CN114623783A - System and method for detecting embedded part of beam body - Google Patents
System and method for detecting embedded part of beam body Download PDFInfo
- Publication number
- CN114623783A CN114623783A CN202210201765.6A CN202210201765A CN114623783A CN 114623783 A CN114623783 A CN 114623783A CN 202210201765 A CN202210201765 A CN 202210201765A CN 114623783 A CN114623783 A CN 114623783A
- Authority
- CN
- China
- Prior art keywords
- bolt
- image
- control module
- fitting
- fitted
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000007747 plating Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 239000011248 coating agent Substances 0.000 claims description 13
- 238000000576 coating method Methods 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 9
- 238000003708 edge detection Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000005253 cladding Methods 0.000 description 12
- 239000000463 material Substances 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 229910000831 Steel Inorganic materials 0.000 description 5
- 239000010959 steel Substances 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/26—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes
- G01B11/27—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes for testing the alignment of axes
- G01B11/272—Measuring arrangements characterised by the use of optical techniques for measuring angles or tapers; for testing the alignment of axes for testing the alignment of axes using photoelectric detection means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/06—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material
- G01B11/0616—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness for measuring thickness ; e.g. of sheet material of coating
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/14—Measuring arrangements characterised by the use of optical techniques for measuring distance or clearance between spaced objects or spaced apertures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/0006—Industrial image inspection using a design-rule based approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Quality & Reliability (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a system and a method for detecting a beam embedded part, which comprise a detection platform for placing the embedded part, and a camera module, an image processing module and a control module which are arranged on one side of the detection platform, wherein the embedded part comprises a bottom plate and bolts, a plurality of bolt holes are arranged on the bottom plate, the bolts are respectively arranged in the bolt holes, and a plating layer is arranged on the surface of the bottom plate; the camera module is used for photographing the bolts in a side view to obtain an image of each bolt and sending the image of each bolt to the image processing module; the image processing module is used for identifying a bolt area and fitting the bolt area; and the control module is used for obtaining the center point coordinates of the bolt according to the fitted image of the bolt and calculating to obtain the offset of the bolt. By the method, the verticality condition of the bolt can be judged, so that whether the verticality of the bolt meets related requirements or not is judged.
Description
Technical Field
The invention relates to the technical field of concrete cover plates, in particular to a system and a method for detecting a beam body embedded part.
Background
The embedded parts are required to be arranged on the bottom surfaces of the box girders in the manufacturing process of the box girders, because the types and the quantity of the steel bars of the box girder body are more, particularly, the steel bars at the positions of the supports at the two ends are more dense, the steel bars of the box girder body collide with the supports and the anchor bars of the anti-falling beam embedded parts, the steel bars of the girder body are difficult to enter a mold, the actual positions of the steel bars deviate from the designed positions seriously, and the stress on the girder body structure is influenced.
The quality of the embedded part determines the overall quality of the box girder, the existing embedded part detection mainly depends on manual experience due to the fact that no professional detection equipment exists, high labor cost is needed, and although the labor cost is high, errors of the detection precision of the embedded part are large due to the fact that the detection level is large in difference between manual work.
Disclosure of Invention
In order to achieve the purpose, the invention discloses a system and a method for detecting a beam body embedded part.
A beam body embedded part inspection system comprises a detection platform for placing embedded parts, and a camera module, an image processing module and a control module which are arranged on one side of the detection platform, wherein the embedded parts comprise a bottom plate and bolts; the camera module is used for shooting the bolts in a side view manner to obtain an image of each bolt and sending the image of each bolt to the image processing module; the image processing module is used for identifying a bolt area and fitting the bolt area; and the control module is used for obtaining the center point coordinates of the bolt according to the fitted image of the bolt and calculating to obtain the offset of the bolt.
As a preferred embodiment, the image processing module includes an acquisition unit that acquires a shape description from the history plane image data of the bolt, a recognition unit, and a fitting unit; the identification unit screens out an area with similarity meeting set conditions with the parameter model from the shape description of the plane image data as a candidate area, and carries out accurate category judgment on the candidate area according to the trained network model to obtain a bolt area image; and the fitting unit is used for fitting the bolt area image.
As a preferred embodiment, fitting the bolt region comprises: smoothing the bolt area image to obtain a smooth image; performing edge detection on the smooth image by adopting a double threshold method, and extracting to obtain an edge image; performing morphological expansion on the edge image, and performing secondary contour extraction on the expanded image by using edge detection; and filtering the image obtained by the secondary contour extraction, determining a region to be fitted, and carrying out ellipse fitting on the contour in the region to be fitted to obtain an ellipse fitting target.
In a preferred embodiment, the control module is configured to identify a center point coordinate of each bolt on the fitted bolt image, convert the center point coordinate of the bolt to obtain a world coordinate of the bolt, and calculate the world coordinate of the camera and the world coordinate of the bolt to obtain an offset of the bolt.
As a preferred embodiment, the control module is configured to identify coordinates of a center point of each of the bolts on the fitted bolt image, and includes: extracting the boundary of each bolt on the fitted bolt image to obtain boundary point coordinates; and calculating to obtain the center point coordinates of each bolt by utilizing the boundary point coordinates of each bolt.
As a preferred embodiment, the device further comprises a plating thickness detection module, and is configured to obtain plating thickness data of the base plate, send the plating thickness data to the control module, and compare the plating thickness data with a preset plating thickness threshold by the control module to obtain a deviation amount of the plating thickness.
A method for inspecting a beam embedded part comprises the following steps: utilizing a camera module to take side view photographing on the bolts to obtain an image of each bolt, and sending the image of each bolt to an image processing module; identifying a bolt area by using an image processing module, and fitting the bolt area; and obtaining the coordinates of the central point of the bolt according to the fitted image of the bolt by using a control module, and calculating to obtain the offset of the bolt.
As a preferred embodiment, identifying the bolt region using the image processing model, and fitting the bolt region includes: acquiring a shape description from the historical planar image data of the bolt by using an acquisition unit; screening out a region with similarity meeting set conditions with the parameter model from the shape description of the plane image data by using an identification unit as a candidate region, and carrying out accurate category judgment on the candidate region according to the trained network model to obtain a bolt region image; and fitting the bolt region image by using a fitting unit.
As a preferred embodiment, obtaining coordinates of a center point of the bolt according to the fitted image of the bolt by using the control module, and calculating and obtaining an offset of the bolt includes: and identifying the coordinate of the central point of each bolt on the fitted bolt image by using a control module, converting the coordinate of the central point of each bolt to obtain the world coordinate of each bolt, and calculating the world coordinate of the camera and the world coordinate of each bolt to obtain the offset of each bolt.
As a preferred embodiment, the method further comprises the following steps: and acquiring the plating layer thickness data of the base plate by using a plating layer thickness detection module, sending the plating layer thickness data to a control module, and comparing the plating layer thickness data with a preset plating layer thickness threshold value by using the control module to obtain the deviation of the plating layer thickness.
The working principle and the beneficial effects of the invention are as follows:
according to the system and the method for detecting the approach of the beam body embedded part, the image of the bolt is identified by the computing console according to the shot bolt image, and the image coordinate of the bolt is obtained; converting the image coordinates of the bolt to obtain world coordinates of the bolt; calculating the world coordinate of the camera and the world coordinate of the bolt to obtain the offset of the bolt; by the method, the verticality condition of the bolt can be judged, so that whether the verticality of the bolt meets related requirements or not is judged.
According to the bolt hole image, calculating the center point coordinate of each bolt hole on the control console identification bolt hole image, calculating the difference value of the center point coordinates of two adjacent bolt holes and taking the absolute value of the difference value as the hole spacing of the adjacent bolt holes; by the method, the hole spacing between the adjacent bolt holes on the embedded part can be measured, the measurement precision and accuracy are improved, and the measurement efficiency is improved.
This application can also measure the cladding material thickness on the bottom plate, acquires cladding material thickness data on the bottom plate through cladding material thickness detector, and the calculation control platform compares cladding material thickness data and the interior predetermined cladding material thickness threshold value that stores of calculation control platform to judge whether cladding material thickness satisfies relevant requirement.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a schematic flow chart of a beam embedded part inspection method for box beam production provided by the invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a beam body embedded part inspection system, wherein an embedded part comprises a base plate and a bolt, a plurality of bolt holes are formed in the base plate, the bolt is respectively installed in each bolt hole, and a coating is arranged on the surface of the base plate. The system comprises a detection platform for placing embedded parts, and a camera module, an image processing module and a control module which are arranged on one side of the detection platform, wherein the camera module is used for taking a picture of each bolt in a side view manner and sending the image of each bolt to the image processing module; the image processing module is used for identifying a bolt area and fitting the bolt area; and the control module is used for obtaining the center point coordinates of the bolt according to the fitted image of the bolt and calculating to obtain the offset of the bolt.
According to the embodiment, the computing console identifies the image of the bolt according to the shot bolt image to obtain the image coordinate of the bolt; converting the image coordinates of the bolt to obtain the world coordinates of the bolt; calculating the world coordinate of the camera and the world coordinate of the bolt to obtain the offset of the bolt; by the method, the verticality condition of the bolt can be judged, so that whether the verticality of the bolt meets related requirements or not can be judged.
As a preferred embodiment, the image processing module includes an acquisition unit that acquires a shape description from the history plane image data of the bolt; the identification unit screens out an area with similarity meeting set conditions with the parameter model from the shape description of the plane image data as a candidate area, and carries out accurate category judgment on the candidate area according to the trained network model to obtain a bolt area image; and the fitting unit is used for fitting the bolt area image.
According to the method and the device, the areas with similarity meeting the set conditions with the parameter model are screened out to serve as the candidate areas, and the accurate category judgment is carried out on the candidate areas according to the trained network model, so that the bolt area image can be obtained more accurately. The network model can adopt the existing neural network model and the like, such as a Bp network, a Hopfield network, an ART network and a Kohonen network; bp networks and Hopfield networks. Preferably, a Bp neural network model is adopted, and the Bp algorithm comprises two processes of forward propagation of signals and backward propagation of errors. That is, the error output is calculated in the direction from the input to the output, and the weight and the threshold are adjusted in the direction from the output to the input. During forward propagation, an input signal acts on an output node through a hidden layer, an output signal is generated through nonlinear transformation, and if actual output does not accord with expected output, the process of backward propagation of errors is carried out. The error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and to distribute the error to all units of each layer, and to use the error signal obtained from each layer as the basis for adjusting the weight of each unit. The error is reduced along the gradient direction by adjusting the connection strength of the input node and the hidden node, the connection strength of the hidden node and the output node and the threshold value, the network parameters (weight and threshold value) corresponding to the minimum error are determined through repeated learning and training, and the training is stopped immediately. At the moment, the trained neural network can process and output the information which is subjected to nonlinear conversion and has the minimum error to the input information of similar samples.
As a preferred embodiment, fitting the bolt region comprises: smoothing the bolt area image to obtain a smooth image; performing edge detection on the smooth image by adopting a double threshold method, and extracting to obtain an edge image; performing morphological expansion on the edge image, and performing secondary contour extraction on the expanded image by using edge detection; and filtering the image obtained by the secondary contour extraction, determining a region to be fitted, and carrying out ellipse fitting on the contour in the region to be fitted to obtain an ellipse fitting target.
The edge detection can adopt the existing algorithm, such as Sobel edge detection and the like. Morphological dilation can be done as a local maximum, which can be done in the existing manner.
The control module is used for identifying the center point coordinate of each bolt on the fitted bolt image, converting the center point coordinate of the bolt, acquiring the world coordinate of the bolt, and calculating the world coordinate of the camera and the world coordinate of the bolt to obtain the offset of the bolt. The control module is used for identifying the coordinates of the center point of each bolt on the image of the fitted bolt, and the control module comprises: extracting the boundary of each bolt on the fitted bolt image to obtain boundary point coordinates; and calculating to obtain the center point coordinate of each bolt by using the boundary point coordinate of each bolt.
According to the bolt hole image, calculating the center point coordinate of each bolt hole on the control console identification bolt hole image, calculating the difference value of the center point coordinates of two adjacent bolt holes and taking the absolute value of the difference value as the hole spacing of the adjacent bolt holes; by the method, the hole spacing between the adjacent bolt holes on the embedded part can be measured, the measurement precision and accuracy are improved, and the measurement efficiency is improved.
In a preferred embodiment, the device further comprises a plating thickness detection module for acquiring plating thickness data of the base plate and sending the plating thickness data to the control module, and the control module compares the plating thickness data with a preset plating thickness threshold value to obtain a deviation amount of the plating thickness.
And the coating thickness data on the base plate is obtained through the coating thickness detector, and the calculation console compares the coating thickness data with a preset coating thickness threshold value stored in the calculation console, so that whether the coating thickness meets related requirements is judged.
As shown in fig. 1, an embodiment of the present application further provides a method for inspecting a beam embedded part, including the following steps: utilizing a camera module to take side view photographing on the bolts to obtain an image of each bolt, and sending the image of each bolt to an image processing module; identifying a bolt area by using an image processing module, and fitting the bolt area; and obtaining the coordinates of the central point of the bolt according to the fitted image of the bolt by using a control module, and calculating to obtain the offset of the bolt.
According to the shot bolt image, the computing console identifies the bolt image to obtain the image coordinate of the bolt; converting the image coordinates of the bolt to obtain the world coordinates of the bolt; calculating the world coordinate of the camera and the world coordinate of the bolt to obtain the offset of the bolt; by the method, the verticality condition of the bolt can be judged, so that whether the verticality of the bolt meets related requirements or not can be judged.
Further, recognizing a bolt region by using an image processing module, and fitting the bolt region includes: acquiring a shape description from the historical planar image data of the bolt by using an acquisition unit; screening out a region with similarity meeting set conditions with the parameter model from the shape description of the plane image data by using an identification unit as a candidate region, and carrying out accurate category judgment on the candidate region according to the trained network model to obtain a bolt region image; and fitting the bolt region image by using a fitting unit.
According to the method and the device, the areas with the similarity meeting the set conditions with the parameter model are screened out to serve as the candidate areas, and the accurate type judgment is carried out on the candidate areas according to the trained network model, so that the bolt area image can be obtained more accurately. The network model can adopt the existing neural network model and the like, such as a Bp network, a Hopfield network, an ART network and a Kohonen network; bp networks and Hopfield networks. Preferably, a Bp neural network model is adopted, and the Bp algorithm comprises two processes of forward propagation of signals and backward propagation of errors. That is, the error output is calculated in the direction from the input to the output, and the weight and the threshold are adjusted in the direction from the output to the input. During forward propagation, an input signal acts on an output node through a hidden layer, an output signal is generated through nonlinear transformation, and if actual output does not accord with expected output, the process of backward propagation of errors is carried out. The error back transmission is to back transmit the output error to the input layer by layer through the hidden layer, and to distribute the error to all units of each layer, and to use the error signal obtained from each layer as the basis for adjusting the weight of each unit. The error is reduced along the gradient direction by adjusting the connection strength of the input node and the hidden node, the connection strength of the hidden node and the output node and the threshold value, the network parameters (weight and threshold value) corresponding to the minimum error are determined through repeated learning and training, and the training is stopped immediately. At the moment, the trained neural network can process and output the information which is subjected to nonlinear conversion and has the minimum error to the input information of similar samples.
Obtaining the coordinates of the center point of the bolt according to the fitted image of the bolt by using a control module, and calculating and obtaining the offset of the bolt comprises the following steps: and identifying the coordinate of the central point of each bolt on the fitted bolt image by using a control module, converting the coordinate of the central point of each bolt to obtain the world coordinate of each bolt, and calculating the world coordinate of the camera and the world coordinate of each bolt to obtain the offset of each bolt.
According to the bolt hole images, the central point coordinates of each bolt hole on the control console identification bolt hole images are calculated, the difference value of the central point coordinates of two adjacent bolt holes is calculated, the absolute value is taken as the hole spacing of the adjacent bolt holes; by the method, the hole spacing between the adjacent bolt holes on the embedded part can be measured, the measurement precision and accuracy are improved, and the measurement efficiency is improved.
Further comprising the steps of: and acquiring plating layer thickness data of the base plate by using a plating layer thickness detection module, sending the plating layer thickness data to a control module, and comparing the plating layer thickness data with a preset plating layer thickness threshold value by using the control module to obtain the deviation of the plating layer thickness.
This application can also measure the cladding material thickness on the bottom plate, acquires cladding material thickness data on the bottom plate through cladding material thickness detector, and the calculation control platform compares cladding material thickness data and the interior predetermined cladding material thickness threshold value that stores of calculation control platform to judge whether cladding material thickness satisfies relevant requirement.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A beam body embedded part inspection system is characterized by comprising a detection platform for placing embedded parts, and a camera module, an image processing module and a control module which are arranged on one side of the detection platform, wherein the embedded parts comprise a bottom plate and bolts, a plurality of bolt holes are formed in the bottom plate, the bolts are respectively installed in the bolt holes, and a coating is arranged on the surface of the bottom plate; the camera module is used for photographing the bolts in a side view to obtain an image of each bolt and sending the image of each bolt to the image processing module; the image processing module is used for identifying a bolt area and fitting the bolt area; and the control module is used for obtaining the center point coordinates of the bolt according to the fitted image of the bolt and calculating to obtain the offset of the bolt.
2. The beam embedment inspection system of claim 1, wherein the image processing module includes an acquisition unit, a recognition unit, and a fitting unit, the acquisition unit acquiring a shape description from historical planar image data of the bolt; the identification unit screens out an area with similarity meeting set conditions with the parameter model from the shape description of the plane image data as a candidate area, and carries out accurate category judgment on the candidate area according to the trained network model to obtain a bolt area image; the fitting unit fits the bolt region image.
3. The beam embedment inspection system of claim 2, wherein fitting a bolt area includes: smoothing the bolt area image to obtain a smooth image; performing edge detection on the smooth image by adopting a double threshold method, and extracting to obtain an edge image; performing morphological expansion on the edge image, and performing secondary contour extraction on the expanded image by using edge detection; and filtering the image obtained by the secondary contour extraction, determining a region to be fitted, and carrying out ellipse fitting on the contour in the region to be fitted to obtain an ellipse fitting target.
4. The system for inspecting a beam embedded part according to claim 1, wherein the control module is configured to identify coordinates of a center point of each bolt on the fitted image of the bolt, convert the coordinates of the center point of the bolt to obtain world coordinates of the bolt, and calculate the world coordinates of the camera and the world coordinates of the bolt to obtain an offset of the bolt.
5. The beam embedment inspection system of claim 4, wherein the control module for identifying center point coordinates of each of said bolts on the image of the fitted bolts includes: extracting the boundary of each bolt on the fitted bolt image to obtain boundary point coordinates; and calculating to obtain the center point coordinate of each bolt by using the boundary point coordinate of each bolt.
6. The beam body embedded part inspection system according to claim 1, further comprising a coating thickness detection module for obtaining coating thickness data of the base plate and sending the coating thickness data to the control module, wherein the control module compares the coating thickness data with a preset coating thickness threshold to obtain a deviation of the coating thickness.
7. A method for inspecting an embedded part of a beam body is characterized by comprising the following steps: utilizing a camera module to take side view photographing on the bolts to obtain an image of each bolt, and sending the image of each bolt to an image processing module; identifying a bolt area by using an image processing module, and fitting the bolt area; and obtaining the coordinates of the central point of the bolt according to the fitted image of the bolt by using a control module, and calculating to obtain the offset of the bolt.
8. The method of claim 7, wherein the bolt regions are identified using an image processing model, and fitting the bolt regions comprises: acquiring a shape description from the historical planar image data of the bolt by using an acquisition unit; screening out a region with similarity meeting set conditions with the parameter model from the shape description of the plane image data by using an identification unit as a candidate region, and carrying out accurate category judgment on the candidate region according to the trained network model to obtain a bolt region image; and fitting the bolt region image by using a fitting unit.
9. The method for inspecting a beam embedded part according to claim 7, wherein the step of obtaining coordinates of a center point of the bolt by using a control module according to the fitted image of the bolt and calculating the offset of the bolt comprises the steps of: and recognizing the coordinate of the central point of each bolt on the fitted bolt image by using a control module, converting the coordinate of the central point of each bolt to obtain the world coordinate of each bolt, and calculating the world coordinate of the camera and the world coordinate of each bolt to obtain the offset of each bolt.
10. The beam embedment inspection method of claim 7, further comprising the steps of: and obtaining the plating thickness data of the base plate by using a plating thickness detection module, sending the plating thickness data to a control module, and comparing the plating thickness data with a preset plating thickness threshold value by the control module to obtain the deviation of the plating thickness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210201765.6A CN114623783A (en) | 2022-03-03 | 2022-03-03 | System and method for detecting embedded part of beam body |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210201765.6A CN114623783A (en) | 2022-03-03 | 2022-03-03 | System and method for detecting embedded part of beam body |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114623783A true CN114623783A (en) | 2022-06-14 |
Family
ID=81900641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210201765.6A Pending CN114623783A (en) | 2022-03-03 | 2022-03-03 | System and method for detecting embedded part of beam body |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114623783A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110230985A (en) * | 2019-07-22 | 2019-09-13 | 株洲时代电子技术有限公司 | A kind of sleeper bolt detection device |
| CN111428731A (en) * | 2019-04-04 | 2020-07-17 | 深圳市联合视觉创新科技有限公司 | Multi-class target identification and positioning method, device and equipment based on machine vision |
| CN113375560A (en) * | 2021-07-13 | 2021-09-10 | 北京好运达智创科技有限公司 | Beam embedded part approach inspection system and method |
-
2022
- 2022-03-03 CN CN202210201765.6A patent/CN114623783A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111428731A (en) * | 2019-04-04 | 2020-07-17 | 深圳市联合视觉创新科技有限公司 | Multi-class target identification and positioning method, device and equipment based on machine vision |
| CN110230985A (en) * | 2019-07-22 | 2019-09-13 | 株洲时代电子技术有限公司 | A kind of sleeper bolt detection device |
| CN113375560A (en) * | 2021-07-13 | 2021-09-10 | 北京好运达智创科技有限公司 | Beam embedded part approach inspection system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108824816B (en) | High-altitude long-span net frame sliding, positioning, installing and monitoring method | |
| CN109341903B (en) | Inhaul cable force measuring method based on edge recognition in computer vision | |
| CN114994061B (en) | Machine vision-based steel rail intelligent detection method and system | |
| CN103033253A (en) | Non-contact vibration detecting method of tower crane structure | |
| CN107798293A (en) | A kind of crack on road detection means | |
| CN110008947A (en) | A kind of silo Grain Quantity monitoring method and device based on convolutional neural networks | |
| CN111896549A (en) | Building crack monitoring system and method based on machine learning | |
| CN115993096A (en) | High-rise building deformation measuring method | |
| CN102081045B (en) | Structural damage identification method based on laser television holographic technique | |
| CN117058600A (en) | Regional bridge group traffic load identification method and system | |
| CN108827200A (en) | A kind of body section intelligent checking system and method | |
| CN116934179A (en) | Building engineering quality detection data analysis management system based on big data | |
| CN114046749B (en) | Method and system for detecting roughness of point-shaped pit joint surface of precast concrete member | |
| CN114549751A (en) | Template monitoring system and method for box girder production | |
| KR101227776B1 (en) | Designing method for displacement estimation on construction using ann and estimating method for displacement of construction | |
| CN117162225B (en) | Demoulding and forming method and system for concrete prefabricated part | |
| CN113935965A (en) | Prefabricated box girder template detecting system | |
| CN114623783A (en) | System and method for detecting embedded part of beam body | |
| WO2024067435A1 (en) | Video-based multi-object displacement tracking monitoring method and apparatus | |
| CN116778520B (en) | Mass license data quality inspection method | |
| CN115983796A (en) | Power transmission line construction progress supervision and early warning method and system | |
| CN116205880A (en) | Gauze defect detection method based on 3D point cloud | |
| KR102292602B1 (en) | Deep learning and image processing based bolt loosening detection method | |
| Avendãno et al. | Image based inspection of concrete cracks using UAV photography | |
| CN114049543A (en) | Automatic identification method for scrap steel unloading change area based on deep learning |
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 |