CN116091431A - Case Liang Binghai detection method, apparatus, computer device, and storage medium - Google Patents
Case Liang Binghai detection method, apparatus, computer device, and storage medium Download PDFInfo
- Publication number
- CN116091431A CN116091431A CN202211720479.7A CN202211720479A CN116091431A CN 116091431 A CN116091431 A CN 116091431A CN 202211720479 A CN202211720479 A CN 202211720479A CN 116091431 A CN116091431 A CN 116091431A
- Authority
- CN
- China
- Prior art keywords
- crack
- box girder
- image
- information
- projection
- 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
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
-
- 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
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- 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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- 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 present application relates to a box girder disease detection method, apparatus, computer device, storage medium and computer program product. The method comprises the following steps: establishing an initial model corresponding to the box girder; identifying the crack image by using a crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment; extracting features of the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection; and outputting crack information of the box girder based on the target model. By adopting the method, the disease information detection efficiency can be improved.
Description
Technical Field
The present application relates to the field of computer technology, and in particular, to a method, an apparatus, a computer device, a storage medium, and a computer program product for detecting a girder disease.
Background
The steel box girder and the concrete box girder are commonly used structural forms of long-span bridges, and the cross section has the characteristics of wide width and flat appearance. Diseases and damages such as surface cracks are easy to generate in the service process of the steel box girder and the concrete box girder, so that a diaphragm plate and an inspection manhole are generally arranged in the box girder, and the traditional inspection mode is manual inspection.
In the conventional technology, the method for detecting the internal diseases of the steel box girder and the concrete box girder generally records disease information (namely crack information of the box girder) such as the positions and the characteristics of the diseases and the like by manual measurement and photographing by staff. However, since disease information can only be measured and recorded manually, the efficiency of obtaining disease information is low.
Disclosure of Invention
In view of the foregoing, it is desirable to provide a box girder disease detection method, apparatus, computer device, computer readable storage medium, and computer program product.
In a first aspect, the present application provides a method for detecting a box girder disease. The method comprises the following steps:
acquiring point cloud data obtained by scanning a box girder, and establishing an initial model corresponding to the box girder based on the point cloud data;
identifying the crack image by using a crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
extracting features of the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection;
and outputting crack information of the box girder based on the target model.
In one embodiment, the fracture identification model includes a backbone network and grid detection heads; the method for identifying the crack image by using the crack identification model to obtain a crack profile information graph comprises the following steps:
extracting features of the crack image through the backbone network to obtain crack feature information;
and integrating the crack characteristic information through the grid detection head to obtain grid coordinates corresponding to the crack outline, and outputting a crack outline information diagram of a crack part contained in the crack image based on the grid coordinates corresponding to the crack outline.
In one embodiment, the projecting the crack profile information map to the initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain the target model including the crack projection includes:
acquiring optical center coordinates corresponding to the crack image when the camera shoots;
constructing projection rays according to the position relation between the optical center coordinates and the crack characteristic point coordinates;
performing collision detection on the projection ray and the initial model to obtain an intersection point coordinate of the projection ray and the initial model, and taking the intersection point coordinate as a projection coordinate of the crack contour information graph in the initial model;
and carrying out projection processing on the crack profile information graph according to the projection coordinates of the crack characteristic points to obtain a target model containing crack projection.
In one embodiment, the crack width feature points include a pixel point of a crack central axis and a pixel point of a crack edge line; extracting the crack profile information graph to obtain width characteristic points of the crack, wherein the method comprises the following steps:
and carrying out axis retrieval in the crack profile information graph by utilizing a medial axis transformation strategy to obtain the central axis of the crack, and obtaining the pixel points of the crack edge line according to the pixel points of the central axis of the crack.
In one embodiment, the fracture size information includes the fracture width calculation and the fracture length calculation; calculating the crack size information according to the pixel point of the central axis of the crack and the pixel point of the edge line of the crack comprises the following steps:
determining a width calculation value of the crack profile information according to the Euclidean distance between the width feature points;
and determining the length of the central axis according to the crack contour information graph, and determining the length calculated value of the crack contour information according to the length of the central axis.
In a second aspect, the present application further provides a box girder disease detection device. The device comprises:
the scanning module is used for acquiring point cloud data obtained by scanning the box girder and establishing an initial model corresponding to the box girder based on the point cloud data;
the identification module is used for identifying the crack image by using the crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
the projection module is used for carrying out feature extraction on the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection;
in one embodiment, the scanning module is specifically configured to:
and acquiring point cloud data obtained by scanning the box girder, and establishing an initial model corresponding to the box girder based on the point cloud data.
In one embodiment, the fracture identification model includes a backbone network and grid detection heads; the identification module is specifically used for:
extracting features of the crack image through the backbone network to obtain crack feature information;
and integrating the crack characteristic information through the grid detection head to obtain grid coordinates corresponding to the crack outline, and outputting a crack outline information diagram of a crack part contained in the crack image based on the grid coordinates corresponding to the crack outline.
In one embodiment, the projection module is specifically configured to:
acquiring optical center coordinates corresponding to the crack image when the camera shoots;
constructing projection rays according to the position relation between the optical center coordinates and the crack characteristic point coordinates;
performing collision detection on the projection ray and the initial model to obtain an intersection point coordinate of the projection ray and the initial model, and taking the intersection point coordinate as a projection coordinate of the crack contour information graph in the initial model;
and carrying out projection processing on the crack profile information graph according to the projection coordinates of the crack characteristic points to obtain a target model containing crack projection.
In one embodiment, the output module is specifically configured to:
determining a width calculation value of the crack profile information according to the Euclidean distance between the width feature points;
and determining the length of the central axis according to the crack contour information graph, and determining the length calculated value of the crack contour information according to the length of the central axis.
In one embodiment, the output module is specifically configured to:
responding to a query instruction aiming at the crack size information, calculating the crack size information according to the pixel points of the central axis of the crack and the pixel points of the edge line of the crack, and outputting the crack size information;
in response to a query instruction for fracture location information, a target model including the fracture projection is shown.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the steps of the method of the first aspect when the processor executes the computer program.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of the first aspect.
In a fifth aspect, the present application also provides a computer program product. The computer program product comprising a computer program which, when executed by a processor, implements the steps of the method of the first aspect.
Acquiring point cloud data obtained by scanning a box girder, and establishing an initial model corresponding to the box girder based on the point cloud data;
identifying the crack image by using a crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
extracting features of the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection;
and outputting crack information of the box girder based on the target model.
According to the box girder disease detection method and device, point cloud data obtained by scanning the box girders are obtained, and an initial model corresponding to the box girders is built based on the point cloud data;
identifying the crack image by using a crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
extracting features of the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection;
outputting crack information of the box girder based on the target model;
the three-dimensional point cloud and the network model inside the steel box girder or the concrete box girder can be established, then diseases inside the box girder are identified according to deep learning, and the disease information is visualized in the three-dimensional model, so that the automatic acquisition of the box girder disease information is realized, and the box girder disease detection efficiency is improved.
Drawings
FIG. 1 is a diagram of the application environment of a box Liang Binghai detection method in one embodiment;
FIG. 2 is a flow diagram of a method of detecting a tank Liang Binghai in one embodiment;
FIG. 3 is a flow diagram of crack image recognition in one embodiment;
FIG. 4 is a flow chart of a disease profile projection method according to one embodiment;
FIG. 5 is a flow chart of a method of calculating disease size in one embodiment;
FIG. 6 is a block diagram of a box Liang Binghai detection device in one embodiment;
fig. 7 is an internal structural diagram of a computer device in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
The box girder disease detection method provided by the embodiment of the application can be applied to an application environment shown in fig. 1. Among these application environments, there may be a box girder, a terminal, a server, a scanning device, a detection device, and a navigation device, where the terminal 102 communicates with the server 104 through a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices, portable wearable devices, and the internet of things devices may be smart televisions, smart vehicle devices, and the like. The portable wearable device may be a smart watch, smart bracelet, headset, or the like. The scanning device may be a lidar; the detection device may be a high resolution camera, an industrial camera; the navigation device may be inertial navigation; the box girder can be a steel box girder or a concrete box girder. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
The embodiment is illustrated by the method applied to the terminal, and it is understood that the method can also be applied to the server, and can also be applied to a system comprising the terminal and the server, and implemented through interaction between the terminal and the server. As shown in fig. 2, a method for detecting a box girder disease is provided, and the method is applied to the terminal in fig. 1 for illustration, and includes the following steps:
The initial model is a three-dimensional model of the internal structure of the box girder.
In this embodiment of the application, the terminal can be integrated with scanning equipment and check out test set, and the terminal can remove along predetermined route to scan the case roof beam inside through scanning equipment, obtain the inside point cloud data of case roof beam. For example, the user may hold the terminal device for movement inside the box girder, or the terminal may be mounted on a movable device that moves according to a predetermined route, thereby scanning the inside of the box girder and obtaining point cloud data inside the box girder. Alternatively, the terminal may be the SALM (Simultaneous Localization and Mapping, instant positioning and mapping) device, including lidar, inertial navigation, and high resolution cameras.
After the terminal acquires the point cloud data, the three-dimensional reconstruction of the inside of the box girder can be performed through the point cloud data to obtain a three-dimensional model of the internal structure of the box girder, and the three-dimensional reconstruction can be an r3live algorithm. Optionally, any reconstruction algorithm capable of implementing three-dimensional reconstruction may be applied to the embodiments of the present application, which are not limited.
And 204, recognizing the crack image by using a crack recognition model to obtain a crack profile information graph.
The crack image is obtained by shooting the crack part of the box girder by the detection equipment. Specifically, the crack image is comprehensively photographed and recorded by a high-resolution camera at positions, such as a box girder top plate, a top plate stiffening rib, a longitudinal and transverse partition plate and the like, where diseases are easy to generate by a user; and (3) manually inspecting positions where diseases such as the bottom plate and the side plates of the box girder are not easy to occur, and photographing and storing records by using a high-resolution camera when the diseases such as cracks are found.
In the embodiment of the application, the terminal can construct an initial crack identification model in advance, acquire a training sample set corresponding to the crack identification model, such as a steel box girder crack detection image with different shapes, train the crack identification model according to the training sample set, and acquire a trained crack identification model.
The terminal can input the crack image into a trained crack identification model to obtain a crack profile information graph. Optionally, the crack identification model is an identification model based on a YOLOV5 target detection algorithm; the crack contour information map is an image formed by arranging anchor frames for crack sites.
And 206, carrying out feature extraction on the crack profile information graph to obtain crack width feature points, and projecting the crack profile information to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection.
The crack width feature points refer to two edge lines of the crack and pixel points on the central axis.
In the embodiment of the application, the terminal processes the crack contour information graph in a gray scale mode. Then, for each pixel point, determining the pixel value of the pixel point contained in the point neighborhood of the pixel point, then determining the median value of the pixel values, and replacing the gray value of the pixel point with the median value by using a median filtering algorithm so as to eliminate isolated noise; then, determining a pixel point with a gray value larger than a preset threshold value, and setting the gray value of the pixel point to 0; determining a pixel point smaller than the set threshold value, and setting the gray value of the pixel point to 255; and finally, processing the defects by using image operation, deleting burrs in the image, and obtaining a binary image of the crack contour information graph with complete morphology.
And extracting a binary image of the crack profile information image by the terminal to obtain crack width characteristic points, projecting the crack characteristic points into the initial model, connecting all the crack characteristic points, and obtaining the connected crack characteristic points as the crack profile.
And step 208, outputting crack information of the box girder based on the target model.
Wherein the crack information includes position information and size information of the crack.
In the embodiment of the application, the terminal outputs the target model including the crack projection and/or outputs the size information of the crack according to the received output instruction. The output instruction may be sent by the terminal or by the server.
Optionally, the terminal may synthesize and output a box girder detection report according to the target model including the crack projection and a preset detection report template.
As shown in fig. 3, in one embodiment, the fracture identification model includes a backbone network and grid detection heads; identifying the crack image by using a crack identification model, wherein obtaining a crack profile information graph comprises:
and step 302, extracting features of the crack image through a backbone network to obtain crack feature information.
In the embodiment of the application, the terminal extracts the image features of the crack part in the crack image through the backbone network to obtain the high-level features, the medium-layer features and the low-level features. And then, fusing the high-level features, the middle-level features and the low-level features to obtain a crack feature map, wherein the crack feature map contains crack feature information.
And 304, identifying the crack characteristic information through a grid detection head to obtain grid coordinates corresponding to the crack contour, and outputting a crack contour information diagram of a crack part contained in the crack image based on the grid coordinates corresponding to the crack contour.
The grid detection head comprises a crack Gird identification module.
In the embodiment of the application, a terminal or a server identifies a crack feature map containing crack feature information through a grid detection head of a grid detection head to obtain grid coordinates corresponding to crack contour information, wherein the grid coordinates essentially comprise four parameters of dividing a center coordinate of each small grid by an image height, dividing the center coordinate by an image width, dividing the grid height by the image height and dividing the grid width by the image width, and the four parameters are used as vertexes of each small grid and are connected to obtain a crack contour information map and output.
In the embodiment of the application, the crack image is extracted and identified through the backbone network, and the grid anchoring frame is added through the grid detection head, so that the effect of outputting the crack part in the crack image in a grid marking mode can be achieved.
As shown in fig. 4, in one embodiment, according to the feature points of the width of the crack in the crack image, projecting the crack profile information graph to the initial model corresponding to the box girder, and obtaining the target model including the projection of the crack includes:
According to the imaging principle, the terminal obtains the actual coordinates of the crack characteristic points according to the preset optical center coordinates, the camera focal length and the pixel coordinates of the crack characteristic points, wherein the optical center coordinates are the origin of a camera coordinate system and can be obtained according to camera parameters.
Specifically, the terminal determines the coordinates of the pixel points in the image coordinate system according to the camera internal parameters, the image size and the coordinates of the pixel points of the crack in the pixel coordinate system by using the known crack positioning information and the pixel coordinates of the crack characteristic points on the image; determining the coordinates of the pixel point in a camera coordinate system according to the coordinates of the pinhole camera model and the crack characteristic points in the image coordinate system; and determining the coordinates of the crack characteristic points in a world coordinate system according to the camera external parameters, the measurement data of the inertial measurement unit and the coordinates of the pixel points in the camera coordinate system, and obtaining the actual coordinates of the crack characteristic points.
In the embodiment of the application, the camera may be a high-resolution camera; the terminal connects the optical center coordinates with the actual coordinates of the crack characteristic points, so that a straight line pointing to the initial model can be obtained, namely the projection rays; and the terminal performs collision detection on the projection rays of the optical center coordinates and the crack characteristic point coordinates and the initial model, and records the intersection point of each projection ray and the initial model, namely the projection coordinates of the crack contour information graph in the initial model.
And step 406, performing projection processing on the crack profile information graph according to the projection coordinates of the crack characteristic points to obtain a target model containing crack projection.
In the embodiment of the application, the terminal connects projection coordinates of the crack characteristic points on the initial model to obtain projection of the crack contour information graph on the initial model, namely the target model containing the crack contour.
In the embodiment of the application, the terminal obtains the projection ray of each crack characteristic point by connecting the pixel coordinate of the crack characteristic point with the optical center coordinate of the high-resolution camera; the intersection point of each crack characteristic point and the initial model can be determined according to the projection rays, each crack characteristic point is connected with the intersection point of the initial model, projection of the crack contour to the initial model can be obtained, namely the target model containing the crack contour, and visual display of the crack position information can be achieved.
In one embodiment, the crack width feature points include pixel points of a crack central axis and pixel points of a crack edge line; extracting the crack profile information graph to obtain width characteristic points of the crack, wherein the method comprises the following steps:
and carrying out axis retrieval in the crack profile information graph by utilizing a medial axis transformation strategy to obtain a crack medial axis, and obtaining pixel points of a crack edge line according to the pixel points of the crack medial axis.
In the embodiment of the application, specifically, a terminal adopts a medial axis transformation algorithm in a skimage library, a medial axis is identified in a crack contour information binary image to obtain a crack medial axis, then three continuous pixel points on the medial axis are taken as tangent lines, vertical lines are taken as bases, the vertical lines are intersected with edge lines, and the intersection points are pixel points of crack characteristic points in the edge lines; in addition, the terminal needs to store the coordinates of the width feature points on each continuous crack, and for the case that a plurality of cracks exist in one image, the terminal can store the correspondence between the coordinates of the cracks and the width feature points.
In this embodiment, the terminal extracts the crack profile information map to obtain the width feature points of the crack, so as to perform projection of the crack profile information map in the initial model and calculation of the crack size information.
In one embodiment, the fracture information includes fracture size information and fracture location information; the outputting crack information of the box girder based on the target model comprises the following steps:
responding to a query instruction aiming at the crack size information, calculating the crack size information according to the pixel points of the central axis of the crack and the pixel points of the edge line of the crack, and outputting the crack size information. And, in response to a query instruction for fracture location information, displaying a target model including a fracture projection.
In the embodiment of the application, when a user initiates a query instruction for the crack size, the terminal calculates the average width and the longest width of the crack according to the calculated length and width characteristics of the crack, and then outputs the average width or the longest width of the crack; when a user initiates a query instruction for the crack position, the terminal outputs and displays the query instruction according to the target model projected by the crack contour information graph.
In this embodiment, the terminal responds to the instruction of the user, so that visual display of the size information and the position information of the crack can be achieved.
As shown in fig. 5, in one embodiment, the crack size information includes a calculated width value of the crack profile information and a calculated length value of the crack profile information; calculating the crack size information according to the pixel point of the central axis of the crack and the pixel point of the edge line of the crack comprises the following steps:
and step 502, determining a width calculated value of the crack profile information according to the Euclidean distance between the width characteristic points.
In the embodiment of the application, a terminal adopts a medial axis transformation algorithm in a skimage library, a medial axis is identified in a binary image of crack profile information to obtain a crack medial axis, then a tangent line is made to a continuous preset number of pixel points on the medial axis, the tangent line is taken as a basis to be a perpendicular line, the perpendicular line is intersected with an edge line, the intersection point is the pixel point of a crack characteristic point in the edge line, further Euclidean distance of the crack characteristic points in the two edge lines is calculated, and the width dimension of a crack is obtained.
And step 504, determining a length calculated value of the crack profile information according to the length of the central axis of the crack profile information.
In the embodiment of the application, the terminal calculates the Euclidean distance of each section of crack characteristic points and sums the Euclidean distances by connecting the crack characteristic points on the central axis, namely the length of the crack.
Alternatively, steps 502 and 504 may not be prioritized.
In the embodiment of the application, the true value of the crack width can still be accurately described after the projection of the crack characteristic points, and the record of the crack size and the accurate display of the crack size in the target model can be achieved through the crack width obtained by the method for calculating the crack size of the crack characteristic points.
In one embodiment, the application further provides an example of a method for detecting a box girder disease, which specifically includes:
the terminal acquires point cloud data obtained by scanning the box girder, and establishes an initial model corresponding to the box girder based on the point cloud data.
The terminal performs feature extraction on the crack image through a backbone network to obtain crack feature information; and identifying the crack characteristic information through a grid detection head to obtain grid coordinates corresponding to the crack outline, and outputting a crack outline information diagram of a crack part contained in the crack image based on the grid coordinates corresponding to the crack outline.
The terminal acquires the optical center coordinates corresponding to the crack image; and constructing projection rays according to the position relation between the optical center coordinates and the crack characteristic point coordinates. And the terminal performs collision detection on the projection ray and the initial model to obtain an intersection point coordinate of the projection ray and the initial model, and takes the intersection point coordinate as a projection coordinate of the crack contour information graph in the initial model.
And the terminal performs projection processing on the crack contour information graph according to the projection coordinates of the crack characteristic points to obtain a target model containing crack projection.
And the terminal performs axis search in the crack profile information graph by using a medial axis transformation strategy to obtain a crack medial axis, and obtains pixel points of a crack edge line according to the pixel points of the crack medial axis.
The terminal responds to a query instruction aiming at the crack size information, and determines a width calculation value of the crack outline information graph according to Euclidean distance between width feature points; and determining the length of the central axis according to the crack contour information graph, determining the length calculation value of the crack contour information according to the length of the central axis, and outputting the crack size information. And the terminal responds to the query instruction aiming at the crack position information, and shows a target model comprising crack projection.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a box girder disease detection device for realizing the box girder disease detection method. The implementation scheme of the solution provided by the device is similar to that described in the above method, so the specific limitation of the embodiment of the box girder disease detection device or embodiments provided below can be referred to the limitation of the box girder disease detection method hereinabove, and will not be repeated here.
In one embodiment, as shown in fig. 6, there is provided a box girder disease detection apparatus, comprising: a scanning module 601, an identification module 602, a projection module 603 and an output module 604, wherein:
the scanning module 601 is configured to obtain point cloud data obtained by scanning a box girder, and establish an initial model corresponding to the box girder based on the point cloud data;
the recognition module 602 is configured to recognize the crack image by using a crack recognition model to obtain a crack profile information map; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
the projection module 603 is configured to perform feature extraction on the crack profile information map to obtain a crack width feature point, and project the crack profile information map to an initial model corresponding to the box girder according to the crack width feature point in the crack image to obtain a target model including crack projection;
and an output module 604, configured to output crack information of the box girder based on the target model.
In one embodiment, the scanning module is specifically configured to:
and acquiring point cloud data obtained by scanning the box girder, and establishing an initial model corresponding to the box girder based on the point cloud data.
In one embodiment, the fracture identification model includes a backbone network and grid detection heads; the identification module is specifically used for:
extracting features of the crack image through the backbone network to obtain crack feature information;
and integrating the crack characteristic information through the grid detection head to obtain grid coordinates corresponding to the crack outline, and outputting a crack outline information diagram of a crack part contained in the crack image based on the grid coordinates corresponding to the crack outline.
In one embodiment, the projection module is specifically configured to:
acquiring optical center coordinates corresponding to the crack image when the camera shoots;
constructing projection rays according to the position relation between the optical center coordinates and the crack characteristic point coordinates;
performing collision detection on the projection ray and the initial model to obtain an intersection point coordinate of the projection ray and the initial model, and taking the intersection point coordinate as a projection coordinate of the crack contour information graph in the initial model;
and carrying out projection processing on the crack profile information graph according to the projection coordinates of the crack characteristic points to obtain a target model containing crack projection.
In one embodiment, the output module includes a computing unit and an output unit; the computing unit is specifically configured to:
determining a width calculation value of the crack profile information according to the Euclidean distance between the width feature points;
and determining the length of the central axis according to the crack contour information graph, and determining the length calculated value of the crack contour information according to the length of the central axis.
The output unit is specifically configured to:
responding to a query instruction aiming at the crack size information, calculating the crack size information according to the pixel points of the central axis of the crack and the pixel points of the edge line of the crack, and outputting the crack size information;
in response to a query instruction for fracture location information, a target model including the fracture projection is shown.
All or part of each module in the box girder disease detection device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program when executed by a processor is to implement a method of detecting a beam defect. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of the method embodiments described above when the computer program is executed.
In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when executed by a processor, implements the steps of the method embodiments described above.
In one embodiment, a computer program product is provided comprising a computer program which, when executed by a processor, performs the steps of:
in an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of the method embodiments described above.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A method for detecting a box girder disease, the method comprising:
acquiring point cloud data obtained by scanning a box girder, and establishing an initial model corresponding to the box girder based on the point cloud data;
identifying the crack image by using a crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
extracting features of the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection;
and outputting crack information of the box girder based on the target model.
2. The method of claim 1, wherein the fracture identification model comprises a backbone network and grid detection heads; the method for identifying the crack image by using the crack identification model to obtain a crack profile information graph comprises the following steps:
extracting features of the crack image through the backbone network to obtain crack feature information;
and integrating the crack characteristic information through the grid detection head to obtain grid coordinates corresponding to the crack outline, and outputting a crack outline information diagram of a crack part contained in the crack image based on the grid coordinates corresponding to the crack outline.
3. The method according to claim 1, wherein the projecting the crack profile information map into the initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain the target model including the crack projection includes:
acquiring optical center coordinates corresponding to the crack image when the camera shoots;
constructing projection rays according to the position relation between the optical center coordinates and the crack characteristic point coordinates;
performing collision detection on the projection ray and the initial model to obtain an intersection point coordinate of the projection ray and the initial model, and taking the intersection point coordinate as a projection coordinate of the crack contour information graph in the initial model;
and carrying out projection processing on the crack profile information graph according to the projection coordinates of the crack characteristic points to obtain a target model containing crack projection.
4. The method of claim 1, wherein the slit width feature points comprise pixels of a slit central axis and pixels of a slit edge line; extracting the crack profile information graph to obtain width characteristic points of the crack, wherein the method comprises the following steps:
and carrying out axis retrieval in the crack profile information graph by utilizing a medial axis transformation strategy to obtain the central axis of the crack, and obtaining the pixel points of the crack edge line according to the pixel points of the central axis of the crack.
5. The method of claim 1, wherein the fracture information comprises fracture size information and fracture location information; the outputting crack information of the box girder based on the target model comprises the following steps:
responding to a query instruction aiming at the crack size information, calculating the crack size information according to the pixel points of the central axis of the crack and the pixel points of the edge line of the crack, and outputting the crack size information;
in response to a query instruction for fracture location information, a target model including the fracture projection is shown.
6. The method of claim 5, wherein the fracture size information comprises the fracture width calculation and a fracture length calculation; calculating the crack size information according to the pixel point of the central axis of the crack and the pixel point of the edge line of the crack comprises the following steps:
determining a width calculation value of the crack profile information according to the Euclidean distance between the width feature points;
and determining the length of the central axis according to the crack contour information graph, and determining the length calculated value of the crack contour information according to the length of the central axis.
7. A beam defect detection apparatus, the apparatus comprising:
the scanning module is used for acquiring point cloud data obtained by scanning the box girder and establishing an initial model corresponding to the box girder based on the point cloud data;
the identification module is used for identifying the crack image by using the crack identification model to obtain a crack profile information graph; the crack image is an image obtained by shooting the crack part of the box girder by the detection equipment;
the projection module is used for carrying out feature extraction on the crack profile information graph to obtain crack width feature points, and projecting the crack profile information graph to an initial model corresponding to the box girder according to the crack width feature points in the crack image to obtain a target model containing crack projection;
and the output module is used for outputting crack information of the box girder based on the target model.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211720479.7A CN116091431A (en) | 2022-12-30 | 2022-12-30 | Case Liang Binghai detection method, apparatus, computer device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211720479.7A CN116091431A (en) | 2022-12-30 | 2022-12-30 | Case Liang Binghai detection method, apparatus, computer device, and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116091431A true CN116091431A (en) | 2023-05-09 |
Family
ID=86200382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211720479.7A Pending CN116091431A (en) | 2022-12-30 | 2022-12-30 | Case Liang Binghai detection method, apparatus, computer device, and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116091431A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116988377A (en) * | 2023-08-09 | 2023-11-03 | 广东省公路建设有限公司湾区特大桥养护技术中心 | Robot and method for detecting apparent diseases in bridge steel box girder |
| CN117152492A (en) * | 2023-08-08 | 2023-12-01 | 广东省公路建设有限公司湾区特大桥养护技术中心 | Method, system, computer equipment and medium for identifying fatigue crack in steel box girder |
-
2022
- 2022-12-30 CN CN202211720479.7A patent/CN116091431A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152492A (en) * | 2023-08-08 | 2023-12-01 | 广东省公路建设有限公司湾区特大桥养护技术中心 | Method, system, computer equipment and medium for identifying fatigue crack in steel box girder |
| CN117152492B (en) * | 2023-08-08 | 2024-04-19 | 广东省公路建设有限公司湾区特大桥养护技术中心 | Method, system, computer equipment and medium for identifying fatigue crack in steel box girder |
| CN116988377A (en) * | 2023-08-09 | 2023-11-03 | 广东省公路建设有限公司湾区特大桥养护技术中心 | Robot and method for detecting apparent diseases in bridge steel box girder |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Deng et al. | Imaging-based crack detection on concrete surfaces using You Only Look Once network | |
| CN109978755B (en) | Panoramic image synthesis method, device, equipment and storage medium | |
| CN116091431A (en) | Case Liang Binghai detection method, apparatus, computer device, and storage medium | |
| CN103703758A (en) | Mobile augmented reality system | |
| KR20150027291A (en) | Optical flow tracking method and apparatus | |
| CN109977952A (en) | Candidate target detection method based on local maximum | |
| CN115984273B (en) | Road disease detection method, device, computer equipment and readable storage medium | |
| CN111832561B (en) | Character sequence recognition method, device, equipment and medium based on computer vision | |
| JP6601613B2 (en) | POSITION ESTIMATION METHOD, POSITION ESTIMATION DEVICE, AND POSITION ESTIMATION PROGRAM | |
| CN113705669A (en) | Data matching method and device, electronic equipment and storage medium | |
| JP2007193850A (en) | Change region recognition apparatus | |
| EP3825804A1 (en) | Map construction method, apparatus, storage medium and electronic device | |
| CN114663598A (en) | Three-dimensional modeling method, device and storage medium | |
| US11423611B2 (en) | Techniques for creating, organizing, integrating, and using georeferenced data structures for civil infrastructure asset management | |
| Sun et al. | Three-dimensional structural displacement measurement using monocular vision and deep learning based pose estimation | |
| US8509520B2 (en) | System and method for establishing association for a plurality of images and recording medium thereof | |
| CN116681959B (en) | Machine learning-based frontal line identification method and device, storage medium and terminal | |
| CN116596935A (en) | Deformation detection method, deformation detection device, computer equipment and computer readable storage medium | |
| CN110516559B (en) | Target tracking method and device suitable for accurate monitoring and computer equipment | |
| CN115830073A (en) | Map element reconstruction method, map element reconstruction device, computer equipment and storage medium | |
| Keyvanfar et al. | Performance comparison analysis of 3D reconstruction modeling software in construction site visualization and mapping | |
| CN115797438A (en) | Object positioning method, device, computer equipment, storage medium and program product | |
| CN116206125A (en) | Appearance defect identification method, appearance defect identification device, computer equipment and storage medium | |
| CN114238541A (en) | Sensitive target information acquisition method and device and computer equipment | |
| CN115063473A (en) | Object height detection method and device, computer equipment and storage medium |
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 |