Semantic Segmentation Method of SAR Image Based on Two-Stage Clustering

An image and clustering technology, applied in the field of image processing, can solve the problems of reduced clustering accuracy, long clustering time, inaccurate segmentation results, etc. Effect

Active Publication Date: 2019-08-06
XIDIAN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that when comparing and inferring the structural features of the disconnected regions in the aggregation region, this method uses the reasoning method of the self-organizing feature map SOM network, which needs to be manually determined. The number of clusters, and the clustering time is long, resulting in a decrease in clustering accuracy and affecting the accuracy of SAR image segmentation
The disadvantage of this method is that the pixel-level features of the SAR image are used to extract the features of the SAR image, and the unique structural features of the SAR image due to the correlation between pixels are not learned, resulting in inaccurate segmentation results.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Semantic Segmentation Method of SAR Image Based on Two-Stage Clustering
  • Semantic Segmentation Method of SAR Image Based on Two-Stage Clustering
  • Semantic Segmentation Method of SAR Image Based on Two-Stage Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention will be further described below in conjunction with the accompanying drawings.

[0030] refer to figure 1 , the concrete steps of the present invention are as follows.

[0031] Step 1, sketch the SAR image.

[0032] For the specific implementation of this step, please refer to the article "Local maximal homogenous regionsearch for SAR speckle reduction with sketch-based geometrical kernel function" published by Jie-Wu et al. in IEEE Transactions on Geoscience and Remote Sensing in 2014, which includes:

[0033] 1a) Input the synthetic aperture radar SAR image, and establish the sketch model of the synthetic aperture radar SAR image:

[0034] 1a1) In the range of [100,150], randomly select a number as the total number of templates;

[0035] 1a2) Construct a template with edges and lines composed of pixels in different directions and scales, use the direction and scale information of the template to construct an anisotropic Gaussian function, and ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a SAR image semantic segmentation method based on two-stage clustering, which mainly solves the problem of inaccurate segmentation of synthetic aperture radar SAR images in the prior art. The implementation steps are as follows: 1) Extract the sketch map according to the sketch model of the SAR image; 2) Regionalize the sketch map to obtain a region map, and divide the SAR image into a mixed aggregation structure object pixel subspace, a structure pixel subspace and a region map according to the region map. Homogeneous pixel subspace; 3) Design the directional statistical vector of the extremely heterogeneous region in the pixel subspace of mixed aggregate structure features; 4) Segment the mixed aggregate structure feature pixel subspace according to the direction statistical vector; 5) Segment the structure The pixel subspace and the homogeneous pixel subspace are segmented accordingly; 6) The segmentation results of the three subspaces are combined to obtain the final segmentation result of the SAR image. The invention can obtain good segmentation effect of SAR image, and can be used for target classification and image interpretation.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a synthetic aperture radar SAR image segmentation method, which can be applied to target detection, target classification, target positioning, target recognition and image interpretation. Background technique [0002] Synthetic aperture radar SAR is especially suitable for large-area landmark imaging. It can penetrate clouds, fog, rain and snow, and has the ability to work around the clock. With the rapid development of SAR image technology, more and more SAR image data are obtained, and it becomes an urgent problem to be solved to automatically interpret SAR images by computer. SAR image segmentation is the premise of SAR image interpretation, and the result of segmentation directly affects the result of SAR image processing. [0003] In the process of SAR imaging, the position of the target is recorded and imaged according to the time sequence of the radar...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/11G06K9/34G06K9/62
CPCG06T7/11G06T2207/10044G06V10/267G06F18/231
Inventor 刘芳李婷婷李远杰焦李成郝红侠古晶陈璞花马文萍马晶晶
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products