SAR Image Segmentation Method Based on Feature Extraction and Clustering Integration
A feature extraction and image segmentation technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of complex calculation, unsuitable for SAR image processing, low algorithm execution efficiency, etc., to suppress speckle noise and reduce calculation. The amount of data and the effect of improving segmentation accuracy
Active Publication Date: 2017-06-13
XIDIAN UNIV
View PDF2 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The prior knowledge required by these algorithms is difficult to obtain in actual SAR image processing, and these algorithms often require training models to make calculations too complex, resulting in low algorithm execution efficiency, so they are not suitable for SAR image processing
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0027] Refer to attached figure 1 , the implementation steps of the present invention are as follows:
[0028] Step 1, input a SAR image with the number of rows X and the number of columns Y, where X and Y are both positive integers.
[0029] Step 2: Extract the features of the SAR image to obtain the grayscale information and texture information of all pixels in the image, and express the grayscale information and texture information extracted from each pixel with a 10-dimensional representation vector.
[0030] The feature extraction of SAR images can use specific filter filtering method, gray level co-occurrence matrix statistical method, Fisher discriminant analysis method and nonlinear feature extraction method represented by kernel method, etc. The purpose of feature extraction is to extract image information The characteristics of the pixels, lines or regions in the image are more prominently expressed.
[0031] The method adopted in this example is: use the median fi...
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
Login to View More Abstract
The invention discloses an SAR image segmentation method based on feature extraction and cluster integration. The SAR image segmentation method mainly solves the problem that sensitivity of paraphase speckle noise and segmentation accuracy in an existing method are low. The SAR image segmentation method comprises the following steps that (1) feature extraction is conducted on an original SAR image, a multi-dimensional feature set is constructed, and dimensionality reduction is conducted on the multi-dimensional feature set so as to obtain a new feature set; (2) repeated selective Kmeans clustering is conducted on the new feature set so as to obtain a plurality of clustering center sequences, and center matching is conducted on the clustering center sequences; (3) by means of the matched clustering center sequences, the new feature set is divided so as to obtain a plurality of mark vectors; (4) the obtained mark vector are integrated to obtain an integrated mark vector; (5) by means of the integrated mark vector, a segmentation result of the SAR image is obtained. The SAR image segmentation method has the advantages of having high paraphase speckle noise robustness and high segmentation accuracy and can be used for target detection and recognition of the SAR image.
Description
technical field [0001] The invention belongs to the technical field of image segmentation, relates to the segmentation of SAR images, and can be used for target detection and recognition of SAR images. Background technique [0002] Synthetic Aperture Radar (SAR) technology plays a vital role in national economy, geological exploration and military affairs, and SAR image processing is an important part of SAR technology. Due to the complexity of the SAR image scene and the huge amount of data, it puts a lot of pressure on the target detection and classification of the SAR image, so the effective segmentation of the SAR image is an urgent need in the application of the SAR image. SAR uses the backscattering of electromagnetic waves on the surface of the ground object to image. Due to this imaging mechanism, the image will be affected by coherent speckle noise. The grayscale difference between the target area and the background area in the image is not large, and the edge of th...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/11G06T7/187G06K9/46G06K9/62
Inventor 白静胡波韩雪云焦李成王爽
Owner XIDIAN UNIV