Parallel underwater image segmentation method and device

An underwater image and image technology, which is applied in the field of parallel segmentation of underwater images and devices, can solve the problems that the non-parallel clustering segmentation method cannot well expand massive underwater images, and does not consider the correlation of multiple images.

Active Publication Date: 2015-07-22
SHENZHEN GRADUATE SCHOOL TSINGHUA UNIV
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The existing technology, the non-parallel clustering segmentation method based on a single image cannot be well extended and applied to the segmentation of massive underwater images; at the same time, because it is only for a single image, it does not consider the relationship between multiple images. Correlation, so it is not able to make full use of the gray similarity between some images to optimize
Existing methods cannot solve the processing efficiency problem of massive underwater image segmentation very well

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
  • Parallel underwater image segmentation method and device
  • Parallel underwater image segmentation method and device
  • Parallel underwater image segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The preferred embodiments of the invention will be further described in detail below.

[0050] Such as figure 1 Shown, the underwater image parallel segmentation method of a kind of embodiment, comprises the steps:

[0051] S1, divide a set of images into different sub-image groups according to the similarity of image attributes.

[0052] The similarity of image attributes may be the similarity of image content or the similarity of gray distribution of images, etc. Based on the similarity of image attributes, a large-scale image collection is grouped to obtain different sub-image groups. For example, if the image itself has a content label and the content contained in the image is marked, it can be grouped according to the content label, otherwise the gray distribution similarity is used.

[0053] The specific method of grouping by the similarity of gray distribution can be as follows:

[0054] 1) obtaining the grayscale histogram of the group of images;

[0055] 2)...

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 parallel underwater image segmentation method and device. The method includes the following steps: S1, dividing a group of images into different subimage groups according to similarities of image attributes; S2, allocating the different subimage groups to different computational resources respectively; S3, classifying each pixel to the corresponding clustering category via the computational resources in parallel according to the membership degree of gray, as a member of the clustering center, of each pixel of the corresponding subimage group, wherein the clustering center is a gray value. By the method and device, underground image segmentation efficiency can be improved.

Description

【Technical field】 [0001] The invention relates to an underwater image parallel segmentation method and device. 【Background technique】 [0002] At present, in the field of ocean observation, there is a general need to deal with the massive underwater images, especially the underwater image segmentation problem. The existing technology mainly focuses on and solves the segmentation accuracy and efficiency of a single underwater image. Therefore, as the number of underwater images collected by equipment such as underwater cameras continues to increase, the existing image processing methods are inefficient. 【Content of invention】 [0003] The existing technology, the non-parallel clustering segmentation method based on a single image cannot be well extended and applied to the segmentation of massive underwater images; at the same time, because it is only for a single image, it does not consider the relationship between multiple images. Therefore, it cannot make full use of the...

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
Inventor 李秀欧阳小刚陈连胜宋靖东
Owner SHENZHEN GRADUATE SCHOOL TSINGHUA 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