Image preprocessing method based on geological radar

An image preprocessing and geological radar technology, applied in the field of image processing, can solve problems such as inaccurate judgment, inability to remove high frequency, and blurred recognition, and achieve accurate results

Pending Publication Date: 2021-03-12
SHANDONG UNIV +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, the existing geological radar images can be processed to a certain extent for tunnel rock cracks, but the processing method is not fixed, and it is often impossible to remove high-frequency (snowflake)-like signals and slight disturbance signals. The image of rock mass cracks in the tunnel formed by radar cannot be processed well, which causes certain interference to the recognition of rock mass crack images in the tunnel collected by geological radar, and the geological characteristics of rock mass in the tunnel formed by geological radar are disturbed Larger, the recognition is more vague, resulting in inaccurate judgment
[0003] Traditional image processing algorithms are difficult to accurately filter the features of ground radar images

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 preprocessing method based on geological radar
  • Image preprocessing method based on geological radar
  • Image preprocessing method based on geological radar

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0058] A preprocessing method based on ground radar images, comprising:

[0059] Step 1: Use the Filter Based on Feature-based Dividing Symbolic Radar Images Representation (FDS-Filter) to filter the ground radar image first;

[0060] Step 2: Use image processing technology to remove reflection signals from the filtered ground radar image;

[0061] Step 3: Use image processing technology to perform offset correction on the ground radar image after reflection removal.

Embodiment 2

[0063] A kind of preprocessing method based on ground radar image, as shown in embodiment 1, difference is, the method that step 1 adopts FDS-Filter to filter comprises the following steps:

[0064] 1.1. Input the entire image into FSD-Filter;

[0065] 1.2. Using the PAA method, the ground radar image T is standardized to a standard normal distribution with an expectation of 0 and a variance of 1, denoted as The filter threshold is set to σ; the value of σ can be filtered according to the on-site distribution, the larger the value, the less detail is preserved;

[0066] 1.3. Use the SAX method to represent the characteristic symbols, and cluster and divide the sub-segment waveforms;

[0067] 1.4. Record the ground radar image A segment of the waveform in Where 1≤i

[0068]

[0069] 1.3. The initially segmented GPR waveform to be represented is the GPR i...

Embodiment 3

[0079] A preprocessing method based on geological radar images, as shown in Example 2, the difference is that the SAX method in step 1.3, that is, the symbolic aggregate approximation method (Symbolic Aggregate Approximation, SAX) is a method that utilizes symbols to The method of radar waveform representation and similarity measurement, for a given radar waveform length n geological radar image T, the process of symbolic aggregation approximation method is as follows:

[0080] a. Put T={d 1 , d 2 ,...,d n} normalized to a radar image with mean 0 and standard deviation 1

[0081] b. Using the piecewise aggregation approximation method (Piecewise Aggregate Approximation, PAA) to Expressed as N equal-length waveform segments, namely in, is the mean value corresponding to the i-th segment, which can be obtained by the following formula:

[0082]

[0083] c. Normalized radar waveform Meet the Gaussian distribution, select the character set size a, and find the corr...

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 image preprocessing method based on geological radar, which belongs to the technical field of image processing. The method comprises the following steps of: firstly, filtering a geological radar image by using a FDS-Filter, removing a reflection signal from the filtered geological radar image by using an image processing technology, and finally, carrying out offset correction on the geological radar image after reflection removal by utilizing an image processing technology. According to the invention, a feature-based segmentation symbol radar image representation filter (FDS-Filter) is adopted to carry out geological image filtering, and various signal interferences in the image are accurately filtered, so that the defects of large geological feature signal disturbance and feature offset of the geological radar image after preprocessing are overcome, and the preprocessed geological radar can accurately display geological characteristics.

Description

technical field [0001] The invention relates to an image preprocessing method based on geological radar, which belongs to the technical field of image processing. Background technique [0002] At present, the existing geological radar images can be processed to a certain extent for tunnel rock cracks, but the processing method is not fixed, and it is often impossible to remove high-frequency (snowflake)-like signals and slight disturbance signals. The image of rock mass cracks in the tunnel formed by radar cannot be processed well, which causes certain interference to the recognition of rock mass crack images in the tunnel collected by geological radar, and the geological characteristics of rock mass in the tunnel formed by geological radar are disturbed Larger, the recognition is more vague, resulting in inaccurate judgment. [0003] It is difficult for traditional image processing algorithms to accurately filter the features of ground radar images. Contents of the inven...

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): G06K9/36G06K9/40G06K9/62G01V3/38
CPCG01V3/38G06V10/20G06V10/30G06F18/23
Inventor 刘健韩勃吕高航薛志超王凯解全一常洪雷王剑宏
Owner SHANDONG 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