An underwater sonar image target segmentation method based on adaptive cultural algorithm

A cultural algorithm and underwater sonar technology, applied in the field of image processing, can solve the problems of less research in the field of underwater sonar images, and achieve the effect of improving the optimization ability and the segmentation accuracy.

Inactive Publication Date: 2019-03-08
HARBIN ENG UNIV
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the research on image segmentation technology is extensive, but there is less research in the field of underwater sonar images

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
  • An underwater sonar image target segmentation method based on adaptive cultural algorithm
  • An underwater sonar image target segmentation method based on adaptive cultural algorithm
  • An underwater sonar image target segmentation method based on adaptive cultural algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0099] The present invention will be further described below in conjunction with the accompanying drawings.

[0100] combine figure 1 , the concrete steps of the present invention are as follows:

[0101] 1 Non-local spatial information smoothing and denoising processing based on adaptive filter degree parameter selection based on golden ratio

[0102] ① Non-local spatial information

[0103] To calculate the value of non-local spatial information, two kinds of square windows need to be defined, which are the search window and the neighborhood window. Assume that the radius of the square search window is r=2, and the radius of the neighborhood window is s=1. figure 2 is a window diagram.

[0104] figure 2 in {v 1 ,v 2 ,...,v 25} form a square search window, v 13 is the center point of the search window. And each pixel in the search window has a square neighborhood window, such as {v 3 ,v 4 ,v 5 ,v 8 ,v 9 ,v 10 ,v 13 ,v 14 ,v 25} consists of v 9 neighborhoo...

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

An underwater sonar image target segmentation method based on an adaptive cultural algorithm relates to the technical field of image processing, and comprises the following steps of (1) smoothing anddenoising non-local spatial information based on adaptive filtering parameter selection of golden section rate; (2) in the population space of the cultural algorithm, using a quantum-derived hybrid frog leapfrog algorithm based on a new search mechanism as an update strategy of the population space; (3) in the belief space of the cultural algorithm, using the adaptive contraction expansion coefficient of the quantum particle swarm optimization algorithm as the renewal strategy of the belief space; (4) adjusting the communication mechanism to increase the utilization of evolutionary informationin population space and belief space. The method of the invention has better searching ability and improved searching efficiency, can better improve segmentation accuracy, and has certain effectiveness and adaptability.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an underwater sonar image target segmentation method based on an adaptive culture algorithm. Background technique [0002] In recent years, sonar imaging has been widely used in underwater landform survey, mine detection, dam foundation detection and other fields due to its advantages of long working distance and strong penetrating power. Underwater target recognition technology includes image denoising, target segmentation, feature extraction and classification processes. Due to the complexity of the marine environment and the influence of various interference factors, underwater sonar images generally have problems such as prominent speckle noise, low contrast, and blurred edge details, which affect the further processing of the image. Therefore, smoothing and denoising the underwater sonar image is an essential step, which is beneficial to the subsequent target segme...

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 Applications(China)
IPC IPC(8): G06T7/11G06T7/136G01S15/89
CPCG06T7/11G06T7/136G01S15/89G01S15/8977G06T2207/20192G06T2207/20004G06T2207/10132
Inventor 王兴梅李其明刘安华孙博轩
Owner HARBIN ENG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap