CN117705822A - Cylinder surface detection method and device based on CIS and storage medium - Google Patents
Cylinder surface detection method and device based on CIS and storage medium Download PDFInfo
- Publication number
- CN117705822A CN117705822A CN202410167916.XA CN202410167916A CN117705822A CN 117705822 A CN117705822 A CN 117705822A CN 202410167916 A CN202410167916 A CN 202410167916A CN 117705822 A CN117705822 A CN 117705822A
- Authority
- CN
- China
- Prior art keywords
- cylinder
- cis
- distance
- cis sensor
- reference plane
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 34
- 230000007547 defect Effects 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 12
- 230000003044 adaptive effect Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention belongs to the technical field of image recognition, and discloses a cylinder surface detection method, a cylinder surface detection device and a storage medium based on CIS, wherein the method comprises the following steps: s1, taking any one of two end surfaces of a cylinder as a reference plane, and controlling the position of a CIS sensor so that the plane where the CIS sensor is positioned is parallel to the axis of the cylinder; s2, changing the distance between the center of the CIS sensor and the reference plane, and controlling the cylinder to rotate around the axis for one circle when changing the distance once, and acquiring side images of the cylinder by using the CIS sensor when the cylinder rotates, so as to obtain a plurality of side images; s3, respectively acquiring end face images of two end faces of the cylinder by using CIS sensors; s4, carrying out image recognition on the side image and the end face image, and judging whether the surface of the cylinder has the defect of a preset type. The invention can realize the detection of the appearance of the cylinder with higher height without increasing the cost of the CIS sensor.
Description
Technical Field
The present invention relates to the field of image recognition, and in particular, to a cylinder surface detection method and apparatus based on CIS, and a storage medium.
Background
The CIS, which is known as Contact Image Sensor, is a contact image sensor, and is composed of contact photosensitive elements. When detecting the surface of a cylindrical product, in order to improve the detection efficiency, the prior art often uses a CIS sensor to acquire an image of the surface of the cylindrical product, and obtains a detection result by performing image recognition on the acquired image.
The invention patent application with the publication number of CN110111315A and the publication date of 2019, 08 and 09 and the patent name of 'a cylinder surface detection method, a cylinder surface detection device and a cylinder surface storage medium based on CIS' discloses related technologies. However, this patent still has the following drawbacks: according to the description of paragraph [0047], in which the CIS sensor scans one revolution against the outer side of the cylinder, the collection of the analog image of the outer side of the cylinder can be completed, that is, when the height of the cylinder is relatively high, the size of the CIS sensor needs to be increased as the height of the cylinder is increased to obtain the complete surface image of the outer side with only one revolution, which definitely increases the cost of the CIS sensor.
Disclosure of Invention
The invention aims to disclose a cylinder surface detection method, a cylinder surface detection device and a storage medium based on CIS, which solve the problem of detecting the appearance of a cylinder with higher height without increasing the cost of a CIS sensor.
In order to achieve the above purpose, the present invention provides the following technical solutions:
in a first aspect, the present invention provides a CIS-based cylinder surface detection method, including:
s1, taking any one of two end surfaces of a cylinder as a reference plane, and controlling the position of a CIS sensor so that the plane where the CIS sensor is positioned is parallel to the axis of the cylinder;
s2, changing the distance between the center of the CIS sensor and the reference plane, and controlling the cylinder to rotate around the axis for one circle when changing the distance once, and acquiring side images of the cylinder by using the CIS sensor when the cylinder rotates, so as to obtain a plurality of side images;
s3, respectively acquiring end face images of two end faces of the cylinder by using CIS sensors;
s4, carrying out image recognition on the side image and the end face image, and judging whether the surface of the cylinder has the defect of a preset type.
Preferably, controlling the position of the CIS sensor such that a plane in which the CIS sensor is located is parallel to an axis of the cylinder includes:
controlling the position of the CIS sensor so that the plane in which the CIS sensor is located is parallel to the axis of the cylinder and the distance between the CIS sensor and the side surface of the cylinder is equal to a preset first distance。
Preferably, S2 comprises:
s21, changing a positional relationship between the center of the CIS sensor and the reference plane such that a distance between the center of the CIS sensor and the reference plane satisfies the following equation:
；
indicating the distance between the center of the CIS sensor and the reference plane when the distance is changed for the first time,/>、/>Respectively representing preset distance weight and size weight, wherein the sum of the distance weight and the size weight is 1,/respectively>An upper limit value representing the distance between the CIS sensor and the side of the cylinder, < >>Represents the diagonal length of the CIS sensor, < +.>Representing a preset diagonal length +.>Representing a preset second distance;
s22, controlling the cylinder to rotate around the axis for one circle, and acquiring a side image of the cylinder by using the CIS sensor when the cylinder rotates;
s23, calculating the distance between the center of the CIS sensor and the reference plane when the distance is changed next based on the side image obtained after the previous distance change；
S24, changing the position relationship between the center of the CIS sensor and the reference plane to make the distance between the center of the CIS sensor and the reference plane equal to；
S25, judgingWhether the height of the camera is larger than the height of the cylinder, if so, stopping shooting the side surface of the cylinder; if not, the process proceeds to S22.
Preferably, S22 includes:
controlling the cylinder according to a set angular velocityThe CIS sensor acquires a side image of the cylinder with an adaptive acquisition cycle as the cylinder rotates about its own axis for one revolution.
Preferably, the adaptive acquisition period is calculated as:
；
wherein,representing an adaptive acquisition period +.>Representing a preset acquisition period,/->The upper limit value of the angular velocity of the rotation of the cylinder is indicated.
Preferably, S23 includes:
saving the side images obtained after the previous distance change to a collection；
Computing a setDefect parameters of the side image in (a);
the next time the distance is changed based on the defect parameter calculation, the distance between the center of the CIS sensor and the reference plane。
Preferably, after each change of distance, the longer side of the CIS sensor is parallel to the reference plane and the shorter side of the CIS sensor is perpendicular to the reference plane.
Preferably, S4 comprises:
performing image stitching on all the obtained side images to obtain a complete side image;
and respectively identifying the end face image and the complete side face image, and judging whether the surface of the cylinder has the defect of a preset type or not.
In a second aspect, the present invention provides a CIS-based cylinder surface detection apparatus, comprising a control processor and a memory for communication connection with the control processor; the memory stores instructions executable by the control processor to enable the control processor to perform a CIS-based cylinder surface detection method of any one of the above.
In a third aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform a CIS-based cylinder surface detection method of any one of the above.
Compared with the prior art, in the process of acquiring the surface image of the cylinder with higher height, the method and the device respectively acquire the side images of different height positions of the cylinder by changing the distance between the center of the CIS sensor and the reference plane, so that the detection of the appearance of the cylinder with higher height can be realized without increasing the cost of the CIS sensor.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a CIS-based cylinder surface detection method according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
As shown in an embodiment of fig. 1, the present invention provides a CIS-based cylinder surface detection method, including:
s1, taking any one of two end surfaces of a cylinder as a reference plane, and controlling the position of a CIS sensor so that the plane where the CIS sensor is positioned is parallel to the axis of the cylinder;
s2, changing the distance between the center of the CIS sensor and the reference plane, and controlling the cylinder to rotate around the axis for one circle when changing the distance once, and acquiring side images of the cylinder by using the CIS sensor when the cylinder rotates, so as to obtain a plurality of side images;
s3, respectively acquiring end face images of two end faces of the cylinder by using CIS sensors;
s4, carrying out image recognition on the side image and the end face image, and judging whether the surface of the cylinder has the defect of a preset type.
In the invention, in the process of acquiring the surface image of the cylinder with higher height, the lateral images of different height positions of the cylinder are respectively acquired by changing the distance between the center of the CIS sensor and the reference plane, so that the detection of the appearance of the cylinder with higher height can be realized without increasing the cost of the CIS sensor.
Specifically, when acquiring the end face image, the CIS sensor may be made to shoot above the end face, thereby obtaining the end face image.
Preferably, controlling the position of the CIS sensor such that a plane in which the CIS sensor is located is parallel to an axis of the cylinder includes:
controlling the position of the CIS sensor so that the plane in which the CIS sensor is located is parallel to the axis of the cylinder and the distance between the CIS sensor and the side surface of the cylinder is equal to a preset first distance。
Specifically, the first distance may have a value ranging from 1 mm to 20 mm.
The plane in which the CIS sensor is located refers to the plane in which the photosensitive unit of the CIS sensor is located.
Preferably, S2 comprises:
s21, changing a positional relationship between the center of the CIS sensor and the reference plane such that a distance between the center of the CIS sensor and the reference plane satisfies the following equation:
；
indicating the distance between the center of the CIS sensor and the reference plane when the distance is changed for the first time,/>、/>Respectively representing preset distance weight and size weight, wherein the sum of the distance weight and the size weight is 1,/respectively>An upper limit value representing the distance between the CIS sensor and the side of the cylinder, < >>Represents the diagonal length of the CIS sensor, < +.>Representing a preset diagonal length +.>Representing a preset second distance;
s22, controlling the cylinder to rotate around the axis for one circle, and acquiring a side image of the cylinder by using the CIS sensor when the cylinder rotates;
s23, calculating the distance between the center of the CIS sensor and the reference plane when the distance is changed next based on the side image obtained after the previous distance change；
S24, changing the center and the base of the CIS sensorPositional relationship between the quasi-planes such that the distance between the center of the CIS sensor and the reference plane is equal to；
S25, judgingWhether the height of the camera is larger than the height of the cylinder, if so, stopping shooting the side surface of the cylinder; if not, the process proceeds to S22.
In the calculation process, the distance between the center of the CIS sensor and the reference plane is continuously changed, so that the side images of the areas with different distances from the side surface of the cylinder to the reference plane are obtained, and the side images of the cylinders with various lengths are obtained on the premise of not increasing the size of the CIS sensor.
And the CIS sensor photographs the side of the cylinder for the first time,computationally, not only the size of the CIS sensor but also +.>Numerical value of (2) such that->The bigger the->The farther the (I) is>The larger the number of the CIS sensor is, the larger the side image of the area of the side of the cylinder is, the larger the range of the side image of the area of the side of the cylinder is, so that the number of times of changing the distance between the center of the CIS sensor and the reference plane is reduced, and the side images of all the areas of the side of the cylinder are obtained more quickly and comprehensively.
Specifically, the rule for determining the upper limit value of the distance is: when the distance between the CIS sensor and the surface of the cylinder is larger than the upper limit value, an image of the surface of the cylinder is acquired, and the obtained image entropy is smaller than a set image entropy threshold value.
Specifically, the predetermined diagonal length is a diagonal length of a commercially available CIS sensor having the largest size.
Preferably, S22 includes:
controlling the cylinder according to a set angular velocityThe CIS sensor acquires a side image of the cylinder with an adaptive acquisition cycle as the cylinder rotates about its own axis for one revolution.
Specifically, in two images with adjacent shooting sequences, which are obtained by adopting an adaptive acquisition period, the same area of the cylinder exists, so that the two images can be spliced.
The self-adaptive acquisition period is adopted, so that the scheme of the invention can be suitable for shooting the cylinder at more rotation angular speeds.
Preferably, the adaptive acquisition period is calculated as:
；
wherein,representing an adaptive acquisition period +.>Representing a preset acquisition period,/->The upper limit value of the angular velocity of the rotation of the cylinder is indicated.
In particular, the method comprises the steps of,the more the value of (2)And if the self-adaptive acquisition period is larger, the smaller the self-adaptive acquisition period is, so that enough identical areas in the cylinder exist in two adjacent side images, and the accuracy of the subsequent image splicing result is improved.
Specifically, the upper limit value of the angular velocity means that when the angular velocity is greater than the upper limit value, the CIS sensor cannot obtain a sufficiently clear side image. For example, whether the obtained side image meets the sharpness requirement may be determined according to whether the image entropy of the side image is greater than a set image entropy threshold.
Preferably, S23 includes:
saving the side images obtained after the previous distance change to a collection；
Computing a setDefect parameters of the side image in (a);
the next time the distance is changed based on the defect parameter calculation, the distance between the center of the CIS sensor and the reference plane。
Preferably, the defect parameter calculating process includes:
first step, respectively obtainCalculated image in each side image:
for the followingSide image +.>Will->The line of pixel points closest to the reference plane in the middle is the 1 st line;
with the number of lines atThe pixel points in the range are used as the pixel points in the calculated image; s is the preset number of lines, mxrow represents +.>A maximum number of rows in (a);
secondly, calculating defect parameters based on all calculated images;
respectively calculating the variance of gray values of pixel points in each calculated image;
the defect parameters were calculated using the following formula:
；
wherein, defpar represents a defect parameter, calphou represents a set of all calculated images,representing the variance of the gray values of the pixels in the computed image i, ncal represents the total number of computed images.
Specifically, the defect parameter mainly reflects the probability of defect existence in the obtained image after the last change of the distance, and the larger the probability of defect existence, the larger the defect coefficient.
Preferably, the method comprises the steps of,the calculation function of (2) is:
；
wherein,indicating the distance between the center of the CIS sensor and the reference plane after the previous change of distance,/>Representing the upper limit value of the set defect parameter, +.>Indicating the set distance.
In particular, the method comprises the steps of,the calculation is influenced by the defect parameters, the greater the defect parameters are +.>And (3) withThe smaller the difference value is, the larger the area of the same area containing the cylinder is in the side images obtained at different heights from the reference plane, so that the more complete defects can be obtained after the subsequent image splicing, and the accuracy of identifying the defects can be improved. Whereas in case the defect parameters are smaller, the present invention is achieved by adding +.>And->The difference between the two is convenient for acquiring the lateral images of the ten thousand cylinders more quickly.
Preferably, after each change of distance, the longer side of the CIS sensor is parallel to the reference plane and the shorter side of the CIS sensor is perpendicular to the reference plane.
Specifically, taking the case of a CIS sensor with an aspect ratio of 3:2 as an example, the longer side with a value of 3 is perpendicular to the reference plane.
Preferably, S4 comprises:
performing image stitching on all the obtained side images to obtain a complete side image;
and respectively identifying the end face image and the complete side face image, and judging whether the surface of the cylinder has the defect of a preset type or not.
Specifically, the defects on the side face of the cylinder can be more complete after splicing, so that the accuracy of the identified defects is improved.
The preset type of defect includes cracks, pits, and the like.
Example 2
The invention provides a cylinder surface detection device based on CIS, which comprises a control processor and a memory, wherein the memory is used for being in communication connection with the control processor; the memory stores instructions executable by the control processor to enable the control processor to perform a CIS-based cylinder surface detection method of any one of the above.
Example 3
The present invention provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform a CIS-based cylinder surface detection method according to any one of the above.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. A CIS-based cylinder surface detection method, comprising:
s1: controlling the position of the CIS sensor by taking any one of two end surfaces of the cylinder as a reference plane, so that the plane where the CIS sensor is positioned is parallel to the axis of the cylinder;
s2: changing the distance between the center of the CIS sensor and the reference plane, and controlling the cylinder to rotate around the axis for one circle when changing the distance once, and acquiring side images of the cylinder by using the CIS sensor when the cylinder rotates, so as to obtain a plurality of side images;
s3: acquiring end face images of two end faces of the cylinder by using CIS sensors respectively;
s4: and carrying out image recognition on the side image and the end image, and judging whether the surface of the cylinder has the defect of a preset type.
2. A CIS-based cylinder surface detection method according to claim 1, wherein controlling the position of the CIS sensor such that the plane in which the CIS sensor is located is parallel to the axis of the cylinder comprises:
the position of the CIS sensor is controlled such that the plane in which the CIS sensor is located is parallel to the axis of the cylinder and the distance between the CIS sensor and the side of the cylinder is equal to a preset first distance predist.
3. A CIS-based cylinder surface detection method according to claim 2, wherein S2 comprises:
s21: the positional relationship between the center of the CIS sensor and the reference plane is changed such that the distance between the center of the CIS sensor and the reference plane satisfies the following equation:
；
indicating the distance between the center of the CIS sensor and the reference plane when the distance is changed for the first time,/>、/>Respectively representing preset distance weight and size weight, wherein the sum of the distance weight and the size weight is 1,/respectively>An upper limit value representing the distance between the CIS sensor and the side of the cylinder, < >>Represents the diagonal length of the CIS sensor, < +.>Representing a preset diagonal length +.>Representing a preset second distance;
s22: controlling the cylinder to rotate around the axis for one circle, and acquiring a side image of the cylinder by using the CIS sensor when the cylinder rotates;
s23: calculating a distance between a center of the CIS sensor and the reference plane when the next change distance is calculated based on the side image obtained after the previous change distance；
S24: changing the positional relationship between the center of the CIS sensor and the reference plane so that the distance between the center of the CIS sensor and the reference plane is equal to；
S25: judgingWhether the height of the camera is larger than the height of the cylinder, if so, stopping shooting the side surface of the cylinder; if not, the process proceeds to S22.
4. A CIS-based cylinder surface detection method according to claim 3, wherein S22 includes:
controlling the cylinder according to a set angular velocityThe CIS sensor acquires a side image of the cylinder with an adaptive acquisition cycle as the cylinder rotates about its own axis for one revolution.
5. The CIS-based cylinder surface detection method of claim 4, wherein the adaptive acquisition period is calculated as a function of:
；
wherein,representing an adaptive acquisition period +.>Representing a preset acquisition period,/->The upper limit value of the angular velocity of the rotation of the cylinder is indicated.
6. A CIS-based cylinder surface detection method according to claim 3, wherein S23 includes:
saving the side images obtained after the previous distance change to a collection；
Computing a setDefect parameters of the side image in (a);
the next time the distance is changed based on the defect parameter calculation, the distance between the center of the CIS sensor and the reference plane。
7. A CIS-based cylinder surface detection method according to claim 1, wherein the longer side of the CIS sensor is parallel to the reference plane and the shorter side of the CIS sensor is perpendicular to the reference plane after each change of distance.
8. The CIS-based cylinder surface detection method according to claim 1, wherein S4 comprises:
performing image stitching on all the obtained side images to obtain a complete side image;
and respectively identifying the end face image and the complete side face image, and judging whether the surface of the cylinder has the defect of a preset type or not.
9. A cylinder surface detection device based on CIS, which is characterized by comprising a control processor and a memory for being in communication connection with the control processor; the memory stores instructions executable by the control processor to enable the control processor to perform a CIS-based cylinder surface detection method according to any one of claims 1 to 8.
10. A computer-readable storage medium storing computer-executable instructions for causing a computer to perform a CIS-based cylinder surface detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410167916.XA CN117705822A (en) | 2024-02-06 | 2024-02-06 | Cylinder surface detection method and device based on CIS and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410167916.XA CN117705822A (en) | 2024-02-06 | 2024-02-06 | Cylinder surface detection method and device based on CIS and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117705822A true CN117705822A (en) | 2024-03-15 |
Family
ID=90152028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410167916.XA Pending CN117705822A (en) | 2024-02-06 | 2024-02-06 | Cylinder surface detection method and device based on CIS and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117705822A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6296387B1 (en) * | 1998-11-30 | 2001-10-02 | Commissariat A L'energie Atomique | Method for correcting image defects from a matrix-type X or γ-ray detector |
| CN102253055A (en) * | 2011-04-27 | 2011-11-23 | 中国计量学院 | Device and method for detecting surface defects of surface with periodical patterns |
| CN103018260A (en) * | 2011-09-27 | 2013-04-03 | 中芯国际集成电路制造(上海)有限公司 | Defect detection method |
| CN103413288A (en) * | 2013-08-27 | 2013-11-27 | 南京大学 | LCD general defect detecting method |
| CN104034795A (en) * | 2014-06-12 | 2014-09-10 | 东北大学 | Method and system for detecting defects of oil-gas pipeline by adopting quadtree algorithm based on regional genetics |
| CN108109146A (en) * | 2018-01-03 | 2018-06-01 | 韦德永 | A kind of pavement marker line defect detection device |
| CN108254540A (en) * | 2018-02-07 | 2018-07-06 | 国家林业局北京林业机械研究所 | A kind of sawn timber surface quality grades divide device and method |
| CN110111315A (en) * | 2019-04-26 | 2019-08-09 | 五邑大学 | A kind of periphery detection method, device and storage medium based on CIS |
| CN209525257U (en) * | 2018-09-29 | 2019-10-22 | 核工业北京地质研究院 | A kind of drilling core imaging spectral scanning system |
-
2024
- 2024-02-06 CN CN202410167916.XA patent/CN117705822A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6296387B1 (en) * | 1998-11-30 | 2001-10-02 | Commissariat A L'energie Atomique | Method for correcting image defects from a matrix-type X or γ-ray detector |
| CN102253055A (en) * | 2011-04-27 | 2011-11-23 | 中国计量学院 | Device and method for detecting surface defects of surface with periodical patterns |
| CN103018260A (en) * | 2011-09-27 | 2013-04-03 | 中芯国际集成电路制造(上海)有限公司 | Defect detection method |
| CN103413288A (en) * | 2013-08-27 | 2013-11-27 | 南京大学 | LCD general defect detecting method |
| CN104034795A (en) * | 2014-06-12 | 2014-09-10 | 东北大学 | Method and system for detecting defects of oil-gas pipeline by adopting quadtree algorithm based on regional genetics |
| CN108109146A (en) * | 2018-01-03 | 2018-06-01 | 韦德永 | A kind of pavement marker line defect detection device |
| CN108254540A (en) * | 2018-02-07 | 2018-07-06 | 国家林业局北京林业机械研究所 | A kind of sawn timber surface quality grades divide device and method |
| CN209525257U (en) * | 2018-09-29 | 2019-10-22 | 核工业北京地质研究院 | A kind of drilling core imaging spectral scanning system |
| CN110111315A (en) * | 2019-04-26 | 2019-08-09 | 五邑大学 | A kind of periphery detection method, device and storage medium based on CIS |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200364849A1 (en) | Method and device for automatically drawing structural cracks and precisely measuring widths thereof | |
| TW202011733A (en) | Method and device for performing target sampling on pictures | |
| US20200288065A1 (en) | Target tracking method and device, movable platform, and storage medium | |
| US20170199099A1 (en) | Method and system for measuring lens distortion | |
| CN109859137B (en) | Wide-angle camera irregular distortion global correction method | |
| CN109489566A (en) | Lithium battery diaphragm material cuts checking method for width, detection system and device | |
| JP2007228154A (en) | Image processor and image processing method | |
| WO2022206161A1 (en) | Feature point recognition-based block movement real-time detection method | |
| CN115436382B (en) | Defect detection system and method for preventing strip breakage of lithium battery pole piece | |
| CN113077392A (en) | High-accuracy automatic reading method for fuzzy photos of pointer table | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| RU2636681C2 (en) | Extended analysis for image-based evaluation of v-ribbed belt wear | |
| CN117705822A (en) | Cylinder surface detection method and device based on CIS and storage medium | |
| CN108982534A (en) | A kind of aluminium foil transfer position and condition automatic detection device and its detection method | |
| CN111429449B (en) | On-line size detection method and system for profile rolling and bending piece | |
| CN109738437B (en) | Self-healing point measuring device and method for metalized film capacitor | |
| CN108428250B (en) | X-corner detection method applied to visual positioning and calibration | |
| JP2004108828A (en) | Image input method, image input device and surface defect inspection device | |
| CN113108919B (en) | Human body temperature detection method, device and storage medium | |
| CN109360176A (en) | Image processing method, device, electronic equipment and computer readable storage medium | |
| JP7361613B2 (en) | Winding inspection method, winding inspection device, and manufacturing method of superconducting coil device | |
| CN112634298B (en) | Image processing method and device, storage medium and terminal | |
| CN110634136B (en) | Pipeline wall damage detection method, device and system | |
| TWI826106B (en) | Detecting system and detecting method | |
| JPH08292158A (en) | Method and apparatus for detecting wrinkle of sheet or the like |
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 |