Unlock instant, AI-driven research and patent intelligence for your innovation.

An unsupervised sonar image segmentation method based on mrf model

An image segmentation, unsupervised technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of unfavorable real-time sonar image processing and target recognition, high algorithm complexity, long time consumption, etc.

Active Publication Date: 2016-05-04
HARBIN ENG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, the commonly used sonar image segmentation model is the MRF (Markov) segmentation model, but when applying the sonar image segmentation model, the existing theories and algorithms need to artificially determine the categories of sonar images to be classified However, there is no fully automatic sonar image segmentation model. The existing algorithms are complex and time-consuming, which is not conducive to real-time sonar image processing and target recognition requirements.

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
  • An unsupervised sonar image segmentation method based on mrf model
  • An unsupervised sonar image segmentation method based on mrf model
  • An unsupervised sonar image segmentation method based on mrf model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] Such as figure 1 As shown, the implementation steps of the non-supervised sonar image segmentation method based on the MRF model of the present invention are as follows:

[0047] Step 1: Raw sonar images (such as figure 2 shown) to perform Gaussian pyramid preprocessing to obtain the preprocessed image (such as Figure 4 shown).

[0048] Step 2: Calculate the grayscale histogram of the preprocessed sonar image (such as Figure 5 shown). The histogram of a digital image with a gray level in the range [0, L-1] is a discrete function h(r k ) = n k , here r k is the kth level of grayscale, n k is the gray level in the image is r k the number of pixels. A normalized histogram is given by P(r k ) = n k / n gives, where k=0,1,...,L-1.

[0049] Step 3: According to the gray histogram obtained in step 2, calculate the classification and number of classifications of sonar images, and the model for automatically determining the classification and number of classificat...

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 relates to an unsupervised sonar image segmentation method based on an MRF model. The unsupervised sonar image segmentation method based on the MRF model is characterized by comprising the following steps: S1, conducting Gaussian pyramid preprocessing on an original sonar image, obtaining a preprocessed image, S2, calculating a grey level histogram of the preprocessed sonar image, S3, calculating the classifications of the sonar image and the number of classifications according to the grey level histogram obtained in S2, and S4, calculating the initialized parameters of the MRF segmentation model according to the number of classifications obtained in S3 and a discrimination function, substituting the initialized parameters into the MRF segmentation model and segmenting the sonar image.

Description

technical field [0001] The invention relates to a non-supervised sonar image segmentation method based on an MRF model. Background technique [0002] As the development of marine resources has attracted more and more attention from all countries in the world, the exploration, search and investigation of underwater resources are also in full swing. Due to the complexity of the underwater environment, sonar is a The most effective sensor currently used in underwater detection. Since the sonar system was born in the late 1950s, sonar equipment used in the military field is mainly used for obstacle avoidance, and the discovery, tracking and identification of some military targets; in recent years, with the development of marine development activities , the application of sonar equipment is not limited to military purposes, and has even been applied to commercial and civilian fields, such as seabed resource development, oil exploration, shipwreck rescue, automatic drawing of sea...

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): G06T7/00
Inventor 叶秀芬张元科张建国李朋张翠翠王璘
Owner HARBIN ENG UNIV