A Mine Target Recognition Method Based on Active Contouring in Sonar Images

A sonar image and target recognition technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of sonar image noise, uneven image intensity, edge leakage, etc., and achieve good anti-noise performance

Active Publication Date: 2017-10-27
SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

2. Sonar images generally have large noise, poor edges, serious shape distortion, and uneven image intensity
Since the edge of the target in the sonar image is relatively blurred, if the edge-based contour evolution model is adopted, edge leakage is likely to occur during the evolution 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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Mine Target Recognition Method Based on Active Contouring in Sonar Images
  • A Mine Target Recognition Method Based on Active Contouring in Sonar Images
  • A Mine Target Recognition Method Based on Active Contouring in Sonar Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0059] 1. Level set function of hyperelliptic constrained active contour model

[0060] The traditional level set function is defined as a signed distance function, and the contour curve represented by the zero level set of this level set will become an arbitrary shape during the evolution process. When the target boundary is greatly distorted, the target contour curve of this method will be greatly deformed during the evolution process, and the final contour curve obtained is irregular and not ideal. To solve this problem, a level set function introducing an ellipse shape constraint is proposed to obtain an ideal target contour. Since the shape of the mine target is relatively regular, the shape-preserving active contour model is adopted, and the shape constraint of the mine target is added to the level set function. The mine studied in this ...

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 relates to the field of automatic target recognition of images, in particular to a mine target recognition method of sonar images. The invention includes proposing an active contour model constrained by a hyperellipse, an active contour model constrained by a multiphase level set, and a sonar image mine target recognition method based on the active contour model. Compared with the general target recognition method, the present invention has the advantages that it can still meet the requirement of identifying the mine target in the noisy sonar image, and can still obtain the accurate outline of the mine target under the condition that the image of the mine target is blurred.

Description

technical field [0001] The invention relates to the field of automatic target recognition of images, in particular to a mine target recognition method of sonar images. Background technique [0002] Sonar is an underwater remote sensing device for mapping seabed topography and a powerful tool for seabed mapping. Its working principle is: the sound pulse is sent from the transducer and propagates to the distance as a spherical wave, and the backscattered waves generated by the seabed are transmitted back to the transducer one after another, and the echo signal is displayed through the graphic device to form a picture reflecting the seabed. Image of geological properties. [0003] Such as figure 1 As shown, the sonar image is divided into three areas according to the gray distribution: the echo area (target area), the sound shadow area and the background area. The echo in the echo area is strong, which is the brighter area in the image, the echo in the background area is wea...

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): G06K9/62
Inventor 朱枫郝颖明李娟娟吴清潇高雷
Owner SHENYANG INST OF AUTOMATION - CHINESE ACAD OF SCI
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