Image segmentation method and system based on Kalman filtering and Markov random field

A Kalman filter, Kalman filter technology, applied in the field of image processing

Active Publication Date: 2020-06-05
SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Defect segmentation methods are usually set according to specific detection objects, not necessarily suitable for image segmentation of defects like alum

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
  • Image segmentation method and system based on Kalman filtering and Markov random field
  • Image segmentation method and system based on Kalman filtering and Markov random field
  • Image segmentation method and system based on Kalman filtering and Markov random field

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0111] The preferred embodiments of the present invention will be further described in detail below.

[0112] Firstly, the collected image is sub-area background sampled, and the image of each area is used as a sub-image, and the background area statistical table is established as the initialization information of the Kalman filter. The background gray level of each sub-image changes slowly, which can be regarded as obeying a Gaussian distribution, and the constant (CV) model is used to describe the gray level change characteristics. Then, the Kalman filter of the constant velocity (CV) model is used to filter the image from different directions, and the heterogeneous regions are found according to the statistical distribution characteristics of the residuals from the Kalman filter, and the abnormal points are interpreted. This filter can also be referred to as a residual detector based on Kalman filtering. Because the detector itself has a hysteresis phenomenon, and it is pr...

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 provides an image segmentation method and system based on Kalman filtering and a Markov random field. The image segmentation method comprises the following steps: carrying out prior processing on an image, partitioning the image, collecting background pixels and to-be-measured object image pixels in each sub-image, setting a Markov random field, setting a Kalman filter, carrying outparameter setting, and initializing the Kalman filter; filtering each row and each column of the whole image in two perpendicular directions; under a Markov random field neighborhood system, carryingout local statistics on an area marked by a Kalman filter, calculating the distance from a current pixel I (I, j) to a background and an object to be measured, judging the category of the current pixel I (I, j), then fusing marking results in two directions, carrying out median filtering is to remove abnormal points, and obtaining a defect segmentation result. According to the technical scheme ofthe invention, the segmentation precision of the to-be-measured object image is improved, and a hole phenomenon is avoided.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to an image segmentation method and system based on Kalman filter and Markov random field. Background technique [0002] Waterworks basically use alum as a water purifier. Whether the treated water is qualified or not depends on the amount of alum added. During the hydrolysis of alum, aluminum hydroxide colloidal precipitates are formed, and the impurities in the water are precipitated together to form alum flowers. Alum in water The number and volume of flowers reflect the addition of alum, so it is necessary to detect the alum flowers in the sedimentation tank of the water plant to detect the amount of alum added. At present, there are mainly three detection methods: (1) manual detection method, through the human naked eye to observe the state of alum flowers formed in the sedimentation tank after the alum is dissolved in water, to judge whether the input amount of alum i...

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): G06T7/00G06T7/11G06T7/194
CPCG06T7/0004G06T7/11G06T7/194G06T2207/20221G06T2207/20032
Inventor 陈宝文程东升黄秀琴
Owner SHENZHEN INSTITUTE OF INFORMATION TECHNOLOGY
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