CN117670976A

CN117670976A - Diameter measurement method based on visual imaging detection equipment and related device

Info

Publication number: CN117670976A
Application number: CN202211058027.7A
Authority: CN
Inventors: 王祥铜
Original assignee: Seizet Technology Shenzhen Co Ltd
Current assignee: Seizet Technology Shenzhen Co Ltd
Priority date: 2022-08-31
Filing date: 2022-08-31
Publication date: 2024-03-08

Abstract

The application discloses a diameter measurement method based on visual imaging detection equipment and a related device. The diameter measurement method comprises the following steps: acquiring point cloud data of an object to be detected, wherein the object to be detected is provided with a plurality of areas to be detected, and the surface of each area to be detected is provided with a target to be detected; projecting the point cloud data into a first two-dimensional gray level image, wherein the gray level value of each point cloud pixel point in the first two-dimensional gray level image is positively correlated with the height value of the point cloud in the corresponding point cloud data; dividing an image area of each area to be detected on the object to be detected from the first two-dimensional gray level image; acquiring a point cloud area image and a point cloud missing area image corresponding to a target to be detected in each image area; and calculating the diameter size of the target to be measured according to the point cloud area image and the point cloud missing area image. By the aid of the scheme, accuracy of detecting the diameter size of the target to be detected can be improved.

Description

Diameter measurement method based on visual imaging detection equipment and related device

Technical Field

The application relates to the technical field of visual imaging detection, in particular to a diameter measurement method based on visual imaging detection equipment and a related device.

Background

At present, in the field of semiconductor measurement such as wafers, three-dimensional morphology of the semiconductor such as the wafers can be detected by adopting 3D visual imaging equipment, and further measurement of corresponding dimensional parameters is carried out according to the three-dimensional morphology. The existing 3D visual imaging apparatus is usually an optical measurement apparatus, which can emit detection light through a light source, and then send a formed modulated light beam to the surface of an object to be measured after the detection light modulation, so that the surface of the object to be measured emits corresponding excitation light (reflection light corresponding to the modulated light beam or fluorescence generated by excitation of the modulated light beam), and further obtains an optical signal corresponding to the excitation light by using a sensor, converts the optical signal into a corresponding electrical signal, and sends the electrical signal to a corresponding processor for processing, thereby obtaining a three-dimensional shape corresponding to semiconductor measurement such as a wafer.

The existing wafer can be provided with a plurality of chips, each chip is provided with a plurality of solder balls, when the diameter of the solder balls on the chip is detected through the 3D visual imaging device, the point cloud acquired by the 3D visual imaging device is generally adopted to process so as to calculate the diameter of the solder balls, however, when the point cloud data are acquired by the 3D visual imaging device, due to the fact that the solder balls are integrally protruded, the point cloud is missed, and therefore the technical problem of inaccurate measurement of the diameter of the solder balls on the chip is caused.

Disclosure of Invention

The main purpose of the application is to provide a diameter measurement method based on visual imaging detection equipment and a related device, and aims to solve the technical problems.

To achieve the above object, the present application proposes a diameter measurement method based on a visual imaging detection apparatus, the diameter measurement method comprising:

acquiring point cloud data of an object to be detected, wherein the object to be detected is provided with a plurality of areas to be detected, and the middle surface of each area to be detected is provided with a target to be detected;

projecting the point cloud data into a first two-dimensional gray level image, wherein gray level values of pixel points of each point cloud in the first two-dimensional gray level image are positively correlated with height values of point clouds corresponding to the point cloud data;

dividing an image area of each area to be detected on the object to be detected from the first two-dimensional gray level image;

acquiring a point cloud area image and a point cloud missing area image corresponding to the target to be detected in each image area;

and calculating the diameter size of the target to be detected according to the point cloud area image and the point cloud missing area image.

Optionally, calculating the diameter size of the target to be measured according to the point cloud area image and the point cloud missing area image includes:

judging whether adjacent point cloud missing area images of the target to be detected have overlapping parts or not:

if no overlapping part exists, calculating the diameter size of the target to be measured according to the area of the region where the combined image data of the point cloud region and the point cloud missing region are located;

and if the overlapping part exists, calculating the diameter size of the target to be measured according to the circumscribed rectangle of the union region of the image data of the point cloud region and the point cloud missing region.

Optionally, calculating the diameter size of the target to be measured by the circumscribed rectangle of the union region of the image data of the root point cloud region and the point cloud missing region includes:

performing expansion processing on the point cloud region image of the target to be detected through a set expansion coefficient so that the expanded point cloud region image intersects with the edge region of the point cloud missing region image;

intersection of the expanded image data of the point cloud region image and the image data of the point cloud missing region image is obtained;

obtaining a union set through the intersection set and the image data of the point cloud area image so as to obtain processed image data;

and establishing a minimum circumscribed rectangle of the point cloud area in the image of the processed image data, and obtaining the diameter size of the target to be detected according to the side length size of the minimum circumscribed rectangle.

Optionally, the calculating the diameter size of the target to be measured according to the area of the region where the combined image data of the point cloud region and the point cloud missing region is located includes:

combining the point cloud missing areas on two opposite sides of the point cloud area to obtain a combined pattern;

calculating the areas of the areas where the combined image data of the point cloud area and the point cloud missing area are located according to the combined pattern;

and performing square calculation according to the area to obtain the diameter size of the surface to-be-measured target.

Optionally, the merging processing is performed on the point cloud missing areas on two opposite sides of the point cloud area to obtain a merged pattern, including:

combining the point cloud missing areas on two opposite sides of the point cloud area to obtain an outer contour line of the combined pattern;

the calculating the area of the combined region of the image data of the point cloud region and the point cloud missing region according to the combined pattern includes:

calculating the area according to the number of pixel points surrounded by the outer contour line; or alternatively

And calculating the area according to the coordinates of the pixel points passing by the periphery of the outer contour line.

Optionally, the step of dividing the image area of each area to be measured on the object to be measured from the first two-dimensional gray scale image includes:

establishing a minimum surrounding area surrounding all the targets to be detected in the area to be detected for each area to be detected, wherein the minimum surrounding area is positioned in the area to be detected, and the minimum surrounding area is not connected with the edge of the area to be detected;

dividing a sub-point cloud corresponding to the minimum surrounding area from the point cloud data according to the coordinate range of the minimum surrounding area;

projecting the sub-point cloud to a corresponding second two-dimensional gray scale image, and setting the second two-dimensional gray scale image as an image area of the area to be detected.

Optionally, the establishing a minimum surrounding area surrounding the at least one target to be measured for each region to be measured includes:

acquiring the minimum external annular shape of all the targets to be detected in the region to be detected;

expanding the minimum external ring by a set distance relative to the target to be detected to form a new external ring;

and determining the area surrounded by the new circumscribing ring as the minimum surrounding area.

In order to achieve the above purpose, the present application further provides a diameter measurement device based on a visual imaging detection device, which includes a data receiving module, an image conversion module, an image segmentation module and an image data processing module that are coupled in sequence;

the data receiving module is used for receiving the acquired point cloud data of the object to be detected, the object to be detected is provided with a plurality of areas to be detected, and the surface in each area to be detected is provided with a target to be detected;

the image conversion module is used for projecting the point cloud data into a first two-dimensional gray level image, wherein gray level values of point cloud pixel points in the first two-dimensional gray level image are positively correlated with height values of point cloud corresponding to the point cloud data;

the image segmentation module is used for segmenting an image area of each area to be detected on the object to be detected from the first two-dimensional gray level image;

the image data processing module is used for acquiring a point cloud area image and a point cloud missing area image corresponding to the target to be detected in each image area; and calculating the diameter size of the target to be measured according to the point cloud area image and the point cloud missing area image.

To achieve the above object, the present application further proposes a visual imaging detection apparatus comprising a memory, a processor and a visual imaging detection apparatus-based diameter measurement program stored on the memory and executable on the processor, the visual imaging detection apparatus-based diameter measurement program, when executed by the processor, implementing the steps of the visual imaging detection apparatus-based diameter measurement method as described above.

To achieve the above object, the present application further proposes a computer-readable storage medium having stored thereon a diameter measurement program based on a visual imaging detection apparatus, which when executed by a processor, implements the steps of the diameter measurement method based on a visual imaging detection apparatus as described above.

In the technical scheme of the application, the diameter size of the target to be detected is comprehensively calculated by adopting the point cloud area image and the point cloud missing area image corresponding to the target to be detected, so that the problem of inaccurate measurement data caused by point cloud missing can be solved, and the accuracy of the diameter size of the detected target to be detected can be improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained from the structures shown in these drawings without inventive effort to a person of ordinary skill in the art.

FIG. 1 is a schematic flow chart of an embodiment of a diameter measurement method based on a visual imaging detection apparatus provided in the present application;

FIG. 2 is a schematic diagram of an image area corresponding to a region to be measured in the subject;

fig. 3a to 3d are schematic flow diagrams illustrating processing of an image region corresponding to a region to be detected in another object according to the present application;

FIG. 4 is a schematic structural view of an embodiment of a diameter measurement device based on a visual imaging detection apparatus provided in the present application;

fig. 5 is a schematic diagram of a framework of an embodiment of a computer readable storage medium provided in the present application.

The implementation, functional features and advantages of the present application will be further described with reference to the accompanying drawings in conjunction with the embodiments.

Detailed Description

The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

In the present embodiment, if a directional instruction is referred to, the directional instruction is merely used to explain the relative positional relationship, movement condition, etc. between the components in a specific posture, and if the specific posture is changed, the directional instruction is changed accordingly.

In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be regarded as not exist and not within the protection scope of the present application.

Fig. 1 is a schematic flow chart of an embodiment of a diameter measurement method based on a visual imaging detection apparatus provided in the present application.

The diameter measurement method based on the visual imaging detection equipment specifically comprises the following steps:

s110: the method comprises the steps of obtaining point cloud data of an object to be detected, wherein the object to be detected is provided with a plurality of areas to be detected, and each area to be detected is provided with at least one target to be detected.

In this step, a visual imaging detection device (e.g., a 3D camera) may be used to scan the measurement surface side of the object to be measured, so that point cloud data on the measurement surface side of the object to be measured may be obtained. The point cloud data are 3d point cloud data, and can represent three-dimensional morphological characteristics of one side of a measuring surface of the object to be measured. In this embodiment, the object to be measured has a plurality of areas to be measured, and each area to be measured has at least one target to be measured.

For example, the object to be tested may be a wafer, and each wafer may be generally divided into a plurality of chip areas, and each chip area may correspond to the above-mentioned area to be tested; one chip may be generally formed in each chip area of the wafer, and each chip surface is provided with a plurality of solder balls. When the diameter of the solder ball arranged on the surface of the chip is measured, the solder ball can form a target to be measured.

S120: and projecting the point cloud data into a first two-dimensional gray level image, wherein the gray level value of each point cloud pixel point in the first two-dimensional gray level image is positively correlated with the height value of the point cloud in the corresponding point cloud data.

After the point cloud data of the object to be detected is obtained, the point cloud data can be converted into a first two-dimensional gray level image.

When detecting an object to be detected, a space coordinate system is generally established with the object to be detected (or a carrying platform for carrying the object to be detected) as a reference. The object to be measured can be horizontally arranged, and the vertical direction is used for representing the height direction of the object to be measured. When the visual imaging detection equipment is adopted to acquire the point cloud data of the object to be detected, the spatial coordinates of each point in the point cloud data can be correspondingly acquired. Converting the point cloud data into a first two-dimensional gray scale image may be represented as projecting the point cloud data into the first two-dimensional gray scale image. Specifically, the coordinates of each point in the point cloud data may be projected onto a horizontal plane to form a pixel, and the gray value of each point is positively correlated with the vertical coordinates thereof, so that a first two-dimensional gray image may be formed.

Specifically, taking a point (X1, Y1, Z1) in the point cloud data as an example, a maximum coordinate value Zmax in the vertical direction and a minimum coordinate value Zmin in the vertical maximum direction in the point cloud data may be selected. The coordinates of the point on the first two-dimensional Gray scale image after projection may be represented as (X1, Y1), and the Gray value g1= (Z1-Zmin)/(Zmax-Zmin) ×gray of the point, where Gray may be a set Gray value. For example, gray may be set to 255 or 65535 or the like.

Through the above operation, each point in the point cloud can be projected into the first two-dimensional gray scale image, and each point has a gray scale value corresponding to the vertical coordinate value at the projection point of the first two-dimensional gray scale image. And the larger the vertical coordinate value of the point in the point cloud data is, the higher the height of the point on the surface is, and the larger the gray value corresponding to the point is.

Further, for the wafer, the solder balls are all disposed on the surface of the measurement surface, that is, the plurality of solder balls have the same reference plane (i.e., measurement surface), and the point cloud data obtained by the visual imaging detection device includes the point cloud of the reference plane and the point cloud of the solder balls, and the point cloud of the solder balls is generally higher than the point cloud of the reference plane. Therefore, the classical ransac algorithm can be used for extracting the reference plane, plane correction is carried out on the point cloud of the solder ball according to the extracted reference plane parameters, and then the corrected point cloud is converted into a first two-dimensional gray level image.

S130: and dividing an image area corresponding to each area to be detected on the object to be detected from the first two-dimensional gray level image.

In this step, an image area corresponding to each area to be detected may be further divided from the first two-dimensional gray scale image. Specifically, a plurality of regions to be measured on the object to be measured can be segmented from the first two-dimensional gray scale image. For the wafer, the setting position of each chip on the wafer can be determined according to the chip distribution diagram on the wafer, and then the coordinate area of each chip area can be obtained according to the setting position, and then the image area corresponding to each area to be detected can be divided on the first two-dimensional gray level image according to the coordinate area of each chip area.

S140: and acquiring a point cloud area image and a point cloud missing area image corresponding to the target to be detected in each image area.

The visual imaging detection device can generally irradiate detection light on the surface of the object to be detected, and then detect the light according to the light information reflected by the surface of the object to be detected, so as to obtain the point cloud on the surface of the object to be detected. For some vision imaging detection devices, the emitted detection light irradiates the surface of the object to be detected at a set angle, and when the object to be detected such as a solder ball on the surface of the wafer is irradiated, the problem that the solder ball waits for the object to be detected to have point cloud defects on two opposite sides along the light propagation direction is usually caused.

When the point cloud is missing, the Z-direction coordinate of the point cloud missing region corresponding to the point on the first two-dimensional gray scale image may be set to 0, that is, the projection region of the point cloud missing region on the first two-dimensional gray scale image is black.

In this step, the image data of the first two-dimensional gray scale image may be processed by using a threshold segmentation method, so as to obtain a point cloud area image and a point cloud missing area image corresponding to the target to be detected.

The Z-direction coordinates of the points on the point cloud missing region image are set to be 0, and then the point cloud missing region image can be obtained by adopting a 0 threshold segmentation method; the point cloud area image corresponding to the target to be detected is usually higher than the reference plane, that is, the point cloud area image corresponding to the target to be detected is usually higher in gray value, so that the point cloud missing area image can be obtained by adopting the self-adaptive threshold segmentation method.

S150: and calculating the diameter size of the target to be measured according to the point cloud area image and the point cloud missing area image.

In this step, the diameter size of the target to be measured may be further calculated according to the obtained point cloud region image and the point cloud missing region image corresponding to the target to be measured.

Therefore, in this embodiment, the diameter size of the target to be measured is comprehensively calculated by using the point cloud area image and the point cloud missing area image corresponding to the target to be measured, so that the problem of inaccurate measurement data caused by the point cloud missing can be reduced, and the accuracy of the detected diameter size of the target to be measured can be improved.

Further, in the embodiment, in step S130, calculating the diameter size of the target to be measured according to the point cloud area image and the point cloud missing area image includes the following method.

Firstly, it is required to determine whether each target to be measured intersects with the point cloud missing region images of other adjacent targets to be measured or has an overlapping region.

If it is determined that the point cloud missing region image of the to-be-detected target and the point cloud missing region images of other adjacent to-be-detected targets do not intersect or do not have an overlapping region, the diameter size of the to-be-detected target can be calculated by adopting the point cloud region image of the to-be-detected target and the whole coverage area of the point cloud missing region image. For example, if the overall coverage area of the point cloud region image and the point cloud missing region image of the target to be measured is determined to be S, the diameter size of the target to be measured

In an embodiment, referring to fig. 2, fig. 2 is a schematic diagram of an image area corresponding to a region to be measured in the subject.

The white portion O1 in the figure corresponds to an image area of the point cloud of the target to be detected, and the black portion O2 in the figure corresponds to an image area of the point cloud of the target to be detected, where the point cloud is missing. In this embodiment, the plurality of objects to be measured are arranged in an array, and the image areas of the missing point clouds of each object to be measured and the adjacent other objects to be measured do not overlap, so that the overall area of the white portion O1 and the black portion O2 may be used to perform the evolution operation according to the above to obtain the diameter size of each object to be measured.

Optionally, for each target to be measured, the point cloud missing regions usually appear at two sides of the point cloud region, so before the overall coverage area of the point cloud region image and the point cloud missing region image is determined, the point cloud missing regions at two sides of the point cloud region need to be combined, so that a combined pattern is obtained. Further, by calculating the area of the combined pattern, the diameter size of the target to be measured can be further calculated.

The area of the combined pattern can be obtained by calculating according to the coordinates of all the pixel points in the area. For example, the coordinates of each point on the outer contour line of the pattern after combination can be determined by the coordinates of the pixel points, and then the whole area enclosed by the outer contour line can be calculated according to the coordinate operation. Or after the outer contour lines of the combined patterns are determined, the number of pixel points surrounded by the outer contour lines can be calculated, and then the whole area surrounded by the outer contour lines can be obtained according to the area of each pixel multiplied by the number of pixel points surrounded by the outer contour lines.

In this step, the merging processing of the point cloud missing areas on both sides of the point cloud area may specifically include the following steps: and adding the two point cloud missing areas at the two sides of the point cloud area to obtain a merging area of the point cloud missing areas of the target point to be detected.

Further, if it is determined that the target to be measured intersects with the point cloud missing region images of other adjacent targets to be measured or has an overlapping region, the calculation of the point cloud region image and the overall coverage area of the point cloud missing region image of each target to be measured is inaccurate, and at this time, the error of the calculated diameter size is increased by adopting the method of calculating the diameter by area evolution.

Therefore, the diameter size of the object to be measured can be calculated by adopting an circumscribed rectangle method. Specifically, for the point cloud area image of the target to be measured, because the solder balls wait for the point cloud to be missing at two opposite sides of the target to be measured along the light propagation direction, the point cloud area image of the target to be measured is usually in or approximately in a spindle shape, and the long axis of the spindle shape is usually perpendicular to the light propagation direction.

In this embodiment, an expansion processing method in morphological image processing is adopted, and expansion processing is performed on a point cloud area image of a target to be detected through a set expansion coefficient, so that the expanded point cloud area image intersects with an edge area of a point cloud missing area image (or the expanded point cloud area image intersects with an edge area at least partially exceeding the point cloud missing area image); and then the intersection of the image data of the expanded point cloud region image and the image data of the point cloud missing region image is obtained, and then the intersection is obtained by the image data of the original point cloud region image, so that the processed image data can be obtained, and further, an external rectangle of the point cloud region is established in the image of the processed image data, the height direction of the external rectangle is perpendicular to the light propagation direction, and at the moment, the length of the height direction of the external rectangle can be correspondingly the diameter size of the target to be measured.

In an embodiment, referring to fig. 3a to 3d, fig. 3a to 3d are schematic flow diagrams illustrating processing of an image region corresponding to a region to be measured in another object of the present application.

As shown in fig. 3a, the point cloud missing area image of each target to be detected in the area to be detected and the point cloud missing area image of other adjacent targets to be detected have an overlapping phenomenon, so that the image area corresponding to the area to be detected can be further processed.

As shown in fig. 3b, taking one of the point cloud missing area images as an example, the point cloud area image of the one of the point cloud missing area images may be expanded according to a set expansion coefficient, so as to expand the point cloud area image to a corresponding line frame L position. The wire frame L may at least partially exceed the black portion O2 (i.e., the point cloud missing region image) in the height direction Y.

As shown in fig. 3c, the intersection data is obtained by further intersecting the image data after the expansion processing with the image data corresponding to the point cloud missing region image of the target to be measured. By intersecting, the wire frame L can be brought into contact with the edge region of the black portion O2, and the portion of the wire frame L beyond the black portion O2 can be removed.

As shown in fig. 3d, further, after obtaining intersection data, a union set of the intersection data and image data corresponding to the point cloud missing area may be further calculated, an image corresponding to the union set may be obtained, a minimum external rectangle M is established according to the remaining wire frame L on the union set image, and a side length of the minimum external rectangle M is parallel to the height direction Y, where the side length of the minimum external rectangle M may correspond to the diameter size of the target to be measured.

Or in other embodiments, in the same area to be measured, if part of the targets to be measured do not overlap with the black portions O2 of the adjacent other targets to be measured, and another part of the targets to be measured overlap with the black portions O2 of the adjacent other targets to be measured; for the part of the targets to be measured which are not overlapped, calculating the diameter size of each target to be measured in the part of the targets to be measured by adopting the algorithm of area evolution as described above; for overlapping part of the objects to be measured, the diameter size of each object to be measured in the part of the objects to be measured can be obtained by establishing a minimum circumscribed rectangle M in the union image as described above.

Further, in the embodiment, in step S130, the image area of each area to be measured on the object to be measured is segmented from the first two-dimensional gray scale image, and specifically, the segmented complete image of each area to be measured may be used as the image area.

Alternatively, in other embodiments, a portion may be segmented from the complete image of each region to be measured as the image region. In this embodiment, a minimum surrounding area surrounding all objects to be measured in the area to be measured may be established for each area to be measured, where the minimum surrounding area is located in the area to be measured and the minimum surrounding area is not connected to the edge of the area to be measured; dividing a sub-point cloud corresponding to the minimum surrounding area from the point cloud data according to the coordinate range of the minimum surrounding area; projecting the sub-point cloud to a corresponding second two-dimensional gray scale image, and setting the second two-dimensional gray scale image as the image area. The method has the advantages that partial image data of the complete image edge area of the area to be measured can be removed, so that interference of edge noise points can be reduced, the number of point clouds contained in subsequent data calculation is reduced, the calculated amount in subsequent dimension measurement is reduced, and therefore the dimension measurement rate can be increased, and the dimension measurement precision is improved.

Taking one area to be tested on a wafer as an example, in a specific embodiment, the area to be tested has a corresponding complete image, the area to be tested corresponds to a single chip, a plurality of solder balls are disposed on the surface of the area to be tested, and each solder ball corresponds to a target to be tested.

When the minimum surrounding area of the area to be measured is acquired, the minimum circumscribing ring surrounding all solder balls can be acquired in the complete image of the area to be measured. Wherein, the minimum external ring shape can be matched with the arrangement shape of all solder balls.

The plurality of solder balls are arranged in an array, the minimum circumscribing ring can be a minimum circumscribing rectangle for surrounding all the solder balls, and the minimum circumscribing rectangle can correspond to a minimum surrounding area corresponding to the area to be detected.

Or, after the minimum external ring surrounding all the solder balls is obtained, the minimum external ring may be expanded to a preset size (for example, the minimum external ring is expanded in an equal proportion under the condition that the position of the central point is unchanged), so as to form a new external ring, the new external ring surrounds the minimum external ring and does not contact the edge of the region to be measured, and the new external ring may correspond to the minimum surrounding region corresponding to the region to be measured.

Therefore, when the point cloud corresponding to the pixel point in the minimum surrounding area is selected to calculate the reference height surface of the target to be measured, the point cloud in the edge area of the area to be measured can be removed, noise interference is reduced, the number of the point clouds can be reduced, the calculated amount is reduced, and the calculation rate is improved.

In the above embodiment, the plurality of solder balls are arranged in an array, and the formed minimum surrounding area may be a rectangle surrounding all the solder balls; in other embodiments, if the plurality of solder balls are arranged in a circular shape, the minimum surrounding area may be a circular shape surrounding all the solder balls.

Further, based on the same inventive concept, the present application further provides a height measuring device based on the visual imaging detection apparatus, referring to fig. 4, fig. 4 is a schematic structural diagram of an embodiment of a diameter measuring device based on the visual imaging detection apparatus provided in the present application.

The diameter measurement device 30 includes a data receiving module 310, an image conversion module 320, an image segmentation module 330, and an image data processing module 340, which are coupled in sequence. The diameter measuring device 30 may be used to implement the diameter measuring method as described previously.

The data receiving module 310 is configured to receive the obtained point cloud data of the object to be measured, where the object to be measured has a plurality of areas to be measured, and each of the areas to be measured has a surface provided with a target to be measured.

The image conversion module 320 is configured to project the point cloud data into a first two-dimensional gray scale image, where a gray scale value of each point cloud pixel point in the first two-dimensional gray scale image is positively correlated with a height value of the point cloud corresponding to the point cloud data.

The image segmentation module 330 is configured to segment an image area of each of the areas to be detected on the object to be detected from the first two-dimensional gray scale image.

The image data processing module 340 is configured to obtain a point cloud area image and a point cloud missing area image corresponding to the target to be detected in each image area; and calculating the diameter size of the target to be measured according to the point cloud area image and the point cloud missing area image.

Further, based on the same inventive concept, the application also provides a visual imaging detection device. Referring to the drawings, the present application provides a schematic frame of an embodiment of a visual imaging detection apparatus. The visual imaging detection apparatus comprises a memory, a processor and a visual imaging detection apparatus-based diameter measurement program stored on the memory and executable on the processor, the visual imaging detection apparatus-based diameter measurement program when executed by the processor performing the steps of the diameter measurement method embodiment of any one of the objects described above.

Referring to fig. 5, fig. 5 is a schematic diagram of a frame of an embodiment of a computer readable storage medium provided in the present application. The computer readable storage medium 40 stores program instructions 410 executable by the processor, the program instructions 410 may be a diameter measurement program based on a visual imaging detection apparatus for implementing the steps of the diameter measurement method embodiment of any of the objects described above.

In the several embodiments provided in the present application, it should be understood that the disclosed methods and apparatuses may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical, or other forms.

The elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over network elements. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application, or a part or all of the technical solution contributing to the prior art, may be embodied in the form of a software product stored in a computer-readable storage medium, including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned computer-readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the scope of the claims, and all equivalent structural changes made in the present application and the accompanying drawings or direct/indirect application in other related technical fields are included in the scope of the present application.

Claims

1. A diameter measurement method based on a visual imaging detection apparatus, the diameter measurement method comprising:

2. The diameter measurement method based on the visual imaging detection apparatus according to claim 1, wherein calculating the diameter size of the object to be measured from the point cloud region image and the point cloud missing region image includes:

3. The method for measuring a diameter based on a visual imaging inspection apparatus according to claim 2, wherein,

the calculating the diameter size of the target to be measured by the circumscribed rectangle of the union region of the image data of the root point cloud region and the point cloud missing region comprises the following steps:

4. The method for measuring a diameter based on a visual imaging inspection apparatus according to claim 2, wherein,

the calculating the diameter size of the target to be measured according to the area of the region where the combined image data of the point cloud region and the point cloud missing region is located comprises the following steps:

5. The method for measuring a diameter based on a visual imaging inspection apparatus according to claim 4, wherein,

the merging processing is performed on the point cloud missing areas at two opposite sides of the point cloud area to obtain a merged pattern, including:

6. The method of claim 1, wherein the step of segmenting the image area of each of the regions to be measured on the object from the first two-dimensional gray scale image comprises:

7. The method for measuring height based on a visual imaging detection apparatus according to claim 6, wherein,

the establishing a minimum surrounding area surrounding the at least one target to be measured for each region to be measured comprises the following steps:

8. The diameter measuring device based on the visual imaging detection equipment is characterized by comprising a data receiving module, an image conversion module, an image segmentation module and an image data processing module which are sequentially coupled;

9. A visual imaging inspection apparatus comprising a memory, a processor and a visual imaging inspection apparatus-based diameter measurement program stored on the memory and executable on the processor, the visual imaging inspection apparatus-based diameter measurement program when executed by the processor implementing the steps of the visual imaging inspection apparatus-based diameter measurement method of any one of claims 1 to 7.

10. A computer-readable storage medium, on which a diameter measurement program based on a visual imaging detection apparatus is stored, which when executed by a processor implements the steps of the diameter measurement method based on a visual imaging detection apparatus according to any one of claims 1 to 7.