Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Segmentation method of sea surface oil spillage image

A technology of sea surface oil spill and image segmentation, which is applied in the field of marine pollution treatment and can solve problems such as affecting the accuracy of oil spill segmentation and edge diffusion.

Active Publication Date: 2015-04-29
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the oil spill segmentation method based on high-order energy functions will lead to edge diffusion, and the edge of the segmented oil spill area tends to spread to the non-oil spill area, resulting in oil spill segmentation results with glitches, which affects the accuracy of oil spill segmentation

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
  • Segmentation method of sea surface oil spillage image
  • Segmentation method of sea surface oil spillage image
  • Segmentation method of sea surface oil spillage image

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0045] A segmentation method of oil spill image on sea surface, such as Figure 8 It includes the following steps:

[0046] Step 1: Construct a high-order Boolean energy function based on the oil spill image

[0047] A SAR oil spill image on the sea is as follows figure 1 As shown, the dark strip from the upper left corner to the lower right corner is the oil spill area, and the rest are non-oil spill areas.

[0048] E ( X ) = X p = 1 N E p ( x p ) + X g E g ( X g ) - - - ( 7 )

[0049] E in formula (7) p (x p ) Is the first-order criterion, E g (X g ) Is a high-order coupling term; P={1,2,...,N} is the pixel label set of the sea surface oil spill image, N is the number of pixels in the image; p represents the label of a certain pixel in the pixel set; X= {x 1 ,x 2 ,...,X N } Is a Boolean variable set, where the element x p Is the category label value of pixel p in the oil spill image on the sea...

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 belongs to the field of marine pollution treatment and particularly relates to a segmentation method of a sea surface oil spillage image. Particularly, a high-order Boolean energy function is established, wherein the high-order Boolean energy function comprises a first-order judging item and a high-order coupling item, the first-order judging item is obtained according to a single pixel energy function and an edge-preserving filter function through convolution so that a good effect of protecting the edge of an oil spillage zone can be achieved; and the high-order coupling item can be used for calculating the coupling performance of similar paired neighboring pixels in a pixel subset so that a long-strip-shaped oil spillage zone can be segmented precisely. The minimum value is obtained according to the established Boolean energy function by adopting a maximum flow / minimum segmentation algorithm, and each Boolean variable value corresponds to the optimum segmentation method of the oil spillage zone in the sea surface oil spillage image when the minimum energy value is adopted. By adopting the segmentation method, the influence of the edge diffusion phenomenon in the process of segmenting the long-strip shaped oil spillage zone can be overcome to a certain extent, and the segmentation accuracy can be improved.

Description

Technical field [0001] The invention relates to the field of marine pollution treatment, and in particular to a method for segmenting sea surface oil spill images. Background technique [0002] With the rapid development of the offshore oil industry and offshore oil transportation industry, and the continuous expansion of offshore oil exploration, development, and the laying of submarine pipelines, oil facilities have become a major source of pollution in the marine environment. Oil spills at sea have caused serious pollution to the marine environment and marine ecology. Protecting the marine environment and preventing pollution on the surface of the ocean has become an urgent problem that needs to be resolved. In order to prevent oil spill pollution on the sea surface, a variety of satellites are deployed to perform daily tasks of tracking and monitoring oil spills at sea. The real-time image of the sea surface transmitted by the satellite is used to detect oil spills on the s...

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): G06T7/00
CPCG06T2207/10032
Inventor 任鹏邸萌萌宋华军
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products