CN112013783A - Bridge crack depth detection method, device and system - Google Patents

Bridge crack depth detection method, device and system Download PDF

Info

Publication number
CN112013783A
CN112013783A CN202011124282.8A CN202011124282A CN112013783A CN 112013783 A CN112013783 A CN 112013783A CN 202011124282 A CN202011124282 A CN 202011124282A CN 112013783 A CN112013783 A CN 112013783A
Authority
CN
China
Prior art keywords
bridge crack
infrared image
thermal infrared
bridge
depth detection
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
Application number
CN202011124282.8A
Other languages
Chinese (zh)
Inventor
邓露
褚鸿鹄
史鹏
王维
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University
Original Assignee
Hunan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hunan University filed Critical Hunan University
Priority to CN202011124282.8A priority Critical patent/CN112013783A/en
Publication of CN112013783A publication Critical patent/CN112013783A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/22—Measuring arrangements characterised by the use of optical techniques for measuring depth
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • 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
    • G06T2207/10048—Infrared image
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30132—Masonry; Concrete

Abstract

The application discloses a bridge crack depth detection method, a bridge crack depth detection device and a bridge crack depth detection system, wherein the method comprises the steps of obtaining a to-be-detected thermal infrared image of the surface where a target bridge crack is located; the thermal infrared image to be detected is obtained by heating the area where the target bridge crack is located by thermal excitation equipment and then collecting the heated area; leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack; training a bridge crack depth detection model: collecting thermal infrared images of bridge cracks with known depth; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment; marking the depth information of the bridge cracks in the thermal infrared image to obtain a marked thermal infrared image and form a crack depth information thermal infrared image database; extracting a training vector from the labeled thermal infrared image; and inputting the training vector into a pre-established deep convolutional neural network for training to obtain a bridge crack depth detection model. And realizing the depth detection of the bridge cracks.

Description

Bridge crack depth detection method, device and system
Technical Field
The application relates to the technical field of bridge detection, in particular to a bridge crack depth detection method, device and system.
Background
The bridge is erected on rivers, lakes, seas or roads, so that vehicles, pedestrians and the like can pass smoothly, and the health condition of the bridge structure has important influence on the safety of lives and properties of people. Cracks are a common defect of bridges, and if repair is not performed in time, the bridge collapse is caused in severe cases. At present, when a crack of a bridge is detected, the position of the crack can be determined and the apparent crack of the bridge can be analyzed based on a visible light image by collecting the visible light image of the bridge, but the depth of the crack cannot be obtained, and particularly for the detection of the depth of the crack at the bottom of the bridge, equipment for detecting the depth of the crack is also lacked due to the special position of the crack.
Therefore, how to determine the depth of the crack should be a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
The application aims to provide a bridge crack depth detection method, a bridge crack depth detection device and a bridge crack depth detection system, so that the crack depth can be detected.
In order to solve the technical problem, the application provides a bridge crack depth detection method, which comprises the following steps:
acquiring a thermal infrared image to be detected of the surface of the target bridge crack; the thermal infrared image to be detected is acquired after the area where the target bridge crack is located is heated by thermal excitation equipment;
leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack;
the bridge crack depth detection model is obtained by training through the following steps:
acquiring a thermal infrared image of the surface where the bridge crack with a known depth is located; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment;
marking the depth information of the bridge cracks in the thermal infrared image to obtain a marked thermal infrared image and form a crack depth information thermal infrared image database;
extracting a training vector from the labeled thermal infrared image;
and inputting the training vector into a pre-built deep convolution neural network for training to obtain the bridge crack depth detection model.
Optionally, before the marking the depth of the bridge crack in the thermal infrared image, the method further includes:
and cutting the thermal infrared image to a preset size.
Optionally, the extracting a training vector from the post-labeling thermal infrared image includes:
and extracting the training vector from the marked thermal infrared image by using a principal component analysis method.
Optionally, before the obtaining of the thermal infrared image to be detected of the target bridge crack, the method further includes:
acquiring a visible light image of the target bridge crack;
and determining the position of the target bridge crack according to the visible light image.
The application still provides a bridge crack degree of depth detection device, includes:
the first acquisition module is used for acquiring a thermal infrared image to be detected of the surface of the target bridge crack; the thermal infrared image to be detected is acquired after the area where the target bridge crack is located is heated by thermal excitation equipment;
the leading-in module is used for leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack;
the second acquisition module is used for acquiring a thermal infrared image of the surface where the bridge crack with the known depth is located; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment;
the marking module is used for marking the depth of the bridge crack in the thermal infrared image to obtain a marked thermal infrared image and form a crack depth information thermal infrared image database;
the extraction module is used for extracting a training vector from the labeled thermal infrared image;
and the input module is used for inputting the training vector into a pre-established deep convolutional neural network for training to obtain the bridge crack depth detection model.
Optionally, the method further includes:
and the cutting module is used for cutting the thermal infrared image to a preset size.
Optionally, the method further includes:
the third acquisition module is used for acquiring a visible light image of the target bridge crack;
and the determining module is used for determining the position of the target bridge crack according to the visible light image.
The application also provides a bridge crack depth detecting system, includes:
an infrared camera;
the thermal excitation equipment is used for directly heating the region where the target bridge crack is located;
the depth detection equipment is used for executing the steps of any one of the bridge crack depth detection methods.
Optionally, the method further includes:
the unmanned aerial vehicle is used for carrying the infrared camera and the thermal excitation equipment;
the setting is in the tray that has the support on the unmanned aerial vehicle rotor is used for fixing distance between unmanned aerial vehicle and the bridge.
Optionally, the method further includes:
a visible light camera.
The bridge crack depth detection method comprises the steps of obtaining a thermal infrared image to be detected of the surface where a target bridge crack is located; the thermal infrared image to be detected is acquired after the area where the target bridge crack is located is heated by thermal excitation equipment; leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack; the bridge crack depth detection model is obtained by training through the following steps: collecting thermal infrared images of bridge cracks with known depth; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment; marking the depth information of the bridge cracks in the thermal infrared image to form a crack depth information thermal infrared image database; extracting a training vector from the labeled thermal infrared image; and inputting the training vector into a pre-established deep convolutional neural network for training to finally obtain a bridge crack depth information quantitative detection model.
Therefore, the bridge crack depth detection method is based on depth learning, the thermal infrared image of the region where the target bridge crack is located and heated by the thermal excitation device is obtained, the thermal infrared image is led into the bridge crack depth detection model which is trained in advance, the depth of the target bridge crack can be determined, and the crack depth can be detected.
In addition, the application also provides a device and a system with the advantages.
Drawings
For a clearer explanation of the embodiments or technical solutions of the prior art of the present application, the drawings needed for the description of the embodiments or prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a flowchart of a bridge crack depth detection method according to an embodiment of the present disclosure;
FIG. 2 is a flowchart of a training process of a bridge crack depth detection model according to an embodiment of the present disclosure;
FIG. 3 is a flowchart of another bridge crack depth detection method according to an embodiment of the present disclosure;
fig. 4 is a structural block diagram of a bridge crack depth detection device provided in the embodiment of the present application;
FIG. 5 is a schematic view of a bridge crack depth detection system provided in an embodiment of the present application;
fig. 6 is a front view of an unmanned aerial vehicle equipped with an infrared camera and a thermal excitation device according to an embodiment of the present disclosure;
fig. 7 is a side view of an unmanned aerial vehicle equipped with an infrared camera and a thermal excitation device according to an embodiment of the present disclosure;
fig. 8 is a top view of an unmanned aerial vehicle equipped with an infrared camera and a thermal excitation device according to an embodiment of the present application.
Detailed Description
In order that those skilled in the art will better understand the disclosure, the following detailed description will be given with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
As described in the background section, currently, when detecting a bridge crack, only apparent information of the crack can be detected, and the crack depth cannot be detected.
In view of the above, the present application provides a bridge crack depth detection method, please refer to fig. 1, where fig. 1 is a flowchart of a bridge crack depth detection method provided in an embodiment of the present application, and the method includes:
step S101: acquiring a thermal infrared image to be detected of the surface of the target bridge crack; and the thermal infrared image to be detected is acquired after the region where the target bridge crack is located is heated by thermal excitation equipment.
It should be noted that the thermal infrared image to be detected is an image of the surface where the crack of the target bridge is located, that is, when the crack of the target bridge is located on the front surface of the bridge, the thermal infrared image to be detected is an image of the front surface of the bridge; and when the target bridge crack is positioned at the bottom of the bridge, the thermal infrared image to be detected is the image of the bridge bottom.
The thermal infrared image to be measured is acquired after the area where the target bridge crack is located is heated by the thermal excitation equipment, namely, the heat generated by the thermal excitation equipment directly acts on the surface of the target bridge crack to heat the crack area.
When the target bridge crack is heated, a gradual heating method, namely a time-resolved infrared radiation method is adopted, in the heating process (continuous heating with the same low excitation power), the surface temperature of the target bridge crack is increased, and if a one-dimensional heat transfer model and a two-layer geometric structure of the target bridge crack are assumed, and the one-dimensional heat transfer model and the two-layer geometric structure refer to the prior related art, the temperature evolution on the surface of the target bridge crack caused by heating has the following relationship:
Figure 375179DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 26741DEST_PATH_IMAGE002
is the heating time; ccIs a constant related to energy absorption; is a mismatch factor, related to the emissivity of the material; l is the estimated vertical depth of the fracture; alpha is alpha0（m2S-1) Is the thermal diffusivity of the surface layer; t is the temperature of the fracture surface; n is a constant for each integration in the formula, and the value of n is from 1 to positive infinity.
The heating time for heating the target bridge crack can be set automatically, and similarly, the heating power of the thermal excitation equipment for heating the target bridge crack can be selected automatically, and the heating is stopped when the temperature of the target bridge crack reaches the preset temperature. The preset temperature is selected as appropriate, and may be generally 40 ℃.
It should be noted that the number of the thermal infrared images to be measured is multiple, and the thermal infrared images are continuously acquired from the beginning of heating the crack of the target bridge to the end of heating.
Step S102: and leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain quantitative information of the target bridge crack depth.
The crack depth detection method in this application not only can detect the positive crack of bridge, through with this method carry on the unmanned aerial vehicle system that this application provided, can also realize the high-efficient detection to bridge beam bottom crack, solved because crack position is special, the problem that conventional means is difficult to detect, the detection method range of application of this application is extensive.
Referring to fig. 2, the process of training the bridge crack depth detection model includes:
step S201: acquiring a thermal infrared image of the surface where the bridge crack with a known depth is located; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment.
It is noted that the bridge cracks of known depth are heated in accordance with the conditions of the target bridge crack, i.e. the heating time and heating power are kept consistent.
The upper limit of the number of the thermal infrared images is not specifically limited in the application, and the number of the thermal infrared images is hundreds, thousands or even more, and the crack depths are different and can be determined according to the situation.
Step S202: and marking the depth of the bridge crack in the thermal infrared image to obtain a marked thermal infrared image.
In the application, the tool for performing bridge crack depth labeling in the thermal infrared image is not particularly limited, for example, the tool is VoTT, OpenCV/CVAT, labelImg, LabelIme, or the like.
Step S203: and extracting a training vector from the labeled thermal infrared image.
And extracting the training vector from the labeled thermal infrared image by using a principal component analysis method so as to reduce the operand of the training vector after the training vector is input into a convolutional neural network. However, the method of extracting the training vector in the present application is not particularly limited, and for example, a method such as linear discriminant analysis, local linear embedding, or laplace feature mapping may be used.
Step S204: and inputting the training vector into a pre-built deep convolution neural network for training to obtain the bridge crack depth detection model.
The training vector is composed of N temperature values assigned to a specific pixel at each time, wherein the specific pixel refers to a pixel of the thermal infrared image corresponding to each time, and the thermal infrared image at each time has one temperature value. The number M of training vectors input in the convolutional neural network depends on the extraction method, for example, when using principal component analysis, the number of training vectors is the number of selected principal components, depending on the number of thermal infrared images of known depth (i.e., the sequence of thermal infrared images up to time t) acquired. Inputting the training vector into a pre-built deep convolution neural network, determining the weight parameter of each node in the model through back propagation operation, and obtaining the bridge crack depth detection model after repeated iterative operation.
Optionally, before the marking the depth of the bridge crack in the thermal infrared image, the method further includes:
and cutting the thermal infrared image to a preset size so as to facilitate marking and subsequent batch training.
The preset size is not particularly limited in the present application, as the case may be.
According to the bridge crack depth detection method, the thermal infrared image collected after the area where the target bridge crack is located is heated through the thermal excitation equipment is obtained, and the thermal infrared image is led into the bridge crack depth detection model trained in advance, so that the depth of the target bridge crack can be determined, and the crack depth can be detected.
Referring to fig. 3, fig. 3 is a flowchart of another bridge crack depth detection method according to an embodiment of the present disclosure, where the method includes:
step S301: and acquiring a visible light image of the target bridge crack.
Step S302: and determining the position of the target bridge crack according to the visible light image.
The process of analyzing the visible light image to obtain the position of the crack of the target bridge is well known to those skilled in the art, and will not be described in detail herein.
Step S303: acquiring a thermal infrared image to be detected of a target bridge crack; and the thermal infrared image to be detected is acquired after the region where the target bridge crack is located is heated by thermal excitation equipment.
Step S304: and leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack.
The bridge crack depth detection device provided by the embodiment of the application is introduced below, and the bridge crack depth detection device described below and the bridge crack depth detection method described above can be referred to correspondingly.
Fig. 4 is a structural block diagram of a bridge crack depth detection device provided in an embodiment of the present application, and referring to fig. 4, the bridge crack depth detection device may include:
the first acquisition module 100 is used for acquiring a thermal infrared image to be detected of the surface where the target bridge crack is located; the thermal infrared image to be detected is acquired after the area where the target bridge crack is located is heated by thermal excitation equipment;
and the importing module 200 is configured to import the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain quantitative information of the target bridge crack depth.
The second acquisition module 300 is used for acquiring a thermal infrared image of a bridge crack with a known depth; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment;
the marking module 400 is used for marking the depth of the bridge crack in the thermal infrared image to obtain a marked thermal infrared image and form a crack depth information thermal infrared image database;
an extracting module 500, configured to extract a training vector from the labeled thermal infrared image;
and the input module 600 is configured to input the training vector into a pre-established deep convolutional neural network for training, so as to obtain the bridge crack depth detection model.
The bridge crack depth detection apparatus of this embodiment is configured to implement the foregoing bridge crack depth detection method, and therefore a specific implementation manner of the bridge crack depth detection apparatus may be seen in the foregoing embodiments of the bridge crack depth detection method, for example, the first obtaining module 100, the importing module 200, and the first obtaining module 100, the second obtaining module 300, the labeling module 400, the extracting module 500, and the input module 600 are respectively configured to implement steps S201, S202, S203, and S204 of the bridge crack depth detection method, so that the specific implementation manner thereof may refer to descriptions of corresponding embodiments of each part, and details are not repeated herein.
Optionally, the bridge crack depth detection device further includes:
and the cutting module is used for cutting the thermal infrared image to a preset size.
Optionally, the extracting module is specifically configured to extract the training vector from the labeled thermal infrared image by using a principal component analysis method.
Optionally, the bridge crack depth detection device further includes:
the third acquisition module is used for acquiring a visible light image of the target bridge crack;
and the determining module is used for determining the position of the target bridge crack according to the visible light image.
The present application further provides a bridge crack depth detection system, please refer to fig. 5, which includes:
an infrared camera 1;
the thermal excitation equipment 2 is used for directly heating the region where the target bridge crack is located;
and the depth detection device 3 is used for executing the steps of the bridge crack depth detection method in the embodiment.
The infrared camera 1 is used for collecting a thermal infrared image to be detected in an area where a target bridge crack is located, which is heated by thermal excitation equipment, and the thermal excitation equipment 2 may be thermal excitation equipment based on a flash lamp array.
Preferably, the bridge crack depth detection system further comprises:
the unmanned aerial vehicle 4 is used for carrying the infrared camera 1 and the thermal excitation equipment 2;
set up and be in tray 5 with the support on the 4 rotors of unmanned aerial vehicle is used for fixing distance between 4 and the bridge of unmanned aerial vehicle.
The unmanned aerial vehicle 4 is used for carrying the infrared camera 1 and the thermal excitation equipment 2, so that cracks at all positions of a bridge can be conveniently detected, especially when the cracks are positioned at the bottom of the bridge, the unmanned aerial vehicle can carry the infrared camera and the thermal excitation equipment to fly to the bottom of the bridge to detect the cracks at the bottom of the bridge, and the problem that the conventional detection equipment is difficult to reach the bottom of the bridge to further detect the cracks is solved; further, in the measurement process, tray 5 pastes the surface of tight bridge and then the distance between fixed unmanned aerial vehicle 4 and the bridge, and shake when avoiding unmanned aerial vehicle 4 to hover, and then lead to thermal excitation equipment 2 to crack heating inhomogeneous, thermal infrared image blurring, influence the degree of depth detection precision. Fig. 6, 7, and 8 show a front view, a side view, and a plan view of the drone 4 having the infrared camera 1 and the thermal excitation device 2 mounted thereon, respectively.
Preferably, the bridge crack depth detection system further comprises:
visible light camera, visible light camera can carry on unmanned aerial vehicle 4 for gather the visible light image of bridge crack.
Preferably, the bridge crack depth detection system further comprises: and the storage device 6 is used for storing the thermal infrared image, the visible light image and the pre-trained bridge crack depth detection model.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The method, the device and the system for detecting the bridge crack depth provided by the application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.

Claims (10)

1. A bridge crack depth detection method is characterized by comprising the following steps:
acquiring a thermal infrared image to be detected of the surface of the target bridge crack; the thermal infrared image to be detected is acquired after the area where the target bridge crack is located is heated by thermal excitation equipment;
leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack;
the bridge crack depth detection model is obtained by training through the following steps:
acquiring a thermal infrared image of the surface where the bridge crack with a known depth is located; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment;
marking the depth information of the bridge cracks in the thermal infrared image to obtain a marked thermal infrared image and form a crack depth information thermal infrared image database;
extracting a training vector from the labeled thermal infrared image;
and inputting the training vector into a pre-built deep convolution neural network for training to obtain the bridge crack depth detection model.
2. The method for detecting the depth of the bridge crack according to claim 1, wherein before the marking the depth of the bridge crack in the thermal infrared image, the method further comprises:
and cutting the thermal infrared image to a preset size.
3. The bridge crack depth detection method of claim 2, wherein the extracting a training vector from the post-annotation thermal infrared image comprises:
and extracting the training vector from the marked thermal infrared image by using a principal component analysis method.
4. The bridge crack depth detection method of any one of claims 1 to 3, wherein before the obtaining of the thermal infrared image to be detected of the target bridge crack, the method further comprises:
acquiring a visible light image of the target bridge crack;
and determining the position of the target bridge crack according to the visible light image.
5. The utility model provides a bridge crack depth detection device which characterized in that includes:
the first acquisition module is used for acquiring a thermal infrared image to be detected of the surface of the target bridge crack; the thermal infrared image to be detected is acquired after the area where the target bridge crack is located is heated by thermal excitation equipment;
the leading-in module is used for leading the thermal infrared image to be detected into a pre-trained bridge crack depth detection model to obtain the depth of the target bridge crack;
the second acquisition module is used for acquiring a thermal infrared image of the surface where the bridge crack with the known depth is located; the thermal infrared image is acquired after the area where the bridge crack is located is heated by thermal excitation equipment;
the marking module is used for marking the depth of the bridge crack in the thermal infrared image to obtain a marked thermal infrared image and form a crack depth information thermal infrared image database;
the extraction module is used for extracting a training vector from the labeled thermal infrared image;
and the input module is used for inputting the training vector into a pre-established deep convolutional neural network for training to obtain the bridge crack depth detection model.
6. The bridge crack depth detection device of claim 5, further comprising:
and the cutting module is used for cutting the thermal infrared image to a preset size.
7. The bridge crack depth detection device of claim 5 or 6, further comprising:
the third acquisition module is used for acquiring a visible light image of the target bridge crack;
and the determining module is used for determining the position of the target bridge crack according to the visible light image.
8. A bridge crack depth detection system, comprising:
an infrared camera;
the thermal excitation equipment is used for directly heating the region where the target bridge crack is located;
depth detection equipment for carrying out the steps of the bridge crack depth detection method according to any one of claims 1 to 4.
9. The bridge fracture depth detection system of claim 8, further comprising:
the unmanned aerial vehicle is used for carrying the infrared camera and the thermal excitation equipment;
the setting is in the tray that has the support on the unmanned aerial vehicle rotor is used for fixing distance between unmanned aerial vehicle and the bridge.
10. The bridge fracture depth detection system of claim 8 or 9, further comprising:
a visible light camera.
CN202011124282.8A 2020-10-20 2020-10-20 Bridge crack depth detection method, device and system Pending CN112013783A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011124282.8A CN112013783A (en) 2020-10-20 2020-10-20 Bridge crack depth detection method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011124282.8A CN112013783A (en) 2020-10-20 2020-10-20 Bridge crack depth detection method, device and system

Publications (1)

Publication Number Publication Date
CN112013783A true CN112013783A (en) 2020-12-01

Family

ID=73527386

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011124282.8A Pending CN112013783A (en) 2020-10-20 2020-10-20 Bridge crack depth detection method, device and system

Country Status (1)

Country Link
CN (1) CN112013783A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113029080A (en) * 2021-03-22 2021-06-25 上海同岩土木工程科技股份有限公司 Non-contact mobile rapid measuring method and device for tunnel crack depth
CN113252700A (en) * 2021-07-01 2021-08-13 湖南大学 Structural crack detection method, equipment and system
CN114119614A (en) * 2022-01-27 2022-03-01 天津风霖物联网科技有限公司 Method for remotely detecting cracks of building

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102589418A (en) * 2011-01-08 2012-07-18 李伟强 Method for detecting positions of concrete crack and reinforcing steel bar of reinforced concrete member
CN207826555U (en) * 2017-12-13 2018-09-07 中新红外科技（武汉）有限公司 A kind of detection unmanned plane

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102589418A (en) * 2011-01-08 2012-07-18 李伟强 Method for detecting positions of concrete crack and reinforcing steel bar of reinforced concrete member
CN207826555U (en) * 2017-12-13 2018-09-07 中新红外科技（武汉）有限公司 A kind of detection unmanned plane

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JINXING QIU 等: "Quantitative evaluation of surface crack depth with laser spot thermography", 《INTERNATIONAL JOURNAL OF FATIGUE》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113029080A (en) * 2021-03-22 2021-06-25 上海同岩土木工程科技股份有限公司 Non-contact mobile rapid measuring method and device for tunnel crack depth
CN113029080B (en) * 2021-03-22 2022-08-02 上海同岩土木工程科技股份有限公司 Non-contact mobile rapid measuring method and device for tunnel crack depth
CN113252700A (en) * 2021-07-01 2021-08-13 湖南大学 Structural crack detection method, equipment and system
CN114119614A (en) * 2022-01-27 2022-03-01 天津风霖物联网科技有限公司 Method for remotely detecting cracks of building

Similar Documents

Publication Publication Date Title
CN112013783A (en) Bridge crack depth detection method, device and system
CN109117876B (en) Dense small target detection model construction method, dense small target detection model and dense small target detection method
CN109657716B (en) Vehicle appearance damage identification method based on deep learning
Dotenco et al. Automatic detection and analysis of photovoltaic modules in aerial infrared imagery
US10657707B1 (en) Photo deformation techniques for vehicle repair analysis
CN108648169B (en) Method and device for automatically identifying defects of high-voltage power transmission tower insulator
CN108460760B (en) Bridge crack image distinguishing and repairing method based on generation type countermeasure network
CN113252700B (en) Structural crack detection method, equipment and system
CN108038846A (en) Transmission line equipment image defect detection method and system based on multilayer convolutional neural networks
Yang et al. Deep learning‐based bolt loosening detection for wind turbine towers
CN109376773A (en) Crack detecting method based on deep learning
Mantel et al. Machine learning prediction of defect types for electroluminescence images of photovoltaic panels
Yan et al. Towards automated detection and quantification of concrete cracks using integrated images and lidar data from unmanned aerial vehicles
Kim et al. Automatic photovoltaic panel area extraction from UAV thermal infrared images
CN114993965B (en) Automatic pollution source identification method and system
CN114894642B (en) Fatigue crack propagation rate testing method and device based on deep learning
CN108509993A (en) A kind of water bursting in mine laser-induced fluorescence spectroscopy image-recognizing method
CN113724259A (en) Well lid abnormity detection method and device and application thereof
CN110390261A (en) Object detection method, device, computer readable storage medium and electronic equipment
Neuhausen et al. Automatic window detection in facade images
CN117011759A (en) Method and system for analyzing multi-element geological information of surrounding rock of tunnel face by drilling and blasting method
Ma et al. Detection of defects in geomembranes using quasi-active infrared thermography
Tajwar et al. Infrared thermography based hotspot detection of photovoltaic module using YOLO
CN116452519A (en) Tyre bulge flaw detection method based on multi-mode information fusion
Rodriguez et al. Segmentation and error detection of PV modules

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20201201