. The resolution of SAR images is relatively low, and there is a certain difference between high-resolution SAR images and optical images; The area is large, the target contained in it is small, and SAR is a slant distance image, which records the relative distance from the target to the sensor, and samples the echo signal at the same time interval. and ground distance conversion, in places with large height differences, the transformation of slant distance and ground distance will cause image distortion, including perspective shrinkage, overlapping, shadows and other phenomena, which increase the difficulty of SAR image segmentation; the third is in the process of SAR imaging , the ground object and the radar antenna move relatively, so that the phase of the echo obtained by the antenna is different, resulting in signal attenuation. When the echo power is much lower than the average level, the corresponding pixel is very dark, otherwise, the pixel is very bright. The cause of coherent speckle noise is caused by coherent imaging sensors. There are a lot of speckle noise in SAR images, and the signal-to-noise ratio is very low. Coupled with some factors in the randomly changing environment and complex background textures, some images in the image look like The blurring of the metavariable, the optical image segmentation algorithm is no longer applicable;

[0008] Second, SAR images inevitably contain serious coherent speckle noise and system noise, the signal-to-noise ratio is low, some factors in the randomly changing environment and complex background textures make image segmentation more difficult, and then appear MRF is used in image engineering, but how to convert the abstract and complex probability and statistics theory of MRF into an actual image algorithm is a big problem, which makes MRF unable to be applied in practice. There are many SAR image segmentation algorithms currently, but they are still There is no algorithm that can produce satisfactory segmentation results for SAR images obtained by various satellites in various states. SAR image segmentation algorithms have problems such as limited applicable objects and poor segmentation results. There is no scientific and reasonable evaluation rule for the quality of SAR image segmentation;

[0009] Third, when using the FCM algorithm to segment an image, the number of categories to be classified must be manually given. This number is usually obtained from experience. Therefore, how to automatically determine the optimal number of image categories to be segmented according to the actual impact is a difficult point and a problem that needs to be solved urgently.

In addition, the FCM algorithm must give the initial clustering focus, which is generally selected randomly, which will make the algorithm very blind, the iterative convergence speed may be greatly reduced, and the number of iterative calculations may increase , it takes a long time, it is difficult to find the global optimal solution, which affects the SAR image segmentation effect, and the FCM algorithm to obtain the global optimal solution is also a problem that needs to be solved urgently. , the segmentation effect is not good, and the original image cannot be accurately segmented while reducing various noise interference in the image segmentation;

[0010] Fourth, the FCM of the prior art is to find the smallest division w of the sample set, but there are the following shortcomings in the high-scoring SAR image segmentation: first, the initial clustering focus affects the clustering results, and second, it is necessary to manually set the clustering The number of classes, the third is that the noise cannot be effectively suppressed, the outlier segmentation and clustering effect is poor, and the fourth is that the algorithm often falls into a local optimum; resulting in unclear details and outlines of the edge area of ​​​​the SAR image, inaccurate segmentation, robustness and reliability. Not good. At the same time, the algorithm is not strong in resistance, and the quality and efficiency of SAR segmentation cannot achieve satisfactory results.

Images