Marine internal wave detection algorithm based on multi-scale mathematical morphological feature fusion

A mathematical morphology and feature fusion technology, applied in computing, image data processing, computer parts and other directions, can solve problems such as inapplicable fluid edges and inconspicuous edges, achieving convenient and efficient algorithms, preserving edge features, and improving accuracy. sexual effect

Inactive Publication Date: 2019-03-01
NANJING UNIV OF SCI & TECH
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The ocean is a fluid, and the hydrological elements in the ocean show the characteristics of weak edges in satellite images, that is, the edges are not obvious, so the gradient method and Canny algorithm are not suitable for the extraction of fluid edges

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
  • Marine internal wave detection algorithm based on multi-scale mathematical morphological feature fusion
  • Marine internal wave detection algorithm based on multi-scale mathematical morphological feature fusion
  • Marine internal wave detection algorithm based on multi-scale mathematical morphological feature fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] An ocean internal wave detection algorithm based on multi-scale mathematical morphology feature fusion, comprising the following steps:

[0044] Step 1, wavelet decomposition: Use wavelet decomposition to decompose the detection object, and finally obtain the high-frequency sub-image and low-frequency sub-image of the source image. In terms of low frequencies, there is only one low frequency approximation sub-image. There are three high-frequency sub-images, which are high-frequency detail sub-images in three directions: horizontal, vertical, and diagonal.

[0045] a. Select the smooth function θ(x,y) as the scaling function, and find the first-order partial derivative ψ of the function θ(x,y) x (x,y) and ψ y (x,y), the ψ x (x,y) and ψ y (x,y) is regarded as a wavelet function.

[0046] B. carry out wavelet transform to image with following formula (1), (2), obtain two components of the horizontal and vertical direction of wavelet transform and

[0047]

[...

Embodiment 2

[0080] The technical effects of the present invention will be described below through simulation.

[0081] An ocean internal wave detection algorithm based on multi-scale mathematical morphology feature fusion, comprising the following steps:

[0082] Step 1, use wavelet decomposition to decompose the detection object, and finally obtain the high-frequency sub-image and low-frequency sub-image of the source image. figure 2 is the original map of ocean internal waves, image 3 It is the edge detection map of the ocean internal wave by the modulus maximum multi-scale wavelet.

[0083] Step 2: Use gray-value mathematical morphology to perform edge detection on low-frequency approximate sub-images containing a large amount of image information to obtain low-frequency image edges, such as Figure 4 shown.

[0084] Different structural elements are used to detect the edge of the image, and the edge image is fused by the method of entity weighted fusion and information entropy, a...

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 marine internal wave detection algorithm based on multi-scale mathematical morphological feature fusion, which comprises the following steps: multi-scale edge detection basedon wavelet transform modulus maximum obtains multi-scale edge information; the multi-scale edge detection obtains multi-scale edge information based on wavelet transform modulus maximum. Multi-scalemorphology is used to detect the edges of the low-frequency sub-images after wavelet decomposition. Then the small interference area is erased by using the connected domain method. Multi-scale waveletedge detection results of modulus maxima and multi-scale morphological edge detection results are fused to obtain multi-structure element multi-scale edge detection image. Compared with the existingtexture filtering method, the filtering result of the invention can not only keep the structure information of the image well, but also filter out some unnecessary texture details. The structure detection and the texture filtering algorithm provided by the invention obtain better effects in identifying and maintaining the weak gradient structure, inhibiting and smoothing the multi-scale and stronggradient texture and the like compared with the existing algorithm.

Description

technical field [0001] The invention relates to the field of computer graphics, in particular to an ocean internal wave detection algorithm based on fusion of multi-scale mathematical morphology features. Background technique [0002] Traditional edge detection methods are mainly based on some local features of the image to detect the structural information in the image. For example, a series of gradient operators such as sobel operator, Roberts operator, and Prewitt operator mainly detect edges by calculating the first-order derivative on the grayscale image. Marr and Hildreth proposed a method that uses Gaussian function to smooth the image first, and then uses Laplacian operator for derivation, and uses zero-crossing points to detect edges. This method is also called LOG (laplacianof gaussian) operator. Another classic edge detection algorithm is the canny operator, which regards the edge as discontinuous pixels in the brightness channel, and obtains the edge of the imag...

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): G06T7/13G06K9/62G06T7/155
CPCG06T7/13G06T7/155G06T2207/10004G06F18/25
Inventor 张雪禹刘梦诗潘海朗
Owner NANJING UNIV OF SCI & TECH
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