Check patentability & draft patents in minutes with Patsnap Eureka AI!

Multi-feature fusion underwater target modeling and optimization method

A multi-feature fusion and underwater target technology, which is applied in the field of multi-feature fusion underwater target modeling and optimization, can solve problems such as inability to accurately locate and extract target information, and achieve the effect of improving overall performance and computing speed

Active Publication Date: 2022-07-26
HOHAI UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: The purpose of this invention is to propose a multi-feature fusion underwater target modeling and optimization method to overcome the problem that the existing modeling technology cannot accurately locate and extract target information, and improve the accuracy of underwater target modeling results sex

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
  • Multi-feature fusion underwater target modeling and optimization method
  • Multi-feature fusion underwater target modeling and optimization method
  • Multi-feature fusion underwater target modeling and optimization method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to clearly highlight the objects and advantages of the present invention, the present invention will be further described below with reference to the accompanying drawings in the examples of the present invention.

[0036] A multi-feature fusion underwater target modeling and optimization method disclosed in the embodiment of the present invention mainly includes the following steps:

[0037] (1) Establish an underwater target area localization model according to the rules of the physical properties of corner points; the physical properties of corner points are: in the area where the target may exist, the detected corner points are densely distributed, and the strength of the physical properties is higher than that of non-physical properties. target presence area;

[0038] (2) according to the described underwater target area positioning model, calculate the density of corner points and the physical appearance strength of each corner point to locate the possibl...

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 multi-feature fusion underwater target modeling and optimization method, which locates the target area by performing similarity modeling on the corner points of underwater image generation, and derives the discrimination basis for underwater target information extraction; The texture and contrast features inside the image select the label that accurately represents the target information in this area, and use the ERM to propagate the label to obtain the initial target image; and combine the image space, texture and color features to optimize the propagation results to solve the initial target image. The problem of uneven grayscale changes. Compared with the traditional underwater target modeling and optimization method, the method of the invention integrates various target features, improves the accuracy of underwater target modeling and improves the overall performance on the premise of ensuring the good operation speed of the algorithm.

Description

technical field [0001] The invention belongs to the technical field of target modeling, and relates to a multi-feature fusion underwater target modeling and optimization method. Background technique [0002] Object modeling technology plays an important role in underwater scientific research and practical engineering. However, under the influence of underwater target diversity, scene complexity and imaging ambiguity, underwater imaging usually faces problems such as complex lighting conditions, low target contrast, and turbid water, which brings great challenges to graph-based underwater target modeling. more difficult. Graph-based target modeling has been widely studied due to its fast and accurate advantages, but this model relies heavily on the selected prior propagation labels, and the complex underwater environment will distort the feature difference between the background and the target, resulting in If the labels representing the target features are not selected acc...

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): G06V10/80G06V10/22G06K9/62G06T7/11G06T7/246G06T7/40G06T7/90
CPCG06T7/11G06T7/40G06T7/90G06T7/246G06V10/22G06F18/253
Inventor 王慧斌朱潮陈哲沈洁
Owner HOHAI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More