CN111209794A - Underground pipeline identification method based on ground penetrating radar image - Google Patents
Underground pipeline identification method based on ground penetrating radar image Download PDFInfo
- Publication number
- CN111209794A CN111209794A CN201911277872.1A CN201911277872A CN111209794A CN 111209794 A CN111209794 A CN 111209794A CN 201911277872 A CN201911277872 A CN 201911277872A CN 111209794 A CN111209794 A CN 111209794A
- Authority
- CN
- China
- Prior art keywords
- image
- ground penetrating
- penetrating radar
- carrying
- underground pipeline
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000149 penetrating effect Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 25
- 201000010099 disease Diseases 0.000 claims abstract description 12
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 12
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000003709 image segmentation Methods 0.000 claims abstract description 5
- 238000003708 edge detection Methods 0.000 claims description 10
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 abstract description 7
- 239000000463 material Substances 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention provides an underground pipeline identification method based on a ground penetrating radar image, which comprises the following steps: step1, carrying out image preprocessing on the obtained ground penetrating radar original image data; step2, carrying out image segmentation on the preprocessed image; and 3, carrying out feature recognition and extraction on the image subjected to threshold segmentation. The underground pipeline identification method based on the ground penetrating radar image can realize quick detection on the underground pipeline, greatly improves the identification accuracy and saves a large amount of manpower and material resources. The judgment result output comprises the number and the positions of the diseases, and the diseases are displayed in the original image in a frame selection mode, so that the diseases are more intuitive and convenient for a user to recognize.
Description
Technical Field
The invention relates to the field of character traffic engineering and the technical field of image processing, in particular to an underground pipeline identification method based on a ground penetrating radar image.
Technical Field
With the acceleration of the urbanization process, pipelines paved on municipal roads are gradually increased, and meanwhile, the detection and repair required by the construction of underground pipelines are also gradually increased. The pipe diameter of the underground pipeline is generally 0.1-1.5 m, the inside of the pipeline is filled with water, air or combustible gas and the like, and the pipeline is generally made of materials such as steel, cement and the like. The identification of the urban underground pipeline has very important significance for the detection, management and maintenance of municipal engineering underground facilities.
Ground penetrating radar has a very wide application as a nondestructive detection technology in both highways and municipal roads. The ground penetrating radar has the advantages of being lossless, rapid and accurate compared with other destructive detection methods for identifying foreign matters in roads including municipal road underground pipelines.
Most ground penetrating radar images are manually identified at present, a large amount of manpower and material resources are required to be invested for manual identification, and meanwhile, the requirements on knowledge storage and experience of an identifier are great. However, the problems can be well solved by using an image processing technology to process and identify and extract the underground pipeline image of the ground penetrating radar.
Disclosure of Invention
In order to solve the problem of how to accurately and automatically position the detection of the underground pipeline of the road, the invention provides the underground pipeline identification method based on the ground penetrating radar image.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
an underground pipeline identification method based on a ground penetrating radar image comprises the following steps:
step1, carrying out image preprocessing on the obtained ground penetrating radar original image data;
step2, carrying out image segmentation on the preprocessed image;
and 3, carrying out feature recognition and extraction on the image subjected to threshold segmentation.
Further, the image preprocessing in step1 includes the following steps:
step 1.1, reading original image data detected by a ground penetrating radar;
step 1.2, carrying out gray processing on the obtained ground penetrating radar image containing the underground pipeline information;
and step 1.3, performing median filtering processing on the grayed ground penetrating radar image.
Further, threshold segmentation is carried out on the edge detection of the ground penetrating radar image by adopting a Canny operator provided by an edge detection function in an MATLAB image processing library for the preprocessed ground penetrating radar image.
Further, the feature identification and extraction in the step3 includes the following steps:
step 3.1, performing morphological closing operation on the ground penetrating radar image subjected to threshold segmentation in the step two;
step 3.2, carrying out connected domain marking on the image after the morphological closing operation;
step 3.3, judging the area of the region marked with the connected domain and the ratio of the long axis to the short axis of the long axis of the circumscribed minimum rectangle;
and 3.4, outputting a judgment result.
And outputting the judgment result, including outputting the number and the positions of the diseases, and performing frame selection display on the diseases in an original image.
Compared with the prior art, the invention has the beneficial effects that:
the underground pipeline identification method based on the ground penetrating radar image can realize quick detection on the underground pipeline, greatly improves the identification accuracy and saves a large amount of manpower and material resources.
The judgment result output comprises the number and the positions of the diseases, and the diseases are displayed in the original image in a frame selection mode, so that the diseases are more intuitive and convenient for a user to recognize.
Drawings
FIG. 1 is a schematic flow chart of a ground penetrating radar image-based underground pipeline identification method according to the present invention;
FIG. 2 is a schematic diagram of a median filtered ground penetrating radar image;
FIG. 3 is a schematic diagram of the ground penetrating radar image after the edge detection threshold segmentation in step 2;
FIG. 4 is a schematic diagram of the ground penetrating radar image recognition decision in step 3.3;
fig. 5 is a schematic diagram of the output of the determination result in the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
As shown in fig. 1 to 5, the present invention provides a method for identifying an underground pipeline based on a ground penetrating radar image, comprising the following steps:
step1, carrying out image preprocessing on the obtained ground penetrating radar original image data; specifically, reading a ground penetrating radar image through MATLAB, converting the ground penetrating radar image into a gray scale map, and performing median filtering on the obtained gray scale map, wherein the result is shown in FIG. 2
Step2, carrying out image segmentation on the preprocessed image;
and 3, carrying out feature recognition and extraction on the image subjected to threshold segmentation.
Further, the image preprocessing described in step1 further includes the following steps:
step 1.1, reading original image data detected by a ground penetrating radar;
step 1.2, carrying out gray processing on the obtained ground penetrating radar image containing the underground pipeline information;
and step 1.3, performing median filtering processing on the grayed ground penetrating radar image.
The underground pipeline image obtained by using the ground penetrating radar is in a bright hyperbolic shape under a dark background, but meanwhile, a high-brightness area is formed at the ground surface by the ground penetrating radar, so that the situation is difficult to analyze by a general area segmentation method. The present invention therefore uses edge detection to segment the image. The method adopts the Canny operator provided by the edge detection function in the MATLAB image processing library to process the ground penetrating radar image, the Canny operator is suitable for different occasions, and the parameters of the Canny operator are allowed to be adjusted according to different implementation specific requirements so as to identify different edge characteristics.
Further, the edge detection algorithm of Canny operator can be divided into the following steps:
step1, smoothing the image with a Gaussian filter;
step2, calculating the magnitude and direction of the gradient by using finite difference of first order partial derivatives;
step3, carrying out non-maximum suppression on the gradient amplitude;
step4 edges are detected and connected using a dual threshold algorithm.
The method mainly comprises the following four steps:
image single-channel input image;
edges stores the output image of the edge in a single channel;
threshold1 first threshold;
threshold2 second threshold;
the Canny function uses the Canny algorithm to find edges in the input image and identify these edges in the output image. the small threshold of threshold1 and threshold2 is used to control edge connection, and the large threshold is used to control the initial segmentation of strong edges.
The result of the dual-threshold image segmentation process is shown in fig. 3.
Further, step three: the method for recognizing and extracting the features of the image after threshold segmentation comprises the following steps:
3.1, performing morphological closing operation on the image subjected to edge detection, wherein the image is mainly used for connecting a broken curve in the edge detection, and reducing misjudgment in a feature extraction stage;
3.2, marking a connected domain on the image after the morphological closing operation;
3.3 the discrimination condition is to discriminate the area marked with the connected component from the ratio of the major axis to the minor axis of the rectangle circumscribing the smallest.
When the ground penetrating radar detects the underground pipeline, a bright hyperbolic shape can be displayed on an image of the radar, and in view of the complexity and time consumption of Hough transform, the area and major axis-minor axis ratio is selected to be used for judging the underground pipeline. Compared with a hyperbolic region, other high-brightness regions are all in a long strip shape, and the area of the high-brightness regions is larger than that of the image at the position of the pipeline, so that most of large-area regions can be excluded by setting a threshold area A, and the threshold area A selected by the embodiment is 1000; meanwhile, as the major axis-minor axis ratio of the minimum rectangle externally connected to the strip-shaped area is far greater than that of the hyperbolic area, a reasonable communicated area is set and the minimum rectangle major axis-minor axis ratio threshold B externally connected to the strip-shaped area is further distinguished from the hyperbolic area, in the embodiment, the threshold B is set to be 3, and the obtained result is shown in fig. 4.
Further, the number and positions of the diseases are identified from the image in fig. 4, the diseases are framed in the original image, and the identification and output results are shown in fig. 5. The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above.
Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (5)
1. An underground pipeline identification method based on a ground penetrating radar image is characterized by comprising the following steps:
step1, carrying out image preprocessing on the obtained ground penetrating radar original image data;
step2, carrying out image segmentation on the preprocessed image;
and 3, carrying out feature recognition and extraction on the image subjected to threshold segmentation.
2. The method for identifying the underground pipeline based on the ground penetrating radar image as claimed in claim 1, wherein the image preprocessing in the step1 comprises the following steps:
step 1.1, reading original image data detected by a ground penetrating radar;
step 1.2, carrying out gray processing on the obtained ground penetrating radar image containing the underground pipeline information;
and step 1.3, performing median filtering processing on the grayed ground penetrating radar image.
3. The method for identifying underground pipelines based on ground penetrating radar images as claimed in claim 1, wherein in the second step, the edge detection of the ground penetrating radar images is subjected to threshold segmentation by using Canny operator provided by edge detection function in MATLAB image processing library.
4. The method for identifying the underground pipeline based on the ground penetrating radar image as claimed in claim 1, wherein the feature identification and extraction in the step3 comprises the following steps:
step 3.1, performing morphological closing operation on the ground penetrating radar image subjected to threshold segmentation in the step 2;
step 3.2, carrying out connected domain marking on the image after the morphological closing operation;
step 3.3, judging the area of the region marked with the connected domain and the ratio of the long axis to the short axis of the long axis of the circumscribed minimum rectangle;
and 3.4, outputting a judgment result.
5. The method for identifying underground pipelines based on ground penetrating radar images as claimed in claim 4, wherein in the step 3.4, the judgment result comprises the number and positions of the diseases in the underground pipelines, and the diseases are displayed in the original image in a frame selection mode.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911277872.1A CN111209794A (en) | 2019-12-11 | 2019-12-11 | Underground pipeline identification method based on ground penetrating radar image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911277872.1A CN111209794A (en) | 2019-12-11 | 2019-12-11 | Underground pipeline identification method based on ground penetrating radar image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111209794A true CN111209794A (en) | 2020-05-29 |
Family
ID=70785074
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911277872.1A Pending CN111209794A (en) | 2019-12-11 | 2019-12-11 | Underground pipeline identification method based on ground penetrating radar image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111209794A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105005042A (en) * | 2015-07-27 | 2015-10-28 | 河南工业大学 | Ground penetrating radar underground target locating method |
CN109716108A (en) * | 2016-12-30 | 2019-05-03 | 同济大学 | A kind of Asphalt Pavement Damage detection system based on binocular image analysis |
CN109903306A (en) * | 2019-02-21 | 2019-06-18 | 东南大学 | A kind of interlayer based on ground penetrating radar image comes to nothing recognition methods |
CN110349134A (en) * | 2019-06-27 | 2019-10-18 | 广东技术师范大学天河学院 | A kind of piping disease image classification method based on multi-tag convolutional neural networks |
-
2019
- 2019-12-11 CN CN201911277872.1A patent/CN111209794A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105005042A (en) * | 2015-07-27 | 2015-10-28 | 河南工业大学 | Ground penetrating radar underground target locating method |
CN109716108A (en) * | 2016-12-30 | 2019-05-03 | 同济大学 | A kind of Asphalt Pavement Damage detection system based on binocular image analysis |
CN109903306A (en) * | 2019-02-21 | 2019-06-18 | 东南大学 | A kind of interlayer based on ground penetrating radar image comes to nothing recognition methods |
CN110349134A (en) * | 2019-06-27 | 2019-10-18 | 广东技术师范大学天河学院 | A kind of piping disease image classification method based on multi-tag convolutional neural networks |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xu et al. | Automatic defect detection and segmentation of tunnel surface using modified Mask R-CNN | |
Park et al. | Patch-based crack detection in black box images using convolutional neural networks | |
Wang et al. | Towards an automated condition assessment framework of underground sewer pipes based on closed-circuit television (CCTV) images | |
CN102819952B (en) | Method for detecting illegal lane change of vehicle based on video detection technique | |
CN102436644B (en) | Unstructured road detection method based on adaptive edge registration | |
CN105447851A (en) | Glass panel sound hole defect detection method and system | |
CN107392141B (en) | Airport extraction method based on significance detection and LSD (least squares distortion) line detection | |
CN114998852A (en) | Intelligent detection method for road pavement diseases based on deep learning | |
CN104021574A (en) | Method for automatically identifying pavement diseases | |
Qu et al. | Lining seam elimination algorithm and surface crack detection in concrete tunnel lining | |
CN106709518A (en) | Android platform-based blind way recognition system | |
CN103136528A (en) | Double-edge detection based vehicle license plate identification method | |
Huang et al. | Edge detection of ore and rock on the surface of explosion pile based on improved Canny operator | |
CN111507971A (en) | Tunnel surface defect detection method | |
Kumar et al. | An automated road roughness detection from mobile laser scanning data | |
CN103413131A (en) | Tower crane recognition method based on spectral and geometric characteristics | |
CN104680787B (en) | A kind of congestion in road detection method | |
CN111209794A (en) | Underground pipeline identification method based on ground penetrating radar image | |
Ren et al. | Preprocessing of Crack Recognition: Automatic Crack-Location Method Based on Deep Learning | |
Gao et al. | Intelligent crack damage detection system in shield tunnel using combination of retinanet and optimal adaptive selection | |
CN108319927B (en) | Method for automatically identifying diseases | |
CN115272189A (en) | Pipeline defect rating method, terminal device and storage medium | |
Kulambayev et al. | Real-Time Road Surface Damage Detection Framework based on Mask R-CNN Model | |
CN116152674A (en) | Dam unmanned aerial vehicle image crack intelligent recognition method based on improved U-Net model | |
Li et al. | Utilizing semantic-level computer vision for fracture trace characterization of hard rock pillars in underground space |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200529 |
|
RJ01 | Rejection of invention patent application after publication |