A sonar image equalization method based on SLIC and adaptive filtering
An adaptive filtering, sonar image technology, applied in image enhancement, image data processing, character and pattern recognition, etc., can solve the problems of complex algorithm design, time-consuming process, uneven grayscale, etc., to avoid inherent data errors, The effect of improving the classification accuracy and solving the problem of gray imbalance
Active Publication Date: 2019-05-03
SHANDONG UNIV
View PDF6 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In the current research on sonar image segmentation and classification, the problem of gray scale imbalance is not considered separately. People mainly focus on classification or segmentation methods. Although better classification or segmentation results can be obtained in this way, the algorithm design more complex and time-consuming process
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
[0024] According to attached Figure 1-5 , specifically describe the embodiments of the present invention.
[0025] Step 1: Median filtering is performed on the sonar image, and the size of the filter is 3 by 3. The purpose of this step is to filter out the speckle noise in the sonar image. Median filtering is a common method in image filtering.
[0026] Step 2, using a simple linear iterative clustering method (proposed by Achanta in 2012), divide the sonar image into irregular image blocks. figure 1 The size of the medium sonar image is 419×317, K l =3000,K l Indicates the number of image blocks divided by SLIC. figure 2 For SLIC clustering results, the white grid lines in the figure are the boundaries of each cluster block.
[0027] Step 3-step 5, use adaptive filtering for each image block obtained by SLIC, this step is a key step of the present invention. The specific process is:
[0028] a. Perform pixel value uniqueization on each image block and its adjacent im...
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 belongs to the technical field of sonar image enhancement, and discloses a sonar image equalization method based on SLIC and adaptive filtering, comprising the following steps: 1, filtering speckle noise in a sonar image; 2, dividing the sonar image into irregular image blocks by using a simple linear iterative clustering method; 3, performing pixel value uniqueness on each image block, sorting pixel values, and obtaining a pixel median; 4, updating the gray values of the image blocks, and traversing all the image blocks according to the step 3; 5, dividing the sonar image into different numbers of image blocks for many times, and repeating the step 3 and the step 4 respectively; and 6, averaging the equalized images obtained in the step 5 for many times to obtain a final gray level equalized image. According to the technical scheme, the gray level similarity of the adjacent super-pixel image blocks and the gray level balance of each super-pixel image block are fully considered, the gray level equalization effect is good, and the method has an obvious effect on improving the classification accuracy of the sonar image.
Description
technical field [0001] The invention relates to the technical field of sonar image enhancement, in particular to a sonar image equalization method based on SLIC and adaptive filtering. Background technique [0002] Sonar image classification is an important means of submarine target recognition, which can be used in the fields of submarine topography detection, submarine survey, submarine pipeline tracking and state detection, etc. At present, the problem of gray level imbalance in sonar images has seriously affected the effect of sonar image classification. Therefore, solving the gray level imbalance of sonar images has a direct impact on improving the accuracy of sonar image classification. [0003] Affected by the complex environment of the seabed, acoustic noise and drag body movement, there are often grayscale distortions in sonar images. The existing sonar image gray level equalization methods are mainly based on the motion state of the drag body, which are provided b...
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 Applications(China)
IPC IPC(8): G06T5/20G06K9/62
Inventor 宋艳李沂滨何波
Owner SHANDONG UNIV