Method for adaptively selecting ground penetrating radar image for detecting moisture damage

Patent metadata

Field	Value
Publication number	US-12085639-B2
Application number	US-202017631454-A
Country	US
Kind code	B2
Filing date	Oct 13, 2020
Priority date	Nov 1, 2019
Publication date	Sep 10, 2024
Grant date	Sep 10, 2024

Abstract

A method for adaptively selecting a ground penetrating radar (GPR) image for detecting a moisture damage is provided. The method adaptively selects the GPR image according to a contrast of the GPR image. The method includes the following steps: S1, reading pre-processed GPR data; S2, adjusting a resolution of a picture; S3, inputting a data set into a recognition model; S4, outputting a moisture damage result; S5, judging whether there is a detection target or not by using an initial random image data set; and S6, generating the GPR image randomly incrementally and selecting the GPR image with a proper contrast. A proper B-scan image is found effectively, quickly and automatically by combining a recognition algorithm and a deep learning model or an image classification model to achieve an automatic recognition and detection based on the GPR image and improving a recognition precision as well.

First claim

What is claimed is:

1. A method for automatically detecting moisture damage defects by adaptively selecting a Ground Penetrating Radar (GPR) image for detecting a moisture damage, wherein the method adaptively selects the GPR image with a proper contrast according to data of the GPR image, comprising the following steps:
S 1 , reading pre-processed GPR data:
generating GPR images with different contrasts randomly in a set contrast data range after pre-processing GPR data to construct an initial random image data set, wherein the initial random image data set comprising N pictures;
S 2 , adjusting resolutions of the N pictures:
defining the initial random image data set as an RID data set, zooming the RID data set to 224*224 to obtain a zoomed data set and defining the zoomed data set as an RBD data set;
zooming a resolution of a moisture damage initial image data set directly to 224*224 to obtain the RBD data set;
S 3 , inputting the RBD data set into a recognition model:
inputting the RBD data set obtained in the step S 2 into the recognition model, and executing a step S 4 after an operation of the recognition model, wherein a picture input resolution size of the recognition model is 224*224 and a picture output resolution size of the recognition model is 224*224;
the recognition model is a mixed deep learning model, wherein the mixed deep learning model is comprised of two portions: a feature extraction adopting ResNet50 and a target detection adopting a YOLO V2 frame;
S 4 , outputting a moisture damage result:
post-processing an output result of the recognition model in the S 3 , wherein the post-processing comprising the following steps:
S 41 , judging a quantity of candidate boxes BBoxes of a spectra in the output result, executing S 42 when the quantity of candidate boxes BBoxes is greater than 1, otherwise, outputting a result directly;
S 42 , judging whether the candidate boxes BBoxes are overlapped or not, executing S 43 when the candidate boxes BBoxes are overlapped, otherwise, outputting the result directly;
S 43 , judging whether label names corresponding to overlapped candidate boxes are identical or not, wherein when label names corresponding to the overlapped candidate boxes are identical, the label names corresponding to merged candidate boxes are invariable and when label names corresponding to the overlapped candidate boxes are not identical, indicating that moisture damage label names and bridge joint label names are comprised simultaneously, the label names are output as bridge joint, Joint;
S 44 , merging the candidate boxes BBoxes, taking a minimum value of intersected candidate boxes in x and y directions, taking a maximum value of w and h, wherein coordinates of a merged candidate box are [x min , Y min , W max , h max ];
S 45 , outputting the result, adjusting an output picture resolution to be equal to a picture resolution of the moisture damage initial image data set in the output result of the recognition model, wherein the output resul is a label name with a target and an image of the candidate box BBoxes (x, y, w, h) corresponding to the target;
S 5 , judging whether a detection target is present or not with the initial random image data set:
S 51 , converting the output result in the S 4 into a matrix A i corresponding to pixel points in a picture, wherein A i is defined as:

A
i

[

m
,
n

]

=

{

1
,

x
i

≤
m
≤

x
i

+

W
i

⁢

and
⁢

y
i

≤
n
≤

y
i

+

h
i

0
,

other

,

where 1≤m≤H 0 , 1≤n≤W 0 ;
wherein H 0 is a picture height of an image output by the recognition model and W 0 is a picture width of the image output by the recognition model;
summating the matrixes A i corresponding to the N pictures in the RID data set and calculating a mean value of the matrixes A i to acquire a mean value matrix A, wherein A is defined as:

A
=

1
N

⁢

∑

i
=
1

N

A
i

;

S 52 , setting k 1 =0.8 and θ 0 =0.5, and updating the mean value matrix A according to a formula below to acquire an updated mean value matrix A;
A ( A <max( k 1 * max(max( A )),θ 0 ))=0;

wherein
k 1 is a target association coefficient;
θ 0 is a minimum value in the matrix A when the target is comprised, and no target is present when the mean value is lower than the minimum value;
max(max(A)) is a maximum value in the mean value matrix A;
S 53 , acquiring a judging condition T for judging whether the target is present or not according to a formula below on a basis of the updated mean value matrix A, and when the judging condition T is equal to 1, indicating that the target is present and when the judging condition Tis equal to 0, indicating that no target is present;

T
=

{

Assignees

• Changan Univ

Inventors

• Zhang Jun
• Tao Jun

Classifications

• G01S13/89

  for mapping or imaging · CPC title

• G01S7/418

  Theoretical aspects · CPC title

• G01S7/417

  involving the use of neural networks · CPC title

• G01S7/41

  using analysis of echo signal for target characterisation; Target signature; Target cross-section · CPC title

• G01S13/885 Primary

  for ground probing (prospecting or detecting using electromagnetic waves G01V3/12) · CPC title