CN115014228A

CN115014228A - Embedded extensometer based on vision measurement and double-shaft vision measurement method

Info

Publication number: CN115014228A
Application number: CN202210707403.4A
Authority: CN
Inventors: 李长太
Original assignee: Shenzhen Haisaimu Technology Co ltd
Current assignee: Shenzhen Haisaimu Technology Co ltd
Priority date: 2022-06-21
Filing date: 2022-06-21
Publication date: 2022-09-06

Abstract

The application provides an embedded extensometer based on visual measurement and a double-axis visual measurement method, which are applied to the technical field of optical measurement experimental mechanics and three-dimensional digital images, wherein the embedded extensometer comprises a platform mechanism, an image acquisition unit and an image processing unit, the image acquisition unit and the image processing unit are arranged in the platform mechanism, the image acquisition unit comprises a lens and a camera, the image processing unit comprises an embedded processor, and the processor is electrically connected with the camera. The marking points are distributed in the axial direction of the sample, and other characteristic marks are not required to be arranged in the transverse direction, so that image acquisition and image processing in visual measurement can be integrated into a whole to form the embedded extensometer, full-automatic deformation measurement can be carried out on material deformation in a biaxial loading test based on vision, the structure is compact, the cost is low, and the full-automatic deformation measurement device can be flexibly applied to different measurement occasions.

Description

Embedded extensometer based on vision measurement and double-shaft vision measurement method

Technical Field

The application relates to the technical field of optical measurement experiment mechanics and three-dimensional digital images, in particular to an embedded extensometer based on visual measurement and a double-shaft visual measurement method.

Background

The deformation detection can be applied to various material tests, on one hand, the product quality is ensured to be qualified, and on the other hand, the rationality of material design is verified. In particular, in the military industry and scientific research field, more and more new materials need to pass biaxial loading tests such as biaxial stretching, biaxial compression, biaxial fatigue and the like of the materials to verify the mechanical properties of the materials.

At present, for the deformation measurement of a material subjected to biaxial loading, extensometers based on visual measurement are preliminarily provided, but the visual schemes of the extensometers can only carry out deformation measurement in one deformation direction (such as axial direction or transverse direction), so that the biaxial measurement still needs to be realized by combining other measurement means, and the extensometers are complex in equipment, inconvenient to operate and high in cost.

Therefore, there is a need to provide a new extensometer solution for dual axis loading tests.

Disclosure of Invention

In view of this, the embodiments of the present disclosure provide an embedded extensometer and a biaxial vision measurement method based on vision measurement, which can perform full-automatic vision identification processing for axial and transverse biaxial loading deformation tests, and have the advantages of simple structure, low cost, more comprehensive functions, and higher efficiency.

The embodiment of the specification provides the following technical scheme:

an embodiment of the present specification provides an embedded extensometer, including: the image acquisition unit and the image processing unit are arranged in the platform mechanism, the image acquisition unit comprises a lens and a camera, the image processing unit comprises an embedded processor, and the processor is electrically connected with the camera;

the camera and the lens are configured to perform the following operations: collecting a target image corresponding to a sample in a biaxial loading test, wherein at least two first mark points are arranged on the axial direction of the sample;

the processor is configured to perform the following operations:

identifying boundary features and marker features in the target image, wherein the boundary features are image features of the boundary of the specimen in the transverse direction in the target image, and the marker features comprise corresponding image features of the at least two first marker points in the target image;

and respectively processing the boundary features and the marking features based on a digital speckle correlation method so as to correspondingly acquire deformation data of the sample in the transverse direction and the axial direction.

An embodiment of the present specification further provides a biaxial vision measurement method, which is applied to the embedded extensometer in any one embodiment of the present application, and the biaxial vision measurement method includes:

in a biaxial loading test, a target image corresponding to a sample is collected through a camera and a lens, wherein at least two first mark points are arranged on the axial direction of the sample;

automatically identifying boundary features and mark features in the target image through a processor, and respectively processing the boundary features and the mark features based on a digital speckle correlation method to correspondingly acquire deformation data corresponding to the specimen in the transverse direction and the axial direction, wherein the boundary features are image features of the boundary of the specimen in the transverse direction in the target image, and the mark features comprise image features corresponding to the at least two first mark points in the target image.

Compared with the prior art, the embodiment of the specification adopts at least one technical scheme which can achieve the beneficial effects that at least:

the measurement of the gauge length is the mark point, only at least two mark points need to be set, the method is very convenient, and the transverse boundary of the sample can be directly used as the characteristic aiming at the transverse mark without arranging other characteristic marks. Meanwhile, the embedded processor (such as a chip) is adopted for controlling image acquisition and processing image calculation, external processing equipment (such as a computer, a server and the like) is not required to be connected, so that the image calculation is carried out while the image acquisition is controlled by the processor, and after the embedded processor is adopted, the structure is simpler, the calculation and control process is simpler, the processing capacity is stronger, and the efficiency is higher.

In addition, the image acquisition and processing are integrated into one measuring head (namely, an embedded extensometer), so that the structure is simple, the image acquisition and processing can be flexibly deployed and used in different application scenes, the image acquisition and analysis of the whole measuring area can be realized through the measuring head, the automatic identification and measurement can be realized aiming at the axial marking point and the transverse boundary, the deployment and the application are quicker and more efficient, and the cost is lower.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in 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 application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a schematic diagram of a two-axis deformation vision measurement scheme for a vision-based embedded extensometer of the present application;

FIG. 2 is a schematic diagram of the construction of an embedded extensometer of the present application;

FIG. 3 is a schematic diagram of the processor computational logic in an embedded extensometer of the present application;

FIG. 4 is a flow chart of a biaxial vision measurement method of the present application.

Detailed Description

Embodiments of the present application are described in detail below with reference to the accompanying drawings.

The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. It is to be understood that the embodiments described are only a few embodiments of the present application and not all embodiments. The present application is capable of other and different embodiments and its several details are capable of modifications and/or changes in various respects, all without departing from the spirit of the present application. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the present application, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number and aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.

It should be further noted that the drawings provided in the following embodiments are only schematic illustrations of the basic concepts of the present application, and the drawings only show the components related to the present application rather than the numbers, shapes and dimensions of the components in actual implementation, and the types, the numbers and the proportions of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.

In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details.

Existing extensometers for visual measurements are still only used in uniaxial loading tests, where the visual measurements are typically two of:

one is by a full-field speckle identification and measurement method, but the operation is complicated, and the use scene is limited, and only the measurement result in the axial direction can be provided.

For example, patent document (publication No. CN 103575227B) discloses a method for implementing a visual extensometer based on data speckle, which is based on digital speckle recognition and deformation measurement, and this measurement method can implement deformation measurement in a full field, but the processes of making speckles and implementing camera calibration are very complicated, the efficiency is too low to implement automatic measurement, and only axial visual measurement can be implemented, and the measurement requirement of fast response cannot be met.

The other type is a transverse video extensometer which is composed of a single camera, a lens, a bracket and the like, shoots a sample at a short distance and can realize the measurement of the transverse deformation of the sample. However, this method can only realize the transverse deformation measurement, which makes the measurement cost high and the structure complex, and in addition, if the bidirectional deformation measurement is to be realized, an axial contact extensometer needs to be matched.

For example, patent document (publication No. CN 209085554U) discloses a lateral video extensometer which is composed of a single camera, a lens, a holder, and the like, and which can take a close-range image of a sample to measure lateral deformation of the sample. Meanwhile, in order to realize full-automatic bidirectional deformation measurement, a full-automatic axial contact extensometer is matched, so that the use process is very complicated, and the efficiency of the measurement process is lower.

In view of the above, the inventor proposes a biaxial measurement scheme of a visual extensometer by deeply researching and improving a visual measurement scheme, an extensometer and the like, wherein the biaxial measurement scheme comprises the following steps: as shown in fig. 1, at least two first mark points are arranged in the axial direction of the sample to form an axial mark feature (i.e. as an axial feature mark), and the boundary of the sample in the transverse direction is used as a transverse feature mark, so that other mark features are not needed, the whole image acquisition and image processing are greatly simplified, and a processor can be introduced into the acquisition front end to form a vision-based embedded extensometer, so that the image calculation processing can be performed while the image is acquired by using the embedded extensometer, the feature mark can be automatically identified, and the transverse and axial biaxial deformation measurement can be realized based on the image feature of the feature mark.

Compared with the traditional visual extensometer scheme based on data speckles, the method has the advantages that complex feature identification (such as speckle pieces) does not need to be set, complex and low-efficiency image processing is not needed to be carried out on the complex feature identification, at least two marking points (namely feature identifications) are only set in the axial direction, automatic identification and measurement can be carried out on the axial marking points and the transverse boundary through the embedded extensometer, non-contact double-axis visual measurement can be realized, the structure is simple, the cost is low, the processing performance is high, and the efficiency is high.

In addition, compare in the horizontal video extensometer of tradition, owing to only need an embedded extensometer, need not other auxiliary equipment, therefore can be directed against various measurement scenes and need use this embedded extensometer to carry out the biax measurement in a flexible way, the adaptability is stronger, and the structure is very simple, need not too much operation, and the operation is very simple, and use cost is low.

The technical solutions provided by the embodiments of the present application are described below with reference to the accompanying drawings.

As shown in fig. 2, embodiments of the present description provide a vision-based embedded extensometer, which may include: platform mechanism 6, image acquisition unit 2 and image processing unit 1, wherein image acquisition unit 2 and image processing unit 1 set up in platform mechanism 6, and image acquisition unit 2 includes camera 21 and camera 22, and image processing unit 1 includes embedded treater (such as chip), the treater is connected with camera 22 electricity.

In implementation, the platform mechanism 6 may be a platform for device installation, debugging, and the like, may be a mechanical structure platform, such as an installation mechanism, and may also be an electromechanical structure platform, such as a pan-tilt, and the like, so as to integrate the image acquisition unit and the image processing unit into the platform mechanism 6, which is not limited herein.

In an embedded extensometer, the camera and the lens are configured to perform the following operations: and acquiring a target image corresponding to the sample in the biaxial loading test. It should be noted that the camera may be an industrial camera device, such as an industrial camera, an industrial video camera, etc.; accordingly, the lens may also be an industrial lens for industrial use. In the implementation, the camera and the lens are selected and used according to the application requirements, and are not limited.

As shown in fig. 1, at least two first mark points may be disposed in the axial direction of the workpiece sample as axial feature marks, so that in the biaxial vision measurement, based on only the feature marks using the first mark points as the axial direction and the feature marks using the transverse boundaries of the sample as the transverse direction, without adding other feature marks, the image processing of these few feature marks can be performed based on these few feature marks without using a high-performance and complex-structure processing unit (such as a computer) to perform complex processing on these feature marks, but based on an embedded processor (such as an ASIC, an FPGA, a DSP, a CPU, and the like), and thus, without the auxiliary processing of other devices, the high-performance and high-efficiency biaxial deformation vision measurement can be achieved.

When the mark points are arranged in the axial direction, the shape of the mark points, the number of the mark points, the mutual arrangement manner between the mark points, the distance between the mark points, and the like may all be determined according to application requirements, and are not limited herein.

In implementation, the processor may be a processor architecture integrated with functional units such as an image recognition functional module for automatically recognizing feature identifiers and a deformation data processing functional module based on digital speckle correlation (DIC). Thus, the processor may be configured to perform the following operations:

and automatically recognizing the characteristic identifier. Specifically, boundary features and mark features in the target image are identified, wherein the boundary features are image features of the boundary of the specimen in the transverse direction in the target image, and the mark features comprise corresponding image features of the at least two first mark points in the target image;

axial and transverse deformations are automatically calculated and analyzed based on DIC. Specifically, the boundary features and the marking features are respectively processed based on a digital speckle correlation method to correspondingly acquire deformation data of the sample in the transverse direction and the axial direction.

It should be noted that the boundary feature may be an image feature of the boundary of the sample in the target image, for example, a coordinate position where each pixel point on the boundary may be used as the boundary feature. The mark feature may be an image feature of a mark point on the sample in the target image, such as a coordinate position of a corresponding pixel of the mark point, for example, the number of pixel points included in the mark point, and the like.

In implementation, the processor may be a processor with a homogeneous architecture, or may be a processor with a heterogeneous architecture, and the processor with the corresponding architecture may be performed according to deployment application needs (such as cost, hardware structure, and the like); also, the processor type may be selected according to the application, such as in the form of an ASIC, FPGA, DSP, CPU, GPU, etc. Therefore, the processor is not limited herein.

In the implementation, a digital speckle correlation (DIC, also called digital image correlation) is a non-contact optical measurement method for measuring data such as deformation displacement by spraying random speckles on the surface of an object and accurately matching corresponding points in speckle images before and after deformation of the object. Therefore, after obtaining the boundary features, the labeled features, the axial direction labeled features and the transverse direction boundary features can be calculated and analyzed based on DIC, so as to obtain deformation data of the sample in the biaxial loading test.

The axial marking points and the transverse boundaries of the sample are used as visual feature identifiers in the biaxial measurement, no other feature identifiers need to be additionally arranged, and complex image processing is not needed to be carried out on the feature identifiers, so that high-performance and high-efficiency automatic image recognition and processing can be carried out on the visual feature identifiers based on an embedded processor, the integral structure of the embedded extensometer is very simple, the deployment, application and related operations are very convenient, and the use cost is lower.

In some embodiments, the coordinates of the mark points, the coordinates of the boundaries, and the like can be used as features to identify the image features in the image, which is beneficial to the recognition and calculation processing of the image features by the processor.

In one example, the marking feature may be identified by identifying corresponding first coordinate information of the at least two first marking points in the target image, where the first coordinate information may be coordinate data of the marking points in the target image.

In one example, a detection algorithm for image features may be provided in the processor, such as using a detection algorithm to automatically detect and identify image features of the transverse boundary and the axial marker in the image, for example, using an edge detection algorithm to identify coordinates of feature identifiers of the transverse boundary and the axial marker in the target image. It should be noted that the image processing algorithm (such as edge detection) may be an operator for performing recognition detection on the feature identifier, and the specific operator is not limited.

In one example, a machine learning model (e.g., a neural network model) may be deployed in the processor to obtain image features whose features are identified in the image based on the neural network. Specifically, a target image dynamically acquired in a biaxial loading test can be input into a neural network model according to frames, and then the neural network model is used for quickly detecting the characterization of a characteristic region (x, y, w, h) corresponding to a transverse boundary and an axial marking point in the target image, wherein x and y are coordinate values in the transverse direction and the axial direction respectively, and w and h are the width and the height of the characteristic region meeting the application requirements respectively. It should be noted that the machine learning model (e.g., the neural network model) may be a classification model trained in advance for the feature identifier, and the specific model is not limited.

In some embodiments, a sub-graph processing algorithm may be employed in the processor, so that after the feature identifier in the target image is identified, the processor may quickly and accurately process the sub-graph region of the feature identifier in the image.

In an implementation, after recognizing that the feature identifier is at an approximate position of the target image, the processor may quickly partition a sub-image region corresponding to each feature identifier (e.g., a mark point in an axial direction) in the target image, and then perform image processing on the sub-image region to obtain second coordinate information as the mark feature. The second coordinate information may be coordinate information capable of meeting a preset requirement, and the coordinate information may be used to reflect coordinates of the sub-image region.

In an example, the first coordinate information can be used as coordinate information for fast recognition processing, then the sub-image region is fast recognized and accurately positioned according to the first coordinate information, and further, the sub-image region is subjected to image refinement processing, so that more accurate second coordinate information can be obtained, and the processing efficiency and accuracy can be improved.

In one example, the processor may first perform corresponding preprocessing on the sub-map region, such as preprocessing including, but not limited to, at least one of the following: and gray level conversion and mean value filtering are carried out, so that the processor can carry out rapid processing on the image of the preprocessed sub-image region, and the processing performance and efficiency of the processor are improved. It should be noted that these image preprocessing methods can also be used for processing the target image, and the preprocessed target image is easier to process, which can further reduce the performance requirement of the processor.

In an example, the processor may perform image processing for edge detection on the sub-image region, so that center coordinate data corresponding to the sub-image region may be determined as the second coordinate information according to the detection result, and the feature of the sub-image region is more accurately reflected by using the coordinate of the center pixel point as the second coordinate information. It should be noted that the edge detection may be performed by using an existing detection method, such as a canny edge detection operator, which may reduce the performance requirement of the processor.

In one example, the processor may perform edge detection on a lateral boundary, i.e., edge detection on the target image in a lateral direction to identify the boundary feature.

In an example, after the edge detection, the processor may further filter the detected edge profile, and fit the edge meeting the preset requirement, so as to return the coordinates of the center point of the fitted sub-image region.

In an example, a mapping relationship between the recognition type of the feature identifier (such as a mark point and a boundary) and the sub-image region matching may be preset in the processor, so that when the image feature of the feature identifier is preliminarily recognized, the processor performs image processing on the sub-image region corresponding to the feature identifier quickly and accurately according to the mapping relationship.

For example, the type of the mark point can be determined according to the central pixel of the sub-image region, and the pixel points of the sub-image region are filtered by adopting different thresholds according to the type of the mark point, so that the filtered image pixel points are easier to process and higher in accuracy.

In one example, the processor may perform edge detection on the image after filtering, for example, edge detection on the filtered gray scale map in conjunction with an edge detection operator (e.g., canny operator).

In some embodiments, by disposing a small number of mark points in the transverse direction, for example, disposing at least two second mark points in the transverse direction of the sample, where the mark features may further include image features corresponding to the at least two second mark points in the target image, the processor may quickly and accurately implement biaxial visual measurement based on the plurality of mark points, that is, image features corresponding to the first mark point, the second mark point, and the boundary are extracted together in the image processing, and perform DIC calculation analysis based on these image features, so that a more accurate deformation result may be obtained.

Specifically, the transverse and axial gauge length can be measured based on the mark points, so that the strain calculation in the gauge length between the multiple mark points can be calculated, for example, the strain results in the axial and transverse gauge lengths can be calculated, the three-dimensional strain measurement can be realized, the comprehensive data processing and analysis of the multiple gauge lengths can be realized, and the measurement result is more accurate.

In some embodiments, an auxiliary light source is further integrated into the embedded extensometer to provide auxiliary light when the camera performs image acquisition.

In implementation, the embedded extensometer further includes a light source 4, where the light source 4 is disposed in the platform mechanism 6, and the light source is used for illuminating when the camera performs image acquisition on the sample.

In one example, the image processing unit 2 (e.g., a processor) is disposed at a central position of the platform mechanism 6, the camera 22 and the lens 21 are disposed on a central axis of the platform mechanism 6, and the light source 4 is disposed at a side of the camera 22, so that the light source 4 provides light for the camera 22 to assist in illuminating.

In some embodiments, an angle measuring device for measuring an angle is integrated in the embedded extensometer, and the angle between the sample and the camera is measured in real time by using the angle measuring device.

In implementation, the embedded extensometer further includes an angle encoder 5, wherein the angle encoder 5 is disposed in the platform mechanism 6, and the angle encoder 5 is used for acquiring an angle between the specimen and the camera.

In some embodiments, after the angle is acquired, the processor may control the camera to perform tracking type image acquisition on the sample, so as to improve the measurement accuracy. Specifically, the processor is further used for controlling the camera to track and acquire a target image of the sample according to the angle.

In some embodiments, the embedded extensometer is integrated with a distance meter for measuring distance, with which the distance between the specimen and the camera is measured. Specifically, embedded extensometer still includes laser range finder 7, and laser range finder 7 sets up in platform mechanism 6, laser range finder 7 be used for measuring the sample with the distance between the camera.

In one example, the laser range finder 7 may be mounted close to the lens, which is beneficial to improve the accuracy of ranging.

In one example, the laser range finder 7 can be installed between the lens and the angle encoder, and the structure is compact, so that the volume of the extensometer is reduced, and the measurement precision is improved.

In some embodiments, each functional component in the extensometer may be mounted in a housing, thereby forming a single unitary body that facilitates use of the extensometer in a variety of environments. Specifically, the embedded extensometer further includes a mounting housing 9, wherein the platform mechanism 6 is mounted in the mounting housing 9.

In one example, the housing is responsible for packaging the mounting and commissioning platform, processor (i.e., chip), industrial camera, industrial lens, light source, angle encoder, laser rangefinder as a whole.

In one example, the housing may be a shell that meets the environmental protection level requirements of the respective application, such that the extensometer may be adapted for use in various environmental levels. It should be noted that the environmental protection level, the selection and design of the housing, etc. can be determined according to the actual application requirements, and are not limited herein.

In some embodiments, the embedded extensometer may transmit the deformation data to a loading tester after acquiring the deformation data, and the tester may perform synchronous analysis on the deformation data and the loading conditions. Specifically, the embedded extensometer further includes: and the wireless communication unit 8 is arranged in the platform mechanism 6, and the wireless communication unit 8 is used for wirelessly transmitting the deformation data to the testing machine so that the testing machine can synchronously analyze the deformation data in combination with loading conditions.

In implementation, the communication mode of the wireless communication unit may adopt a corresponding data communication connection according to application requirements, such as mobile communication, WIFI, bluetooth, wireless local area network, and the like, which is not limited herein.

It should be noted that the extensometer can also perform wireless communication with a back-end computing device (such as a computer, a server, etc.) through the wireless communication unit 8, so as to facilitate the back-end processing and using of the deformation data.

In some embodiments, the setting of the marking point may be a pasting manner. Specifically, at least two first marker points are adhered to the axial direction of the sample, and/or at least two second marker points are adhered to the transverse direction of the sample.

In some implementations, after the image features of the feature identifiers are identified, a gauge length measurement can be made based on the image features. In particular, the processor is further configured to perform a gauge length measurement based on the marking feature and/or the boundary feature.

In some embodiments, as shown in FIG. 3, the control and computation logic of the processor includes the following:

firstly, pasting mark points on the surface of a sample, and pasting at least two mark points in proportion;

then, the processor controls the camera to automatically identify the characteristics of the mark points as a measurement gauge length when shooting the sample;

then, the processor controls the camera to shoot the sample for image acquisition, so that a dynamic image in the loading test process is acquired;

and finally, synchronously calculating the acquired images by using a DIC software algorithm integrated in the processor to obtain a calculated deformation result in real time, and synchronizing the calculated deformation result into a testing machine through wireless transmission, so that the testing machine forms synchronous analysis of loading force and deformation.

Based on the same inventive concept, the embodiment of the specification provides a biaxial visual measurement method for carrying out visual measurement of a biaxial loading test by using an embedded extensometer based on any one embodiment of the specification.

As shown in fig. 4, the biaxial vision measuring method includes:

step S202, in a biaxial loading test, a target image corresponding to a sample is collected through a camera and a lens, wherein at least two first mark points are arranged on the axial direction of the sample;

step S204, automatically identifying boundary features and mark features in the target image through a processor, and respectively processing the boundary features and the mark features based on a digital speckle correlation method to correspondingly acquire deformation data corresponding to the specimen in the transverse direction and the axial direction, wherein the boundary features are image features of the boundary of the specimen in the transverse direction in the target image, and the mark features comprise image features corresponding to the at least two first mark points in the target image.

It should be noted that, in the biaxial visual measurement method, related control and processing can be performed according to the function of the embedded extensometer, and details are not repeated here.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the product embodiments described later, since they correspond to the method, the description is simple, and the relevant points can be referred to the partial description of the system embodiments.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present application should be covered within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An embedded extensometer, characterized by comprising: the image acquisition unit and the image processing unit are arranged in the platform mechanism, the image acquisition unit comprises a lens and a camera, the image processing unit comprises an embedded processor, and the processor is electrically connected with the camera;

the camera and the lens are configured to perform the following operations: acquiring a target image corresponding to a sample in a biaxial loading test, wherein at least two first mark points are arranged on the axial direction of the sample;

the processor is configured to perform the following operations:

2. The embedded extensometer of claim 1 further including a light source disposed in the platform mechanism for illuminating as the camera captures images of the specimen.

3. The embedded extensometer of claim 1 further including an angle encoder disposed in the platform mechanism for acquiring an angle between the specimen and the camera.

4. The embedded extensometer of claim 3 wherein the processor is further configured to control the camera to track a target image of the specimen according to the angle.

5. The embedded extensometer of claim 1 further including a laser rangefinder disposed in the platform mechanism for measuring the distance between the specimen and the camera.

6. The embedded extensometer of claim 1 further including a mounting housing in which the platform mechanism is mounted.

7. The embedded extensometer of claim 1 wherein the embedded extensometer further includes: the wireless communication unit is arranged in the platform mechanism and is used for wirelessly transmitting the deformation data to a testing machine so that the testing machine can synchronously analyze the deformation data in combination with loading conditions.

8. The embedded extensometer of claim 1 wherein the axially disposed at least two first marker points of the test specimen includes: at least two first marker points are adhered to the axial direction of the sample.

9. The embedded extensometer of any one of claims 1-8 wherein the processor is further configured to perform gauge length measurements based on the marking features and/or the boundary features.

10. A biaxial vision measuring method applied to the embedded extensometer of any one of claims 1 to 9, characterized by comprising: