CN112710632A - Method and system for detecting high and low refractive indexes of glass beads - Google Patents
Method and system for detecting high and low refractive indexes of glass beads Download PDFInfo
- Publication number
- CN112710632A CN112710632A CN202110306319.7A CN202110306319A CN112710632A CN 112710632 A CN112710632 A CN 112710632A CN 202110306319 A CN202110306319 A CN 202110306319A CN 112710632 A CN112710632 A CN 112710632A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- processing
- refractive index
- low refractive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 65
- 239000011521 glass Substances 0.000 title claims abstract description 31
- 239000011324 bead Substances 0.000 title claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 77
- 238000005457 optimization Methods 0.000 claims abstract description 21
- 238000012937 correction Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 15
- 230000011218 segmentation Effects 0.000 claims abstract description 15
- 230000000877 morphologic effect Effects 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000003384 imaging method Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 239000004005 microsphere Substances 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 238000001448 refractive index detection Methods 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 3
- 230000004075 alteration Effects 0.000 claims description 2
- 230000006835 compression Effects 0.000 claims description 2
- 238000007906 compression Methods 0.000 claims description 2
- 238000004148 unit process Methods 0.000 claims description 2
- 238000010191 image analysis Methods 0.000 abstract description 2
- 238000003672 processing method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 230000003628 erosive effect Effects 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000010339 dilation Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241000760358 Enodes Species 0.000 description 1
- BPQQTUXANYXVAA-UHFFFAOYSA-N Orthosilicate Chemical compound [O-][Si]([O-])([O-])[O-] BPQQTUXANYXVAA-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000010292 electrical insulation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 239000003981 vehicle Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/41—Refractivity; Phase-affecting properties, e.g. optical path length
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10141—Special mode during image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20056—Discrete and fast Fourier transform, [DFT, FFT]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method and a system for detecting high and low refractive indexes of glass beads, wherein the method comprises the following steps: sequentially carrying out distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square method fitting circle processing on the acquired high-refractive-index image; sequentially carrying out distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, contour optimization and least square method circle fitting processing on the collected low-refractive-index image; and obtaining the radius of the contour circle and the coordinate value of the center of the circle according to the processing, and further calculating the refractive indexes in the high refractive index image and the low refractive index image. The invention has the advantages that: the method not only can simultaneously detect the high refractive index and the low refractive index of the glass beads, but also greatly improves the detection efficiency and the detection accuracy through the image analysis processing method.
Description
Technical Field
The invention relates to the field of glass bead refractive index detection, in particular to a method and a system for detecting the high refractive index and the low refractive index of glass beads.
Background
The glass beads are silicate materials, have good chemical stability, mechanical strength and electrical insulation, have the unique characteristic of having a retro-reflection characteristic to light, and are widely applied to the fields of highways, railways, ports, ocean transportation, mines, tunnels, fire protection, urban construction and the like as various marks, warning boards, vehicle photographing and lifesaving appliances and the like; along with the rapid development of highway construction in China, the dosage of glass microspheres matched with a road retroreflective material is rapidly increased, and the glass microspheres play an increasingly important role in traffic safety products and facilities such as advertising signs, reflective films, reflective ink and reflective marked lines.
The existing methods for measuring the refractive index of the glass microspheres mainly comprise an imaging method, a primary rainbow method, a secondary rainbow method and the like; however, the existing measurement technology has the defects of complex light path adjustment, difficult realization of automatic quantitative measurement process, low transmittance, poor imaging effect and the like based on an imaging method; can only measure the glass microballon of low refracting index based on a rainbow method, can only measure the glass microballon of high refracting index based on the secondary rainbow method, can not realize the simultaneous measurement of high low refracting index, have the shortcoming of function singleness, the measurement to the glass microballon refracting index is realized through adjusting the light path to the current moreover, but the light path is adjusted troublesome and complicated under the general condition, need adopt the measurement of belt annular scale, and adjust the precision not high, maneuverability is poor.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides a method and a system for detecting the high and low refractive indexes of glass beads, and solves the defects of the existing method for detecting the refractive indexes of the glass beads.
The purpose of the invention is realized by the following technical scheme: a method for detecting high and low refractive indexes of glass beads comprises the following steps:
sequentially carrying out distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square method fitting circle processing on the acquired high-refractive-index image; sequentially carrying out distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, contour optimization and least square method circle fitting processing on the collected low-refractive-index image;
and obtaining the radius of the contour circle and the coordinate value of the center of the circle according to the processing, and further calculating the refractive indexes in the high refractive index image and the low refractive index image.
The aberration correction process includes:
inputting a high refractive index image or a low refractive index image in an image pixel coordinate system
The central coordinate in the image is set as the origin of the image physical coordinate system, and the conversion matrix of the image pixel coordinate system and the image physical coordinate system is obtained according to the size of each pixel in the image physical coordinate system, so as to obtain the image physical coordinate system of the high refractive index image or the low refractive index image
；
Physical coordinate system of image
Conversion to camera coordinate system
Then the camera coordinate system
Conversion to world coordinate system
；
Further obtaining an internal parameter matrix, a perspective projection matrix and a scale factor of the camera, and correcting the input high refractive index image and low refractive index image according to the internal parameter matrix, the perspective projection matrix and the scale factor of the camera
。
The gradation enhancement processing includes: for the gray scale of corrected distortionrIs inputted to the image
By the gray enhancement formula:
processed to obtain a gray scale ofsOutput image of (2)
Linear expansion or compression of input image gray scale is realized, and the step is used as an output image
Input image of the next step
。
The contrast enhancement process includes: for input image
Low-pass filtering is carried out, and calculation is carried out according to the obtained gray value and the original value to obtain a result value:
to obtainTo the output image
The method can emphasize the high-frequency region of the image to make the image clearer, and the step is used as an output image
Input image of the next step
。
The threshold segmentation process includes: selecting an input image
The gray value satisfies the gray range [ MinGray, MaxGray]All satisfied pixel points are used as an area to return;
the morphological treatment comprises the following steps: and sequentially performing expansion and corrosion treatment on the region obtained after the threshold segmentation treatment, or sequentially performing corrosion and expansion treatment to filter out interference information in the image.
The Fourier transform processing includes:
fourier transform: carrying out Fourier transform on the image subjected to contrast enhancement to convert the time domain image into a frequency domain image;
gaussian convolution: convolving the image subjected to Fourier transform with a convolution kernel template, enabling the origin of the convolution kernel template to coincide with a point on the image, multiplying the point on the convolution kernel template with the corresponding point on the image, adding the products of the points to obtain the convolution value of the point, and processing each point on the image in such a way to obtain a convolution image;
inverse Fourier transform: and carrying out inverse Fourier transform on the convolution image to convert the frequency domain image into a time domain image.
The contour optimization extraction process includes:
screening the contours in the image through a theoretical roundness value, and calculating the area and the perimeter of the screened contours;
and calculating an actual circularity value of the circular contour according to the area and the perimeter, comparing the actual circularity value with the theoretical circularity value, judging that the screened contour is the circular contour if the actual circularity value is within the error range of the theoretical circularity value, and screening and extracting again if the actual circularity value is not within the error range of the theoretical circularity value any more.
The least squares fitting circle processing comprises:
equation based on circular curves
And
let a point in the sample set
At a distance from the center of the circle of
Then, then
；
Finding points
The difference between the square of the distance to the circular edge and the square of the radius is:
；
order to
Is composed of
The sum of the squares of (a) and (b),
， 
greater than 0, so that the function presents a minimum value greater than or equal to 0,
to calculate the partial derivatives for a, b, c, let the partial derivatives equal to 0, get the extreme points:
，
， 
；
and calculating the values of a, B and c to obtain the fitting values of A, B and R.
A detection system based on a glass bead high and low refractive index detection method comprises:
an image acquisition module: collecting high and low refractive index images and transmitting the collected images to an image processing module;
an image processing module: carrying out distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, Fourier transform, contour optimization and least square method circle fitting processing on the input high and low refractive index images, and then transmitting the processing result to a data processing module;
a data processing module: and analyzing and processing the data, calculating according to the circle radius and the imaging distance to obtain the refractive index, and finally outputting and storing data information.
The image processing module comprises a high-refractive-index image processing unit and a low-refractive-index image processing unit;
the high-refractive-index image processing unit processes the input high-refractive-index image through distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square fitting circle in sequence to obtain the radius and the imaging distance of the circular contour;
and the low-refractive-index image processing unit is used for processing the input low-refractive-index image through distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, contour optimization extraction and least square method fitting circle in sequence to obtain the radius and the imaging distance of the circular contour.
The invention has the following advantages: the method and the system for detecting the high refractive index and the low refractive index of the glass beads can simultaneously detect the high refractive index and the low refractive index of the glass beads, and greatly improve the detection efficiency and the detection accuracy rate through an image analysis processing method.
Drawings
FIG. 1 is a schematic flow diagram of the process of the present invention;
FIG. 2 is a schematic diagram of an image pixel coordinate system to an image physical coordinate system 1;
FIG. 3 is a schematic diagram of an image pixel coordinate system to an image physical coordinate system 2;
FIG. 4 is a schematic diagram of a camera coordinate system to an image physical coordinate system;
FIG. 5 is a schematic diagram of a world coordinate system to a camera coordinate system.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the detailed description of the embodiments of the present application provided below in connection with the appended drawings is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. The invention is further described below with reference to the accompanying drawings.
In the present invention, f (x, y) represents an input image, g (x, y) represents an output image, and f (x, y) and g (x, y) in each step represent different images, that is, the output image g (x, y) in one processing step represents the input image f (x, y) in the next processing step after the next processing step.
Example 1
As shown in fig. 1, the invention relates to a method for detecting high and low refractive indexes of glass beads, which mainly comprises the following steps:
starting and initializing a program, automatically initializing after software is started, loading a configuration file, detecting a camera connection state, and entering a detection waiting state;
manually adjusting the position of the glass bead sample, and starting a high-refractive-index camera for image acquisition or low-refractive-index camera for image acquisition after the image achieves the optimal image acquisition effect; the high-refractive-index camera and the low-refractive-index camera adopt independent cameras and independent threads, so that real-time image reading, processing, transmission and display can be realized;
after image acquisition is successful, the image enters an image processing module, information which is required by people is obtained through a series of algorithm processing, and finally, the radius of the circle is extracted; the high-refractive-index image processing module mainly uses algorithms including distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square method fitting circle; algorithms mainly used by the low refractive index image processing module comprise distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphology processing, contour optimization extraction and least square method fitting circle. The module carries out a series of processing on the image through a special algorithm and transmits a calculation result to the data processing module;
and calculating to obtain the refractive index according to the circle radius and the imaging distance through a data processing module, and finally outputting data and finishing measurement.
Further, the distortion correction: the imaging process of the camera is essentially a transformation of the coordinate system. Firstly, converting the points in the space from the world coordinate system to the camera coordinate system, then projecting the points to the imaging plane (image physical coordinate system), and finally converting the data on the imaging plane to the image pixel coordinate system. But distortion is introduced due to lens manufacturing accuracy and variations in the assembly process, resulting in distortion of the original image. The distortion of the lens is classified into radial distortion and tangential distortion.
Radial distortion: is a distortion distributed along the radius of the lens, which arises because the rays are more curved away from the center of the lens than closer to the center. The distortion of the center of the optical axis of the imager is 0, and the distortion becomes more serious when the optical axis moves to the edge along the radius direction of the lens. The mathematical model of distortion can be described by the first terms of taylor series expansion around the principal point (principal point), usually using the first two terms, i.e. k1 and k2, and for a lens with large distortion, such as a fish-eye lens, the description can be added by using the third term k3, and a point on the imager is adjusted according to its distribution position in the radial direction by the formula:
wherein:
where (x 0, y 0) is the original position of the distortion point on the imager and (x, y) is the new position after the distortion is true;
tangential distortion: this is caused by the fact that the lens itself is not parallel to the camera sensor plane (imaging plane) or image plane, which is often caused by mounting deviations of the lens to the lens module. The distortion model can be described with two additional parameters p1 and p 2:
wherein
， 
， 
As a parameter of the radial distortion,
， 
is a tangential distortion parameter. To sum up, we need 5 parameters (a), (b), (c), (d
， 
， 
， 
， 
) Describing the lens distortion, the invention eliminates the camera distortion through the camera calibration, namely distortion correction.
The purpose of camera calibration is to obtain internal parameters (distortion parameters) and external parameters of a camera and obtain the relationship between two-dimensional plane pixel coordinates and three-dimensional world coordinates. Four coordinate systems: camera coordinate system, image physical coordinate system, image pixel coordinate system, and world coordinate system (reference coordinate system).
Image coordinate system: the coordinate system is a coordinate system with a pixel as a unit, the origin of the coordinate system is at the upper left, the position of each pixel point is expressed by the pixel as a unit, so the coordinate system is called an image pixel coordinate system (u, v), u and v respectively represent the number of columns and rows of the pixel in a digital image, but the position of the pixel is not represented by a physical unit, so an image coordinate system with a physical unit, called an image physical coordinate system (x, y), needs to be established, the coordinate system takes the intersection point of an optical axis and an image plane as the origin, the point is generally positioned in the center of the image, but the point can be deviated in many cases due to manufacturing reasons. In millimeters. The two coordinate axes are respectively parallel to the image pixel coordinate system. Namely: pixel coordinates (u, v), physical coordinates (x, y).
As shown in fig. 2, if the coordinates of the origin of the image physical coordinate system in the image pixel coordinate system are (u0, v0), and the size of each pixel in the image physical coordinate system is dx, dy, the relationship between the two coordinate systems is:
the matrix form is:
but in general, the two axes are not perpendicular to each other:
as shown in fig. 3, this time:
written in matrix form as:
as shown in fig. 4, camera coordinate system (Xc, Yc, Zc) to image coordinate system (x, y);
according to the similar triangle principle, the following results are obtained:
as shown in fig. 5, world coordinate system (Xw, Yw, Zw) to camera coordinate system (Xc, Yc, Zc);
combining the above formula to obtain:
wherein the content of the first and second substances,
a reference matrix within the camera is represented,
denotes a perspective photography matrix, and s = Zc denotes a scale factor.
And (3) gray level enhancement: the gray scale of an input image is linearly expanded or compressed, a mapping function is a linear equation, the input image is f (x, y), the gray scale is r, the output image is g (x, y), and the gray scale is s; the expression is as follows: factor and k are parameter factors;
contrast enhancement: the high frequency regions (edges and corners) of the image are mainly emphasized, so that the obtained image is clearer. Firstly, low-pass filtering (mean _ image) is carried out on the image g (x, y), and a result value (res) is obtained by calculating according to the obtained gray value (mean) and the original value (orig), wherein the expression is as follows: factor is a parameter Factor
Threshold segmentation: selecting pixels with gray values satisfying a gray interval [ MinGray, MaxGray ] from the input image f (x, y), and returning all satisfied points as an area, wherein the expression is as follows:
wherein MinGray represents the minimum gray value of the optimal gray value range, MaxGray represents the maximum gray value of the optimal gray value range, and if the gray value is about 100 pixels, the gray value interval can be set to [90,110 ].
Morphological treatment: mathematical morphology is composed of a set of morphological algebraic operators, whose basic operations are 4: dilation, erosion, opening and closing operations, the main function of which is to preserve the basic features of the image and to remove extraneous structures; by performing morphological processing on the region obtained by threshold segmentation, some interference information can be filtered out
Swelling (Dilate): is a process of merging all background points in contact with an object into the object and expanding the boundary to the outside. Can be used to fill in voids in objects. Dilation can be viewed as the dual operation of erosion, which is defined as: ba is obtained by translating the structural element B by a, and if Ba hits X, we note the point a. The set of all points a satisfying the above condition is called the result of expansion of X by B.
Corrosion (enode): is a method for eliminating boundary points, and makes the boundary shrink inwards. Small and meaningless objects can be eliminated. The result of X erosion with S is a collection of all X' S that remain in X after S is translated by X. In other words, the set obtained by corroding X with S is a set of the origin positions of S when S is completely included in X, and is formulated as:
open operation (Close): first swell and then decay is called close (close), i.e. close (x) = E (d (x)). In general, the closing operation is able to fill small lakes (i.e., pores), closing small cracks, while leaving the overall position and shape unchanged.
Closed operation (Open): opening and closing are dual operations. Erosion followed by dilation is called open (open), i.e., open (x) = D (e (x)). The function is as follows: small objects are eliminated, separated objects are obtained at the fine points, and the positions and the shapes are invariable.
Fourier transform: the frequency of the image is an index that characterizes how strongly the gray level in the image changes. Each point of the frequency domain image is from the whole original image, and when the image processing is carried out, the points on the frequency spectrum image and the points on the image do not have the one-to-one correspondence relationship, a place with severe gray level change or a region with relatively slow gray level change in the image is needed to be obtained in many times, and the place with severe gray level change is a place with large gray level change or a place with large gradient, and the frequency of the place is high; the place where the gray level changes slowly is the place where the gradient is small, and the frequency is low; the Fourier Transform (FT) functions to Transform a signal from the spatial or time domain to the frequency domain. The method is characterized in that the data is converted into a frequency spectrum format of abscissa frequency and ordinate amplitude (or phase) from a waveform diagram format of an abscissa time sampling value and an ordinate sampling value. The inverse fourier transform is to restore the frequency domain to the spatial or time domain.
Furthermore, Fourier transform is carried out on the image after contrast enhancement, Gaussian convolution is carried out on the Fourier image, and finally the Fourier image is restored to be a space domain image, so that the original characteristics which are difficult to perceive can be obviously enhanced, and great help is brought to next contour optimization extraction;
fourier transform formula:
gaussian convolution: the convolution is carried out by a template (convolution kernel) and an image, for a point on the image, the original point of the template is coincided with the point, then the point on the template is multiplied with the corresponding point on the image, then the products of the points are added to obtain the convolution value of the point, and each point on the image is processed in this way to finally obtain the convolution image. Convolution is an integral operation used to find the area of the overlapping region of two curves. The replacement of the pixel value of a point by a weighted average of the pixel values of its surrounding points can be seen as a weighted sum, which can be used to eliminate noise and feature enhancement.
Convolution formula:
wherein
To output an image (output image in the fourier transform step),
in order to input an image, the image is,
for the template (convolution kernel), a general convolution kernel uses a two-dimensional gaussian distribution function:
the inverse fourier transform equation:
wherein, f (x, y) image matrix, row and column of x/y image.
Contour optimization extraction: and (5) carrying out a process of screening the contour through roundness. For a circular profile, the radius is r, the area is S, and the perimeter is L:
from the above formula, it can be seen that C is a fixed value (theoretical value) when the contour is a standard circle, and the contour obtained by the foregoing algorithm processing often has many contours, including a circular contour and a non-circular contour, and only a circle is needed, so that the area and the perimeter of the contour can be calculated, and then the needed circular contour can be screened out by the above formula. When the calculated actual roundness value is within an error range of ± 10% of the theoretical roundness value, the screened contour is represented as a circular contour.
Fitting a circle by a least square method: least squares (least squares analysis) is a mathematical optimization technique that finds the best functional match for a set of data by minimizing the sum of the squares of the errors. The least squares method is a calculation method for finding the best matching function of a set of data by finding some absolute unknown true values by the simplest method and minimizing the sum of squared errors, and is generally used for curve fitting (least squares fitting). The least square circle fitting method is a detection method based on statistics, and can realize sub-pixel level accurate fitting positioning.
The formula for the circle:
wherein A, B is the center coordinate of the circle, and R is the radius
Order to
, 
, 
Another equation for the circular curve can be derived:
by finding a, b, c, the radius parameter of the circle can be obtained:
let one point in the sample set (here, the sample set is the set of all points on the extracted contour)
To the center of a circleA distance of
:
Dot
The difference between the square of the distance to the circular edge and the square of the radius is:
order to
Is composed of
Sum of squares of
the values of a, B and c can be obtained by solving the equation set, and then the fitting values of A, B and R can be obtained by the above formula.
Example 2
The invention also relates to a glass bead high and low refractive index detection system which comprises an initialization module, an image acquisition module, an image processing module and a data processing module.
Further, the initialization module: loading system parameters, configuration files and initializing a camera;
an image acquisition module: collecting high and low refractive index images and transmitting the collected images to an image processing module;
an image processing module: the high-refractive-index image processing module is divided into a high-refractive-index image processing module and a low-refractive-index image processing module, different algorithms are respectively adopted, and the algorithms mainly used by the high-refractive-index image processing module comprise distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square method fitting circle; algorithms mainly used by the low refractive index image processing module comprise distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphology processing, contour optimization extraction and least square method fitting circle. The module carries out a series of processing on the image through a special algorithm and transmits a calculation result to the data processing module;
a data processing module: and analyzing and processing the data, and finally outputting and storing the data.
The foregoing is illustrative of the preferred embodiments of this invention, and it is to be understood that the invention is not limited to the precise form disclosed herein and that various other combinations, modifications, and environments may be resorted to, falling within the scope of the concept as disclosed herein, either as described above or as apparent to those skilled in the relevant art. And that modifications and variations may be effected by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A method for detecting the high and low refractive indexes of glass beads is characterized by comprising the following steps: the detection method comprises the following steps:
sequentially carrying out distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square method fitting circle processing on the acquired high-refractive-index image; sequentially carrying out distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, contour optimization and least square method circle fitting processing on the collected low-refractive-index image;
and obtaining the radius of the contour circle and the coordinate value of the center of the circle according to the processing, and further calculating the refractive indexes in the high refractive index image and the low refractive index image.
2. The method for detecting the high and low refractive indexes of the glass microspheres according to claim 1, wherein the method comprises the following steps: the aberration correction process includes:
inputting a high refractive index image or a low refractive index image in an image pixel coordinate system
The central coordinate in the image is set as the origin of the image physical coordinate system, and the conversion matrix of the image pixel coordinate system and the image physical coordinate system is obtained according to the size of each pixel in the image physical coordinate system, so as to obtain the image physical coordinate system of the high refractive index image or the low refractive index image
；
Physical coordinate system of image
Conversion to camera coordinate system
Then the camera coordinate system
Conversion to world coordinate system
；
Further obtaining a camera internal reference matrix, a perspective projection matrix and a scale factor, and correcting the input high refractive index image and low refractive index image according to the camera internal reference matrix, the perspective projection matrix and the scale factor to obtain an image
。
3. The method for detecting the high and low refractive indexes of the glass microspheres according to claim 2, wherein the method comprises the following steps: the grayscale enhancement includes: for the gray scale of corrected distortionrIs inputted to the image
By the gray enhancement formula:
processed to obtain a gray scale ofsOutput image of (2)
Linear expansion or compression of the input image gray scale is realized, and the gray scale is enhanced
Input image as next step
。
4. The method for detecting the high and low refractive indexes of the glass microspheres according to claim 2, wherein the method comprises the following steps: the contrast enhancement includes:for input image
Low-pass filtering is carried out, and calculation is carried out according to the obtained gray value and the original value to obtain a result value:
to obtain an output image
The method can emphasize the high-frequency region of the image, make the image clearer, and enhance the contrast of the output image in the step
Input image as next step
Wherein, in the step (A),resthe value of the result is represented by,Factorthe parameter factors are represented by a number of parameters,meanwhich represents a gray-scale value of the image,origrepresenting the original value.
5. The method for detecting the high and low refractive indexes of the glass microspheres according to claim 2, wherein the method comprises the following steps: the threshold segmentation process includes: selecting an input image
The gray value satisfies the gray range [ MinGray, MaxGray]Returning all satisfied pixel points as a region, wherein MinGray represents the minimum gray value of the optimal gray value range, and MaxGray represents the maximum gray value of the optimal gray value range;
the morphological treatment comprises the following steps: and sequentially performing expansion and corrosion treatment on the region obtained after the threshold segmentation treatment, or sequentially performing corrosion and expansion treatment to filter out interference information in the image.
6. The method for detecting the high and low refractive indexes of the glass microspheres according to claim 2, wherein the method comprises the following steps: the Fourier transform processing includes:
fourier transform: carrying out Fourier transform on the image subjected to contrast enhancement to convert the time domain image into a frequency domain image;
gaussian convolution: convolving the image subjected to Fourier transform with a convolution kernel template, enabling the origin of the convolution kernel template to coincide with a point on the image, multiplying the point on the convolution kernel template with the corresponding point on the image, adding the products of the points to obtain the convolution value of the point, and processing each point on the image in such a way to obtain a convolution image;
inverse Fourier transform: and carrying out inverse Fourier transform on the convolution image to convert the frequency domain image into a time domain image.
7. The method for detecting the high and low refractive indexes of the glass microspheres according to claim 2, wherein the method comprises the following steps: the contour optimization extraction process includes:
screening the contours in the image through a theoretical roundness value, and calculating the area and the perimeter of the screened contours;
and calculating an actual circularity value of the circular contour according to the area and the perimeter, comparing the actual circularity value with the theoretical circularity value, judging that the screened contour is the circular contour if the actual circularity value is within the error range of the theoretical circularity value, and screening and extracting again if the actual circularity value is not within the error range of the theoretical circularity value.
8. A detection system based on a glass bead high and low refractive index detection method is characterized in that: it includes:
an image acquisition module: collecting high and low refractive index images and transmitting the collected images to an image processing module;
an image processing module: carrying out distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, Fourier transform, contour optimization and least square method circle fitting processing on the input high and low refractive index images, and then transmitting the processing result to a data processing module;
a data processing module: and analyzing and processing the data, calculating according to the circle radius and the imaging distance to obtain the refractive index, and finally outputting and storing data information.
9. The detection system based on the glass bead high and low refractive index detection method according to claim 8, characterized in that: the image processing module comprises a high-refractive-index image processing unit and a low-refractive-index image processing unit;
the high-refractive-index image processing unit processes the input high-refractive-index image through distortion correction, contrast enhancement, Fourier transform, contour optimization extraction and least square fitting circle in sequence to obtain the radius and the imaging distance of the circular contour;
and the low-refractive-index image processing unit is used for processing the input low-refractive-index image through distortion correction, gray level enhancement, contrast enhancement, threshold segmentation, morphological processing, contour optimization extraction and least square method fitting circle in sequence to obtain the radius and the imaging distance of the circular contour.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110306319.7A CN112710632A (en) | 2021-03-23 | 2021-03-23 | Method and system for detecting high and low refractive indexes of glass beads |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110306319.7A CN112710632A (en) | 2021-03-23 | 2021-03-23 | Method and system for detecting high and low refractive indexes of glass beads |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112710632A true CN112710632A (en) | 2021-04-27 |
Family
ID=75550192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110306319.7A Pending CN112710632A (en) | 2021-03-23 | 2021-03-23 | Method and system for detecting high and low refractive indexes of glass beads |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112710632A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114842018A (en) * | 2022-07-06 | 2022-08-02 | 苏州拉索生物芯片科技有限公司 | Method for extracting characteristics of microbeads in high-density gene chip, terminal and storage medium |
Citations (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5431415A (en) * | 1977-08-15 | 1979-03-08 | Toshiba Kasei Kougiyou Kk | High refractive index glass for use as glass beads |
| JPS63123835A (en) * | 1987-10-22 | 1988-05-27 | Union:Kk | Glass bead of high refractive index |
| CA1286269C (en) * | 1986-03-11 | 1991-07-16 | Yuji Ishihara | All-weather type pavement marking sheet material |
| CN1119975A (en) * | 1994-06-02 | 1996-04-10 | 三菱电机株式会社 | Optical processing method and apparatus for carrying out the same |
| US5620775A (en) * | 1995-11-03 | 1997-04-15 | Minnesota Mining And Manufacturing Company | Low refractive index glass microsphere coated article having a smooth surface and a method for preparing same |
| EP0848833A1 (en) * | 1995-09-15 | 1998-06-24 | Minnesota Mining And Manufacturing Company | Retroreflective transfer sheet and applique |
| JP2000086290A (en) * | 1999-08-10 | 2000-03-28 | Asahi Techno Glass Corp | High-refractive-index glass bead and its heat treatment |
| JP2001048586A (en) * | 1999-08-03 | 2001-02-20 | Nisshin Steel Co Ltd | Light reflecting glass bead and its production |
| US7088333B1 (en) * | 1999-03-12 | 2006-08-08 | Matsushita Electric Industrial Co., Ltd. | Surface lighting device and portable terminal using the same |
| CN101526484A (en) * | 2009-04-13 | 2009-09-09 | 江南大学 | Bearing defect detecting technique based on embedded-type machine vision |
| EP2224227A4 (en) * | 2008-01-16 | 2011-06-22 | Nippon Telegraph & Telephone | Surface plasmon resonance measuring device, sample cell, and measuring method |
| CN201909758U (en) * | 2010-12-15 | 2011-07-27 | 四川大学 | Device for measuring refractive index of high refractive index glass microsphere |
| CN102156108A (en) * | 2010-12-15 | 2011-08-17 | 四川大学 | Method and device for calibrating rainbow ring radius of secondary rainbow |
| CN102221937A (en) * | 2010-04-15 | 2011-10-19 | 上海天派无线科技有限公司 | Real-time video image coordinate recognition system and method |
| CN104079818A (en) * | 2013-03-26 | 2014-10-01 | 佳能株式会社 | Image pickup apparatus, image processing system, image pickup system and image processing method |
| CN104751147A (en) * | 2015-04-16 | 2015-07-01 | 成都汇智远景科技有限公司 | Image recognition method |
| CN104819959A (en) * | 2015-04-17 | 2015-08-05 | 四川大学 | Device and method for measuring refractive index of low refractive index glass beads |
| CN104819960A (en) * | 2015-02-12 | 2015-08-05 | 四川大学 | Apparatus and method for measuring glass micro-bead refractive index |
| US20160230018A1 (en) * | 2015-02-11 | 2016-08-11 | LKF Materials A/S | Composition, marking and kit of parts for forming a marking, such as a road marking |
| CN107123095A (en) * | 2017-04-01 | 2017-09-01 | 上海联影医疗科技有限公司 | A kind of PET image reconstruction method, imaging system |
| CN107407691A (en) * | 2015-01-22 | 2017-11-28 | 贝克顿迪金森公司 | Device and system for the molecular bar code of unicellular amplifying nucleic acid target |
| CN108231645A (en) * | 2017-12-29 | 2018-06-29 | 广东工业大学 | High-precision locating method and device in a kind of wafer level inversion vision system |
| CN108876768A (en) * | 2018-05-30 | 2018-11-23 | 杭州舜浩科技有限公司 | Light guide plate shadow defect inspection method |
| KR20190001717A (en) * | 2017-06-28 | 2019-01-07 | 주식회사 성진에스이 | Lane Paint Composition with Improved Visibility during Rain |
| CN109523565A (en) * | 2018-11-15 | 2019-03-26 | 湖北工业大学 | A kind of diffraction light-free Moire fringe center positioning method and system |
| CN109716104A (en) * | 2016-07-25 | 2019-05-03 | 光声技术股份有限公司 | The instrument of the orthogonal fluorescence optoacoustic volume projection of total registration for obtaining tissue and its method used |
| CN109785245A (en) * | 2018-12-06 | 2019-05-21 | 江苏大学 | A kind of light spot image dressing method |
| US10481002B2 (en) * | 2011-09-30 | 2019-11-19 | General Electric Company | Systems and methods for self-referenced detection and imaging of sample arrays |
| CN110766689A (en) * | 2019-11-06 | 2020-02-07 | 深圳微品致远信息科技有限公司 | Method and device for detecting article image defects based on convolutional neural network |
| CN111043973A (en) * | 2019-12-12 | 2020-04-21 | 浙江大学 | Hydrogen isotope crystallization height and surface roughness interference measurement device and method |
| CN111626290A (en) * | 2019-12-31 | 2020-09-04 | 中国航天科工集团八五一一研究所 | Infrared ship target detection and identification method under complex sea surface environment |
| CN111860670A (en) * | 2020-07-28 | 2020-10-30 | 平安科技（深圳）有限公司 | Domain adaptive model training method, image detection method, device, equipment and medium |
-
2021
- 2021-03-23 CN CN202110306319.7A patent/CN112710632A/en active Pending
Patent Citations (32)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS5431415A (en) * | 1977-08-15 | 1979-03-08 | Toshiba Kasei Kougiyou Kk | High refractive index glass for use as glass beads |
| CA1286269C (en) * | 1986-03-11 | 1991-07-16 | Yuji Ishihara | All-weather type pavement marking sheet material |
| JPS63123835A (en) * | 1987-10-22 | 1988-05-27 | Union:Kk | Glass bead of high refractive index |
| CN1119975A (en) * | 1994-06-02 | 1996-04-10 | 三菱电机株式会社 | Optical processing method and apparatus for carrying out the same |
| EP0848833A1 (en) * | 1995-09-15 | 1998-06-24 | Minnesota Mining And Manufacturing Company | Retroreflective transfer sheet and applique |
| US5620775A (en) * | 1995-11-03 | 1997-04-15 | Minnesota Mining And Manufacturing Company | Low refractive index glass microsphere coated article having a smooth surface and a method for preparing same |
| US7088333B1 (en) * | 1999-03-12 | 2006-08-08 | Matsushita Electric Industrial Co., Ltd. | Surface lighting device and portable terminal using the same |
| JP2001048586A (en) * | 1999-08-03 | 2001-02-20 | Nisshin Steel Co Ltd | Light reflecting glass bead and its production |
| JP2000086290A (en) * | 1999-08-10 | 2000-03-28 | Asahi Techno Glass Corp | High-refractive-index glass bead and its heat treatment |
| EP2224227A4 (en) * | 2008-01-16 | 2011-06-22 | Nippon Telegraph & Telephone | Surface plasmon resonance measuring device, sample cell, and measuring method |
| CN101526484A (en) * | 2009-04-13 | 2009-09-09 | 江南大学 | Bearing defect detecting technique based on embedded-type machine vision |
| CN102221937A (en) * | 2010-04-15 | 2011-10-19 | 上海天派无线科技有限公司 | Real-time video image coordinate recognition system and method |
| CN201909758U (en) * | 2010-12-15 | 2011-07-27 | 四川大学 | Device for measuring refractive index of high refractive index glass microsphere |
| CN102156108A (en) * | 2010-12-15 | 2011-08-17 | 四川大学 | Method and device for calibrating rainbow ring radius of secondary rainbow |
| US10481002B2 (en) * | 2011-09-30 | 2019-11-19 | General Electric Company | Systems and methods for self-referenced detection and imaging of sample arrays |
| CN104079818A (en) * | 2013-03-26 | 2014-10-01 | 佳能株式会社 | Image pickup apparatus, image processing system, image pickup system and image processing method |
| CN107407691A (en) * | 2015-01-22 | 2017-11-28 | 贝克顿迪金森公司 | Device and system for the molecular bar code of unicellular amplifying nucleic acid target |
| US20160230018A1 (en) * | 2015-02-11 | 2016-08-11 | LKF Materials A/S | Composition, marking and kit of parts for forming a marking, such as a road marking |
| CN104819960A (en) * | 2015-02-12 | 2015-08-05 | 四川大学 | Apparatus and method for measuring glass micro-bead refractive index |
| CN104751147A (en) * | 2015-04-16 | 2015-07-01 | 成都汇智远景科技有限公司 | Image recognition method |
| CN104819959A (en) * | 2015-04-17 | 2015-08-05 | 四川大学 | Device and method for measuring refractive index of low refractive index glass beads |
| CN109716104A (en) * | 2016-07-25 | 2019-05-03 | 光声技术股份有限公司 | The instrument of the orthogonal fluorescence optoacoustic volume projection of total registration for obtaining tissue and its method used |
| CN107123095A (en) * | 2017-04-01 | 2017-09-01 | 上海联影医疗科技有限公司 | A kind of PET image reconstruction method, imaging system |
| KR20190001717A (en) * | 2017-06-28 | 2019-01-07 | 주식회사 성진에스이 | Lane Paint Composition with Improved Visibility during Rain |
| CN108231645A (en) * | 2017-12-29 | 2018-06-29 | 广东工业大学 | High-precision locating method and device in a kind of wafer level inversion vision system |
| CN108876768A (en) * | 2018-05-30 | 2018-11-23 | 杭州舜浩科技有限公司 | Light guide plate shadow defect inspection method |
| CN109523565A (en) * | 2018-11-15 | 2019-03-26 | 湖北工业大学 | A kind of diffraction light-free Moire fringe center positioning method and system |
| CN109785245A (en) * | 2018-12-06 | 2019-05-21 | 江苏大学 | A kind of light spot image dressing method |
| CN110766689A (en) * | 2019-11-06 | 2020-02-07 | 深圳微品致远信息科技有限公司 | Method and device for detecting article image defects based on convolutional neural network |
| CN111043973A (en) * | 2019-12-12 | 2020-04-21 | 浙江大学 | Hydrogen isotope crystallization height and surface roughness interference measurement device and method |
| CN111626290A (en) * | 2019-12-31 | 2020-09-04 | 中国航天科工集团八五一一研究所 | Infrared ship target detection and identification method under complex sea surface environment |
| CN111860670A (en) * | 2020-07-28 | 2020-10-30 | 平安科技（深圳）有限公司 | Domain adaptive model training method, image detection method, device, equipment and medium |
Non-Patent Citations (5)
| Title |
|---|
| 代小红编: "《基于机器视觉的数字图像处理与识别研究[M]》", 31 December 2012 * |
| 宓超等: "《装卸机器视觉及其应用[M]》", 31 December 2016 * |
| 张充等: "彩虹法和成像法测量玻璃微珠折射率对比研究", 《光学与光电技术》 * |
| 杨帆等: "《精通图像处理经典算法 MATLAB版 第2版[M]》", 31 December 2018 * |
| 辛洪兵: "《计算机数字图像处理[M]》", 31 December 2015 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114842018A (en) * | 2022-07-06 | 2022-08-02 | 苏州拉索生物芯片科技有限公司 | Method for extracting characteristics of microbeads in high-density gene chip, terminal and storage medium |
| CN114842018B (en) * | 2022-07-06 | 2022-10-11 | 苏州拉索生物芯片科技有限公司 | Method for extracting characteristics of microbeads in high-density gene chip, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | HDCB-Net: A neural network with the hybrid dilated convolution for pixel-level crack detection on concrete bridges | |
| CN107122737B (en) | Automatic detection and identification method for road traffic signs | |
| CN111274843B (en) | Truck overload monitoring method and system based on monitoring video | |
| CN103729853B (en) | High score remote sensing image building under three-dimension GIS auxiliary damages detection method | |
| CN111079556A (en) | Multi-temporal unmanned aerial vehicle video image change area detection and classification method | |
| CN105160652A (en) | Handset casing testing apparatus and method based on computer vision | |
| CN112488046B (en) | Lane line extraction method based on high-resolution images of unmanned aerial vehicle | |
| CN111667470B (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
| CN111340855A (en) | Road moving target detection method based on track prediction | |
| CN113256653B (en) | Heterogeneous high-resolution remote sensing image registration method for high-rise ground object | |
| CN105405138B (en) | Waterborne target tracking based on conspicuousness detection | |
| CN114219773B (en) | Pre-screening and calibrating method for bridge crack detection data set | |
| CN112699267B (en) | Vehicle type recognition method | |
| CN110969669A (en) | Visible light and infrared camera combined calibration method based on mutual information registration | |
| CN115830004A (en) | Surface defect detection method, device, computer equipment and storage medium | |
| CN111950559A (en) | Pointer instrument automatic reading method based on radial gray scale | |
| CN115018785A (en) | Hoisting steel wire rope tension detection method based on visual vibration frequency identification | |
| CN112710632A (en) | Method and system for detecting high and low refractive indexes of glass beads | |
| CN113158954B (en) | Automatic detection method for zebra crossing region based on AI technology in traffic offsite | |
| CN111325724B (en) | Tunnel crack region detection method and device | |
| Wu et al. | Research on crack detection algorithm of asphalt pavement | |
| CN111428538B (en) | Lane line extraction method, device and equipment | |
| CN115909285A (en) | Radar and video signal fused vehicle tracking method | |
| CN108010076B (en) | End face appearance modeling method for intensive industrial bar image detection | |
| CN114862883A (en) | Target edge extraction method, image segmentation method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210427 |