CN115655104B - Method for measuring size of concave object by multidirectional image capturing - Google Patents
Method for measuring size of concave object by multidirectional image capturing Download PDFInfo
- Publication number
- CN115655104B CN115655104B CN202211257703.3A CN202211257703A CN115655104B CN 115655104 B CN115655104 B CN 115655104B CN 202211257703 A CN202211257703 A CN 202211257703A CN 115655104 B CN115655104 B CN 115655104B
- Authority
- CN
- China
- Prior art keywords
- measured
- size
- light sources
- measuring
- concave object
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000003384 imaging method Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 abstract description 8
- 238000005286 illumination Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002301 combined effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a method for measuring the size of a concave object by multidirectional image capturing, which relates to the field of size measurement and comprises the following steps: placing an object to be measured at a specified photographing position, and enabling a surface to be measured to be aligned with a camera at a fixed position; at least two light sources uniformly surrounding the central axis of the surface to be measured are sequentially and independently turned on and photographed, and the at least two light sources are obliquely arranged towards the center of the surface to be measured; performing pixel comparison on at least two obtained photos, and reserving dark pixel points; recombining and arranging the reserved dark pixels to form a new image; the new image formed is analyzed by a computer to determine the desired size. According to the invention, the object to be measured is photographed for many times by the camera, different shadows are formed by different illumination angles of photographing each time, and each deeper pixel point is recombined into a new picture for computer recognition, so that recognition errors are greatly reduced, and cost is saved.
Description
Technical Field
The invention relates to the field of size measurement, in particular to a method for measuring the size of a concave object by multi-directional image capturing.
Background
It is often necessary to measure the dimensions of some concave objects, both in the manufacturing process and in the ordinary life of people.
The concave objects such as some tubular objects, box objects and the like, if the parameters such as the inner diameter, the outer diameter, the length, the width, the height and the like of the concave objects need to be measured, the prior art is mainly divided into contact measurement and plane and scanning image capturing processing measurement technologies. The contact type measurement is to measure the object by using a measuring member like a vernier caliper which is in contact with the object, but the measuring method has low efficiency, poor precision and easy environmental limitation, and can not contact the measured object in some occasions. The plane plus scanning imaging processing measurement technology is long in time consumption on one hand and high in cost on the other hand; if the photographing identification technology is directly adopted, the computer is easy to recognize errors when automatically identifying the outline of the object in the image.
Disclosure of Invention
Aiming at the problem that the contour of a photo image of an object is difficult to identify by a computer in the prior art so that errors are easy to occur in measuring the sizes of the object, the invention aims to provide a method for measuring the sizes of the concave object by multi-directional image capturing, so as to solve the problem, enable the computer to quickly and accurately identify the contour line of the object, and further accurately and quickly measure the geometric size parameters of the object, and the specific technical scheme is as follows:
A method for measuring the size of a concave object by multi-directional imaging is characterized in that: the method comprises the following steps:
S1: placing an object to be measured at a specified photographing position, and enabling a surface to be measured to be aligned with a camera at a fixed position;
S2, sequentially and independently opening at least two light sources uniformly arranged around the central axis of the surface to be measured and photographing, wherein the at least two light sources are obliquely arranged towards the center of the surface to be measured;
S3: performing pixel comparison on at least two photos obtained in the step S2, and reserving dark pixel points;
S4: recombining and arranging the dark color pixel points reserved in the step S3 to form a new image;
s5: the new image formed in S4 is analyzed by a computer to measure the required size.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the object to be measured is photographed for many times through the camera, the illumination angles of photographing are different each time, the characteristics of the concave object are utilized, shadows with different angles are formed by the photographed pictures, dark pixel points are selected through pixel contrast, the selected dark pixel points are recombined into a new picture for computer identification, compared with the picture obtained by directly photographing the object, the identification error of the computer on the picture is greatly reduced, and compared with the laser scanning technology, the measuring cost is reduced.
Preferably: the number of the light sources is 2-4.
It is possible to completely synthesize shadows having the same shape as the object to be measured by using at least two light sources, but if too many light sources are provided to take pictures a plurality of times, not only is time wasted but also costs are increased, so 2-4 are the preferred number of light sources.
Preferably: the number of the light sources is 4.
When the two light sources are arranged, the included angle equivalent to the image capturing is 180 degrees, however, due to various reasons, the obtained shadow area is difficult to reach 180 degrees, and the included angle formed by the shadow area is generally slightly smaller than 180 degrees, so that a small part of the synthesized picture is difficult to identify when the two light sources are selected;
The three light sources are adopted to make up the defects of two light sources, but the three light sources are required to be accurately arranged on three vertexes of the equilateral triangle, the accuracy requirement of the installation point is very high, and the production cost is improved to a certain extent, so that 4 light sources are selected as the optimal scheme at present.
Preferably: the included angle between the irradiation direction of the light source and the surface to be measured is 20-60 degrees.
After the position of the light source is fixed, the included angle between the irradiation of the light source and the surface of the measured object has great influence on the definition of the outline of the measured object. When the light source is smaller than 20 degrees, the whole picture is dark, the color difference between the whole picture and the surrounding scene is small, and the outline misjudgment is easy to be caused by low identification threshold value, so that the external point is identified during measurement, and the measured value is larger than the true value; when the light source is more than 60 degrees, the overall picture brightness is high, the outlines of the measured object plane and the inner non-measured plane show high brightness values, the outline points are easy to be recognized by a computer, and therefore the size values cannot be measured.
Further: the at least two light sources are located in the same vertical plane.
By ensuring that the light sources are in the same vertical plane, the parameters such as the irradiation intensity, the irradiation area and the like of the light sources to the surface to be measured can be relatively consistent, and the consistency of the parameters such as the shadow area, the color depth and the like of each photo can be ensured as much as possible.
Further: the step S2 is completed in a dark environment.
The method is completed in a dark environment, dark pixels of the shot photo are more obvious, the probability of misjudgment during pixel comparison is low, and the probability of error during the recognition of the synthesized pattern by a computer is also smaller.
Further: further comprising S6: the computer transmits the size information measured in S5 to the controller.
The measured size information is transmitted to the controller, so that the size information can be conveniently further utilized, and particularly, the next processing procedure can be carried out industrially according to the size information of some raw materials or workpieces.
Drawings
Fig. 1 is a schematic front view (omitting the object to be measured) for showing the positional relationship of the camera and the light source in embodiment 1;
FIG. 2 is a left side view of the camera and light source positional relationship of FIG. 1;
fig. 3 is a photograph effect diagram of the upper light source in embodiment 2 when turned on;
FIG. 4 is a photograph showing the effect of the lower light source of example 2 when turned on;
Fig. 5 is a diagram of the combined effect of fig. 3 and 4.
Fig. 6 is a view showing the photographing effect of using different angle light sources for objects to be measured having different inner diameters.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
In the description of the present invention, it should be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "provided," "connected," and the like are to be construed broadly, and may be fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Embodiment one:
As shown in fig. 1 and 2, a horizontally arranged camera 1 is first installed in a closed box to ensure that the camera is in a dark environment during shooting, and an object to be measured 3 is placed in a position facing the camera 1. The box body is internally provided with 4 light sources 2, the four light sources 2 are uniformly arranged around the axis of the surface to be measured 3 and are all arranged towards the center of the surface to be measured 3, and as the object to be measured is concave, the shadow with the center angle of 180 degrees can be formed by the photos shot by each light source 2, so that the 4 light sources 2 are completely enough to form the shadow with 360 degrees. The four light sources 2 are positioned in the same plane, so that the plane formed by the four light sources 2 is parallel to the surface 3 to be measured, and the distances from the four light sources 2 to the center of the surface 3 to be measured are equal.
After an object to be measured is placed, 4 light sources 2 are sequentially and independently turned on and photographed, then the 4 obtained photographs are subjected to pixel comparison, and the pixel comparison technology is the prior art, for example, mvp machine vision algorithm platform software can be utilized. The purpose of pixel comparison is to select the deepest pixel point in 4 photos, and after each pixel point is compared in turn, each selected deepest pixel point is synthesized into a new picture, and the new picture is identified by a computer, so that the size of an object to be measured on the surface 3 to be measured is measured. Because each pixel point of the synthesized picture is the darkest pixel point and the shape of the pixel point is consistent with the surface to be detected 3, compared with a direct photographing computer, the image is easier to identify, and the probability of error generation during identification is greatly reduced. After the size is measured, the computer sends the size information to the controller so as to facilitate the operation of the subsequent process by using the size data.
As shown in FIG. 2, the included angle A between each light source 2 and the plane to be measured is preferably 20-60 degrees, so as to make the computer recognize the outline of the synthesized picture most accurate and minimize the error.
Embodiment two:
Unlike the first embodiment, the number of the light sources 2 is changed to two, the surface 3 to be measured is respectively irradiated from the upper side and the lower side, as shown in fig. 3 to 5, fig. 3 is a photograph taken when the upper light source 2 is irradiated, fig. 4 is a photograph taken when the lower light source 2 is irradiated, the photographs of fig. 3 and fig. 4 are synthesized according to the above method to obtain the photograph in fig. 5, therefore, it can be seen that the central angle of the shadow part obtained by irradiating the single light source 2 is difficult to reach 180 degrees, the synthesized photograph still has a light color of a part of the region, and the probability of error generated during computer recognition is larger than that of the probability of error generated when 4 light sources 2 are used. But since the two light sources 2 can be used with low cost, the two light sources can be used in situations where the accuracy requirements are not too high.
As shown in fig. 6, the size of the included angle a between the light source and the surface to be measured 3 has a great influence on the definition of the outline of the composite picture. The effect diagram of the photo discharged by adopting light sources with different angles for objects to be detected (phi 40 mm-phi 200 mm) with different inner diameters is shown in the diagram, and it can be clearly seen from fig. 6 that when the included angle A between the light source and the surface to be detected 3 is too small, such as 0 DEG and 15 DEG, the synthesized picture is dark, the color difference between the synthesized picture and the surrounding scene is small, the false judgment of the outline is easily caused due to the low identification threshold value, and the external point is identified during measurement, so that the measured value is larger than the true value; when the included angle A between the light source and the surface to be measured 3 is too large, such as 75 degrees and 90 degrees, the outlines of the object surface to be measured and the inner non-measured surface show high brightness values, so that outline points are easy to be unrecognized, and the size value cannot be measured. Therefore, the included angle A between the light source and the surface 3 to be measured is ensured to be 20-60 degrees, the computer identifies the contour of the synthesized picture to be the most accurate, and the error is the smallest.
The foregoing has shown and described the basic principles and main features of the present invention and the advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (6)
1. A method for measuring the size of a concave object by multi-directional imaging is characterized in that: the method comprises the following steps:
S1: placing an object to be measured at a specified photographing position, and enabling a surface to be measured to be aligned with a camera at a fixed position;
S2, sequentially and independently opening at least two light sources uniformly arranged around the central axis of the surface to be measured and photographing, wherein the at least two light sources are obliquely arranged towards the center of the surface to be measured;
S3: performing pixel comparison on at least two photos obtained in the step S2, and reserving dark pixel points;
S4: recombining and arranging the dark color pixel points reserved in the step S3 to form a new image;
S5: analyzing the new image formed in the step S4 by using a computer, and measuring the required size;
the included angle between the irradiation direction of the light source and the surface to be measured is 20-60 degrees.
2. A method for measuring the size of a concave object for multi-directional imaging as defined in claim 1, wherein: the number of the light sources is 2-4.
3. A method for measuring the size of a concave object for multi-directional imaging as defined in claim 2, wherein: the number of the light sources is 4.
4. A method for measuring the size of a concave object for multi-directional imaging as defined in claim 1, wherein: the at least two light sources are located in the same vertical plane.
5. A method for measuring the size of a concave object for multi-directional imaging according to any one of claims 1 to 4, wherein: the step S2 is completed in a dark environment.
6. The method for measuring the size of a concave object for multi-directional imaging according to claim 5, wherein: further comprising S6: the computer transmits the size information measured in S5 to the controller.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211257703.3A CN115655104B (en) | 2022-10-14 | 2022-10-14 | Method for measuring size of concave object by multidirectional image capturing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211257703.3A CN115655104B (en) | 2022-10-14 | 2022-10-14 | Method for measuring size of concave object by multidirectional image capturing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115655104A CN115655104A (en) | 2023-01-31 |
| CN115655104B true CN115655104B (en) | 2024-07-23 |
Family
ID=84987849
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211257703.3A Active CN115655104B (en) | 2022-10-14 | 2022-10-14 | Method for measuring size of concave object by multidirectional image capturing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115655104B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013028A (en) * | 2006-01-31 | 2007-08-08 | 欧姆龙株式会社 | Image processing method and image processor |
| CN101438129A (en) * | 2006-04-05 | 2009-05-20 | K·赛佩莱 | Method for measuring/recognizing shape |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7907765B2 (en) * | 2001-03-28 | 2011-03-15 | University Of Washington | Focal plane tracking for optical microtomography |
| JP2014137482A (en) * | 2013-01-17 | 2014-07-28 | Olympus Corp | Photographing device and photographing illumination device |
| CN103630070A (en) * | 2013-04-08 | 2014-03-12 | 苏州工业园区凯艺精密科技有限公司 | Detection method for image detector and image detector |
| JP6403446B2 (en) * | 2014-06-09 | 2018-10-10 | 株式会社キーエンス | Image inspection apparatus, image inspection method, image inspection program, computer-readable recording medium, and recorded apparatus |
| CN108240793A (en) * | 2018-01-26 | 2018-07-03 | 广东美的智能机器人有限公司 | Dimension of object measuring method, device and system |
| CN109596058A (en) * | 2019-02-01 | 2019-04-09 | 东莞中科蓝海智能视觉科技有限公司 | Size detection and identification method for plastic workpiece |
| CN112734847A (en) * | 2021-01-15 | 2021-04-30 | 中国科学技术大学 | Multi-target optical fiber position accurate detection positioning system and method |
| CN114119779A (en) * | 2021-10-29 | 2022-03-01 | 浙江凌迪数字科技有限公司 | Method for generating material map through multi-angle polishing shooting and electronic device |
-
2022
- 2022-10-14 CN CN202211257703.3A patent/CN115655104B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013028A (en) * | 2006-01-31 | 2007-08-08 | 欧姆龙株式会社 | Image processing method and image processor |
| CN101438129A (en) * | 2006-04-05 | 2009-05-20 | K·赛佩莱 | Method for measuring/recognizing shape |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115655104A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN208672539U (en) | A kind of foliated glass edge faults detection device based on Image Acquisition | |
| JP3867724B2 (en) | Surface condition inspection method, surface condition inspection apparatus and substrate inspection apparatus using the method | |
| US8948491B2 (en) | Method and apparatus for detecting surface unevenness of object under inspection | |
| TWI440847B (en) | Inspection method | |
| US20140043472A1 (en) | Tire surface shape measuring device and tire surface shape measuring method | |
| WO2010090605A1 (en) | Methods for examining a bonding structure of a substrate and bonding structure inspection devices | |
| CN102713671A (en) | Point cloud data processing device, point cloud data processing method, and point cloud data processing program | |
| CN106643555B (en) | Connector recognition methods based on structured light three-dimensional measurement system | |
| WO2022126870A1 (en) | Three-dimensional imaging method and method based on light field camera and three-dimensional imaging measuring production line | |
| CN112001917A (en) | Machine vision-based geometric tolerance detection method for circular perforated part | |
| JP2009115512A (en) | Article inspection method | |
| US9245375B2 (en) | Active lighting for stereo reconstruction of edges | |
| CN115082538A (en) | 3D reconstruction system and method of multi-vision gimbal parts surface based on line structured light projection | |
| JP2000121338A (en) | Electronic component inspecting device | |
| US10853935B2 (en) | Image processing system, computer readable recording medium, and image processing method | |
| Lin et al. | Real-time image-based defect inspection system of internal thread for nut | |
| CN115655104B (en) | Method for measuring size of concave object by multidirectional image capturing | |
| TWI480507B (en) | Method and system for three-dimensional model reconstruction | |
| CN113566706B (en) | Device and method for composite rapid high-precision visual positioning | |
| JP2006322951A (en) | Method and device for surface condition inspection, and device for inspecting substrate | |
| CN118129615A (en) | Wafer film thickness detection light beam calibration method, device and system | |
| JP4218283B2 (en) | Target projection type three-dimensional shape measuring method and apparatus | |
| JP6121123B2 (en) | Measuring device and measuring method | |
| JP5280918B2 (en) | Shape measuring device | |
| JP2021071359A (en) | Substrate inspection device, substrate processing device and substrate inspection method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |