CN111402227B - Bridge crack detection method - Google Patents
Bridge crack detection method Download PDFInfo
- Publication number
- CN111402227B CN111402227B CN202010174163.7A CN202010174163A CN111402227B CN 111402227 B CN111402227 B CN 111402227B CN 202010174163 A CN202010174163 A CN 202010174163A CN 111402227 B CN111402227 B CN 111402227B
- Authority
- CN
- China
- Prior art keywords
- bridge
- crack
- cracks
- segmentation
- image
- 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.)
- Active
Links
Images
Classifications
-
- 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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic 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
- G06T7/10—Segmentation; Edge detection
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a bridge crack detection method, belongs to the technical field of bridge detection, and aims to improve the detection precision and efficiency of bridge crack detection. The method comprises the following steps: carrying out crack segmentation on the collected group of bridge images; and detecting and classifying the bridge cracks by adopting a pre-constructed bridge crack classification model according to the crack segmentation result. The method comprises the following steps that an improved GAC algorithm model is adopted for the bridge crack segmentation treatment, so that visible cracks in a bridge bottom image shot by a high-definition camera of an unmanned aerial vehicle are segmented; the construction of the bridge crack classification model adopts a deep learning method, and a deep convolution-based neural network model is designed for identifying the bridge; the three-dimensional reconstruction and crack information detection of the bridge cracks adopt a moving cube algorithm to determine the number, the average width, the geometric properties and the overall spatial relationship of the cracks, so that professionals can perform qualitative or quantitative analysis on the cracks. The invention realizes that the building problems such as corresponding crack detection and the like are solved by utilizing the computer detection technology based on deep learning.
Description
Technical Field
The invention relates to a bridge crack detection method, and belongs to the technical field of bridge detection.
Background
At present, the bridge crack detection and maintenance mainly depend on manual detection. The manual detection method is time-consuming and requires a large amount of manpower, material resources and financial resources, not only is the detection accuracy low and the human influence factor large, but also in many cases, the crack cannot be detected visually due to the inaccessibility of the region or the microscopic size of the crack.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a bridge crack detection method which can improve the efficiency and the precision of bridge crack detection.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
a bridge crack detection method comprises the following steps:
carrying out crack segmentation on the collected group of bridge images;
and detecting and classifying the bridge cracks by adopting a pre-constructed bridge crack classification model according to the crack segmentation result.
Further, the method for performing crack segmentation on the acquired bridge image comprises the following steps:
dividing cracks in each bridge image to serve as initial contours by adopting a spectral clustering algorithm promoted based on Nystrom approximation theory;
sequentially mapping the divided cracks to the next bridge image along the upward direction to serve as the initial contour of the crack in the bridge image, and finishing the division of each crack by adopting an improved GAC model until the division of all bridge images is finished;
and sequentially mapping the cracks which are segmented along the upward direction onto the next bridge image along the downward direction, wherein the cracks are used as initial contours of the cracks in the bridge image, and the segmentation of each crack is completed by adopting an improved GAC model until all bridge images are segmented.
Further, the method for completing the segmentation of each fracture by using the improved GAC model comprises the following steps:
calculating the gray level mean value and the gray level standard deviation of each divided crack area, and taking the gray level mean value and the gray level standard deviation as the gray level similarity information of each crack area;
constructing a gray level similarity information item according to the gray level similarity information;
and adding the gray level similarity information item as an external energy item to an energy functional of the GAC model, thereby improving the GAC model.
Further, the method for constructing the bridge crack classification model comprises the following steps:
collecting original bridge images containing various cracks;
carrying out crack marking and crack segmentation on the collected original bridge image to construct a sample data set of bridge cracks;
initially constructing 8 layers of deep convolutional neural networks by combining global characteristics of a bridge, wherein each deep convolutional neural network comprises a first input layer, a third convolutional layer, a third pooling layer, a second full-connection layer and an output layer, and a softmax classifier is adopted;
and training and testing the constructed deep convolution neural network by adopting the sample data set so as to determine the structure and parameters of the bridge crack classification model.
Further, data cleaning is carried out on the original bridge image, and unmarked bridge images are eliminated.
Further, the method further comprises: before crack segmentation is carried out, the bridge image is converted into a gray image, and enhancement and normalization processing are carried out on the gray image.
Further, the method further comprises:
and performing three-dimensional reconstruction on the bridge crack according to the crack segmentation result so as to obtain the three-dimensional visualization effect of the crack.
Further, three-dimensional reconstruction and crack information detection are carried out on the bridge cracks by adopting a moving cube algorithm.
Furthermore, when the crack is divided, the local extreme value corresponding to the noise and the irregular detail is eliminated.
Further, the types of the cracks include: plastic cracks, shrinkage cracks, arch bridge radial cracks, longitudinal cracks at the gap between the underbelly boxes, pier cap cracks and arch foot cracks.
Compared with the prior art, the invention has at least the following beneficial effects:
the bridge crack classification model is adopted to detect and classify the bridge cracks, so that the bridge crack detection precision and efficiency can be obviously improved, and the computer detection technology based on deep learning is utilized to solve the building problems such as corresponding crack detection.
Drawings
FIG. 1 is a flow chart of a bridge crack detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a bridge fracture segmentation method according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for constructing a bridge crack classification model according to an embodiment of the present invention;
fig. 4 is a diagram of an algorithm platform framework applicable to the method of the present invention according to an embodiment of the present invention.
Detailed Description
The method comprises four parts of a bridge crack segmentation processing method, bridge crack classification model establishment, three-dimensional bridge crack reconstruction and crack information detection and bridge crack detection platform establishment. The method comprises the following steps that an improved GAC algorithm model is adopted for the bridge crack segmentation treatment, so that visible cracks in a bridge bottom image shot by a high-definition camera of an unmanned aerial vehicle are segmented; the construction of the bridge crack classification model adopts a deep learning method, and a deep convolution-based neural network model is designed for identifying the bridge; the three-dimensional reconstruction and crack information detection of the bridge cracks adopt a moving cube algorithm to determine the number, the average width, the geometric properties and the overall spatial relationship of the cracks, so that professionals can perform qualitative or quantitative analysis on the cracks; and (3) building a bridge crack detection platform, wherein a high-performance building image processing platform which is characterized by a bridge crack detection technology of deep learning is built. Based on the platform, key problems such as bridge crack detection processing and analysis are researched. The research of the invention is carried out from the four aspects, and the building problems such as corresponding crack detection and the like are solved by utilizing the computer detection technology based on deep learning.
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
As shown in fig. 1, the bridge crack detection method provided by the embodiment of the invention includes the following steps:
adopt unmanned aerial vehicle high definition digtal camera to shoot a set of bridge image. In the flight process of the unmanned aerial vehicle, the safety distances between different unmanned aerial vehicles and detection positions are controlled according to the difference of detection objects: pier and tower column are generally controlled to be about 5 meters, the complex terrain parts such as cable and steel member are generally controlled to be about 10 meters, and the specific safety distance is determined by combining the field condition; generally, a light-facing surface of a detection object is selected for image acquisition, so that backlight is avoided, and the success rate of data acquisition is improved; generally, the detection is carried out in a windless environment in sunny days, so that the influence of environmental factors is reduced as much as possible, and the safety risk in the detection process is reduced; the unmanned aerial vehicle shooting time interval is not larger than 3 s; keep interval between unmanned aerial vehicle height and the wall roof beam not have obvious change in the shooting time, the difference in angle between the adjacent picture is ignored.
The method comprises the following steps: carrying out bridge crack segmentation treatment on a group of bridge images:
step 1: a Spectral Clustering algorithm (SCN) based on Nystrom approximation theory popularization is adopted to segment visible cracks in each image as an initial contour;
step 2: sequentially mapping the segmented visible cracks to the next image along the upward direction to serve as the initial contour of the crack in the image, and then completing segmentation of each crack by adopting an improved GAC model until all the image segmentation is finished;
step 3: and sequentially mapping the visible cracks which are already segmented onto the next image along the downward direction to serve as initial contours of the cracks in the C image, and then completing segmentation of each crack by adopting the improved GAC model until all the image segmentation is finished.
Because the shooting time interval between the adjacent pictures in each group of bridge images is short, and the difference between the adjacent positions and the time is small, the corresponding gray information between the adjacent pictures changes slowly. Therefore, the segmentation of the non-segmented cracks can be guided by using the gray scale information of the segmented crack portions as the similarity information, which contributes to improving the segmentation accuracy and the segmentation efficiency of the bridge cracks to a certain extent. In the embodiment of the invention, a specific method for completing the segmentation of each crack by adopting an improved GAC model comprises the following steps:
calculating the gray level mean value and the gray level standard deviation of the segmented crack area, taking the gray level mean value and the gray level standard deviation as the gray level similarity information of the crack area, and constructing a gray level similarity information item according to the gray level similarity information; then, the term is used as an external energy term to be added to an energy functional of the GAC model, so that the GAC model is improved.
Step two: classifying and detecting the bridge cracks by adopting a pre-constructed bridge crack classification model;
the specific method for constructing the bridge crack classification model comprises the following steps:
(1) data collection: collecting and arranging 3000 original bridge images, and selecting 400 cases of bridge images of plastic cracks, shrinkage cracks, arch bridge radial cracks, longitudinal cracks at gaps between boxes under the belly, abutment cap cracks and arch foot cracks according to marks; 1800 cases are taken as training data, and 1200 cases are taken as test data.
(2) Image preprocessing: performing data cleaning on all collected data, removing unmarked data, converting the collected images into gray images, performing enhancement processing on images with weak contrast, and normalizing the images into experimental data with the same size;
(3) and (3) fracture splitting treatment: by adopting the crack segmentation processing method, the cracks in the image are segmented and extracted, and a bridge crack sample data set is constructed for training and testing of the DCNN;
(4) constructing DCNN: initially constructing a deep convolutional neural network with 8 layers (excluding input and output layers) by combining global features of a bridge, wherein the deep convolutional neural network comprises an input layer, three convolutional layers, three pooling layers, two full-connection layers and an output layer, and a softmax classifier is adopted;
(5) discussing different model parameters of the same model structure: aiming at the bridge global feature sample space set, discussing the influence of input images with different spatial resolutions and different iteration times on the DCNN recognition rate and the training time;
(6) discussing different model structures: on the basis of an initially constructed 8-layer network structure and global characteristics, discussing the identification of different model structures on bridge cracks by changing the size of a convolution kernel, the number of characteristic graphs and the number of network layers;
(7) and (3) comparing and analyzing different optimization algorithms: after a proper model structure is selected, the influence of a pooling method (mean value sampling and maximum value sampling), an activation function (Sigmoid function and Re LU function) and a training algorithm (batch gradient descent method and gradient descent method with elastic momentum) on a recognition result is contrastively analyzed;
(8) and (3) decision evaluation: different model parameters and structures are analyzed and discussed through comparison experiments, and a reference basis is provided for constructing a proper deep convolution neural network for computer-aided detection of bridge cracks, so that the identification performance is improved, and the network robustness and generalization capability are enhanced.
Step three: three-dimensional reconstruction and crack information detection of bridge cracks;
the volume data set of an image is composed of a series of two-dimensional slices. Assuming that the resolution of each slice is M × N and the number of slices (including virtual slices) is L, the slices constitute a spatially discrete data field with a resolution of M × N × L. This data field can be seen as the result of sampling the continuous function f (x, y, z) in x, y, z directions at certain intervals. If the volume data is considered as a sampled set of some object property in a spatial region and the values at non-sampled points are estimated by interpolation of their neighboring sampled points, then the set of points with some same value in the spatial region will constitute an iso-surface. Because the gray values and the like of different cracks are different in the image, when an appropriate value is selected to define the isosurface, three-dimensional reconstruction of different cracks can be realized. In the embodiment of the invention, the three-dimensional reconstruction and crack information detection of the bridge cracks adopt a moving cube algorithm to determine the number, the average width, the geometric property and the overall spatial relationship of the cracks, so that professionals can perform qualitative or quantitative analysis on the cracks.
As shown in fig. 4, an embodiment of the present invention further provides a bridge crack detection platform, which can be used in the bridge crack detection method, and the platform has strong computing power and storage capability, so that the requirement of bridge crack research can be met, and technical support can be provided for other image applications. The algorithm platform integral framework is divided into three layers: bottom layer, middle layer, application layer.
(1) Bottom layer
The bottom layer is mainly constructed by using mature open source algorithm libraries such as ITK, VTK, FSL and the like. The basic algorithms of image reading and writing, filtering, registering, segmenting, format conversion and the like existing in the ITK are mainly reserved. For VTK, because VTK is a software package developed for a general visualization field and not only for a crack detection field, some algorithms and data structures thereof are not required for crack detection, and these large and complicated algorithms and data structures greatly increase the difficulty of users. Therefore, the functions of surface drawing, grid drawing and volume drawing commonly used in three-dimensional display of crack detection are mainly reserved in the algorithm platform. The underlying algorithms also include FSL and self-research algorithms. In addition, if other excellent crack detection processing and analysis algorithm libraries exist, the excellent crack detection processing and analysis algorithm libraries can be integrated into the bottom-layer algorithm.
(2) Intermediate layer
The method is established on a bottom-layer algorithm, and a plurality of common basic algorithms are connected and combined and packaged into a relatively complete and practical application function, so that the operation of an algorithm researcher on the bottom layer is simplified, and the work of writing bottom-layer codes is reduced. The middle layer generalizes the bottom layer algorithm into five parts, namely format conversion, filtering, registration, segmentation and display of the crack image. The middle layer reserves a uniform interface for the same type of algorithm so as to facilitate the calling of the application layer.
(3) Application layer
And recombining the executable programs provided by the middle layer at the application layer by using a graphical interaction interface to form three modules with interaction functions, namely a format conversion module, a registration and segmentation module and a display interaction module, so that the application of a user is facilitated.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (6)
1. A bridge crack detection method is characterized by comprising the following steps:
carrying out crack segmentation on the collected group of bridge images;
detecting and classifying the bridge cracks by adopting a pre-constructed bridge crack classification model according to the crack segmentation result;
according to the crack segmentation result, performing three-dimensional reconstruction on the bridge crack so as to obtain the three-dimensional visualization effect of the crack;
performing three-dimensional reconstruction and crack information detection on the bridge cracks by adopting a moving cube algorithm;
the method for carrying out crack segmentation on the acquired bridge image comprises the following steps:
dividing cracks in each bridge image to serve as initial contours by adopting a spectral clustering algorithm promoted based on Nystrom approximation theory;
sequentially mapping the divided cracks to the next bridge image along the upward direction to serve as the initial contour of the crack in the bridge image, and finishing the division of each crack by adopting an improved GAC model until the division of all bridge images is finished;
sequentially mapping the cracks segmented along the upward direction to the next bridge image along the downward direction to serve as initial contours of the cracks in the bridge image, and completing segmentation of each crack by adopting an improved GAC model until all bridge images are segmented;
the method for completing the segmentation of each crack by adopting the improved GAC model comprises the following steps:
calculating the gray level mean value and the gray level standard deviation of each divided crack area, and taking the gray level mean value and the gray level standard deviation as the gray level similarity information of each crack area;
constructing a gray level similarity information item according to the gray level similarity information;
and adding the gray level similarity information item as an external energy item to an energy functional of the GAC model, thereby improving the GAC model.
2. The bridge crack detection method of claim 1, wherein the bridge crack classification model construction method comprises the following steps:
collecting original bridge images containing various cracks;
carrying out crack marking and crack segmentation on the collected original bridge image to construct a sample data set of bridge cracks;
initially constructing 8 layers of deep convolutional neural networks by combining global characteristics of a bridge, wherein each deep convolutional neural network comprises a first input layer, a third convolutional layer, a third pooling layer, a second full-connection layer and an output layer, and a softmax classifier is adopted;
and training and testing the constructed deep convolution neural network by adopting the sample data set so as to determine the structure and parameters of the bridge crack classification model.
3. The bridge crack detection method of claim 2, wherein the original bridge image is subjected to data cleaning to remove unmarked bridge images.
4. The bridge crack detection method of claim 1 or 3, further comprising: before crack segmentation is carried out, the bridge image is converted into a gray image, and enhancement and normalization processing are carried out on the gray image.
5. The bridge crack detection method of claim 1 wherein local extrema corresponding to noise and irregular detail are eliminated during crack segmentation.
6. The bridge crack detection method of claim 1, wherein the types of cracks comprise: plastic cracks, shrinkage cracks, arch bridge radial cracks, longitudinal cracks at the gap between the underbelly boxes, pier cap cracks and arch foot cracks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010174163.7A CN111402227B (en) | 2020-03-13 | 2020-03-13 | Bridge crack detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010174163.7A CN111402227B (en) | 2020-03-13 | 2020-03-13 | Bridge crack detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111402227A CN111402227A (en) | 2020-07-10 |
| CN111402227B true CN111402227B (en) | 2022-09-23 |
Family
ID=71430807
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010174163.7A Active CN111402227B (en) | 2020-03-13 | 2020-03-13 | Bridge crack detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111402227B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111968079B (en) * | 2020-07-28 | 2023-11-17 | 武汉光谷卓越科技股份有限公司 | Three-dimensional pavement crack extraction method based on local extremum of section and segmentation sparsity |
| CN112508030A (en) * | 2020-12-18 | 2021-03-16 | 山西省信息产业技术研究院有限公司 | Tunnel crack detection and measurement method based on double-depth learning model |
| CN113358659B (en) * | 2021-04-25 | 2022-07-19 | 上海工程技术大学 | Camera array type imaging method for automatic detection of high-speed rail box girder crack |
| CN113506281B (en) * | 2021-07-23 | 2024-02-27 | 西北工业大学 | Bridge crack detection method based on deep learning framework |
| CN113674175B (en) * | 2021-08-23 | 2024-07-23 | 江苏科技大学 | Underwater robot image enhancement method for detecting damage of cross-sea bridge structure |
| CN114241215B (en) * | 2022-02-18 | 2022-05-17 | 广东建科交通工程质量检测中心有限公司 | Non-contact detection method and system for apparent cracks of bridge |
| CN114674827B (en) * | 2022-03-04 | 2024-09-20 | 兰州交通大学 | Bridge crack detection method based on two-stage deep learning strategy |
| CN114775457A (en) * | 2022-03-16 | 2022-07-22 | 浙江广厦建设职业技术大学 | Detection device for repairing ancient bridge and detection method thereof |
| CN114724040A (en) * | 2022-05-06 | 2022-07-08 | 悉地（苏州）勘察设计顾问有限公司 | Concrete crack identification method and system based on aerial splicing image |
| CN114943693B (en) * | 2022-05-09 | 2023-07-25 | 盐城工学院 | Jetson Nano bridge crack detection method and system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106910186A (en) * | 2017-01-13 | 2017-06-30 | 陕西师范大学 | A kind of Bridge Crack detection localization method based on CNN deep learnings |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3006240C (en) * | 2015-04-27 | 2022-12-13 | Wuhan Wuda Zoyon Science And Technology Co., Ltd. | A stepwise refinement detection method for pavement cracks |
-
2020
- 2020-03-13 CN CN202010174163.7A patent/CN111402227B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106910186A (en) * | 2017-01-13 | 2017-06-30 | 陕西师范大学 | A kind of Bridge Crack detection localization method based on CNN deep learnings |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111402227A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111402227B (en) | Bridge crack detection method | |
| Zhang et al. | Real-time detection of cracks on concrete bridge decks using deep learning in the frequency domain | |
| CN108416307B (en) | Method, device and equipment for detecting pavement cracks of aerial images | |
| CN108564097B (en) | Multi-scale target detection method based on deep convolutional neural network | |
| WO2017215622A1 (en) | Object segmentation method and apparatus and computing device | |
| CN111178206B (en) | Building embedded part detection method and system based on improved YOLO | |
| CN110991444B (en) | License plate recognition method and device for complex scene | |
| Li et al. | Automatic bridge crack identification from concrete surface using ResNeXt with postprocessing | |
| CN112435214B (en) | Priori frame linear scaling-based pollen detection method and device and electronic equipment | |
| CN111798417A (en) | SSD-based remote sensing image target detection method and device | |
| CN115131330A (en) | Method and system for detecting and measuring surface defects of steel rail by fusing multi-source sensors | |
| Ehtisham et al. | Computing the characteristics of defects in wooden structures using image processing and CNN | |
| CN114049572A (en) | Detection method for identifying small target | |
| CN105405138A (en) | Water surface target tracking method based on saliency detection | |
| CN114332473A (en) | Object detection method, object detection device, computer equipment, storage medium and program product | |
| CN116503760A (en) | Unmanned aerial vehicle cruising detection method based on self-adaptive edge feature semantic segmentation | |
| Reis et al. | ReCRNet: a deep residual network for crack detection in historical buildings | |
| Qin et al. | Classification of pavement crack types based on square bounding box diagonal matching method | |
| CN116012709B (en) | High-resolution remote sensing image building extraction method and system | |
| CN112084941A (en) | Target detection and identification method based on remote sensing image | |
| Yazid et al. | Automated system form concrete damage classification identification using pretrained deep learning model | |
| CN114118125A (en) | Multi-modal input and space division three-dimensional target detection method | |
| Yang et al. | An modified intelligent real-time crack detection method for bridge based on improved target detection algorithm and transfer learning | |
| Barkiah et al. | Overcoming Overfitting Challenges with HOG Feature Extraction and XGBoost-Based Classification for Concrete Crack Monitoring | |
| Li et al. | Research on Small Target Detection Technology for River Floating Garbage Based on Improved YOLOv7 |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |