WO2021227286A1 - Mobile testing method and apparatus for regularity of honeycomb product with ultra-large area - Google Patents

Mobile testing method and apparatus for regularity of honeycomb product with ultra-large area Download PDF

Info

Publication number
WO2021227286A1
WO2021227286A1 PCT/CN2020/109727 CN2020109727W WO2021227286A1 WO 2021227286 A1 WO2021227286 A1 WO 2021227286A1 CN 2020109727 W CN2020109727 W CN 2020109727W WO 2021227286 A1 WO2021227286 A1 WO 2021227286A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
honeycomb
camera
cell
product
Prior art date
Application number
PCT/CN2020/109727
Other languages
French (fr)
Chinese (zh)
Inventor
王中钢
施冲
周伟
许平
姚曙光
高广军
高天宇
Original Assignee
中南大学
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Priority claimed from CN202010388402.9A external-priority patent/CN111583241B/en
Priority claimed from CN202010388343.5A external-priority patent/CN111583238B/en
Application filed by 中南大学 filed Critical 中南大学
Publication of WO2021227286A1 publication Critical patent/WO2021227286A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation

Definitions

  • the invention relates to the fields of design, manufacture and application of lightweight structural products for transportation, machinery, aerospace, ships and other equipment, and in particular to a mobile inspection method and device for the regularity of ultra-large-area honeycomb products.
  • the lightweight honeycomb structure is widely used in various engineering fields due to its excellent load-bearing and energy-absorbing properties.
  • various structural defects such as the bend, warpage, and cell deformity of the honeycomb core block inevitably appear, and these defects have been proved to have a greater bearing and energy absorption performance. Influence. Therefore, the inspection and evaluation of the regularity of cellular products to avoid the risk of using inferior products and to further improve the regularity of cellular products urgently need to be carried out.
  • the existing related technologies mainly include:
  • Chinese Patent Application Nos. 201610585321.1 and 201610585419.7 (both filing dates are July 22, 2016), respectively disclose a method and device for measuring the shape of a honeycomb core, including the following steps: covering the surface to be measured with a reflector on the honeycomb core
  • the thin film adopts the vacuum adsorption method to make the reflective film close to the honeycomb core to be tested surface, and the reflective film at the honeycomb cells is recessed downward; the reflective film on the tested surface is scanned and measured to obtain honeycomb cores in different spatial positions
  • the wall height can analyze the cell deformation of the honeycomb core.
  • This method is based on the idea of physical length measurement and uses negative pressure adsorption film to perform detection. It can initially obtain the approximate position of the edge, but the accuracy is low and the efficiency is low. Especially for the extraction of the characteristic edge of the pore size and thin-walled honeycomb structure, it is difficult to achieve .
  • the Chinese patent application number is 201710203081.9 (application date is September 1, 2017), which discloses an automatic detection method for honeycomb defects of remote sensor hoods based on machine vision, including the following steps: acquiring a honeycomb image of the hood; Preprocess the mask honeycomb image to reduce noise; perform feature extraction on the preprocessed mask honeycomb image to obtain the features of the straight line segment of the mask honeycomb edge; screen the feature vectors of normal and defective cells as positive and negative samples, and establish an artificial neural network ,train.
  • Chinese patent application number is 201510740221.7 (application date November 04, 2015), which discloses a checkerboard corner automatic screening method for corner detection;
  • China patent application number is 200710194135.6 (application date December 2007) 05) discloses a surface shape measuring device;
  • Chinese patent application number is 200810166508.3 (application date October 08, 2008) discloses a three-dimensional shape measurement method,
  • Chinese patent application number is 201010557356.7 (application date November 2010 22nd) disclosed a detection and recognition method for the triple X combination mark.
  • the corresponding surface shape detection technology was reported, and this type of technology was mainly for the recognition and measurement of the shape and surface contour.
  • the purpose of the present invention is to provide a mobile inspection method and device for the regularity of a super-large area honeycomb product to solve the problems of complicated honeycomb quality inspection operations and inaccurate judgment results in the prior art, which are not suitable for the inspection of honeycomb products on a production line. .
  • the first aspect of the present invention provides a mobile inspection method for the regularity of ultra-large-area cellular products, including:
  • the setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product includes:
  • the movement route of the camera is set according to the step length, so that the camera can obtain an image of the entire cellular product.
  • the calculating the average deviation of all cell angles in the honeycomb cell image, and evaluating the quality of the honeycomb according to the average includes: calculating the deviation of all cell angles in the partial image of each honeycomb product Average value, and calculate the average value of the deviation of each image again, compare this value with the preset value, if it is less than the preset value, the product is qualified; or splice the partial image of the honeycomb into the overall image of the honeycomb product, and then Calculate the average deviation of all cell angles in the overall image, compare this value with the preset value, and if it is less than the preset value, the product is qualified.
  • the method further includes: mosaic partial images of the honeycomb;
  • the partial honeycomb image stitching is to stitch partial photos of honeycomb products obtained by moving the camera to form an overall honeycomb image, wherein the stitching method is implemented by Sift or Surf algorithm.
  • the setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product further includes:
  • the performing binarization processing on the image to obtain a binarized image includes:
  • the denoising image is subjected to binarization processing to obtain a binarized image.
  • the performing binarization processing on the denoising image to obtain a binarized image includes:
  • the initial binarized image is subjected to morphological filtering processing to obtain a binarized image.
  • the extracting the vertices of the honeycomb cells in the binarized image includes:
  • the included angles are in the sequence of boundary pixels, between two points of the boundary pixels Side, the angle between two pixel points that are separated from the boundary pixel point by a first preset value and the line connecting the cell boundary pixel point;
  • the method further includes: calculating the average value of the internal angle deviations of the three cell internal angles of the common vertices in the honeycomb cell image, and evaluating the honeycomb quality according to the average value of the internal angles.
  • a cellular quality detection device including:
  • the route setting module is used to set the moving route of the camera according to the camera's field of view, so that the camera can obtain the image of the entire cellular product;
  • the binarization processing module is configured to perform binarization processing on the honeycomb image to obtain a binarized image
  • a vertex extraction module for extracting the vertices of honeycomb cells in the binarized image
  • a cellular cell image reconstruction module configured to reconstruct a cellular cell image according to the mapping relationship between the vertices and the cells
  • the honeycomb quality detection module is used to calculate the average deviation of all cell angles in the cell image of the honeycomb, and evaluate the quality of the honeycomb according to the average.
  • the route setting module includes:
  • the step size setting unit is configured to set the movement step size of the camera according to the camera's field of view range, where the movement step size is the distance between two adjacent images taken;
  • the route setting unit is used to set the moving route of the camera according to the step length, so that the camera can obtain an image of the entire cellular product.
  • the route setting module further includes:
  • the step length adjustment unit is used to adjust the step length so that the overlapping area of two adjacent images is 5%-10% of a single picture.
  • the binarization processing module includes:
  • An image denoising unit configured to perform filtering processing on the image to remove noise to obtain a denoised image
  • the binarization processing unit is configured to perform binarization processing on the denoising image to obtain a binarized image.
  • the binarization processing module further includes: a filtering unit
  • binarization processing unit After the binarization processing unit performs binarization processing on the denoised image to obtain an initial binarized image
  • the filtering unit performs morphological filtering processing on the initial binarized image to obtain a binarized image.
  • vertex extraction module is used for:
  • the included angles are in the sequence of boundary pixels, between two points of the boundary pixels Side, the angle between two pixel points that are separated from the boundary pixel point by a first preset value and the line connecting the cell boundary pixel point;
  • a shelf a lifting device, a walking gantry, and a slide rail;
  • the storage table is used to hold the honeycomb to be tested, and a levelness indicator board is arranged on it;
  • the lifting device is connected with the placing table, and is used to drive the honeycomb to be detected up and down;
  • the walking gantry is arranged on the slide rail, and the walking gantry is provided with the image acquisition module so that the image acquisition module can move in a horizontal direction.
  • a calibration module Also includes: a calibration module
  • the calibration module is used in conjunction with the stage to check the accuracy of the detection device.
  • the honeycomb quality detection module is also used to calculate the average value of the internal angle deviations of the three internal angles of the common vertices in the honeycomb cell image, and evaluate the honeycomb quality according to the average value of the internal angles.
  • a storage medium is provided, and a computer program is stored on the storage medium, and when the program is executed by a processor, the steps of the method described in any one of the above technical solutions are implemented.
  • an electronic device including a memory, a display, a processor, and a computer program stored on the memory and running on the processor, and when the processor executes the program.
  • the average deviation of the cell angle is obtained.
  • the smaller the deviation average the more regular the cells are.
  • a concept of regularity can be introduced, that is, the closer the honeycomb is to a full hexagon, The higher the regularity; experiments have also proved that the higher the regularity of the honeycomb product, the better the stiffness and strength, that is, the better the quality of the honeycomb product. Therefore, the present invention can determine the honeycomb product through simple operation and processing. Quality, suitable for testing the quality of honeycomb products on the production line.
  • Fig. 1 is a flow chart of a mobile inspection method for regularity of a super-large-area honeycomb product according to a first embodiment of the present invention
  • FIG. 2 is a flow chart of a mobile camera-style detection method for cell regularity according to a specific embodiment of the present invention
  • Fig. 3 is a schematic diagram of camera movement shooting according to an embodiment of the present invention.
  • FIG. 4 is a top view of a honeycomb product quality inspection device according to an alternative embodiment of the present invention.
  • Fig. 5 is a front view of a honeycomb product quality inspection device according to an alternative embodiment of the present invention.
  • 1 Storage table
  • 2 Digital camera
  • 3 Control system
  • 4 Lifting device
  • 5 Fixture
  • 6 Walking gantry
  • 7 Slide rail
  • 8 Mobile device.
  • the first aspect of the present invention provides a mobile inspection method for the regularity of ultra-large-area honeycomb products, including:
  • setting the camera's moving route according to the camera's field of view so that the camera can traverse the entire cellular product includes: setting the camera's moving step according to the camera's field of view, and the moving step is two adjacent ones. The distance between the images taken in the second time; the camera's moving route is set according to the step length, so that the camera can obtain the image of the entire cellular product.
  • setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product also includes: adjusting the step length so that the overlapping area of the two adjacent images is 5 of that of a single picture. %-10%.
  • calculating the average deviation of all cell angles in the honeycomb cell image, and evaluating the honeycomb quality according to the average includes: calculating the average deviation of all cell angles in the partial image of each honeycomb product, and Calculate the average value of the deviation of each image again, compare this value with the preset value, if it is less than the preset value, the product is qualified; or stitch the partial image of the honeycomb into the overall image of the honeycomb product, and then obtain the overall image The average value of the deviation of all cell angles in the cell, compare this value with the preset value, if it is less than the preset value, the product is qualified.
  • the method further includes: honeycomb partial image stitching; honeycomb partial image stitching is to stitch partial photos of the honeycomb product obtained by moving the camera to form an overall honeycomb image, wherein the stitching method adopts Sift Or Surf algorithm implementation.
  • binarizing an image to obtain a binarized image includes: filtering the image to remove noise to obtain a denoised image; binarizing the denoised image to obtain a binarized image .
  • performing binarization processing on the denoised image to obtain a binarized image includes: performing binarization processing on the denoised image to obtain an initial binarized image; performing morphology on the initial binarized image Filter processing to obtain a binarized image.
  • extracting the vertices of the honeycomb cells in the binarized image includes: closing the binarized image to obtain a smooth honeycomb vertex image; processing the honeycomb wall to take the largest circle center on the smooth honeycomb vertex image , Get the apex of the honeycomb cell.
  • extracting the vertices of the honeycomb cell in the binarized image includes: obtaining a skeleton diagram of the honeycomb product based on the binarized image; and extracting boundary pixels belonging to the same cell from the skeleton diagram , Get the boundary pixel sequence of the cell; respectively obtain the angles corresponding to the boundary pixels, and obtain the angle sequence corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, on both sides of the boundary pixels, The included angle between two pixels that are separated from the boundary pixel by a first preset value and the line of the cell boundary pixel; the second preset size window is used to suppress the included angle sequence by non-minimal value , Set the included angle other than the minimum value of the included angle in the window as the first preset included angle; when the non-minimum value suppression of the included angle sequence is completed, determine that the minimum value is less than the second preset included angle
  • the boundary pixels corresponding to the included angles are the vertices.
  • a mobile camera-style detection method for cell regularity includes the following steps: camera setting, image acquisition, image processing, vertex extraction, cell Reconstruction, quality assessment;
  • “Camera setting” includes setting the camera movement step length and route. After setting, the camera moves along the specified route in a unit of step length. One shot is taken for each movement step: according to the product size and the camera's field of view size Set the camera's X- and Y-direction movement steps to ensure that the overlapping area of adjacent photos is 5%-10% of a single photo; set the route of the camera moving along the X-axis and Y-axis to ensure that the camera can finally be completely Traverse the entire honeycomb product, as shown in Figure 3;
  • the "image processing" sequence includes: image stitching, noise reduction filtering, binarization, morphological filtering, to obtain morphological images;
  • Image stitching is to stitch the partial photos of the honeycomb product taken by the camera moving to obtain the overall photo of the honeycomb product, which is realized by the Sift or Surf algorithm;
  • Noise reduction filter is to use median filter method to filter out the noise of the image
  • Morphological filtering is to eliminate pixels whose area is less than a given threshold and reduce the error caused by binarization
  • the first method of "vertex extraction” After traversing the image, the smallest window in which the smallest pixel value is 0 and the number of pixels greater than 0 is used as the statistical window, and the window is used to traverse the image again, and the pixel value in the window is Assign a pixel number of 1 to the center point of the window, extract the point with the maximum pixel number of pixel value 1, record it as a vertex, use an annihilation window with a side length equal to the side length of the cell, and use this point as the center annihilation window The number of pixels with a pixel value of 1 is set to 0, and the point with the maximum value of the pixel with a pixel value of 1 is extracted and recorded. Repeat this step until the number of pixels with a pixel value of 1 is less than the given threshold, then the vertex extraction is completed ;
  • the first step of the second method of "vertex extraction” is the skeletonization process.
  • the “skeletonization” is based on the morphological image, and the line with the pixel value of 1 is drawn by the line segment with the line width of 1 pixel. ;
  • the second step uses a window of 5 ⁇ 5 pixels to calculate the corner response function value R of each pixel, for which the R value is greater than 1% of the maximum R value of all pixels and is 3 ⁇ 3 centered on it
  • the pixel with the maximum value of the neighborhood is extracted and its coordinates are recorded as vertices;
  • the third method of "vertex extraction” The first step is to carry out skeletonization processing; the second step is to count all the pixels with the pixel value of 1 clockwise or counterclockwise on the basis of the skeleton diagram. The number of changes in the pixel value of the domain. If the number of changes is 6, or the number of changes is 4, and the pixel is not on the same straight line with the other two points in its eight neighborhood, the coordinates are extracted and recorded as vertices;
  • Cell reconstruction is to connect the extracted vertices according to the mapping relationship between cells and vertices to obtain a cell reconstruction graph
  • the first method of "cell reconstruction” traverse the image and encounter a pixel with a pixel value of 0, then use the Moore neighborhood tracking algorithm for boundary tracking, and make a window with each boundary point as the center. Determine whether there are vertices in the window, if there are vertices, record their numbers and mark them sequentially.
  • stop tracking When encountering the starting tracking pixel of the cell, stop tracking and set the pixel value of the cell to 1, and repeat the above In the process, until there is no point with a pixel value of 0, the vertices of each cell are connected in sequence to complete the reconstruction of the cell;
  • the second method of "cell reconstruction” For each vertex, calculate the distance between all other vertices and it, select the three nearest points and record, calculate the distance between all vertices and the nearest three points, and sum them. Divide by twice the number of vertices to get the average honeycomb cell side length A. Select the vertices located in the area outside the 1A ⁇ 2A width of the image edge. For each of the vertices, connect to the nearest three points respectively. So as to obtain the reconstructed image of the honeycomb;
  • the first step is to calculate: calculate the angular deviation value of all cells and its total average value, line deviation value and its total average value ;
  • the second step of judgment That is, compared with the set tolerance zone, the one that falls within the tolerance zone is judged as qualified, otherwise it is judged as unqualified.
  • the method further includes: calculating the average value of the internal angle deviations of the three cell internal angles of the common vertices in the honeycomb cell image, and evaluating the honeycomb quality according to the average value of the internal angles.
  • a cellular quality detection device including: a route setting module, configured to set a movement route of the camera according to the camera's field of view range, so that the camera can obtain an image of the entire cellular product;
  • the camera is used to obtain the honeycomb image;
  • the binarization processing module is used to binarize the honeycomb image to obtain the binarized image;
  • the vertex extraction module is used to extract the vertices of the honeycomb cells in the binarized image;
  • the honeycomb The cell image reconstruction module is used to reconstruct the honeycomb cell image according to the mapping relationship between the vertices and the cells;
  • the honeycomb quality detection module is used to calculate the average deviation of all the cell angles in the honeycomb cell image, and according to The average value evaluates the honeycomb quality.
  • the route setting module includes: a step length setting unit for setting the movement step length of the camera according to the camera's field of view range, and the movement step length is the distance between two adjacent images taken;
  • the route setting unit is used to set the moving route of the camera according to the step length, so that the camera can obtain the image of the entire cellular product.
  • the route setting module further includes: a step length adjustment unit for adjusting the step length so that the overlapping area of the images taken twice adjacently is 5%-10% of a single picture.
  • the binarization processing module includes: an image denoising unit for filtering the image to remove noise to obtain a denoised image; a binarization processing unit for binarizing the denoised image Processing to obtain a binarized image.
  • the binarization processing module further includes: a filtering unit; the denoising image is binarized in the binarization processing unit to obtain the initial binarized image; the filtering unit is used to binarize the initial The image undergoes morphological filtering to obtain a binary image.
  • the vertex extraction module includes: a closed operation processing unit for performing closed operation processing on the binarized image to obtain a smooth honeycomb vertex image; a vertex extraction unit for performing a honeycomb wall on the smooth honeycomb vertex image Take the center of the largest circle to get the apex of the honeycomb cell.
  • the vertex extraction module includes: a closed operation processing unit for performing closed operation processing on the binarized image to obtain a smooth honeycomb vertex image; a honeycomb wall intersection extraction unit for sequentially extracting the smooth honeycomb vertex image After expansion and corrosion processing, only the image of the intersection of the honeycomb wall is obtained; the vertex extraction unit is used for processing the maximum circle center of the honeycomb wall on the image of the intersection of the honeycomb wall to obtain the apex of the honeycomb cell.
  • the vertex extraction module is specifically used to: obtain the skeleton image of the honeycomb product on the basis of the binary image; extract the boundary pixels belonging to the same cell from the skeleton image to obtain the boundary of the cell Pixel sequence; respectively obtain the angles corresponding to the boundary pixels, and obtain the angle sequence corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, on both sides of the boundary pixels, and are separated from the boundary pixels.
  • the included angle outside the minimum value of the angle is set as the first preset included angle; when the non-minimum value suppression of the included angle sequence is completed, determine the boundary pixels corresponding to the included angle of all the minimum values that are smaller than the second preset included angle Points are vertices.
  • the present invention further includes: a storage table, a lifting device, a walking gantry, and a slide rail; the storage table is used to hold the honeycomb to be inspected, and a levelness indicator board is arranged on it; the lifting device is connected to the storage table , Used to drive the honeycomb to be detected up and down; the walking gantry is arranged on the slide rail, and the walking gantry is provided with an image acquisition module so that the image acquisition module can move in the horizontal direction.
  • the present invention further includes: a calibration module; the calibration module is used in conjunction with the stage to check the accuracy of the detection device.
  • a mobile camera-type detection system for cell regularity which includes a table, a digital camera, a control system, a lifting device, a fixture, and a walking gantry.
  • the digital camera and control system are connected; level adjustment device and level indicator board are set on the stage, and the side of the fixture near the honeycomb is painted bright yellow to assist in image processing;
  • the digital camera is at least One, with a resolution of not less than 1080P, equipped with a telecentric lens to obtain high-resolution cellular product photos and reduce its distortion in the depth of field; its installation method is fixed or/and mobile; digital When there is one camera, the installation method can be fixed or mobile; when the digital camera array is multiple, the installation method is fixed;
  • the lifting device includes a storage table, a guide rail, an electric push rod or an electro-hydraulic push rod, and the storage table is used for Place the tested honeycomb part, which can be moved up and down along the guide rail under the drive of an electric push rod or an electro-hydraulic push rod to adjust the height of the tested honeycomb part to ensure that the upper end surface of the tested honeycomb part is flush with the upper end surface of the fixture;
  • the clamp is composed of four plates and a driving
  • the digital camera is installed on the beam of the walking gantry, which can be moved horizontally along the beam under the drive of the mobile device; the walking gantry can be moved longitudinally along the slide rail under the drive of the mobile device, and the movement of the digital camera and the walking gantry All are controlled by the control system.
  • the control system includes a system control module, a calculation and analysis module, and a result display module; the control module controls the start and stop of the system, the movement of the lifting device, and the camera moving device; the calculation and analysis module uses the corresponding analysis software to analyze the photos collected by the digital camera and calculates The geometric regularity of the honeycomb sample is evaluated, and the geometric regularity of the honeycomb sample is evaluated according to the selected evaluation standard and threshold, and the evaluation result is passed to the result display module, and the result display module can display the result; the result display module can According to the product quality assessment results, the green light is displayed for qualified quality, and the red light is displayed for unqualified.
  • the calibration board is a display board with an electronic ink screen that can display standard honeycombs with adjustable side lengths and wall thicknesses. The outside of the screen displays a color that contrasts with the honeycombs. After placing the calibration board on the stage and positioning it with a fixture, adjust the digital camera to a suitable position, obtain a photo of the calibration board, and pass it to the software of the control system for calibration, and check the detection accuracy of the system.
  • the honeycomb quality detection module is also used to calculate the average value of the internal angle deviations of the three internal angles of the common vertices in the honeycomb cell image, and evaluate the honeycomb quality according to the average value of the internal angles.
  • a storage medium is provided, and a computer program is stored on the storage medium, and when the program is executed by a processor, the steps of any one of the above technical solutions are implemented.
  • an electronic device including a memory, a display, a processor, and a computer program stored in the memory and running on the processor.
  • the processor executes the program, any of the above technical solutions is implemented. Steps of a method.
  • the present invention aims to protect a mobile inspection method for the regularity of a super-large-area honeycomb product.
  • the image is binarized to obtain a binarized image; the vertices of the honeycomb cell in the binarized image are extracted; the honeycomb cell image is reconstructed according to the mapping relationship between the vertices and the cells; all the cells in the honeycomb cell image are calculated.
  • the average value of the deviation of the element angle, and the honeycomb quality is evaluated based on the average value.
  • the method is novel and efficient. For honeycomb products with a large area, it can realize rapid detection of geometric regularity.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

A mobile testing method for the regularity of a honeycomb product with an ultra-large area, and a quality testing apparatus. The mobile testing method for the regularity of a honeycomb product with an ultra-large area comprises: setting a movement route of a camera according to the field-of-view range of the camera, such that the camera can acquire an image of a whole honeycomb product (S1); acquiring a honeycomb image (S2); performing binarization processing on the honeycomb image to obtain a binarized image (S3); extracting the vertexes of honeycomb cells in the binarized image (S4); according to mapping relationships between the vertexes and the cells, performing reconstruction to obtain a honeycomb cell image (S5); and calculating the average deviation value of all cell angles in the honeycomb cell image, and evaluating the honeycomb quality according to the average value (S6). For a honeycomb product with a relatively large area, rapid testing for geometric regularity can be realized.

Description

超大面积蜂窝产品规整度的移动式检测方法及装置Mobile detection method and device for regularity of ultra-large area honeycomb products 技术领域Technical field
本发明涉及交通、机械、航空航天、船舶等装备的轻质结构产品设计、制造及应用等领域，尤其涉及一种超大面积蜂窝产品规整度的移动式检测方法及装置。The invention relates to the fields of design, manufacture and application of lightweight structural products for transportation, machinery, aerospace, ships and other equipment, and in particular to a mobile inspection method and device for the regularity of ultra-large-area honeycomb products.
背景技术Background technique
轻质蜂窝结构以其优异的承载与吸能特性而被广泛应用到各种工程领域。然而，在该产品的生产制造过程中，不可避免地出现蜂窝芯块拱弯、翘曲、胞孔畸形等各型结构性缺陷，而这些缺陷已被证实对其承载与吸能性能产生较大影响。因此，有关蜂窝产品规整性检测与评估以规避低劣产品的使用风险，进一步改进蜂窝规整度的工作亟待开展。The lightweight honeycomb structure is widely used in various engineering fields due to its excellent load-bearing and energy-absorbing properties. However, in the production process of the product, various structural defects such as the bend, warpage, and cell deformity of the honeycomb core block inevitably appear, and these defects have been proved to have a greater bearing and energy absorption performance. Influence. Therefore, the inspection and evaluation of the regularity of cellular products to avoid the risk of using inferior products and to further improve the regularity of cellular products urgently need to be carried out.
由于蜂窝产品为周期排列多孔结构，具有典型的多顶点、细薄壁、承载面宽等特征，传统超声检测技术无法获得其结构性缺陷的特征信息。现有相关技术主要包括：Since the honeycomb product has a periodic arrangement of porous structures, with typical features such as multiple vertices, thin walls, and wide bearing surfaces, traditional ultrasonic inspection technology cannot obtain the characteristic information of its structural defects. The existing related technologies mainly include:
中国专利申请号为201610585321.1和201610585419.7(申请日均为2016年07月22日)，分别公开了一种蜂窝芯面形的测量方法及实现装置，包括如下步骤：在蜂窝芯待测面覆上反射薄膜，采用真空吸附的方式使所述反射薄膜紧贴蜂窝芯待测面，且使蜂窝孔格处的反射薄膜向下凹陷；对待测面反射薄膜扫描测量，获得蜂窝芯在不同空间位置的蜂窝壁高度，能够分析蜂窝芯的孔格变形。该方法基于物理长度测定的思想，利用负压吸附薄膜实施检测，可初步获得棱边的大致位置，但精度差、效率低，尤其对细孔径、薄壁蜂窝结构的特征边提取，实现难度大。Chinese Patent Application Nos. 201610585321.1 and 201610585419.7 (both filing dates are July 22, 2016), respectively disclose a method and device for measuring the shape of a honeycomb core, including the following steps: covering the surface to be measured with a reflector on the honeycomb core The thin film adopts the vacuum adsorption method to make the reflective film close to the honeycomb core to be tested surface, and the reflective film at the honeycomb cells is recessed downward; the reflective film on the tested surface is scanned and measured to obtain honeycomb cores in different spatial positions The wall height can analyze the cell deformation of the honeycomb core. This method is based on the idea of physical length measurement and uses negative pressure adsorption film to perform detection. It can initially obtain the approximate position of the edge, but the accuracy is low and the efficiency is low. Especially for the extraction of the characteristic edge of the pore size and thin-walled honeycomb structure, it is difficult to achieve .
中国专利申请号为201710203081.9(申请日为2017年9月1日)，公开了一种基于机器视觉的遥感器遮光罩蜂窝缺陷自动检测方法，包括以下步骤：获取遮光罩蜂窝图像；对获取的遮光罩蜂窝图像进行预处理，减少噪声；对经过预处理的遮光罩蜂窝图像进行特征提取，得到遮光罩蜂窝边缘直线段特征；筛选正常蜂窝和缺陷蜂窝的特征向量作为正负样本，人工神经网络建立、训练。中国优秀硕士论文全文数据库收录的2017年王薇所作的《基于机器视觉的蜂窝结构三维外形测量技术研究》，公开了采用正六边形和正四边形网格的图像化识别方法，提出了一种基于直线分段(LSD)的单元网格处理方法，获取单个网格边界信息，通过计算待评估直线区域内像素与该区域矩形包围盒夹角判定是否为目标直线段，从而实现单元网格边缘线段的提取，进一步定位网格交点。该类方法主要定位于规则几何六边形与四边形的线段提取，仅涉及了单一胞元蜂窝的线条特征提取。The Chinese patent application number is 201710203081.9 (application date is September 1, 2017), which discloses an automatic detection method for honeycomb defects of remote sensor hoods based on machine vision, including the following steps: acquiring a honeycomb image of the hood; Preprocess the mask honeycomb image to reduce noise; perform feature extraction on the preprocessed mask honeycomb image to obtain the features of the straight line segment of the mask honeycomb edge; screen the feature vectors of normal and defective cells as positive and negative samples, and establish an artificial neural network ,train. In 2017, Wang Wei’s "Research on the 3D Shape Measurement Technology of Honeycomb Structure Based on Machine Vision" included in the full-text database of China's outstanding master's thesis published a method of image recognition using regular hexagons and regular quadrilateral grids, and proposed a straight line Segmented (LSD) unit grid processing method, obtains the boundary information of a single grid, and determines whether it is the target straight line segment by calculating the angle between the pixel in the straight line area to be evaluated and the rectangular bounding box of the area, so as to realize the edge line segment of the unit grid Extract and further locate the grid intersection. This type of method is mainly located in the line segment extraction of regular geometric hexagons and quadrilaterals, and only involves the line feature extraction of a single cell honeycomb.
除此以外，中国专利申请号为201510740221.7(申请日2015年11月04日)，公开了一种边角检测的棋盘格角点自动筛选方法；中国专利申请号为200710194135.6(申请日2007年12月05日)公开了一种表面形状测定装置；中国专利申请号为200810166508.3(申请日2008年10月08日)公开了一种三维形状测量方法，中国专利申请号为201010557356.7(申请日2010年11月22日)公开了一种三X组合标记的检测识别方法均报导了相应的表面形状检测技术，该类技术均只主要针对形状表面轮廓进行识别与测定。In addition, the Chinese patent application number is 201510740221.7 (application date November 04, 2015), which discloses a checkerboard corner automatic screening method for corner detection; China patent application number is 200710194135.6 (application date December 2007) 05) discloses a surface shape measuring device; Chinese patent application number is 200810166508.3 (application date October 08, 2008) discloses a three-dimensional shape measurement method, Chinese patent application number is 201010557356.7 (application date November 2010 22nd) disclosed a detection and recognition method for the triple X combination mark. The corresponding surface shape detection technology was reported, and this type of technology was mainly for the recognition and measurement of the shape and surface contour.
发明内容Summary of the invention
(一)发明目的(1) Purpose of the invention
本发明的目的是提供一种超大面积蜂窝产品规整度的移动式检测方法及装置以解决现有技术对蜂窝质量检测操作复杂及判断结果不准确，不适用生产线上蜂窝产品的检测问题。。The purpose of the present invention is to provide a mobile inspection method and device for the regularity of a super-large area honeycomb product to solve the problems of complicated honeycomb quality inspection operations and inaccurate judgment results in the prior art, which are not suitable for the inspection of honeycomb products on a production line. .
(二)技术方案(2) Technical solution
为解决上述问题，本发明的第一方面提供了一种超大面积蜂窝产品规整 度的移动式检测方法，包括：In order to solve the above-mentioned problems, the first aspect of the present invention provides a mobile inspection method for the regularity of ultra-large-area cellular products, including:
根据相机的视场范围设定相机的移动路线，使所述相机可以获取整个蜂窝产品的图像；Set the camera's moving route according to the camera's field of view, so that the camera can acquire the image of the entire cellular product;
获取蜂窝图像；Obtain a honeycomb image;
将所述蜂窝图像进行二值化处理，得到二值化图像；Performing binarization processing on the honeycomb image to obtain a binarized image;
提取所述二值化图像中蜂窝胞元的顶点；Extracting the vertices of the honeycomb cell in the binarized image;
根据所述顶点与胞元的映射关系，重构得到蜂窝胞元图像；According to the mapping relationship between the vertices and the cells, reconstruct a honeycomb cell image;
计算所述蜂窝胞元图像中所有胞元角的偏差平均值，并根据所述平均值评价所述蜂窝质量。Calculate the average deviation of all cell angles in the honeycomb cell image, and evaluate the honeycomb quality according to the average.
进一步地，所述根据相机的视场范围设定相机的移动路线，使所述相机可以遍历整个蜂窝产品包括：Further, the setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product includes:
根据相机的视场范围设定相机的移动步长，所述移动步长为相邻两次拍摄的图像的间隔距离；Set the movement step length of the camera according to the camera's field of view range, where the movement step length is the distance between two adjacent images taken;
根据所述步长设定所述相机的移动路线，使所述相机可以获取整个蜂窝产品的图像。The movement route of the camera is set according to the step length, so that the camera can obtain an image of the entire cellular product.
进一步地，所述计算所述蜂窝胞元图像中所有胞元角的偏差平均值，并根据所述平均值评价所述蜂窝质量，包括：计算每张蜂窝产品局部图像中所有胞元角的偏差平均值，并将各张图像的偏差平均值再次求取平均值，将此值与预设值比较，若小于预设值，则产品合格；或将蜂窝局部图像拼接成蜂窝产品整体图像，再求取整体图像中所有胞元角的偏差平均值，将此值与预设值比较，若小于预设值则产品合格。Further, the calculating the average deviation of all cell angles in the honeycomb cell image, and evaluating the quality of the honeycomb according to the average, includes: calculating the deviation of all cell angles in the partial image of each honeycomb product Average value, and calculate the average value of the deviation of each image again, compare this value with the preset value, if it is less than the preset value, the product is qualified; or splice the partial image of the honeycomb into the overall image of the honeycomb product, and then Calculate the average deviation of all cell angles in the overall image, compare this value with the preset value, and if it is less than the preset value, the product is qualified.
进一步地，在所述获取蜂窝图像步骤之后还包括：蜂窝局部图像拼接；Further, after the step of acquiring the honeycomb image, the method further includes: mosaic partial images of the honeycomb;
所述蜂窝局部图像拼接是将相机移动拍摄得到的蜂窝产品局部照片进行拼接得整体的蜂窝图像，其中，拼接方法采用Sift或Surf算法实现。The partial honeycomb image stitching is to stitch partial photos of honeycomb products obtained by moving the camera to form an overall honeycomb image, wherein the stitching method is implemented by Sift or Surf algorithm.
进一步地，所述根据相机的视场范围设定相机的移动路线，使所述相机可以遍历整个蜂窝产品还包括：Further, the setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product further includes:
调节步长，使相邻两次拍摄的图像重合面积为单张图片的5％-10％。Adjust the step length so that the overlapping area of the two adjacent images is 5%-10% of a single image.
进一步地，所述将所述图像进行二值化处理，得到二值化图像包括：Further, the performing binarization processing on the image to obtain a binarized image includes:
将所述图像进行滤波处理去除噪声，得到去噪图像；Filtering the image to remove noise to obtain a denoised image;
将所述去噪图像进行二值化处理，得到二值化图像。The denoising image is subjected to binarization processing to obtain a binarized image.
进一步地，所述将所述去噪图像进行二值化处理，得到二值化图像包括：Further, the performing binarization processing on the denoising image to obtain a binarized image includes:
将所述去噪图像进行二值化处理，得到初始二值化图像；Performing binarization processing on the denoised image to obtain an initial binarized image;
将所述初始二值化图像进行形态学滤波处理，得到二值化图像。The initial binarized image is subjected to morphological filtering processing to obtain a binarized image.
进一步地，所述提取所述二值化图像中蜂窝胞元的顶点包括：Further, the extracting the vertices of the honeycomb cells in the binarized image includes:
在二值化图像基础上，获取蜂窝产品的骨架图；Based on the binary image, obtain the skeleton diagram of the honeycomb product;
从所述骨架图中提取出属于同一个胞元的边界像素点，得到所述胞元的所述边界像素点序列；Extracting boundary pixels belonging to the same cell from the skeleton image to obtain the sequence of boundary pixels of the cell;
分别获取与所述边界像素点对应的夹角，得到与所述边界像素点对应的所述夹角序列；所述夹角为在所述边界像素点序列中，在所述边界像素点的两侧，分别与所述边界像素点相隔第一预设值个像素的两个像素点与所述胞元边界像素点连线的夹角；Obtain the included angles corresponding to the boundary pixels to obtain the sequence of included angles corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, between two points of the boundary pixels Side, the angle between two pixel points that are separated from the boundary pixel point by a first preset value and the line connecting the cell boundary pixel point;
采用第二预设值大小的窗口，对所述夹角序列进行非极小值抑制，将除了所述窗口中夹角的最小值之外的夹角设置为第一预设夹角；Using a window with a second preset value size to perform non-minimum suppression on the included angle sequence, and set an included angle other than the minimum value of the included angle in the window as the first preset included angle;
当完成所述夹角序列的所述非极小值抑制时，确定所有所述最小值中小于第二预设夹角的夹角对应的所述边界像素点为所述顶点。When the non-minimum value suppression of the included angle sequence is completed, it is determined that the boundary pixels corresponding to the included angles that are smaller than the second preset included angle among all the minimum values are the vertices.
进一步地，还包括：计算蜂窝胞元图像中共顶点的三个胞元内角的内角偏差平均值，并根据所述内角平均值评价蜂窝质量。Further, the method further includes: calculating the average value of the internal angle deviations of the three cell internal angles of the common vertices in the honeycomb cell image, and evaluating the honeycomb quality according to the average value of the internal angles.
根据本发明的另一个方面，提供一种蜂窝质量检测装置，包括：According to another aspect of the present invention, there is provided a cellular quality detection device, including:
路线设定模块，用于根据相机的视场范围设定相机的移动路线，使所述相机可以获取整个蜂窝产品的图像；The route setting module is used to set the moving route of the camera according to the camera's field of view, so that the camera can obtain the image of the entire cellular product;
相机，用于获取蜂窝图像；Camera, used to obtain cellular images;
二值化处理模块，用于将所述蜂窝图像进行二值化处理，得到二值化图像；The binarization processing module is configured to perform binarization processing on the honeycomb image to obtain a binarized image;
顶点提取模块，用于提取所述二值化图像中蜂窝胞元的顶点；A vertex extraction module for extracting the vertices of honeycomb cells in the binarized image;
蜂窝胞元图像重构模块，用于根据所述顶点与胞元的映射关系，重构得到蜂窝胞元图像；A cellular cell image reconstruction module, configured to reconstruct a cellular cell image according to the mapping relationship between the vertices and the cells;
蜂窝质量检测模块，用于计算所述蜂窝胞元图像中所有胞元角的偏差平均值，并根据所述平均值评价所述蜂窝质量。The honeycomb quality detection module is used to calculate the average deviation of all cell angles in the cell image of the honeycomb, and evaluate the quality of the honeycomb according to the average.
进一步地，所述路线设定模块包括：Further, the route setting module includes:
步长设定单元，用于根据相机的视场范围设定相机的移动步长，所述移动步长为相邻两次拍摄的图像的间隔距离；The step size setting unit is configured to set the movement step size of the camera according to the camera's field of view range, where the movement step size is the distance between two adjacent images taken;
路线设定单元，用于根据所述步长设定所述相机的移动路线，使所述相机可以获取整个蜂窝产品的图像。The route setting unit is used to set the moving route of the camera according to the step length, so that the camera can obtain an image of the entire cellular product.
进一步地，所述路线设定模块还包括：Further, the route setting module further includes:
步长调节单元，用于调节步长，使相邻两次拍摄的图像重合面积为单张图片的5％-10％。The step length adjustment unit is used to adjust the step length so that the overlapping area of two adjacent images is 5%-10% of a single picture.
进一步地，所述二值化处理模块包括：Further, the binarization processing module includes:
图像去噪单元，用于将所述图像进行滤波处理去除噪声，得到去噪图像；An image denoising unit, configured to perform filtering processing on the image to remove noise to obtain a denoised image;
二值化处理单元，用于将所述去噪图像进行二值化处理，得到二值化图像。The binarization processing unit is configured to perform binarization processing on the denoising image to obtain a binarized image.
进一步地，所述二值化处理模块还包括：滤波单元Further, the binarization processing module further includes: a filtering unit
在所述二值化处理单元将所述去噪图像进行二值化处理，得到初始二值化图像后；After the binarization processing unit performs binarization processing on the denoised image to obtain an initial binarized image;
所述滤波单元，将所述初始二值化图像进行形态学滤波处理，得到二值化图像。The filtering unit performs morphological filtering processing on the initial binarized image to obtain a binarized image.
进一步地，所述顶点提取模块用于：Further, the vertex extraction module is used for:
在二值化图像基础上，获取蜂窝产品的骨架图；Based on the binary image, obtain the skeleton diagram of the honeycomb product;
从所述骨架图中提取出属于同一个胞元的边界像素点，得到所述胞元的所述边界像素点序列；Extracting boundary pixels belonging to the same cell from the skeleton image to obtain the sequence of boundary pixels of the cell;
分别获取与所述边界像素点对应的夹角，得到与所述边界像素点对应的所述夹角序列；所述夹角为在所述边界像素点序列中，在所述边界像素点的 两侧，分别与所述边界像素点相隔第一预设值个像素的两个像素点与所述胞元边界像素点连线的夹角；Obtain the included angles corresponding to the boundary pixels, respectively, to obtain the sequence of included angles corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, between two points of the boundary pixels Side, the angle between two pixel points that are separated from the boundary pixel point by a first preset value and the line connecting the cell boundary pixel point;
采用第二预设值大小的窗口，对所述夹角序列进行非极小值抑制，将除了所述窗口中夹角的最小值之外的夹角设置为第一预设夹角；Using a window with a second preset value size to perform non-minimum suppression on the included angle sequence, and set an included angle other than the minimum value of the included angle in the window as the first preset included angle;
当完成所述夹角序列的所述非极小值抑制时，确定所有所述最小值中小于第二预设夹角的夹角对应的所述边界像素点为所述顶点。When the non-minimum value suppression of the included angle sequence is completed, it is determined that the boundary pixels corresponding to the included angles that are smaller than the second preset included angle among all the minimum values are the vertices.
进一步地，还包括：置物台、升降装置、行走式龙门架、滑轨；Further, it also includes: a shelf, a lifting device, a walking gantry, and a slide rail;
所述置物台用于盛放待检测蜂窝，其上设置有水平度示值板；The storage table is used to hold the honeycomb to be tested, and a levelness indicator board is arranged on it;
所述升降装置与所述置物台连接，用于带动所述待检测蜂窝升降；The lifting device is connected with the placing table, and is used to drive the honeycomb to be detected up and down;
所述行走式龙门架设置在所述滑轨上，且所述行走式龙门架设置有所述图像获取模块，使所述图像获取模块可在水平方向移动。The walking gantry is arranged on the slide rail, and the walking gantry is provided with the image acquisition module so that the image acquisition module can move in a horizontal direction.
进一步地，还包括：标定模块；Further, it also includes: a calibration module;
所述标定模块与所述置物台配合使用，用于校核检测装置的准确性。The calibration module is used in conjunction with the stage to check the accuracy of the detection device.
进一步地，所述蜂窝质量检测模块，还用于计算蜂窝胞元图像中共顶点的三个胞元内角的内角偏差平均值，并根据所述内角平均值评价蜂窝质量。Further, the honeycomb quality detection module is also used to calculate the average value of the internal angle deviations of the three internal angles of the common vertices in the honeycomb cell image, and evaluate the honeycomb quality according to the average value of the internal angles.
根据本发明的又一方面，提供一种储存介质，所述存储介质上存储有计算机程序，所述程序被处理器执行时实现上述技术方案中任意一项所述方法的步骤。According to another aspect of the present invention, a storage medium is provided, and a computer program is stored on the storage medium, and when the program is executed by a processor, the steps of the method described in any one of the above technical solutions are implemented.
根据本发明的又一方面，提供一种电子设备，包括存储器、显示器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现上述技术方案中任意一项所述方法的步骤。According to yet another aspect of the present invention, there is provided an electronic device including a memory, a display, a processor, and a computer program stored on the memory and running on the processor, and when the processor executes the program The steps of the method described in any one of the above technical solutions are implemented.
(三)有益效果(3) Beneficial effects
本发明的上述技术方案具有如下有益的技术效果：The above technical solution of the present invention has the following beneficial technical effects:
通过本发明方法及装置对蜂窝图像处理得到胞元角的偏差平均值，偏差平均值越小，说明胞元越规整，在这里可以引入一个规整度的概念，就是蜂窝越接近整六边形，规整度就越高；通过实验也证明了，规整度越高的蜂窝产品刚度和强度都越好，即蜂窝产品的质量越好，因此，本发明通过简单的 操作处理即可判断出蜂窝产品的质量，适于生产线上蜂窝产品质量的检测。By processing the honeycomb image by the method and device of the present invention, the average deviation of the cell angle is obtained. The smaller the deviation average, the more regular the cells are. Here, a concept of regularity can be introduced, that is, the closer the honeycomb is to a full hexagon, The higher the regularity; experiments have also proved that the higher the regularity of the honeycomb product, the better the stiffness and strength, that is, the better the quality of the honeycomb product. Therefore, the present invention can determine the honeycomb product through simple operation and processing. Quality, suitable for testing the quality of honeycomb products on the production line.
附图说明Description of the drawings
图1是根据本发明第一实施方式的超大面积蜂窝产品规整度的移动式检测方法流程图；Fig. 1 is a flow chart of a mobile inspection method for regularity of a super-large-area honeycomb product according to a first embodiment of the present invention;
图2是根据本发明一具体实施方式的蜂窝胞元规整度的移动相机式检测方法流程图；2 is a flow chart of a mobile camera-style detection method for cell regularity according to a specific embodiment of the present invention;
图3是根据本发明一具体实施方式的相机移动拍摄示意图；Fig. 3 is a schematic diagram of camera movement shooting according to an embodiment of the present invention;
图4是根据本发明一可选实施方式的蜂窝产品质量检测装置的俯视图；4 is a top view of a honeycomb product quality inspection device according to an alternative embodiment of the present invention;
图5是根据本发明一可选实施方式的蜂窝产品质量检测装置的主视图。Fig. 5 is a front view of a honeycomb product quality inspection device according to an alternative embodiment of the present invention.
附图标记：Reference signs:
1：置物台；2：数码相机；3：控制系统；4：升降装置；5：夹具；6：行走式龙门架；7：滑轨；8：移动装置。1: Storage table; 2: Digital camera; 3: Control system; 4: Lifting device; 5: Fixture; 6: Walking gantry; 7: Slide rail; 8: Mobile device.
具体实施方式Detailed ways
为使本发明的目的、技术方案和优点更加清楚明了，下面结合具体实施方式并参照附图，对本发明进一步详细说明。应该理解，这些描述只是示例性的，而并非要限制本发明的范围。此外，在以下说明中，省略了对公知结构和技术的描述，以避免不必要地混淆本发明的概念。In order to make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings. It should be understood that these descriptions are only exemplary, and are not intended to limit the scope of the present invention. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concept of the present invention.
显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.
此外，下面所描述的本发明不同实施方式中所涉及的技术特征只要彼此之间未构成冲突就可以相互结合。In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
如图1所示，本发明的第一方面提供了一种超大面积蜂窝产品规整度的移动式检测方法，包括：As shown in Figure 1, the first aspect of the present invention provides a mobile inspection method for the regularity of ultra-large-area honeycomb products, including:
S1：根据相机的视场范围设定相机的移动路线，使相机可以获取整个蜂 窝产品的图像；S1: Set the camera's moving route according to the camera's field of view, so that the camera can obtain the image of the entire honeycomb product;
S2：获取蜂窝图像；S2: Obtain a honeycomb image;
S3：将蜂窝图像进行二值化处理，得到二值化图像；S3: Binarize the honeycomb image to obtain a binary image;
S4：提取二值化图像中蜂窝胞元的顶点；S4: Extract the vertices of the honeycomb cell in the binarized image;
S5：根据顶点与胞元的映射关系，重构得到蜂窝胞元图像；S5: According to the mapping relationship between the vertices and the cells, reconstruct the image of the honeycomb cell;
S6：计算蜂窝胞元图像中所有胞元角的偏差平均值，并根据平均值评价蜂窝质量。S6: Calculate the average deviation of all cell angles in the honeycomb cell image, and evaluate the honeycomb quality based on the average.
在本发明实施例中，根据相机的视场范围设定相机的移动路线，使相机可以遍历整个蜂窝产品包括：根据相机的视场范围设定相机的移动步长，移动步长为相邻两次拍摄的图像的间隔距离；根据步长设定相机的移动路线，使相机可以获取整个蜂窝产品的图像。In the embodiment of the present invention, setting the camera's moving route according to the camera's field of view so that the camera can traverse the entire cellular product includes: setting the camera's moving step according to the camera's field of view, and the moving step is two adjacent ones. The distance between the images taken in the second time; the camera's moving route is set according to the step length, so that the camera can obtain the image of the entire cellular product.
在本发明实施例中，根据相机的视场范围设定相机的移动路线，使相机可以遍历整个蜂窝产品还包括：调节步长，使相邻两次拍摄的图像重合面积为单张图片的5％-10％。In the embodiment of the present invention, setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product also includes: adjusting the step length so that the overlapping area of the two adjacent images is 5 of that of a single picture. %-10%.
在本发明实施例中，计算蜂窝胞元图像中所有胞元角的偏差平均值，并根据平均值评价蜂窝质量，包括：计算每张蜂窝产品局部图像中所有胞元角的偏差平均值，并将各张图像的偏差平均值再次求取平均值，将此值与预设值比较，若小于预设值，则产品合格；或将蜂窝局部图像拼接成蜂窝产品整体图像，再求取整体图像中所有胞元角的偏差平均值，将此值与预设值比较，若小于预设值则产品合格。In the embodiment of the present invention, calculating the average deviation of all cell angles in the honeycomb cell image, and evaluating the honeycomb quality according to the average, includes: calculating the average deviation of all cell angles in the partial image of each honeycomb product, and Calculate the average value of the deviation of each image again, compare this value with the preset value, if it is less than the preset value, the product is qualified; or stitch the partial image of the honeycomb into the overall image of the honeycomb product, and then obtain the overall image The average value of the deviation of all cell angles in the cell, compare this value with the preset value, if it is less than the preset value, the product is qualified.
在本发明实施例中，在获取蜂窝图像步骤之后还包括：蜂窝局部图像拼接；蜂窝局部图像拼接是将相机移动拍摄得到的蜂窝产品局部照片进行拼接得整体的蜂窝图像，其中，拼接方法采用Sift或Surf算法实现。In the embodiment of the present invention, after the step of acquiring the honeycomb image, the method further includes: honeycomb partial image stitching; honeycomb partial image stitching is to stitch partial photos of the honeycomb product obtained by moving the camera to form an overall honeycomb image, wherein the stitching method adopts Sift Or Surf algorithm implementation.
在本发明实施例中，将图像进行二值化处理，得到二值化图像包括：将图像进行滤波处理去除噪声，得到去噪图像；将去噪图像进行二值化处理，得到二值化图像。In the embodiment of the present invention, binarizing an image to obtain a binarized image includes: filtering the image to remove noise to obtain a denoised image; binarizing the denoised image to obtain a binarized image .
在本发明实施例中，将去噪图像进行二值化处理，得到二值化图像包括： 将去噪图像进行二值化处理，得到初始二值化图像；将初始二值化图像进行形态学滤波处理，得到二值化图像。In the embodiment of the present invention, performing binarization processing on the denoised image to obtain a binarized image includes: performing binarization processing on the denoised image to obtain an initial binarized image; performing morphology on the initial binarized image Filter processing to obtain a binarized image.
在本发明实施例中，提取二值化图像中蜂窝胞元的顶点包括：将二值化图像进行闭运算处理，得到平滑蜂窝顶点图像；在平滑蜂窝顶点图像上进行蜂窝壁取最大圆圆心处理，得到蜂窝胞元的顶点。In the embodiment of the present invention, extracting the vertices of the honeycomb cells in the binarized image includes: closing the binarized image to obtain a smooth honeycomb vertex image; processing the honeycomb wall to take the largest circle center on the smooth honeycomb vertex image , Get the apex of the honeycomb cell.
在本发明实施例中，提取二值化图像中蜂窝胞元的顶点包括：在二值化图像基础上，获取蜂窝产品的骨架图；从骨架图中提取出属于同一个胞元的边界像素点，得到胞元的边界像素点序列；分别获取与边界像素点对应的夹角，得到与边界像素点对应的夹角序列；夹角为在边界像素点序列中，在边界像素点的两侧，分别与边界像素点相隔第一预设值个像素的两个像素点与胞元边界像素点连线的夹角；采用第二预设值大小的窗口，对夹角序列进行非极小值抑制，将除了窗口中夹角的最小值之外的夹角设置为第一预设夹角；当完成夹角序列的非极小值抑制时，确定所有最小值中小于第二预设夹角的夹角对应的边界像素点为顶点。In the embodiment of the present invention, extracting the vertices of the honeycomb cell in the binarized image includes: obtaining a skeleton diagram of the honeycomb product based on the binarized image; and extracting boundary pixels belonging to the same cell from the skeleton diagram , Get the boundary pixel sequence of the cell; respectively obtain the angles corresponding to the boundary pixels, and obtain the angle sequence corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, on both sides of the boundary pixels, The included angle between two pixels that are separated from the boundary pixel by a first preset value and the line of the cell boundary pixel; the second preset size window is used to suppress the included angle sequence by non-minimal value , Set the included angle other than the minimum value of the included angle in the window as the first preset included angle; when the non-minimum value suppression of the included angle sequence is completed, determine that the minimum value is less than the second preset included angle The boundary pixels corresponding to the included angles are the vertices.
如图2所示，在本发明一具体实施例中，提供一种蜂窝胞元规整度的移动相机式检测方法，方法包括以下步骤：相机设定、获取图像、图像处理、顶点提取、胞元重构、质量评估；As shown in FIG. 2, in a specific embodiment of the present invention, a mobile camera-style detection method for cell regularity is provided. The method includes the following steps: camera setting, image acquisition, image processing, vertex extraction, cell Reconstruction, quality assessment;
1、“相机设定”包括设定相机移动步长及路线，设定好后，相机沿指定路线以一个步长为单位进行移动，每移动一步进行一次拍摄：根据产品尺寸及相机视场大小设定相机X向及Y向移动步长，保证相邻照片的重叠区域面积为单张照片的5％-10％；设定相机依次沿X轴及Y轴移动的路线，保证相机最终能完全遍历整个蜂窝产品，如图3所示；1. "Camera setting" includes setting the camera movement step length and route. After setting, the camera moves along the specified route in a unit of step length. One shot is taken for each movement step: according to the product size and the camera's field of view size Set the camera's X- and Y-direction movement steps to ensure that the overlapping area of adjacent photos is 5%-10% of a single photo; set the route of the camera moving along the X-axis and Y-axis to ensure that the camera can finally be completely Traverse the entire honeycomb product, as shown in Figure 3;
2、“获取图像”包括拍摄图像和计算机读取图像；2. "Acquisition of images" includes photographed images and computer-read images;
3、“图像处理”顺序包括：图像拼接、降噪滤波、二值化、形态学滤波，获得形态图像；3. The "image processing" sequence includes: image stitching, noise reduction filtering, binarization, morphological filtering, to obtain morphological images;
3.1、“图像拼接”是将相机移动拍摄得到的蜂窝产品局部照片进行拼接 得到蜂窝产品的整体照片，采用Sift或Surf算法实现；3.1. "Image stitching" is to stitch the partial photos of the honeycomb product taken by the camera moving to obtain the overall photo of the honeycomb product, which is realized by the Sift or Surf algorithm;
3.2、“降噪滤波”是采用中值滤波法滤除图像的噪声；3.2. "Noise reduction filter" is to use median filter method to filter out the noise of the image;
3.3、“二值化”：将产品轮廓图像的像素值置为1，将产品的背景图像的像素值置为0；3.3. "Binarization": Set the pixel value of the product outline image to 1, and set the pixel value of the product background image to 0;
3.4、“形态学滤波”是消除面积小于给定阈值的像素，降低二值化带来的误差；3.4. "Morphological filtering" is to eliminate pixels whose area is less than a given threshold and reduce the error caused by binarization;
4、“顶点提取”是在“图像处理”的基础上寻找胞元的顶点并记录；4. "Vertex extraction" is to find and record the vertices of the cell on the basis of "image processing";
4.1、“顶点提取”的第一种方法：采用遍历图像后其内最小的像素值为0的像素数大于0的最小窗口作为统计窗口，采用该窗口再次遍历图像，将窗口内的像素值为1的像素数赋给窗口中心点上，提取像素值为1的像素数最大值的点，将其记录为顶点，采用边长等于胞元边长的湮灭窗口，将该点为中心的湮灭窗口内的像素值为1的像素数置0，再次提取像素值为1的像素数最大值的点并记录，不断重复这个步骤，直到像素值为1的像素数小于给定阈值，则顶点提取完毕；4.1. The first method of "vertex extraction": After traversing the image, the smallest window in which the smallest pixel value is 0 and the number of pixels greater than 0 is used as the statistical window, and the window is used to traverse the image again, and the pixel value in the window is Assign a pixel number of 1 to the center point of the window, extract the point with the maximum pixel number of pixel value 1, record it as a vertex, use an annihilation window with a side length equal to the side length of the cell, and use this point as the center annihilation window The number of pixels with a pixel value of 1 is set to 0, and the point with the maximum value of the pixel with a pixel value of 1 is extracted and recorded. Repeat this step until the number of pixels with a pixel value of 1 is less than the given threshold, then the vertex extraction is completed ；
4.2、“顶点提取”的第二种方法的第一步进行骨架化处理，“骨架化”是以形态图像为基础，将像素值为1的线条采用线宽为1个像素的线段绘制骨架图；第二步采用5×5个像素的窗口计算每个像素点的角点响应函数值R，对于其R值大于所有像素点的最大R值的1％且是以其为中心的3×3邻域的最大值的像素点，提取其坐标并记录为顶点；4.2. The first step of the second method of "vertex extraction" is the skeletonization process. The "skeletonization" is based on the morphological image, and the line with the pixel value of 1 is drawn by the line segment with the line width of 1 pixel. ; The second step uses a window of 5×5 pixels to calculate the corner response function value R of each pixel, for which the R value is greater than 1% of the maximum R value of all pixels and is 3×3 centered on it The pixel with the maximum value of the neighborhood is extracted and its coordinates are recorded as vertices;
4.3、“顶点提取”的第三种方法第一步进行骨架化处理；第二步是在骨架图的基础上，对所有像素值为1的像素点，顺时针或逆时针依次统计其八邻域像素值的变化次数，若遇到变化次数为6，或变化次数为4且该像素点与其八邻域的另两点不在同一条直线上的像素点，则提取其坐标并记录为顶点；4.3. The third method of "vertex extraction" The first step is to carry out skeletonization processing; the second step is to count all the pixels with the pixel value of 1 clockwise or counterclockwise on the basis of the skeleton diagram. The number of changes in the pixel value of the domain. If the number of changes is 6, or the number of changes is 4, and the pixel is not on the same straight line with the other two points in its eight neighborhood, the coordinates are extracted and recorded as vertices;
5、“胞元重构”是将提取的顶点依据胞元与顶点的映射关系连线，得到胞元重构图；5. "Cell reconstruction" is to connect the extracted vertices according to the mapping relationship between cells and vertices to obtain a cell reconstruction graph;
5.1、“胞元重构”的第一种方法：遍历图像，遇到像素值为0的像素点， 则采用摩尔邻域追踪算法进行边界追踪，并以每个边界点为中心做一个窗口，判断该窗口内有无顶点，若有则记录其编号并依次为其标记序号，遇到该胞元的起始追踪像素时，停止追踪并将该胞元的像素值置为1，再次重复上述过程，直到不再存在像素值为0的点，将各胞元的顶点按序号依次连线完成胞元的重构；5.1. The first method of "cell reconstruction": traverse the image and encounter a pixel with a pixel value of 0, then use the Moore neighborhood tracking algorithm for boundary tracking, and make a window with each boundary point as the center. Determine whether there are vertices in the window, if there are vertices, record their numbers and mark them sequentially. When encountering the starting tracking pixel of the cell, stop tracking and set the pixel value of the cell to 1, and repeat the above In the process, until there is no point with a pixel value of 0, the vertices of each cell are connected in sequence to complete the reconstruction of the cell;
5.2、“胞元重构”的第二种方法：对于每个顶点，计算其余所有顶点与它的距离，选取距离最近的三点并记录，计算所有顶点与最近三点的距离并求和，除以顶点数的两倍，得到平均蜂窝胞元边长A，选取位于图像边缘向内1A～2A宽度之外区域的顶点，对于其中的每个顶点，分别与最近的三点进行连线，从而得到蜂窝的重构图像；5.2. The second method of "cell reconstruction": For each vertex, calculate the distance between all other vertices and it, select the three nearest points and record, calculate the distance between all vertices and the nearest three points, and sum them. Divide by twice the number of vertices to get the average honeycomb cell side length A. Select the vertices located in the area outside the 1A～2A width of the image edge. For each of the vertices, connect to the nearest three points respectively. So as to obtain the reconstructed image of the honeycomb;
6、“质量评估”是以当前的胞元重构图为基础，第一步计算：即：计算出所有胞元的角偏差值及其总的平均值、线偏差值及其总的平均值；第二步判断：即：与设置的公差带相比较，落在公差带范围内的判定为合格，否则判定为不合格。6. "Quality evaluation" is based on the current cell reconstruction graph. The first step is to calculate: calculate the angular deviation value of all cells and its total average value, line deviation value and its total average value ; The second step of judgment: That is, compared with the set tolerance zone, the one that falls within the tolerance zone is judged as qualified, otherwise it is judged as unqualified.
在本发明实施例中，还包括：计算蜂窝胞元图像中共顶点的三个胞元内角的内角偏差平均值，并根据内角平均值评价蜂窝质量。In the embodiment of the present invention, the method further includes: calculating the average value of the internal angle deviations of the three cell internal angles of the common vertices in the honeycomb cell image, and evaluating the honeycomb quality according to the average value of the internal angles.
在本发明实施例的另一个方面，提供一种蜂窝质量检测装置，包括：路线设定模块，用于根据相机的视场范围设定相机的移动路线，使相机可以获取整个蜂窝产品的图像；相机，用于获取蜂窝图像；二值化处理模块，用于将蜂窝图像进行二值化处理，得到二值化图像；顶点提取模块，用于提取二值化图像中蜂窝胞元的顶点；蜂窝胞元图像重构模块，用于根据顶点与胞元的映射关系，重构得到蜂窝胞元图像；蜂窝质量检测模块，用于计算蜂窝胞元图像中所有胞元角的偏差平均值，并根据平均值评价蜂窝质量。In another aspect of the embodiments of the present invention, there is provided a cellular quality detection device, including: a route setting module, configured to set a movement route of the camera according to the camera's field of view range, so that the camera can obtain an image of the entire cellular product; The camera is used to obtain the honeycomb image; the binarization processing module is used to binarize the honeycomb image to obtain the binarized image; the vertex extraction module is used to extract the vertices of the honeycomb cells in the binarized image; the honeycomb The cell image reconstruction module is used to reconstruct the honeycomb cell image according to the mapping relationship between the vertices and the cells; the honeycomb quality detection module is used to calculate the average deviation of all the cell angles in the honeycomb cell image, and according to The average value evaluates the honeycomb quality.
在本发明实施例中，路线设定模块包括：步长设定单元，用于根据相机的视场范围设定相机的移动步长，移动步长为相邻两次拍摄的图像的间隔距离；路线设定单元，用于根据步长设定相机的移动路线，使相机可以获取整个蜂窝产品的图像。In the embodiment of the present invention, the route setting module includes: a step length setting unit for setting the movement step length of the camera according to the camera's field of view range, and the movement step length is the distance between two adjacent images taken; The route setting unit is used to set the moving route of the camera according to the step length, so that the camera can obtain the image of the entire cellular product.
在本发明实施例中，路线设定模块还包括：步长调节单元，用于调节步长，使相邻两次拍摄的图像重合面积为单张图片的5％-10％。In the embodiment of the present invention, the route setting module further includes: a step length adjustment unit for adjusting the step length so that the overlapping area of the images taken twice adjacently is 5%-10% of a single picture.
在本发明实施例中，二值化处理模块包括：图像去噪单元，用于将图像进行滤波处理去除噪声，得到去噪图像；二值化处理单元，用于将去噪图像进行二值化处理，得到二值化图像。In the embodiment of the present invention, the binarization processing module includes: an image denoising unit for filtering the image to remove noise to obtain a denoised image; a binarization processing unit for binarizing the denoised image Processing to obtain a binarized image.
在本发明实施例中，二值化处理模块还包括：滤波单元；在二值化处理单元将去噪图像进行二值化处理，得到初始二值化图像后；滤波单元，将初始二值化图像进行形态学滤波处理，得到二值化图像。In the embodiment of the present invention, the binarization processing module further includes: a filtering unit; the denoising image is binarized in the binarization processing unit to obtain the initial binarized image; the filtering unit is used to binarize the initial The image undergoes morphological filtering to obtain a binary image.
在本发明实施例中，顶点提取模块包括：闭运算处理单元，用于将二值化图像进行闭运算处理，得到平滑蜂窝顶点图像；顶点提取单元，用于在平滑蜂窝顶点图像上进行蜂窝壁取最大圆圆心处理，得到蜂窝胞元的顶点。In the embodiment of the present invention, the vertex extraction module includes: a closed operation processing unit for performing closed operation processing on the binarized image to obtain a smooth honeycomb vertex image; a vertex extraction unit for performing a honeycomb wall on the smooth honeycomb vertex image Take the center of the largest circle to get the apex of the honeycomb cell.
在本发明实施例中，顶点提取模块包括：闭运算处理单元，用于将二值化图像进行闭运算处理，得到平滑蜂窝顶点图像；蜂窝壁交汇处提取单元，用于将平滑蜂窝顶点图像依次经过膨胀处理和腐蚀处理，得到只有蜂窝壁交汇处图像；顶点提取单元，用于在蜂窝壁交汇处图像上进行蜂窝壁取最大圆圆心处理，得到蜂窝胞元的顶点。In the embodiment of the present invention, the vertex extraction module includes: a closed operation processing unit for performing closed operation processing on the binarized image to obtain a smooth honeycomb vertex image; a honeycomb wall intersection extraction unit for sequentially extracting the smooth honeycomb vertex image After expansion and corrosion processing, only the image of the intersection of the honeycomb wall is obtained; the vertex extraction unit is used for processing the maximum circle center of the honeycomb wall on the image of the intersection of the honeycomb wall to obtain the apex of the honeycomb cell.
在本发明实施例中，顶点提取模块具体用于：在二值化图像基础上，获取蜂窝产品的骨架图；从骨架图中提取出属于同一个胞元的边界像素点，得到胞元的边界像素点序列；分别获取与边界像素点对应的夹角，得到与边界像素点对应的夹角序列；夹角为在边界像素点序列中，在边界像素点的两侧，分别与边界像素点相隔第一预设值个像素的两个像素点与胞元边界像素点连线的夹角；采用第二预设值大小的窗口，对夹角序列进行非极小值抑制，将除了窗口中夹角的最小值之外的夹角设置为第一预设夹角；当完成夹角序列的非极小值抑制时，确定所有最小值中小于第二预设夹角的夹角对应的边界像素点为顶点。In the embodiment of the present invention, the vertex extraction module is specifically used to: obtain the skeleton image of the honeycomb product on the basis of the binary image; extract the boundary pixels belonging to the same cell from the skeleton image to obtain the boundary of the cell Pixel sequence; respectively obtain the angles corresponding to the boundary pixels, and obtain the angle sequence corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, on both sides of the boundary pixels, and are separated from the boundary pixels. The included angle between the two pixels of the first preset value of pixels and the boundary pixel of the cell; using a window of the second preset size, the included angle sequence is suppressed by non-minimum values, except for the clip in the window The included angle outside the minimum value of the angle is set as the first preset included angle; when the non-minimum value suppression of the included angle sequence is completed, determine the boundary pixels corresponding to the included angle of all the minimum values that are smaller than the second preset included angle Points are vertices.
在本发明实施例中，还包括：置物台、升降装置、行走式龙门架、滑轨；置物台用于盛放待检测蜂窝，其上设置有水平度示值板；升降装置与置物台 连接，用于带动待检测蜂窝升降；行走式龙门架设置在滑轨上，且行走式龙门架设置有图像获取模块，使图像获取模块可在水平方向移动。In the embodiment of the present invention, it further includes: a storage table, a lifting device, a walking gantry, and a slide rail; the storage table is used to hold the honeycomb to be inspected, and a levelness indicator board is arranged on it; the lifting device is connected to the storage table , Used to drive the honeycomb to be detected up and down; the walking gantry is arranged on the slide rail, and the walking gantry is provided with an image acquisition module so that the image acquisition module can move in the horizontal direction.
在本发明实施例中，还包括：标定模块；标定模块与置物台配合使用，用于校核检测装置的准确性。In the embodiment of the present invention, it further includes: a calibration module; the calibration module is used in conjunction with the stage to check the accuracy of the detection device.
如图4-5所示，在本发明一具体实施例中，提供一种蜂窝胞元规整度的移动相机式检测系统，包括置物台、数码相机、控制系统、升降装置、夹具、行走式龙门架、滑轨、移动装置和标定模块；数码相机和控制系统相连接；置物台上设置水平调节装置和水平度示值板，夹具靠近蜂窝一侧均涂成亮黄色，辅助图像处理；数码相机至少为一台，其分辨率不低于1080P，配置远心镜头，以得到高分辨率的蜂窝产品照片，且减小其在景深范围内的畸变；其安装方式为固定式或/和移动式；数码相机为一台时，安装方式有固定式或移动式；数码相机阵列为多台时，安装方式为固定式；升降装置包括置物台、导轨、电动推杆或电液推杆，置物台用于放置被测蜂窝件，其可在电动推杆或电液推杆的驱动下沿导轨上下移动，调节被测蜂窝件的高度，以保证被测蜂窝件的上端面与夹具的上端面平齐；夹具由四块平板及驱动装置组成，可在驱动装置的作用下向被测蜂窝件靠拢，靠紧被测蜂窝件后锁死，用于定位及固定被测蜂窝件。As shown in Figure 4-5, in a specific embodiment of the present invention, a mobile camera-type detection system for cell regularity is provided, which includes a table, a digital camera, a control system, a lifting device, a fixture, and a walking gantry. Frame, slide rail, moving device and calibration module; digital camera and control system are connected; level adjustment device and level indicator board are set on the stage, and the side of the fixture near the honeycomb is painted bright yellow to assist in image processing; the digital camera is at least One, with a resolution of not less than 1080P, equipped with a telecentric lens to obtain high-resolution cellular product photos and reduce its distortion in the depth of field; its installation method is fixed or/and mobile; digital When there is one camera, the installation method can be fixed or mobile; when the digital camera array is multiple, the installation method is fixed; the lifting device includes a storage table, a guide rail, an electric push rod or an electro-hydraulic push rod, and the storage table is used for Place the tested honeycomb part, which can be moved up and down along the guide rail under the drive of an electric push rod or an electro-hydraulic push rod to adjust the height of the tested honeycomb part to ensure that the upper end surface of the tested honeycomb part is flush with the upper end surface of the fixture; The clamp is composed of four plates and a driving device, which can be moved closer to the tested honeycomb part under the action of the driving device, and locked after being close to the tested honeycomb part for positioning and fixing the tested honeycomb part.
数码相机安装在行走式龙门架的横梁上，可在移动装置的驱动下沿横梁横向移动；行走式龙门架可在移动装置的驱动下沿滑轨纵向移动，数码相机及行走式龙门架的移动均由控制系统控制。The digital camera is installed on the beam of the walking gantry, which can be moved horizontally along the beam under the drive of the mobile device; the walking gantry can be moved longitudinally along the slide rail under the drive of the mobile device, and the movement of the digital camera and the walking gantry All are controlled by the control system.
控制系统包括系统控制模块、计算分析模块及结果示值模块；控制模块控制系统启停及升降装置、相机移动装置的运动；计算分析模块采用相应分析软件对数码相机采集的照片进行分析，计算出蜂窝样品的几何规整度，并根据选定的评估标准及阈值对蜂窝样品的几何规整度进行评估，将评估结果传递给结果示值模块，由结果示值模块进行结果显示；结果示值模块可根据产品质量评定结果进行显示，质量合格显示绿灯，不合格显示红灯。The control system includes a system control module, a calculation and analysis module, and a result display module; the control module controls the start and stop of the system, the movement of the lifting device, and the camera moving device; the calculation and analysis module uses the corresponding analysis software to analyze the photos collected by the digital camera and calculates The geometric regularity of the honeycomb sample is evaluated, and the geometric regularity of the honeycomb sample is evaluated according to the selected evaluation standard and threshold, and the evaluation result is passed to the result display module, and the result display module can display the result; the result display module can According to the product quality assessment results, the green light is displayed for qualified quality, and the red light is displayed for unqualified.
标定模块：标定板为一个采用电子墨水屏的显示板，可显示边长、壁厚 可调的标准蜂窝，屏幕外侧显示与蜂窝成对比色的颜色。将该标定板放置于置物台并用夹具定位后，调整数码相机至合适位置，获取该标定板的照片，传递给控制系统的软件进行标定，校核系统的检测准确性。Calibration module: The calibration board is a display board with an electronic ink screen that can display standard honeycombs with adjustable side lengths and wall thicknesses. The outside of the screen displays a color that contrasts with the honeycombs. After placing the calibration board on the stage and positioning it with a fixture, adjust the digital camera to a suitable position, obtain a photo of the calibration board, and pass it to the software of the control system for calibration, and check the detection accuracy of the system.
在本发明实施例中，蜂窝质量检测模块，还用于计算蜂窝胞元图像中共顶点的三个胞元内角的内角偏差平均值，并根据内角平均值评价蜂窝质量。In the embodiment of the present invention, the honeycomb quality detection module is also used to calculate the average value of the internal angle deviations of the three internal angles of the common vertices in the honeycomb cell image, and evaluate the honeycomb quality according to the average value of the internal angles.
在本发明实施例的又一方面，提供一种储存介质，存储介质上存储有计算机程序，程序被处理器执行时实现上述技术方案中任意一项方法的步骤。In another aspect of the embodiments of the present invention, a storage medium is provided, and a computer program is stored on the storage medium, and when the program is executed by a processor, the steps of any one of the above technical solutions are implemented.
在本发明实施例的又一方面，提供一种电子设备，包括存储器、显示器、处理器及存储在存储器上并可在处理器上运行的计算机程序，处理器执行程序时实现上述技术方案中任意一项方法的步骤。In yet another aspect of the embodiments of the present invention, an electronic device is provided, including a memory, a display, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the program, any of the above technical solutions is implemented. Steps of a method.
本发明旨在保护一种超大面积蜂窝产品规整度的移动式检测方法，包括：根据相机的视场范围设定相机的移动路线，使相机可以获取整个蜂窝产品的图像；获取蜂窝图像；将蜂窝图像进行二值化处理，得到二值化图像；提取二值化图像中蜂窝胞元的顶点；根据顶点与胞元的映射关系，重构得到蜂窝胞元图像；计算蜂窝胞元图像中所有胞元角的偏差平均值，并根据平均值评价蜂窝质量。该方法新颖、高效，对于面积较大的蜂窝产品，可是实现几何规整性的快速检测。The present invention aims to protect a mobile inspection method for the regularity of a super-large-area honeycomb product. The image is binarized to obtain a binarized image; the vertices of the honeycomb cell in the binarized image are extracted; the honeycomb cell image is reconstructed according to the mapping relationship between the vertices and the cells; all the cells in the honeycomb cell image are calculated The average value of the deviation of the element angle, and the honeycomb quality is evaluated based on the average value. The method is novel and efficient. For honeycomb products with a large area, it can realize rapid detection of geometric regularity.
应当理解的是，本发明的上述具体实施方式仅仅用于示例性说明或解释本发明的原理，而不构成对本发明的限制。因此，在不偏离本发明的精神和范围的情况下所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。此外，本发明所附权利要求旨在涵盖落入所附权利要求范围和边界、或者这种范围和边界的等同形式内的全部变化和修改例。It should be understood that the above-mentioned specific embodiments of the present invention are only used to exemplarily illustrate or explain the principle of the present invention, and do not constitute a limitation to the present invention. Therefore, any modifications, equivalent substitutions, improvements, etc. made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modifications that fall within the scope and boundary of the appended claims, or equivalent forms of such scope and boundary.

Claims (13)

  1. 一种超大面积蜂窝产品规整度的移动式检测方法，其特征在于，包括：A mobile inspection method for the regularity of ultra-large-area honeycomb products, which is characterized in that it includes:
    根据相机的视场范围设定相机的移动路线，使所述相机可以获取整个蜂窝产品的图像；Set the camera's moving route according to the camera's field of view, so that the camera can acquire the image of the entire cellular product;
    获取蜂窝图像；Obtain a honeycomb image;
    将所述蜂窝图像进行二值化处理，得到二值化图像；Performing binarization processing on the honeycomb image to obtain a binarized image;
    提取所述二值化图像中蜂窝胞元的顶点；Extracting the vertices of the honeycomb cell in the binarized image;
    根据所述顶点与胞元的映射关系，重构得到蜂窝胞元图像；According to the mapping relationship between the vertices and the cells, reconstruct a honeycomb cell image;
    计算所述蜂窝胞元图像中所有胞元角的偏差平均值，并根据所述平均值评价所述蜂窝质量。Calculate the average deviation of all cell angles in the honeycomb cell image, and evaluate the honeycomb quality according to the average.
  2. 根据权利要求1所述的方法，其特征在于，所述根据相机的视场范围设定相机的移动路线，使所述相机可以遍历整个蜂窝产品包括：The method according to claim 1, wherein the setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product comprises:
    根据相机的视场范围设定相机的移动步长，所述移动步长为相邻两次拍摄的图像的间隔距离；Set the movement step length of the camera according to the camera's field of view range, where the movement step length is the distance between two adjacent images taken;
    根据所述步长设定所述相机的移动路线，使所述相机可以获取整个蜂窝产品的图像。The movement route of the camera is set according to the step length, so that the camera can obtain an image of the entire cellular product.
  3. 根据权利要求2所述的方法，其特征在于，所述根据相机的视场范围设定相机的移动路线，使所述相机可以遍历整个蜂窝产品还包括：The method according to claim 2, wherein the setting the movement route of the camera according to the camera's field of view so that the camera can traverse the entire cellular product further comprises:
    调节步长，使相邻两次拍摄的图像重合面积为单张图片的5％-10％。Adjust the step length so that the overlapping area of the two adjacent images is 5%-10% of a single image.
  4. 根据权利要求1所述的方法，其特征在于，所述计算所述蜂窝胞元图像中所有胞元角的偏差平均值，并根据所述平均值评价所述蜂窝质量，包括：计算每张蜂窝产品局部图像中所有胞元角的偏差平均值，并将各张图像的偏差平均值再次求取平均值，将此值与预设值比较，若小于预设值，则产品合格；或将蜂窝局部图像拼接成蜂窝产品整体图像，再求取整体图像中所有胞元角的偏差平均值，将此值与预设值比较，若小于预设 值则产品合格。The method according to claim 1, wherein the calculating the average value of the deviation of all the cell angles in the cell image of the honeycomb, and evaluating the quality of the honeycomb according to the average value, comprises: calculating each honeycomb The average value of the deviation of all cell angles in the partial image of the product, and the average value of the deviation of each image is calculated again, and the value is compared with the preset value. If it is less than the preset value, the product is qualified; or the honeycomb The partial images are spliced into the overall image of the honeycomb product, and then the average deviation of all cell angles in the overall image is calculated, and this value is compared with the preset value. If it is less than the preset value, the product is qualified.
  5. 根据权利要求4所述的方法，其特征在于，The method of claim 4, wherein:
    所述蜂窝局部图像拼接是将相机移动拍摄得到的蜂窝产品局部照片进行拼接得整体的蜂窝图像，其中，拼接方法采用Sift或Surf算法实现。The partial honeycomb image stitching is to stitch partial photos of honeycomb products obtained by moving the camera to form an overall honeycomb image, wherein the stitching method is implemented by Sift or Surf algorithm.
  6. 根据权利要求1所述的评价方法，其特征在于，所述将所述图像进行二值化处理，得到二值化图像包括：The evaluation method according to claim 1, wherein the performing binarization processing on the image to obtain a binarized image comprises:
    将所述图像进行滤波处理去除噪声，得到去噪图像；Filtering the image to remove noise to obtain a denoised image;
    将所述去噪图像进行二值化处理，得到二值化图像。The denoising image is subjected to binarization processing to obtain a binarized image.
  7. 根据权利要求6所述的评价方法，其特征在于，所述将所述去噪图像进行二值化处理，得到二值化图像包括：The evaluation method according to claim 6, wherein the binarizing the denoised image to obtain the binarized image comprises:
    将所述去噪图像进行二值化处理，得到初始二值化图像；Performing binarization processing on the denoised image to obtain an initial binarized image;
    将所述初始二值化图像进行形态学滤波处理，得到二值化图像。The initial binarized image is subjected to morphological filtering processing to obtain a binarized image.
  8. 根据权利要求1所述的评价方法，其特征在于，所述提取所述二值化图像中蜂窝胞元的顶点包括：The evaluation method according to claim 1, wherein the extracting the vertices of the honeycomb cells in the binarized image comprises:
    在二值化图像的基础上，获取蜂窝产品的骨架图；On the basis of the binary image, obtain the skeleton diagram of the honeycomb product;
    从所述骨架图中提取出属于同一个胞元的边界像素点，得到所述胞元的所述边界像素点序列；Extracting boundary pixels belonging to the same cell from the skeleton image to obtain the sequence of boundary pixels of the cell;
    分别获取与所述边界像素点对应的夹角，得到与所述边界像素点对应的所述夹角序列；所述夹角为在所述边界像素点序列中，在所述边界像素点的两侧，分别与所述边界像素点相隔第一预设值个像素的两个像素点与所述胞元边界像素点连线的夹角；Obtain the included angles corresponding to the boundary pixels to obtain the sequence of included angles corresponding to the boundary pixels; the included angles are in the sequence of boundary pixels, between two points of the boundary pixels Side, the angle between two pixel points that are separated from the boundary pixel point by a first preset value and the line connecting the cell boundary pixel point;
    采用第二预设值大小的窗口，对所述夹角序列进行非极小值抑制，将除了所述窗口中夹角的最小值之外的夹角设置为第一预设夹角；Using a window with a second preset value size to perform non-minimum suppression on the included angle sequence, and set an included angle other than the minimum value of the included angle in the window as the first preset included angle;
    当完成所述夹角序列的所述非极小值抑制时，确定所有所述最小值中小于第二预设夹角的夹角对应的所述边界像素点为所述顶点。When the non-minimum value suppression of the included angle sequence is completed, it is determined that the boundary pixels corresponding to the included angles that are smaller than the second preset included angle among all the minimum values are the vertices.
  9. 根据权利要求1所述的评价方法，其特征在于，还包括：The evaluation method according to claim 1, further comprising:
    计算蜂窝胞元图像中共顶点的三个胞元内角的内角偏差平均值，并根 据所述内角平均值评价蜂窝质量。Calculate the average value of the internal angle deviations of the three internal angles of the common vertices in the honeycomb cell image, and evaluate the honeycomb quality based on the average value of the internal angles.
  10. 一种蜂窝质量检测装置，其特征在于，包括：A honeycomb quality detection device, which is characterized in that it comprises:
    路线设定模块，用于根据相机的视场范围设定相机的移动路线，使所述相机可以获取整个蜂窝产品的图像；The route setting module is used to set the moving route of the camera according to the camera's field of view, so that the camera can obtain the image of the entire cellular product;
    相机，用于获取蜂窝图像；Camera, used to obtain cellular images;
    二值化处理模块，用于将所述蜂窝图像进行二值化处理，得到二值化图像；The binarization processing module is configured to perform binarization processing on the honeycomb image to obtain a binarized image;
    顶点提取模块，用于提取所述二值化图像中蜂窝胞元的顶点；A vertex extraction module for extracting the vertices of honeycomb cells in the binarized image;
    蜂窝胞元图像重构模块，用于根据所述顶点与胞元的映射关系，重构得到蜂窝胞元图像；A cellular cell image reconstruction module, configured to reconstruct a cellular cell image according to the mapping relationship between the vertices and the cells;
    蜂窝质量检测模块，用于计算所述蜂窝胞元图像中所有胞元角的偏差平均值，并根据所述平均值评价所述蜂窝质量。The honeycomb quality detection module is used to calculate the average deviation of all cell angles in the cell image of the honeycomb, and evaluate the quality of the honeycomb according to the average.
  11. 根据权利要求10所述的检测装置，其特征在于，还包括：置物台、升降装置、行走式龙门架、滑轨；The detection device according to claim 10, further comprising: a storage table, a lifting device, a walking gantry, and a slide rail;
    所述置物台用于盛放待检测蜂窝，其上设置有水平度示值板；The storage table is used to hold the honeycomb to be tested, and a levelness indicator board is arranged on it;
    所述升降装置与所述置物台连接，用于带动所述待检测蜂窝升降；The lifting device is connected with the placing table, and is used to drive the honeycomb to be detected up and down;
    所述行走式龙门架设置在所述滑轨上，且所述行走式龙门架设置有所述图像获取模块，使所述图像获取模块可在水平方向移动。The walking gantry is arranged on the slide rail, and the walking gantry is provided with the image acquisition module so that the image acquisition module can move in a horizontal direction.
  12. 一种储存介质，其特征在于，所述存储介质上存储有计算机程序，所述程序被处理器执行时实现权利要求1-10中任意一项所述方法的步骤。A storage medium, characterized in that a computer program is stored on the storage medium, and when the program is executed by a processor, the steps of the method according to any one of claims 1-10 are realized.
  13. 一种电子设备，其特征在于，包括存储器、显示器、处理器及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述程序时实现权利要求1-10中任意一项所述方法的步骤。An electronic device characterized by comprising a memory, a display, a processor, and a computer program stored in the memory and running on the processor, and the processor implements claim 1 when the program is executed. Steps of the method described in any one of 10.
PCT/CN2020/109727 2020-05-09 2020-08-18 Mobile testing method and apparatus for regularity of honeycomb product with ultra-large area WO2021227286A1 (en)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
CN202010388343.5 2020-05-09
CN202010388402.9A CN111583241B (en) 2020-05-09 2020-05-09 Mobile detection method and device for regularity of ultra-large area honeycomb products
CN202010388402.9 2020-05-09
CN202010388343.5A CN111583238B (en) 2020-05-09 2020-05-09 Method for extracting vertex of included angle of contour line of honeycomb, method for detecting vertex of included angle of contour line of honeycomb and device for detecting vertex of included angle of contour line of honeycomb

Publications (1)

Publication Number Publication Date
WO2021227286A1 true WO2021227286A1 (en) 2021-11-18

Family

ID=78526339

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/109727 WO2021227286A1 (en) 2020-05-09 2020-08-18 Mobile testing method and apparatus for regularity of honeycomb product with ultra-large area

Country Status (1)

Country Link
WO (1) WO2021227286A1 (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100743936B1 (en) * 2006-08-11 2007-07-30 박홍욱 Reinforced materials with honeycomb type for earthquake-resistance, repair, rehabilitation of concrete structures
CN103793712A (en) * 2014-02-19 2014-05-14 华中科技大学 Image recognition method and system based on edge geometric features
CN104369188A (en) * 2014-11-20 2015-02-25 中国计量学院 Workpiece grabbing device and method based on machine vision and ultrasonic transducer
CN109063229A (en) * 2018-06-14 2018-12-21 南京航空航天大学 A kind of honeycomb sandwich layer construction design method of ball-shape robot bumper housings
CN110189322A (en) * 2019-06-04 2019-08-30 广州视源电子科技股份有限公司 Measurement method of planeness, device, equipment, storage medium and system
CN210253172U (en) * 2019-07-19 2020-04-07 东莞恩浩电子有限公司 Automatic system for visual inspection

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100743936B1 (en) * 2006-08-11 2007-07-30 박홍욱 Reinforced materials with honeycomb type for earthquake-resistance, repair, rehabilitation of concrete structures
CN103793712A (en) * 2014-02-19 2014-05-14 华中科技大学 Image recognition method and system based on edge geometric features
CN104369188A (en) * 2014-11-20 2015-02-25 中国计量学院 Workpiece grabbing device and method based on machine vision and ultrasonic transducer
CN109063229A (en) * 2018-06-14 2018-12-21 南京航空航天大学 A kind of honeycomb sandwich layer construction design method of ball-shape robot bumper housings
CN110189322A (en) * 2019-06-04 2019-08-30 广州视源电子科技股份有限公司 Measurement method of planeness, device, equipment, storage medium and system
CN210253172U (en) * 2019-07-19 2020-04-07 东莞恩浩电子有限公司 Automatic system for visual inspection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
CUI CAN; WANG ZHONGGANG; ZHOU WEI; WU YONGJUN; WEI WANHUI: "Branch point algorithm for structural irregularity determination of honeycomb", COMPOSITES PART B, ELSEVIER, AMSTERDAM, NL, vol. 162, 19 October 2018 (2018-10-19), AMSTERDAM, NL, pages 323 - 330, XP085596185, ISSN: 1359-8368, DOI: 10.1016/j.compositesb.2018.10.062 *

Similar Documents

Publication Publication Date Title
US11551341B2 (en) Method and device for automatically drawing structural cracks and precisely measuring widths thereof
Shan et al. A stereovision-based crack width detection approach for concrete surface assessment
JP6620477B2 (en) Method and program for detecting cracks in concrete
WO2021227287A1 (en) Method and apparatus for honeycomb product regularity inspection on production line
CN102032875B (en) Image-processing-based cable sheath thickness measuring method
CN109087274A (en) Electronic device defect inspection method and device based on multidimensional fusion and semantic segmentation
CN109886939B (en) Bridge crack detection method based on tensor voting
CN111784684B (en) Method and device for detecting internal defects of transparent product at fixed depth based on laser assistance
CN105160652A (en) Handset casing testing apparatus and method based on computer vision
CN106996748A (en) A kind of wheel footpath measuring method based on binocular vision
CN104700395A (en) Method and system for detecting appearance crack of structure
CN104880389A (en) Mixed crystal degree automatic measurement and fine classification method for steel crystal grains, and system thereof
CN103593663A (en) Image positioning method of banknote printing plate
CN110189375A (en) A kind of images steganalysis method based on monocular vision measurement
CN115330684A (en) Underwater structure apparent defect detection method based on binocular vision and line structured light
CN111583241B (en) Mobile detection method and device for regularity of ultra-large area honeycomb products
WO2021227286A1 (en) Mobile testing method and apparatus for regularity of honeycomb product with ultra-large area
WO2021227288A1 (en) Method for evaluating geometrical morphology of honeycomb product, and detection and evaluation system
CN111583235B (en) Branch point identification vertex extraction method and system for detecting cellular regularity
Ziqiang et al. Research of the algorithm calculating the length of bridge crack based on stereo vision
CN111583242B (en) Morphological vertex extraction method and detection device for honeycomb regularity detection
CN114965693A (en) Ultrasonic C scanning automatic alignment system based on virtual-real registration
WO2021227285A1 (en) Image recognition method for geometrical regularity of cellular structure, and system
Xu et al. On-line visual inspection system for backside weld of tailored blanks laser welding
CN111583238B (en) Method for extracting vertex of included angle of contour line of honeycomb, method for detecting vertex of included angle of contour line of honeycomb and device for detecting vertex of included angle of contour line of honeycomb

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20935008

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20935008

Country of ref document: EP

Kind code of ref document: A1