CN111105466A - Calibration method of camera in CT system - Google Patents
Calibration method of camera in CT system Download PDFInfo
- Publication number
- CN111105466A CN111105466A CN201911246466.9A CN201911246466A CN111105466A CN 111105466 A CN111105466 A CN 111105466A CN 201911246466 A CN201911246466 A CN 201911246466A CN 111105466 A CN111105466 A CN 111105466A
- Authority
- CN
- China
- Prior art keywords
- camera
- image
- coordinates
- corner
- hospital bed
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 239000011159 matrix material Substances 0.000 claims abstract description 16
- 238000012937 correction Methods 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 12
- 238000013527 convolutional neural network Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000011900 installation process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Apparatus For Radiation Diagnosis (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a calibration method of a camera in a CT system, which is characterized in that the method collects images in the moving process of a CT sickbed through the camera with fixed position and view angle; establishing a camera coordinate system, selecting one or more corner points of a hospital bed as reference points, and detecting the coordinates of the reference points from all acquired images by a corner point detection method; selecting an image with a reference point closest to the center of the camera during collection as a standard image, taking the coordinates of the reference point in the standard image as standard coordinates, and calculating the standard coordinates of the reference points on other images except the standard image in a camera view coordinate system according to the moving square and the moving distance of the sickbed; finally solving a correction coefficient matrix which can map the reference point coordinates of each image to corresponding standard coordinates; and correcting the image to be corrected newly acquired by the camera through the correction coefficient matrix. The invention can directly utilize the CT hospital bed to quickly and accurately correct the camera.
Description
Technical Field
The invention relates to the technical field of medical imaging, in particular to a calibration method of a camera in a CT system.
Background
In the process of applying machine vision, in order to determine the correlation between the three-dimensional geometric position of a certain point on the surface of an object in space and the corresponding point in an image, a geometric model of camera imaging must be established, and the parameters of the geometric model are the parameters of a camera. These parameters must be obtained by experiments and calculations under most conditions. In image measurement or machine vision application, calibration of camera parameters is a very critical link, and the accuracy of a calibration result and the stability of an algorithm directly influence the accuracy of a result generated by the operation of a camera.
The checkerboard calibration method is the most common camera calibration method at present, and comprises the following specific steps:
step 1: shooting a black and white checkerboard image;
step 2: finding the corner points (or key mark points) in the checkerboard by an algorithm (opencv or matlab function);
step 3: calculating a parameter matrix and a distortion coefficient of the camera through the image corner points;
step 4: and inputting an image to be calibrated, and correcting the image through a parameter matrix and a distortion coefficient of the camera.
The disadvantages of the prior art are as follows:
1. the requirements on parameters such as the size and the flatness of the checkerboard are high;
2. the chessboard marking needs a flat chessboard marking plate, the price of the professional marking plate is high, the size of the customized marking plate is large, the portability is poor when the product is installed in a hospital, and the chessboard is not suitable for being integrated in the product.
3. The image after checkerboard correction still needs bed calibration so as to calculate the corresponding relation between the size of the bed and the pixels, and the calculation is relatively complex.
Disclosure of Invention
The purpose of the invention is as follows: in order to overcome the defects of the prior art, the invention provides a calibration method of a camera in a CT system, which can directly utilize a CT hospital bed to correct the camera.
The technical scheme is as follows: in order to achieve the technical effects, the technical scheme provided by the invention is as follows:
a calibration method of a camera in a CT system comprises the following steps:
(1) arranging a camera above a CT hospital bed, and keeping the position and the visual angle of the camera fixed;
(2) selecting one or more corner points of a sickbed as reference points, enabling the sickbed to move in the same direction at equal intervals, acquiring sickbed images through a camera once when the sickbed moves, and selecting an image with the reference point closest to the center of the camera during acquisition as a standard image from all acquired images;
(3) establishing a camera view angle coordinate system, and detecting the coordinates of the sickbed corner points in all the acquired images under the camera view angle coordinate system by a corner point detection method;
(4) calculating the standard coordinates of the reference points on other images except the standard image in a camera view angle coordinate system according to the moving square and the moving distance of the sickbed by taking the coordinates of the reference points in the standard image as the standard coordinates;
(5) solving a correction coefficient matrix which can map the reference point coordinates of each image extracted in the step (3) to corresponding standard coordinates; and correcting the image to be corrected newly acquired by the camera through the correction coefficient matrix.
Further, in the step (2), if there are a plurality of reference points, an image with the minimum total distance between the reference point and the center of the camera during acquisition is selected as a standard image.
Further, the corner point detection method includes: harris test, sift test, surf test.
Further, the corner detection method is a hospital bed corner extraction method based on a convolutional neural network, and comprises the following steps:
1) constructing a sample:
moving the CT hospital bed for multiple times, acquiring a hospital bed image through a camera every time the CT hospital bed is moved, and manually marking four corner points of the hospital bed in the hospital bed image and corner point coordinates under a camera view coordinate system to obtain a sample image;
2) building a hospital bed corner extraction model based on a convolutional neural network, training the model through a sample image, and automatically extracting hospital bed corners and corner coordinates according to an input hospital bed surface image through the trained model;
3) and extracting the coordinates of the corner points of the hospital bed in the input image through the constructed model for extracting the corner points of the hospital bed based on the convolutional neural network.
Has the advantages that: compared with the prior art, the invention has the following advantages:
1. the invention does not need to customize a checkerboard, but utilizes the necessary sickbed in the CT product to calibrate the camera, thereby reducing the cost;
2. the customized checkerboard has poor portability and is inconvenient to carry in the installation process of a hospital, and the camera can be calibrated anywhere by using a sickbed in the product, so that the convenience degree is high;
3. after the checkerboard calibration camera is used, the relationship between the size of the hospital bed and the pixels still needs to be calibrated, and the calibration method can calculate in one step, so that the complexity of camera calibration is reduced.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a diagram of a corner extraction model of a patient bed based on a convolutional neural network in a preferred embodiment;
fig. 3 is a schematic view of a camera view coordinate system constructed in the preferred embodiment.
Detailed Description
The invention will be further described with reference to the following drawings and specific embodiments.
Fig. 1 is a flowchart illustrating an embodiment of a calibration method for a camera in a CT system according to the present invention, as shown in fig. 1, the method includes the following steps:
s1: arranging a camera above a CT hospital bed, and keeping the position and the visual angle of the camera fixed;
s2: selecting one or more corner points of a sickbed as reference points, enabling the sickbed to move in the same direction at equal intervals, acquiring sickbed images through a camera once when the sickbed moves, and selecting an image with the reference point closest to the center of the camera during acquisition as a standard image from all acquired images;
s3: establishing a camera view angle coordinate system, and detecting the coordinates of the sickbed corner points in all the acquired images under the camera view angle coordinate system by a corner point detection method;
s4: calculating the standard coordinates of the reference points on other images except the standard image in a camera view angle coordinate system according to the moving square and the moving distance of the sickbed by taking the coordinates of the reference points in the standard image as the standard coordinates;
s5: solving a correction coefficient matrix which can map the reference point coordinates of each image extracted in the step S3 to corresponding standard coordinates; and correcting the image to be corrected newly acquired by the camera through the correction coefficient matrix.
In step S1, a camera is placed above the CT bed, keeping the camera position and view angle fixed. Specifically speaking, the camera can be located directly over the sick bed and also can be located the frame, and the sick bed can be covered in the camera visual angle, does not restrict camera mounted position.
In step S2, one or more corner points of the patient ' S bed are selected as reference points, the patient ' S bed is moved in the same direction at equal intervals, images of the patient ' S bed are acquired by the camera once each movement, and an image with the reference point closest to the center of the camera during acquisition is selected as a standard image from all the acquired images. Specifically, since the distortion of the center of the camera is minimized, the image captured when the subject is displaced from the center of the camera by the minimum amount (i.e., when the subject is being captured) is the most accurate. When a reference point (one or more of four corner points of a sickbed) is selected, the reference point can continuously move relative to the center of the camera because the sickbed continuously moves, and the reference point is closest to the center point of the camera at a shooting position, and the reference point shot by the camera is close to a positive shot. If only one reference point is selected, selecting an image of the reference point closest to the center of the camera during shooting as a standard image; if a plurality of selected reference points exist, the distance between each reference point and the center of the camera when each image is shot is calculated, then for each image, the total distance between all the reference points and the center of the camera when the image is shot is calculated, the image with the minimum total distance is selected, and the image is the image with the reference point closest to the center of the camera when the image is shot.
In step S3, a camera view coordinate system is established, and coordinates of the patient bed corner points in all the acquired images in the camera view coordinate system are detected by a corner point detection method. Specifically, since the camera position is fixed and the viewing angle direction is also fixed, the size of the camera viewing angle coordinate system is actually the size of the actual image captured by the camera. A point can be randomly selected from an image to serve as an origin point, such as a central point of the image, the upper left corner, the upper right corner, the lower left corner, the lower right corner and the like of the image, then a horizontal and vertical coordinate axis is added, coordinate scales are set, at the moment, the corner point of a sickbed in the image can be manually marked, and the coordinates of the corner point of the sickbed in the image are obtained through a constructed camera view angle coordinate system. The corner detection method comprises a harris detection method, a sift detection method, a surf detection method and a hospital bed corner extraction method based on a convolutional neural network.
In step S4, the coordinates of the reference points in the standard image are used as standard coordinates, and the standard coordinates of the reference points on the images other than the standard image in the camera view coordinate system are calculated according to the movement square and the movement distance of the patient bed. Specifically, after the standard coordinates are calculated, the camera view coordinate system is established, and the movement direction and the movement distance of the patient bed are known, so that the theoretical position coordinates of the reference point after the patient bed moves each time can be completely obtained, and the theoretical position coordinates are the standard position coordinates of the reference point in images shot each time under the condition that the camera is not distorted.
In step S5, solving a correction coefficient matrix that maps the reference point coordinates of each image extracted in step S3 to the corresponding standard coordinates; and correcting the image to be corrected newly acquired by the camera through the correction coefficient matrix. Specifically, the correction coefficient matrix is a mapping relation between actually extracted reference point coordinates and standard coordinates, and after the actually extracted reference point coordinates and the theoretical standard coordinates are obtained, the correction coefficient matrix can be obtained through a simultaneous equation.
The following provides a preferred embodiment to further illustrate the technical solution of the present invention.
The preferred embodiment comprises the steps of:
step 1: arranging a camera above a CT hospital bed, keeping the position of the camera fixed, and keeping the visual angle of the camera vertically downward;
step 2: establishing a camera view angle coordinate system, taking the upper left corner of an image collected by a camera as an original point O, transversely rightwards as the positive direction of an X axis, longitudinally downwards as the positive direction of a Y axis, setting scales of the X axis and the Y axis as required, and obtaining the camera view angle coordinate system with good components as shown in figure 3.
Step 3: building a sick bed corner extraction model based on a convolutional neural network, comprising the steps of
1) Constructing a sample:
moving the CT hospital bed for multiple times, acquiring a hospital bed image by a camera every time the CT hospital bed is moved, and manually marking corner coordinates of four corner points of the hospital bed in the hospital bed image under a camera view coordinate system to obtain a sample image;
2) building a hospital bed corner extraction model based on a convolutional neural network as shown in fig. 2, wherein the hospital bed corner extraction model comprises an input layer, a deep convolutional network, an upper sampling layer and an output layer; the color image of 640 x 480 x 3 is input into the input layer, after the characteristics are extracted through the convolution network, the size is restored to 640 x 480 x 1 through the up-sampling, and finally the color image is output through the output layer.
Training the model through a sample image, wherein a network loss function adopts a mean square error function:
Loss＝(yp-yt)2
wherein, ypPredict output for network, ytIs a true mark.
And when the model is trained, searching for the optimal parameter by adopting a gradient descent method. The trained model can automatically extract the corner points and the corner point coordinates of the sickbed according to the input sickbed surface image.
Step 4: selecting one corner point x of the sickbediThe sickbed is used as a reference point, the sickbed is enabled to move in the same direction along the length direction of the sickbed at equal intervals, the moving distance is H each time, and the reference point is ensured to be over against the center of the camera after a certain movement; acquiring a sickbed image through a camera every time the sickbed image moves, and selecting an image with a reference point closest to the center of the camera during acquisition as a standard image from all acquired images;
step 5: detecting the coordinates of the sickbed corner points in all the acquired images under a camera view angle coordinate system through a trained sickbed corner point extraction model based on a convolutional neural network;
step 6: calculating the standard coordinates of the reference points on other images except the standard image in a camera view angle coordinate system according to the moving direction and the moving distance of the sickbed by taking the coordinates of the reference points in the standard image as the standard coordinates;
step 7: solving a correction coefficient matrix which can map the extracted reference point coordinates of each image to corresponding standard coordinates; and correcting the image to be corrected newly acquired by the camera through the correction coefficient matrix.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (4)
1. A calibration method of a camera in a CT system is characterized by comprising the following steps:
(1) arranging a camera above a CT hospital bed, and keeping the position and the visual angle of the camera fixed;
(2) selecting one or more corner points of a sickbed as reference points, enabling the sickbed to move in the same direction at equal intervals, acquiring sickbed images through a camera once when the sickbed moves, and selecting an image with the reference point closest to the center of the camera during acquisition as a standard image from all acquired images;
(3) establishing a camera view angle coordinate system, and detecting the coordinates of the sickbed corner points in all the acquired images under the camera view angle coordinate system by a corner point detection method;
(4) calculating the standard coordinates of the reference points on other images except the standard image in a camera view angle coordinate system according to the moving square and the moving distance of the sickbed by taking the coordinates of the reference points in the standard image as the standard coordinates;
(5) solving a correction coefficient matrix which can map the reference point coordinates of each image extracted in the step (3) to corresponding standard coordinates; and correcting the image to be corrected newly acquired by the camera through the correction coefficient matrix.
2. The method as claimed in claim 1, wherein in step (2), if there are more than one reference points, an image with the smallest total distance between the reference point and the center of the camera is selected as the standard image.
3. The method of claim 1, wherein the corner point detecting method comprises: harris test, sift test, surf test.
4. The method for calibrating a camera in a CT system according to claim 1, wherein the corner detection method is a method for extracting corners of a patient bed based on a convolutional neural network, comprising the steps of:
1) constructing a sample:
moving the CT hospital bed for multiple times, acquiring a hospital bed image through a camera every time the CT hospital bed is moved, and manually marking four corner points of the hospital bed in the hospital bed image and corner point coordinates under a camera view coordinate system to obtain a sample image;
2) building a hospital bed corner extraction model based on a convolutional neural network, training the model through a sample image, and automatically extracting hospital bed corners and corner coordinates according to an input hospital bed surface image through the trained model;
3) and extracting the coordinates of the corner points of the hospital bed in the input image through the constructed model for extracting the corner points of the hospital bed based on the convolutional neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911246466.9A CN111105466B (en) | 2019-12-04 | 2019-12-04 | Calibration method of camera in CT system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911246466.9A CN111105466B (en) | 2019-12-04 | 2019-12-04 | Calibration method of camera in CT system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111105466A true CN111105466A (en) | 2020-05-05 |
| CN111105466B CN111105466B (en) | 2024-02-02 |
Family
ID=70422100
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911246466.9A Active CN111105466B (en) | 2019-12-04 | 2019-12-04 | Calibration method of camera in CT system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111105466B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640157A (en) * | 2020-05-28 | 2020-09-08 | 华中科技大学 | Checkerboard corner detection method based on neural network and application thereof |
| CN113382177A (en) * | 2021-05-31 | 2021-09-10 | 上海东方传媒技术有限公司 | Multi-view-angle surrounding shooting method and system |
| CN113467203A (en) * | 2021-06-10 | 2021-10-01 | 东莞市多普光电设备有限公司 | Method for aligning platform by using camera, aligning device and direct imaging photoetching equipment |
| EP4075384A1 (en) * | 2021-04-15 | 2022-10-19 | Aptiv Technologies Limited | Methods and systems for determining pre-determined points in an input image |
| CN118537334A (en) * | 2024-07-25 | 2024-08-23 | 山东电力建设第三工程有限公司 | Method, system, equipment and medium for detecting flatness of heliostat backboard |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008014940A (en) * | 2006-06-08 | 2008-01-24 | Fast:Kk | Camera calibration method for camera measurement of planar subject and measuring device applying same |
| CN109171789A (en) * | 2018-09-18 | 2019-01-11 | 上海联影医疗科技有限公司 | A kind of calibration method and calibration system for diagnostic imaging equipment |
| CN109671122A (en) * | 2018-12-14 | 2019-04-23 | 四川长虹电器股份有限公司 | Trick camera calibration method and device |
-
2019
- 2019-12-04 CN CN201911246466.9A patent/CN111105466B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008014940A (en) * | 2006-06-08 | 2008-01-24 | Fast:Kk | Camera calibration method for camera measurement of planar subject and measuring device applying same |
| CN109171789A (en) * | 2018-09-18 | 2019-01-11 | 上海联影医疗科技有限公司 | A kind of calibration method and calibration system for diagnostic imaging equipment |
| CN109671122A (en) * | 2018-12-14 | 2019-04-23 | 四川长虹电器股份有限公司 | Trick camera calibration method and device |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640157A (en) * | 2020-05-28 | 2020-09-08 | 华中科技大学 | Checkerboard corner detection method based on neural network and application thereof |
| CN111640157B (en) * | 2020-05-28 | 2022-09-20 | 华中科技大学 | Checkerboard corner detection method based on neural network and application thereof |
| EP4075384A1 (en) * | 2021-04-15 | 2022-10-19 | Aptiv Technologies Limited | Methods and systems for determining pre-determined points in an input image |
| CN113382177A (en) * | 2021-05-31 | 2021-09-10 | 上海东方传媒技术有限公司 | Multi-view-angle surrounding shooting method and system |
| CN113467203A (en) * | 2021-06-10 | 2021-10-01 | 东莞市多普光电设备有限公司 | Method for aligning platform by using camera, aligning device and direct imaging photoetching equipment |
| CN113467203B (en) * | 2021-06-10 | 2024-01-23 | 东莞市多普光电设备有限公司 | Method for aligning platform by camera, aligning device and direct imaging lithography equipment |
| CN118537334A (en) * | 2024-07-25 | 2024-08-23 | 山东电力建设第三工程有限公司 | Method, system, equipment and medium for detecting flatness of heliostat backboard |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111105466B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111105466A (en) | Calibration method of camera in CT system | |
| CN102768762B (en) | Digital camera calibration method targeted to shield tunnel defect digital radiography detection and device thereof | |
| CN108764257A (en) | A kind of pointer instrument recognition methods of various visual angles | |
| US9292925B2 (en) | Imaging system and control method thereof | |
| CN104224212A (en) | CT system, CT system scanning positioning method and CT system calibration method | |
| CN105865326A (en) | Object size measurement method and image database data acquisition method | |
| JP6516558B2 (en) | Position information processing method | |
| CN109920003B (en) | Camera calibration detection method, device and equipment | |
| CN106780623A (en) | A kind of robotic vision system quick calibrating method | |
| CN105823416A (en) | Method for measuring object through multiple cameras and device thereof | |
| CN106447733B (en) | Method, system and device for determining cervical vertebra mobility and moving axis position | |
| CN109360794B (en) | Visual detection method and device for secondary printing precision of crystalline silicon photovoltaic solar cell electrode | |
| CN108489423B (en) | Method and system for measuring horizontal inclination angle of product surface | |
| CN109308462B (en) | Finger vein and knuckle print region-of-interest positioning method | |
| CN112509060B (en) | CT secondary scanning positioning method and system based on image depth learning | |
| CN104732520A (en) | Cardio-thoracic ratio measuring algorithm and system for chest digital image | |
| CN107966100A (en) | Measuring method and measuring system based on camera array | |
| CN109409290A (en) | A kind of thermometer calibrating reading automatic recognition system and method | |
| CN107123147A (en) | Scaling method, device and the binocular camera system of binocular camera | |
| CN108895959A (en) | A kind of camera calibration plate angle point calculating method based on sub-pix | |
| CN107560541A (en) | The measuring method and device of picture centre deviation | |
| CN109540084B (en) | Method and device for measuring three-dimensional attitude of part in floating liquid | |
| CN112184784B (en) | Dual-spectrum image alignment method and device, electronic equipment and storage medium | |
| CN108917722A (en) | Vegetation coverage calculation method and device | |
| CN112634375B (en) | Plane calibration and three-dimensional reconstruction method in AI intelligent detection |
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 |