CN115631359B - Image data processing method and device for machine vision recognition - Google Patents
Image data processing method and device for machine vision recognition Download PDFInfo
- Publication number
- CN115631359B CN115631359B CN202211436965.6A CN202211436965A CN115631359B CN 115631359 B CN115631359 B CN 115631359B CN 202211436965 A CN202211436965 A CN 202211436965A CN 115631359 B CN115631359 B CN 115631359B
- Authority
- CN
- China
- Prior art keywords
- image
- template
- mathematical model
- regression algorithm
- data processing
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Optimization (AREA)
- Software Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Multimedia (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application discloses an image data processing method and device for machine vision recognition, which are used for obtaining the matching degree of a recognition image acquired by a machine vision system and a template image. Firstly, inputting an image to be recognized into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model; then comparing the matching regression value with a preset template regression value; and finally, outputting the matching degree of the identification image and the template image according to the comparison result. Because the regression analysis is adopted to replace the correlation calculation of the matching, a regression classifier can be obtained by a learning method by collecting or generating a large amount of various vectors, and the pre-calculation can be performed firstly when a standard template is established, so that the retrieval is very quick.
Description
Technical Field
The invention relates to the technical field of industrial robots, in particular to an image data processing method and device for machine vision recognition.
Background
With the development of information technology, people have also imparted human visual abilities to computers, robots, or various intelligent devices without the loss of power. Since artificial intelligence requires thinking and action like a human, it is first necessary to help a machine "understand the world" to develop artificial intelligence. Machine vision is to use a machine to replace human eyes to observe, measure and judge things. The machine vision system architecture is mainly divided into two parts, namely hardware equipment and a software algorithm, wherein the hardware equipment mainly comprises a light source system, a lens, a camera, an image acquisition card and a vision processor; the software package center algorithm mainly comprises a traditional digital image processing algorithm and an image processing algorithm based on deep learning. Machine vision is an integrated technology including image processing, mechanical engineering, control, electrical light source illumination, optical imaging, sensors, analog and digital video technology, computer hardware and software technology (image enhancement and analysis algorithms, image cards, I/O cards, etc.). A typical machine vision application system comprises an image capture module, a light source system, an image digitization module, a digital image processing module, an intelligent judgment decision module and a mechanical control execution module. The applications of machine vision in the industrial field fall into four main categories, including: identification, detection, measurement, location, and guidance. For example, in the field of automatic assembly based on machine vision guidance, it is often necessary to first find and identify an object to be assembled or an object area to be assembled (which is also a pattern of some kind of image), for example, in a flexible insert system, it is necessary to find some kind of object or device to be inserted in an input area, and on the other hand, it may be necessary to identify the position to be inserted and also to perform intelligent identification.
The conventional identification method is template matching, and usually adopts a correlation analysis method, i.e. calculating correlation area correlation coefficients of two areas (a pattern of a template and a candidate area), wherein one is a template image area of an object to be searched, and the other is a candidate area image area to be queried. (there are two ways to select the candidate region, namely, to perform waterfall search in the whole region to be checked, namely, to match the region where each pixel is located, and the device or object that is searched by the candidate is highly matched, or to adopt the image blocking technology, namely, to segment different blocks (Blob) first and then perform the correlation analysis). However, this method has two major disadvantages, namely, all blobs need to be matched, or all areas of positions (pixels) need to be matched; secondly, if the acquisition of the standard template to be searched is inaccurate, mismatching can be caused. If the placing direction of the device to be inserted is not allowed to strictly maintain a certain parallel or vertical angle, matching (using correlation analysis) needs to be performed on candidate regions at different positions and different directions, which consumes a lot of time, and the robustness of matching is affected to a certain extent.
Disclosure of Invention
The invention mainly solves the technical problem that the machine vision system in the prior art has technical defects in matching identification.
According to a first aspect, an embodiment provides an image data processing method for machine vision recognition, which is used for obtaining a matching degree between a recognition image acquired by a machine vision system and a template image, and the image data processing method includes:
inputting an image to be recognized into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model;
comparing the matching regression value with a preset template regression value, and outputting the matching degree of the identification image and the template image according to the comparison result; the template regression value is obtained by inputting the template image into the ridge regression algorithm mathematical model.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm includes:
rotating a preset rotating point in the template image for n times according to a preset rotation increment d degrees, wherein n is a natural number;
stretching the template image and each template rotation image acquired by n times of rotation into a vector x respectively to acquire the vector x 0 ，x 1 ，x 2 ，…，x n Wherein, the vector x 0 Obtaining for stretching the template image; vector x 1 ，x 2 ，…，x n Rotating the image acquisition for stretching the n templates;
unifying vectors x by extending to both sides according to a preset maximum vector size 0 ，x 1 ，x 2 ，…，x n The size of (d);
vector x of uniform size 0 ，x 1 ，x 2 ，…，x n As a positive sample of the ridge regression algorithm, setting the regression value of each vector x to be 1;
and randomly translating any one of the template images and each template rotation image acquired by n times of rotation, wherein the regression value of the translation image acquired after the random translation is as follows:
y(u,v) = Exp[-(u-u 0 ) 2 -(v-v 0 ) 2 ];
wherein (u) 0 ，v 0 ) Is the coordinate of the preset rotation point in the template image, and (u, v) is the coordinate of the translated preset rotation point;
and corresponding all the obtained translated images after translation to vectors x with uniform size to form the ridge regression algorithm mathematical model.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm further includes:
the ridge regression algorithm mathematical model comprises a ridge regression algorithm formula, the ridge regression algorithm formula comprising:
y=Wx+b；
the ridge regression algorithm formula represents all the vectors x with uniform size and a linear regression model with the offset of y, b is a constant, and W represents a vector.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm further includes:
carrying out minimization processing on the ridge regression algorithm formula, wherein the minimization processing formula is as follows:
||y-Wx-b|| 2 +λ*||W|| 2 ；
wherein λ is a weighting coefficient of a regular term, the obtaining formula of the vector W is:
W=(X T X+λI) -1 X T Y；
where X is the matrix formed by all X and Y is the matrix formed by all Y.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm further includes:
a nonlinear kernel function Q (x) is adopted to replace x to form nonlinear mapping, and a kernel function K (x 1, x 2) = Q (x 1) Q (x 2) is adopted to obtain the nonlinear mapping
W=K(X T ,X) -1 K(X T ,Y) ；
Where X is the matrix formed by all X and Y is the matrix formed by all Y.
In an embodiment, the preset rotation point is a central point of the template image.
In one embodiment, the template regression value is set to 1.
According to a second aspect, an embodiment provides an image data processing apparatus for machine vision recognition, configured to apply the image data processing method according to the first aspect to obtain a matching degree between a recognition image acquired by a machine vision system and a template image, the image data processing apparatus including:
the identification image acquisition module is used for acquiring an identification image acquired by a machine vision system;
the regression value acquisition module is used for inputting the image to be recognized into a preset ridge regression algorithm mathematical model so as to acquire a matching regression value output by the ridge regression algorithm mathematical model;
the comparison module is used for comparing the matching regression value with a preset template regression value and outputting the matching degree of the identification image and the template image according to the comparison result; the template regression value is obtained by inputting the template image into the ridge regression algorithm mathematical model;
and the result output module is used for outputting a matching result according to the matching degree.
In one embodiment, the image data processing apparatus further comprises a display module; the display module is used for displaying the matching result.
According to a third aspect, an embodiment provides a computer-readable storage medium comprising a program executable by a processor to implement the image data processing method according to the first aspect.
According to the image data processing method of the embodiment, firstly, an image to be recognized is input into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model; then comparing the matching regression value with a preset template regression value; and finally, outputting the matching degree of the identification image and the template image according to the comparison result. Because the regression analysis is adopted to replace the correlation calculation of the matching, a regression classifier can be obtained by a learning method by collecting or generating a large amount of various vectors, and the pre-calculation can be performed firstly when a standard template is established, so that the retrieval is very quick.
Drawings
FIG. 1 is a flow chart illustrating a method for processing image data according to an embodiment;
FIG. 2 is a flow diagram illustrating a method for obtaining a mathematical model of a ridge regression algorithm in an embodiment;
FIG. 3 is a diagram illustrating rotation of a template image according to an embodiment;
FIG. 4 is a diagram illustrating a translation of a standard image according to an embodiment;
FIG. 5 is a schematic diagram illustrating the translation of a non-standard image in another embodiment;
FIG. 6 is a schematic diagram illustrating a structural connection of the image data processing apparatus according to an embodiment.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments have been given like element numbers associated therewith. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, one skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
In the embodiment of the present application, regression analysis is used instead of calculation of the correlation of the matching (correlation coefficient), that is, a learning method is used instead of the correlation analysis. The basic inventive concept is that a template region image is stretched into a vector, so that the coefficient regressed by the vector formed by the standard template is 1, the more similar the regression value of the vector is close to 1, and the less similar the regression value is zero. By collecting or generating a large number of various vectors, a regression classifier can be obtained by a learning method, and pre-calculation can be performed when a standard template is established, so that the retrieval is very quick.
Example one
Referring to fig. 1, a flow chart of an image data processing method in an embodiment is shown for obtaining a matching degree between an identification image acquired by a machine vision system and a template image, the image data processing method includes:
And inputting the image to be recognized into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model.
And comparing the matching regression value with a preset template regression value. The template regression value is obtained by inputting the template image into a mathematical model of a ridge regression algorithm. In one embodiment, the template regression value is set to 1.
And step 103, outputting the matching degree.
And outputting the matching degree of the identification image and the template image according to the comparison result of the matching regression value and the template regression value.
Referring to fig. 2, a flow chart of an embodiment of a method for obtaining a mathematical model of a ridge regression algorithm is shown, in one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm includes:
Referring to fig. 3, an embodiment of a schematic diagram of template image rotation is shown, in which a preset rotation point in the template image is rotated n times by a preset rotation increment d °, where n is a natural number. In one embodiment, the predetermined rotation point is a center point of the template image.
Stretching the template image and each template rotation image acquired by n times of rotation into a vector x to acquire the vector x 0 ，x 1 ，x 2 ，…，x n Wherein, the vector x 0 Obtaining a stretching template image; vector x 1 ，x 2 ，…，x n The image acquisition is rotated for stretching n templates.
Unifying vectors x by extending to both sides according to a preset maximum vector size 0 ，x 1 ，x 2 ，…，x n The size of (c). Vector x of uniform size 0 ，x 1 ，x 2 ，…，x n As a positive sample of the ridge regression algorithm, setting the regression value of each vector x to be 1;
Please refer to fig. 4, which is a diagram illustrating the standard image being shifted according to an embodiment, because the standard image has no angular deviation, the standard image does not need to be rotated (i.e. the rotation angle is 0 degrees). Please refer to fig. 5, which is a schematic diagram illustrating the translation of the non-standard image in another embodiment, because the non-standard image can be overlapped with the standard image after being rotated, and therefore the rotation adjustment is required.
Randomly translating any image in the template images and each template rotation image acquired by n times of rotation, wherein the regression value of the translation image acquired after the random translation is as follows:
y(u,v) = Exp[-(u-u 0 ) 2 -(v-v 0 ) 2 ];
wherein (u) 0 ，v 0 ) The coordinates of a preset rotation point in the template image, and (u, v) the coordinates of the translated preset rotation point.
And corresponding all the translated images obtained after translation to vectors x with uniform size to form a ridge regression algorithm mathematical model.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm further includes:
the ridge regression algorithm mathematical model comprises a ridge regression algorithm formula, the ridge regression algorithm formula comprising:
y=Wx+b；
the ridge regression algorithm formula represents all the vectors x with uniform size and a linear regression model with the offset of y, b is a constant, and W represents a vector.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm further includes:
carrying out minimization processing on the ridge regression algorithm formula, wherein the minimization processing formula is as follows:
||y-Wx-b|| 2 +λ*||W|| 2 ；
where λ is a weighting coefficient of a regular term, the obtaining formula of the vector W is:
W=(X T X+λI) -1 X T Y；
where X is the matrix formed by all X and Y is the matrix formed by all Y.
In one embodiment, the method for obtaining the mathematical model of the ridge regression algorithm further includes:
a nonlinear kernel function Q (x) is adopted to replace x to form nonlinear mapping, and a kernel function K (x 1, x 2) = Q (x 1) Q (x 2) is adopted to obtain the nonlinear mapping
W=K(X T ,X) -1 K(X T ,Y) ；
Where X is the matrix formed by all X and Y is the matrix formed by all Y.
Referring to fig. 6, a schematic diagram of a structural connection of an image data processing apparatus in an embodiment, and an embodiment of the present application further discloses an image data processing apparatus for obtaining a matching degree between an identification image acquired by a machine vision system and a template image by applying the image data processing method described above, where the image data processing apparatus includes an identification image obtaining module 10, a regression value obtaining module 20, a comparison module 30, and a result output module 40. The identification image acquisition module 10 is used for acquiring an identification image acquired by a machine vision system. The regression value obtaining module 20 is configured to input the image to be recognized into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model. The comparison module 30 is configured to compare the matching regression value with a preset template regression value, and output the matching degree between the recognition image and the template image according to the comparison result, where the template regression value is obtained by inputting the template image into the mathematical model of the ridge regression algorithm. The result output module 40 is used for outputting the matching result according to the matching degree.
In an embodiment, the image data processing apparatus further includes a display module 50, and the display module 50 is configured to display the matching result.
The image data processing method disclosed in the embodiment of the application comprises the steps of firstly inputting an image to be recognized into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model; then comparing the matching regression value with a preset template regression value; and finally, outputting the matching degree of the identification image and the template image according to the comparison result. Because the regression analysis is adopted to replace the correlation calculation of the matching, a regression classifier can be obtained by a learning method by collecting or generating a large amount of various vectors, and the pre-calculation can be performed firstly when a standard template is established, so that the retrieval is very quick.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the controller, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a controller, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (9)
1. An image data processing method for machine vision recognition, which is used for acquiring the matching degree of a recognition image acquired by a machine vision system and a template image, and comprises the following steps:
inputting an image to be recognized into a preset ridge regression algorithm mathematical model to obtain a matching regression value output by the ridge regression algorithm mathematical model;
comparing the matching regression value with a preset template regression value, and outputting the matching degree of the identification image and the template image according to the comparison result; the template regression value is obtained by inputting the template image into the ridge regression algorithm mathematical model;
the method for acquiring the ridge regression algorithm mathematical model comprises the following steps:
rotating a preset rotating point in the template image for n times according to a preset rotation increment d degrees, wherein n is a natural number;
stretching the template image and each template rotation image acquired by n times of rotation into a vector x respectively to acquire the vector x 0 ，x 1 ，x 2 ，…，x n Wherein, the vector x 0 Obtaining for stretching the template image; vector x 1 ，x 2 ，…，x n Rotating the image acquisition for stretching the n templates;
unifying vectors x by extending to both sides according to a preset maximum vector size 0 ，x 1 ，x 2 ，…，x n The size of (d);
vector x of uniform size 0 ，x 1 ，x 2 ，…，x n As a positive sample of the ridge regression algorithm, setting the regression value of each vector x to be 1;
and randomly translating any one of the template images and each template rotation image acquired by n times of rotation, wherein the regression value of the translation image acquired after the random translation is as follows:
y(u,v) = Exp[-(u-u 0 ) 2 -(v-v 0 ) 2 ];
wherein (u) 0 ，v 0 ) Is the coordinate of the preset rotation point in the template image, and (u, v) is the coordinate of the translated preset rotation point;
and corresponding all the obtained translated images after translation to vectors x with uniform size to form the ridge regression algorithm mathematical model.
2. The image data processing method of claim 1, wherein the method for obtaining a mathematical model of a ridge regression algorithm further comprises:
the ridge regression algorithm mathematical model comprises a ridge regression algorithm formula, the ridge regression algorithm formula comprising:
y=Wx+b；
the ridge regression algorithm formula represents all the vectors x with uniform size and a linear regression model with the offset of y, b is a constant, and W represents a vector.
3. The image data processing method of claim 2, wherein the method of obtaining a mathematical model of a ridge regression algorithm further comprises:
carrying out minimization processing on the ridge regression algorithm formula, wherein the minimization processing formula is as follows:
||y-Wx-b|| 2 +λ*||W|| 2 ；
where λ is a weighting coefficient of a regular term, the obtaining formula of the vector W is:
W=(X T X+λI) -1 X T Y；
where X is the matrix formed by all X and Y is the matrix formed by all Y.
4. The image data processing method of claim 3, wherein the method of obtaining a mathematical model of a ridge regression algorithm further comprises:
a nonlinear kernel function Q (x) is adopted to replace x to form nonlinear mapping, and a kernel function K (x 1, x 2) = Q (x 1) Q (x 2) is adopted to obtain the nonlinear mapping
W=K(X T ,X) -1 K(X T ,Y) ；
Where X is the matrix formed by all X and Y is the matrix formed by all Y.
5. The image data processing method according to claim 1, wherein the preset rotation point is a center point of the template image.
6. The image data processing method of claim 1, wherein the template regression value is 1.
7. A computer-readable storage medium characterized by comprising a program executable by a processor to implement the image data processing method as claimed in claim 1 or 6.
8. An image data processing device for machine vision recognition, which is used for applying the image data processing method according to any one of claims 1 to 6 to obtain the matching degree of a recognition image acquired by a machine vision system and a template image, and comprises:
the identification image acquisition module is used for acquiring an identification image acquired by a machine vision system;
the regression value acquisition module is used for inputting the image to be recognized into a preset ridge regression algorithm mathematical model so as to acquire a matching regression value output by the ridge regression algorithm mathematical model;
the comparison module is used for comparing the matching regression value with a preset template regression value and outputting the matching degree of the identification image and the template image according to the comparison result; the template regression value is obtained by inputting the template image into the ridge regression algorithm mathematical model;
and the result output module is used for outputting a matching result according to the matching degree.
9. The image data processing apparatus according to claim 8, further comprising a display module; the display module is used for displaying the matching result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211436965.6A CN115631359B (en) | 2022-11-17 | 2022-11-17 | Image data processing method and device for machine vision recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211436965.6A CN115631359B (en) | 2022-11-17 | 2022-11-17 | Image data processing method and device for machine vision recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115631359A CN115631359A (en) | 2023-01-20 |
| CN115631359B true CN115631359B (en) | 2023-03-14 |
Family
ID=84910369
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211436965.6A Active CN115631359B (en) | 2022-11-17 | 2022-11-17 | Image data processing method and device for machine vision recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631359B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10096132B2 (en) * | 2016-01-27 | 2018-10-09 | Samsung Electronics Co., Ltd. | Method and apparatus for positioning feature point |
| CN107894189B (en) * | 2017-10-31 | 2019-08-23 | 北京艾克利特光电科技有限公司 | A kind of photoelectric sighting system and its method for automatic tracking of target point automatic tracing |
| CN108550161B (en) * | 2018-03-20 | 2021-09-14 | 南京邮电大学 | Scale self-adaptive kernel-dependent filtering rapid target tracking method |
| CN109978908B (en) * | 2019-03-21 | 2023-04-28 | 西安电子科技大学 | Single-target rapid tracking and positioning method suitable for large-scale deformation |
| CN110276785B (en) * | 2019-06-24 | 2023-03-31 | 电子科技大学 | Anti-shielding infrared target tracking method |
-
2022
- 2022-11-17 CN CN202211436965.6A patent/CN115631359B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115631359A (en) | 2023-01-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Moreno-Noguer | 3d human pose estimation from a single image via distance matrix regression | |
| Funke et al. | Generative adversarial networks for specular highlight removal in endoscopic images | |
| Coiras et al. | Segment-based registration technique for visual-infrared images | |
| CN109903313B (en) | Real-time pose tracking method based on target three-dimensional model | |
| Huang et al. | An automatic analog instrument reading system using computer vision and inspection robot | |
| Probst et al. | Automatic tool landmark detection for stereo vision in robot-assisted retinal surgery | |
| US10366307B2 (en) | Coarse-to-fine search method, image processing device and recording medium | |
| US11145080B2 (en) | Method and apparatus for three-dimensional object pose estimation, device and storage medium | |
| Kwon et al. | Practical guide to machine vision software: an introduction with LabVIEW | |
| Clement et al. | How to train a cat: Learning canonical appearance transformations for direct visual localization under illumination change | |
| Ahmine et al. | Adaptive lucas-kanade tracking | |
| Kaymak et al. | Implementation of object detection and recognition algorithms on a robotic arm platform using raspberry pi | |
| CN111507288A (en) | Image detection method, image detection device, computer equipment and storage medium | |
| Żak et al. | Local image features matching for real-time seabed tracking applications | |
| Koo et al. | Recovering the 3D shape and poses of face images based on the similarity transform | |
| CN115631359B (en) | Image data processing method and device for machine vision recognition | |
| Murase et al. | Parametric eigenspace representation for visual learning and recognition | |
| Zang et al. | A flexible visual inspection system combining pose estimation and visual servo approaches | |
| CN115019396A (en) | Learning state monitoring method, device, equipment and medium | |
| Sadeghi et al. | Unsupervised performance analysis of 3D face alignment with a statistically robust confidence test | |
| Krishna et al. | Convolution neural network for image registration | |
| Srivastava | Method of determining dynamic distance of an object from camera devices using ML and its applications | |
| Maciura et al. | Granular computing in mosaicing of images from capsule endoscopy | |
| Gao et al. | Object recognition and augmentation for wearable-assistive system using egocentric RGB-D sensor | |
| Ćirić et al. | CNN-Based Object Detection for Robot Grasping in Cluttered Environment |
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 |