A Sonar Image Segmentation Method Based on Offset Field Level Set

An image segmentation and level set technology, applied in image analysis, image enhancement, image data processing and other directions, can solve problems such as inapplicability and complex algorithms, achieve good segmentation results, do not increase the amount of calculation, and resist noise interference.

Active Publication Date: 2022-03-18
HARBIN ENG UNIV
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method utilizes the Markov segmentation model, but the overall algorithm is relatively complex and not suitable for operation in the actual marine environment

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
  • A Sonar Image Segmentation Method Based on Offset Field Level Set
  • A Sonar Image Segmentation Method Based on Offset Field Level Set
  • A Sonar Image Segmentation Method Based on Offset Field Level Set

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The invention is further described below with reference to the accompanying drawings:

[0051] Such as figure 1 A sonar image segmentation method based on an offset field level, containing the following steps:

[0052] Step (1): figure 2 , The source image is subjected to a non-sampling contour wave transform, respectively, and the primary and secondary image multi-scale decomposition, resulting in a low frequency sub-image, including a first low frequency image, a second low frequency image;

[0053] Step (2): According to the low frequency sub-image, combined with the Markov quad neighborhood model, the Markov quad neighborhood model parameters are estimated:

[0054] Image domain In all 点 pixel values ​​i (x) is random variable, i (x) = i x Probability P (i (x) = i x ) Is expressed as conditional probability p (i x | Ω). Pixel x neighborhood is expressed x , When the probability P (i x | Ω) = p (i x When | η)> 0, the current pixel values ​​are designed to be related to th...

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 sonar image segmentation method based on an offset field level set, belonging to the field of digital image processing, comprising the following steps: performing multi-scale decomposition on a source image to obtain a low-frequency sub-band image; according to the low-frequency sub-band image, combining Markov four-neighborhood model, estimating the parameters of the Markov four-neighborhood model; resubstituting the parameters of the Markov four-neighborhood model into the low-frequency sub-band image to obtain a local texture image; deriving the three-phase model based on the level set theory of the original offset field Offset field level set theory; replace the source image with local texture images, construct the energy function of the improved offset field level set model, minimize the energy function of the improved offset field level set model, and drive the contour to converge to the edge of the region; Output the segmentation result. The invention can effectively resist the noise interference of the sonar image, and accurately segment the three types of regions in the sonar image without increasing the amount of calculation.

Description

Technical field [0001] The present invention belongs to the field of digital image processing, and more particularly to a sonar image segmentation method based on an offset field level. Background technique [0002] As marine resources are increasingly valued by countries around the world, the exploration, search and investigation of underwater resources are also in full swing, due to the complexity of underwater environment, compared with optical imaging, laser detecting a type of sensor, sonar is The most effective sensor currently applied to underwater detection. Since the birth of the sonar system, since the birth of the military field, the sonar is used in the military field, mainly for obstacles, and discovery, tracking and identification of some military goals; in recent years, with marine development activities The application of sonar equipment is not limited to military purposes, and even has been applied to commercial and civilian fields, such as submarine resource dev...

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): G06T7/11
CPCG06T7/11G06T2207/10132G06T2207/20116
Inventor 卞红雨张健张志刚黄靖伟王子麒
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