Embedded extensometer and biaxial vision measurement method based on vision measurement

Abstract

The present application provides an embedded extensometer and a biaxial visual measurement method based on visual measurement, which are applied to the fields of optical experimental mechanics and three-dimensional digital image technology. The embedded extensometer includes 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 includes a lens and a camera. The image processing unit includes an embedded processor, and the processor is electrically connected to the camera. By arranging marking points in the axial direction of the specimen and eliminating the need for arranging other feature marks in the lateral direction, the image acquisition and image processing in the visual measurement can be integrated into one to form an embedded extensometer. The embedded extensometer can perform fully automatic deformation measurement of material deformation in a biaxial loading test based on vision. The structure is compact, the cost is low, and it can be flexibly applied to different measurement scenarios.

Description

Technical Field

[0001] The present application relates to the fields of optical measurement experimental mechanics and three-dimensional digital image technology, and in particular to an embedded extensometer based on vision measurement and a biaxial vision measurement method. Background Art

[0002] Deformation detection can be applied to various material tests, both to ensure product quality and to verify the rationality of material design. In particular, in the military and scientific research fields, an increasing number of new materials require biaxial loading tests such as biaxial tension, biaxial compression, and biaxial fatigue to verify their mechanical properties.

[0003] Currently, there are preliminary extensometer solutions based on visual measurement for measuring material deformation under biaxial loading. However, the visual solutions of these extensometers can often only measure deformation in one deformation direction (such as axial or lateral). Therefore, other measurement methods are still needed to achieve biaxial measurement. The equipment is complex, inconvenient to operate, and the cost is high.

[0004] Therefore, a new extensometer solution is needed for biaxial loading tests. Summary of the Invention

[0005] In view of this, the embodiments of this specification provide an embedded extensometer and a biaxial visual measurement method based on visual measurement, which can perform fully automatic visual recognition processing for axial and transverse biaxial loading deformation tests, with a simple structure, low cost, more comprehensive functions and higher efficiency.

[0006] The embodiments of this specification provide the following technical solutions:

[0007] An embodiment of the present specification provides an embedded extensometer, comprising: a platform mechanism, an image acquisition unit, and an image processing unit, wherein 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 to the camera;

[0008] The camera and the lens are configured to perform the following operations: acquiring a target image corresponding to a specimen in a biaxial loading test, wherein at least two first marking points are provided in an axial direction of the specimen;

[0009] The processor is configured to perform the following operations:

[0010] Identifying boundary features and marking features in the target image, wherein the boundary feature is an image feature of the horizontal boundary of the sample in the target image, and the marking feature includes image features corresponding to the at least two first marking points in the target image;

[0011] The boundary features and the mark features are processed respectively based on the digital speckle correlation method to obtain corresponding deformation data of the sample in the transverse direction and the axial direction.

[0012] The present specification also provides a biaxial visual measurement method, which is applied to the embedded extensometer described in any embodiment of the present application. The biaxial visual measurement method includes:

[0013] In a biaxial loading test, a target image corresponding to a sample is captured by a camera and a lens, wherein at least two first marking points are set in the axial direction of the sample;

[0014] Boundary features and marker features in the target image are automatically identified by a processor, and the boundary features and marker features are respectively processed based on a digital speckle correlation method to obtain corresponding deformation data of the specimen in the transverse and axial directions, wherein the boundary feature is an image feature of the boundary of the specimen in the transverse direction in the target image, and the marker feature includes image features corresponding to the at least two first marker points in the target image.

[0015] Compared with the prior art, the at least one technical solution adopted in the embodiments of this specification can achieve the following beneficial effects:

[0016] For measuring the gauge length as a marking point, only at least two marking points need to be set, which is very convenient. Moreover, for the lateral marking, the lateral boundary of the specimen can be directly used as the feature, without the need to arrange other feature identifiers. At the same time, by using an embedded processor (such as a chip) for image acquisition control and image calculation processing, there is no need to connect to an external processing device (such as a computer, server, etc.). This allows the processor to control image acquisition while performing image calculations. Moreover, by using an embedded processor, the structure is simpler, the calculation and control process is simpler, the processing power is stronger, and the efficiency is higher.

[0017] In addition, integrating image acquisition and processing into a measuring head (i.e., an embedded extensometer) not only has a simple structure, but can also be flexibly deployed and used in different application scenarios. The measuring head can capture and analyze images of the entire measurement area, and can automatically identify and measure axial marking points and lateral boundaries, making deployment and application faster, more efficient, and less costly. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0019] Figure 1 This is a schematic diagram of the structure of a vision-based embedded extensometer for biaxial deformation vision measurement in this application;

[0020] Figure 2 It is a schematic structural diagram of an embedded extensometer in this application;

[0021] Figure 3 is a schematic diagram of the calculation logic of the processor in an embedded extensometer in this application;

[0022] Figure 4 It is a flow chart of a dual-axis vision measurement method in this application. DETAILED DESCRIPTION

[0023] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the features in the following embodiments and embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without making creative work are within the scope of protection of this application.

[0025] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on this application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement an apparatus and / or practice a method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this apparatus and / or practice this method.

[0026] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0027] Additionally, in the following description, specific details are provided to provide a thorough understanding of the examples, however, one skilled in the art will appreciate that the examples can be practiced without these specific details.

[0028] Existing visual measurement extensometers are still only used in uniaxial loading tests, where visual measurement is usually of the following two types:

[0029] One method is to use full-field speckle recognition and measurement methods, but the operation is complicated and the usage scenarios are limited, and it can only provide measurement results in the axial direction.

[0030] For example, the patent document (publication number CN 103575227 B) discloses a method for implementing a visual extensometer based on data speckle. This method is based on digital speckle recognition and deformation measurement. This measurement method can achieve full-field deformation measurement, but the process of producing speckle and implementing camera calibration is very complicated and inefficient, making it impossible to achieve automated measurement. Moreover, it can only achieve axial visual measurement and cannot meet the measurement requirements of fast response.

[0031] The other method is a transverse video extensometer, which consists of a single camera, lens, and bracket. It captures the specimen at close range and can measure its transverse deformation. However, this method only measures transverse deformation, which increases measurement costs and complicates the structure. Furthermore, for bidirectional deformation measurement, an axial contact extensometer is required.

[0032] For example, the patent document (publication number CN 209085554 U) discloses a transverse video extensometer, which consists of a single camera, lens, and bracket. It captures close-up images of a specimen and measures its transverse deformation. To achieve fully automated bidirectional deformation measurement, it uses a fully automated axial contact extensometer, which is cumbersome to use and results in low measurement efficiency.

[0033] In view of this, the inventors conducted in-depth research and improved exploration on visual measurement schemes and extensometers, and proposed a biaxial measurement scheme based on visual extensometers: Figure 1 As shown, at least two first marking points are set in the axial direction of the sample to form an axial marking feature (i.e., as an axial feature identifier), and the boundary of the sample in the lateral direction is used as a lateral feature identifier, without the need for other identification features, so that the overall image acquisition and image processing are greatly simplified, and then a processor can be introduced into the acquisition front end to form a vision-based embedded extensometer, so that the embedded extensometer can be used to perform image calculation and processing while acquiring the image, which can not only automatically identify the feature identifier, but also realize the lateral and axial biaxial deformation measurement based on the image features of the feature identifier.

[0034] Compared with the traditional visual extensometer solution based only on data speckle, there is no need to set up complex feature identification (such as speckle sheets), nor is there any need to perform complex and inefficient image processing on complex feature identification. Instead, only at least two marking points (i.e., feature identifications) are set in the axial direction. The axial marking points and lateral boundaries can be automatically identified and measured by the embedded extensometer, which not only realizes non-contact biaxial visual measurement, but also has a simple structure, low cost, strong processing performance and high efficiency.

[0035] In addition, compared with traditional lateral video extensometers, since only one embedded extensometer is required and no other auxiliary equipment is needed, the embedded extensometer can be flexibly used for biaxial measurement according to various measurement scenarios. It has stronger adaptability, a very simple structure, does not require excessive operation, is very simple to operate, and has low cost of use.

[0036] The following describes the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0037] like Figure 2 As shown, an embodiment of this specification provides a vision-based embedded extensometer, which may include: a platform mechanism 6, an image acquisition unit 2 and an image processing unit 1, wherein the image acquisition unit 2 and the image processing unit 1 are arranged in the platform mechanism 6, the image acquisition unit 2 includes a lens 21 and a camera 22, and the image processing unit 1 includes an embedded processor (such as a chip), which is electrically connected to the camera 22.

[0038] During implementation, the platform mechanism 6 can be a platform for equipment installation, debugging, etc. It can be a mechanical structure platform, such as an installation mechanism, or an electromechanical structure platform, such as a pan-tilt head, so as to facilitate the integration of the image acquisition unit and the image processing unit into the platform mechanism 6, which is not limited here.

[0039] In the embedded extensometer, the camera and lens are configured to capture a target image corresponding to the specimen during a biaxial loading test. It should be noted that the camera can be an industrial imaging device, such as an industrial camera or an industrial video camera; accordingly, the lens can also be an industrial lens. In practice, the camera and lens are selected and used based on application requirements and are not limited thereto.

[0040] As mentioned above Figure 1As shown, at least two first marking points can be set in the axial direction of the workpiece sample as axial feature identifiers, so that in the biaxial visual measurement, only based on the first marking point as the axial feature identifier and the lateral boundary of the sample as the lateral feature identifier, without adding other feature identifiers, it is possible to perform complex processing on these feature identifiers based on these small number of feature identifiers without using a high-performance, complex-structured processing unit (such as a computer). Instead, it is only necessary to perform image processing on these small number of feature identifiers based on an embedded processor (such as an ASIC, FPGA, DSP, CPU and other processors), thereby achieving high-performance and high-efficiency biaxial deformation visual measurement without the need for auxiliary processing of other equipment.

[0041] It should be noted that when setting marking points in the axial direction, the shape of the marking points, the number of marking points, the arrangement of the marking points, the spacing between the marking points, etc. can all be determined according to application needs and are not limited here.

[0042] In practice, the processor may be a processor architecture that integrates functional units such as an image recognition module for automatic feature identification and a deformation data processing module based on digital speckle correlation (DIC). Therefore, the processor may be configured to perform the following operations:

[0043] Automatic recognition of feature identification. Specifically, identifying boundary features and marker features in the target image, wherein the boundary feature is the image feature of the horizontal boundary of the sample in the target image, and the marker feature includes the image features corresponding to the at least two first marker points in the target image;

[0044] The axial and lateral deformations are automatically calculated and analyzed based on DIC. Specifically, the boundary features and the marker features are processed based on the digital speckle correlation method to obtain the corresponding deformation data of the sample in the lateral and axial directions.

[0045] It should be noted that boundary features can be image features of the specimen boundary in the target image, such as the coordinate positions of each pixel on the boundary. Marker features can be image features of a marker point on the specimen in the target image, such as the coordinate positions of the pixels corresponding to the marker point, the number of pixels contained in the marker point, etc.

[0046] In practice, processors can be either homogeneous or heterogeneous, depending on the deployment application requirements (e.g., cost, hardware structure, etc.). Furthermore, processor types can be selected based on the application, such as ASIC, FPGA, DSP, CPU, GPU, etc. Therefore, no processor restrictions are imposed here.

[0047] In practice, digital image correlation (DIC) is a non-contact optical measurement method that uses random speckle patterns applied to an object's surface and then precisely matches corresponding points in the speckle images before and after deformation to measure deformation and other data. Therefore, after obtaining boundary and marker features, DIC can be used to calculate and analyze the axial marker features and transverse boundary features, thereby obtaining deformation data for the specimen during a biaxial loading test.

[0048] By using the axial marking points and lateral boundaries of the specimen as visual feature identifiers in biaxial measurement, there is no need to add any other feature identifiers, nor is there any need for complex image processing on these feature identifiers. Therefore, high-performance and high-efficiency automatic image recognition and processing can be performed on these visual feature identifiers based on an embedded processor, making the overall structure of the embedded extensometer very simple, deployment and related operations very convenient, and the cost of use also lower.

[0049] In some embodiments, the coordinates of the marking points, the coordinates of the boundaries, etc. may be used as image features in the image as feature identifiers, which facilitates the recognition and computational processing of these image features by the processor.

[0050] In one example, first coordinate information corresponding to the at least two first marking points in the target image may be identified as the marking feature, wherein the first coordinate information may be coordinate data of the marking points in the target image.

[0051] In one example, an image feature detection algorithm can be incorporated into a processor. For example, a detection algorithm can be used to automatically detect and identify image features such as lateral boundaries and axial markers in an image. For example, an edge detection algorithm can be used to identify the coordinates of feature markers such as lateral boundaries and axial markers in a target image. It should be noted that an image processing algorithm (e.g., edge detection) can be an operator for identifying and detecting feature markers, and the specific operator is not limited.

[0052] In one example, a machine learning model (such as a neural network model) can be deployed in a processor to obtain image features of feature identifiers in an image based on a neural network. Specifically, the target image dynamically collected in a biaxial loading test can be input into the neural network model frame by frame, and then the neural network model can be used to quickly detect the feature area (x, y, w, h) representation corresponding to the lateral boundary and axial mark point in the target image, where x and y are the lateral and axial coordinate values, respectively, and w and h are the width and height of the feature area that meet the application requirements. It should be noted that the machine learning model (such as a neural network model) can be a classification model that has been pre-trained for feature identifiers, and the specific model is not limited.

[0053] In some embodiments, a sub-image processing algorithm may be used in the processor, so that after identifying a feature identifier in a target image, the processor can quickly and accurately process the sub-image region where the feature identifier is located in the image.

[0054] During implementation, after identifying the approximate location of the feature marker in the target image, the processor can quickly divide the target image into sub-image regions corresponding to the feature markers (e.g., axial marker points), and then perform image processing on the sub-image regions to obtain second coordinate information as the marker feature. The second coordinate information can be coordinate information that meets preset requirements and can be used to reflect the coordinates of the sub-image region.

[0055] In one example, the aforementioned first coordinate information can be used as coordinate information for rapid identification processing, and then the sub-image area can be quickly identified and accurately located based on the first coordinate information. Then, image refinement processing of the sub-image area can obtain more accurate second coordinate information, which can improve processing efficiency and accuracy.

[0056] In one example, the processor can first preprocess the sub-image region. For example, the preprocessing includes but is not limited to at least one of the following processing methods: grayscale conversion and mean filtering. This allows the processor to quickly process the image in the preprocessed sub-image region, improving the processor's processing performance and efficiency. It should be noted that these image preprocessing methods can also be used to process the target image. The preprocessed target image is easier to process, further reducing the performance requirements of the processor.

[0057] In one example, the processor can perform image processing for edge detection on the sub-image area, thereby determining the center coordinate data corresponding to the sub-image area as the second coordinate information based on the detection results. This allows the use of the coordinates of the center pixel point as the second coordinate information to more accurately reflect the characteristics of the sub-image area. It should be noted that edge detection can use existing detection methods, such as the Canny edge detection operator, to reduce processor performance requirements.

[0058] In one example, the processor may perform edge detection on a horizontal boundary, that is, perform edge detection on the target image in a horizontal direction to identify the boundary features.

[0059] In one example, after edge detection, the processor may further filter the detected edge contours and fit the edges that meet preset requirements, thereby returning the coordinates of the center point of the fitted sub-image area.

[0060] In one example, a mapping relationship between the recognition type of a feature identifier (such as a marker point or boundary) and the matching sub-image area can be preset in the processor, so that when the processor preliminarily identifies the image features of the feature identifier, it can quickly and accurately perform image processing on the sub-image area corresponding to the feature identifier based on the mapping relationship.

[0061] For example, the marker point type can be determined based on the center point pixel of the sub-image area, and different thresholds can be used to filter the pixels of the sub-image area according to the marker point type, so that the filtered image pixels are easier to process and more accurate.

[0062] In one example, the processor may perform edge detection on the image after filtering, for example, performing edge detection on the filtered grayscale image in combination with an edge detection operator (such as a Canny operator).

[0063] In some embodiments, by setting a small number of marking points in the horizontal direction, for example, at least two second marking points are set in the horizontal direction of the sample, the marking feature may also include the image features corresponding to the at least two second marking points in the target image, so that the processor can quickly and accurately realize two-axis visual measurement based on multiple marking points, that is, the image features corresponding to the first marking point, the second marking point and the boundary are extracted together in the image processing, and DIC calculation analysis is performed based on these image features, so that more accurate deformation results can be obtained.

[0064] Specifically, both the transverse and axial gauge lengths can be measured based on the marking points, so that the strain within the gauge length between multiple marking points can be calculated, such as the strain results within the axial and transverse gauge lengths. This can not only realize three-dimensional strain measurement, but also realize comprehensive data processing and analysis of multiple gauge lengths, and the measurement results are more accurate.

[0065] In some embodiments, an auxiliary light source is integrated into the embedded extensometer to provide auxiliary light when the camera is capturing images.

[0066] In practice, the embedded extensometer further includes a light source 4 , wherein the light source 4 is disposed in the platform mechanism 6 , and the light source is used for illuminating when the camera captures an image of the sample.

[0067] In one example, the image processing unit 2 (such as a processor) is arranged in the middle position of the platform mechanism 6, the camera 22 and the lens 21 are arranged on the central axis of the platform mechanism 6, and the light source 4 is arranged on one side of the camera 22 to facilitate the light source 4 to provide auxiliary lighting for the camera 22.

[0068] In some embodiments, an angle measuring device for measuring an angle is integrated into the embedded extensometer, and the angle between the sample and the camera is measured in real time using the angle measuring device.

[0069] In practice, 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 to obtain the angle between the sample and the camera.

[0070] In some embodiments, after obtaining the angle, the processor can control the camera to track and capture images of the sample to improve measurement accuracy. Specifically, the processor is further configured to control the camera to track and capture a target image of the sample based on the angle.

[0071] In some embodiments, the embedded extensometer is integrated with a distance measuring rangefinder, which is used to measure the distance between the sample and the camera. Specifically, the embedded extensometer further includes a laser rangefinder 7, which is disposed in the platform mechanism 6 and is used to measure the distance between the sample and the camera.

[0072] In one example, the laser rangefinder 7 can be installed close to the lens, which is beneficial to improving the accuracy of distance measurement.

[0073] In one example, the laser rangefinder 7 can be installed between the lens and the angle encoder. The structure is compact, which is beneficial to reducing the volume of the extensometer and improving the measurement accuracy.

[0074] In some embodiments, the various functional components of the extensometer can be installed in a housing to form an independent whole, which facilitates the use of the extensometer in various environments. Specifically, the embedded extensometer further includes a mounting housing 9, wherein the platform mechanism 6 is installed in the mounting housing 9.

[0075] In one example, the housing is responsible for packaging the installation and debugging platform, processor (ie, chip), industrial camera, industrial lens, light source, angle encoder, and laser rangefinder into a whole.

[0076] In one example, the housing can be a housing that meets the environmental protection level requirements of the corresponding application, allowing the extensometer to be used in various environmental levels. It should be noted that the environmental protection level and the selection and design of the housing can be determined according to the actual application needs and are not limited here.

[0077] In some embodiments, after acquiring deformation data, the embedded extensometer can transmit the deformation data to a loading tester, which then performs a synchronous analysis of the deformation data and the loading conditions. Specifically, the embedded extensometer further includes a wireless communication unit 8 disposed within the platform mechanism 6 and configured to wirelessly transmit the deformation data to the tester, enabling the tester to perform a synchronous analysis based on the deformation data and the loading conditions.

[0078] In implementation, the communication mode of the wireless communication unit may adopt corresponding data communication connection according to application requirements, such as mobile communication, WIFI, Bluetooth, wireless local area network, etc., which is not limited here.

[0079] It should be noted that the extensometer can also communicate wirelessly with a back-end computing device (such as a computer, server, etc.) through the wireless communication unit 8, so as to facilitate the back-end processing and use of the deformation data.

[0080] In some embodiments, the marking points may be pasted, specifically, at least two first marking points are pasted in the axial direction of the sample, and / or at least two second marking points are pasted in the transverse direction of the sample.

[0081] In some embodiments, after the image features of the feature marker are identified, gauge length measurement may be performed based on these image features. Specifically, the processor is further configured to perform gauge length measurement based on the marker features and / or the boundary features.

[0082] In some embodiments, as Figure 3 As shown, the control and calculation logic of the processor includes the following:

[0083] First, stick marking points on the surface of the sample, and stick at least two marking points proportionally;

[0084] Then, the processor controls the camera to automatically identify the marking point features as the measurement standard length when photographing the sample;

[0085] Next, the processor controls the camera to capture images of the sample, thereby capturing dynamic images of the loading test process;

[0086] Finally, the DIC software algorithm integrated in the processor performs synchronous calculations on the collected images, obtaining the calculated deformation results in real time. It can also be synchronized to the testing machine via wireless transmission, and the testing machine can perform a synchronous analysis of the loading force and deformation.

[0087] Based on the same inventive concept, an embodiment of this specification provides a biaxial visual measurement method for performing visual measurement of a biaxial loading test based on the embedded extensometer described in any embodiment of this specification.

[0088] As shown in Figure 4, the dual-axis visual measurement method includes:

[0089] Step S202: In a biaxial loading test, a target image corresponding to the sample is captured by a camera and a lens, wherein at least two first marking points are set along the axis of the sample;

[0090] Step S204: automatically identifying boundary features and marker features in the target image through a processor, and processing the boundary features and marker features respectively based on a digital speckle correlation method to obtain corresponding deformation data of the specimen in the transverse and axial directions, wherein the boundary feature is an image feature of the transverse boundary of the specimen in the target image, and the marker feature includes image features corresponding to the at least two first marker points in the target image.

[0091] It should be noted that the dual-axis visual measurement method can be controlled and processed according to the functions of the embedded extensometer, which will not be described in detail here.

[0092] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the product embodiments described later are relatively simple to describe because they correspond to the methods. For relevant parts, refer to the description of the system embodiments.

[0093] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. An embedded extensometer, characterized in that: include: A platform mechanism, an image acquisition unit, and an image processing unit, wherein the image acquisition unit and the image processing unit are arranged in the platform mechanism, the image acquisition unit includes a lens and a camera, and the image processing unit includes an embedded processor, and the processor is electrically connected to the camera; The camera and the lens are configured to perform the following operations: acquiring a target image corresponding to a specimen in a biaxial loading test, wherein at least two first marking points are provided in an axial direction of the specimen; The processor is configured to perform the following operations: Identifying boundary features and marking features in the target image, wherein the boundary feature is an image feature of the horizontal boundary of the sample in the target image, and the marking feature includes image features corresponding to the at least two first marking points in the target image; The boundary features and the mark features are processed respectively based on a digital speckle correlation method to obtain corresponding deformation data of the sample in the transverse direction and the axial direction; The embedded extensometer further includes a light source, which is disposed in the platform mechanism and is used for illuminating when the camera captures an image of the sample; The embedded extensometer further includes an angle encoder, which is disposed in the platform mechanism and is used to obtain the angle between the sample and the camera; The processor is further configured to control the camera to track and capture a target image of the sample according to the angle; The embedded extensometer further includes a laser rangefinder, which is disposed in the platform mechanism and is used to measure the distance between the sample and the camera; The embedded extensometer further includes a mounting housing, wherein the platform mechanism is mounted in the mounting housing; The embedded extensometer further includes: a wireless communication unit, the wireless communication unit being disposed in the platform mechanism, the wireless communication unit being configured to wirelessly transmit the deformation data to the testing machine, so that the testing machine performs synchronous analysis based on the deformation data in combination with loading conditions; The at least two first marking points are provided on the axial direction of the sample, comprising: at least two first marking points are attached on the axial direction of the sample; The processor is further configured to perform gauge distance measurement based on the marking feature and / or the boundary feature.

2. A dual-axis visual measurement method, characterized in that: Applied to the embedded extensometer according to claim 1, the biaxial visual measurement method comprises: in a biaxial loading test, capturing a target image corresponding to a specimen by means of a camera and a lens, wherein at least two first marking points are provided in an axial direction of the specimen; Boundary features and marker features in the target image are automatically identified by a processor, and the boundary features and marker features are respectively processed based on a digital speckle correlation method to obtain corresponding deformation data of the specimen in the transverse and axial directions, wherein the boundary feature is an image feature of the boundary of the specimen in the transverse direction in the target image, and the marker feature includes image features corresponding to the at least two first marker points in the target image.

Images