Calibration Method, Device, Electronic Device and Storage Medium

Abstract

The present disclosure provides a calibration method, apparatus, electronic device, and storage medium. The calibration method includes: obtaining a to-be-calibrated image, where the to-be-calibrated image is an image obtained through an eyepiece in the rangefinder, and a reference object is provided in the eyepiece; performing image processing on the to-be-calibrated image to obtain error information of a target object and the reference object in the to-be-calibrated image; and calibrating the rangefinder according to the error information. By performing image processing on the to-be-calibrated image obtained from the eyepiece to obtain the error information of the target object and the reference object in the to-be-calibrated image, and then calibrating the rangefinder according to the error information, manual calibration is not required, the calibration efficiency of the rangefinder is improved, and further the production efficiency of the laser rangefinder is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of calibration, and particularly relates to a calibration method, device, electronic device and storage medium. Background Art

[0002] The miniaturization and portability of laser rangefinders is a development trend of civilian laser rangefinders. Handheld laser rangefinders are widely used in engineering projects such as construction and transportation due to their convenience in carrying, and are also widely used in leisure fields such as golf and hunting for various ranging occasions. However, most of the existing laser rangefinders are manually calibrated before leaving the factory. The laser rangefinder is placed on a well-adjusted jig, and the user observes through the eyepiece whether the target point coincides with the collimation center. Such a calibration method requires a lot of manpower, resulting in low calibration efficiency of the laser rangefinder, thus affecting the low production efficiency of the laser rangefinder. Summary of the Invention

[0003] Embodiments of the present invention provide a calibration method, device, electronic device and storage medium, aiming to solve the problem that the calibration method requires a lot of manpower, resulting in low calibration efficiency of the laser rangefinder, thus affecting the low production efficiency of the laser rangefinder. By performing image processing on the to-be-calibrated image obtained from the eyepiece, the error information between the target object and the reference object in the to-be-calibrated image is obtained, and then the rangefinder is calibrated according to the error information, without manual calibration, improving the calibration efficiency of the rangefinder, and further improving the production efficiency of the laser rangefinder.

[0004] In a first aspect, an embodiment of the present invention provides a calibration method, the method comprising:

[0005] Obtain a to-be-calibrated image, where the to-be-calibrated image is an image obtained through the eyepiece of the rangefinder, and a reference object is provided in the eyepiece;

[0006] Perform image processing on the to-be-calibrated image to obtain error information between a target object and the reference object in the to-be-calibrated image;

[0007] Calibrate the rangefinder according to the error information.

[0008] Further, the step of obtaining the to-be-calibrated image comprises:

[0009] Install the rangefinder on a well-adjusted jig;

[0010] Collect an image of the eyepiece of the rangefinder through an image device to obtain the to-be-calibrated image.

[0011] Further, the step of performing image processing on the image to be calibrated to obtain the error information between the target object and the reference object in the image to be calibrated includes:

[0012] Preprocess the image to be calibrated;

[0013] Perform recognition processing on the preprocessed image to be calibrated through a preset image recognition model to obtain the error information between the target object and the reference object in the image to be calibrated.

[0014] Further, the image recognition model includes a common network, a first recognition network, and a second recognition network. The inputs of the first recognition network and the second recognition network are both connected to the output of the common network. The step of performing recognition processing on the preprocessed image to be calibrated through a preset image recognition model to obtain the error information between the target object and the reference object in the image to be calibrated includes:

[0015] Process the preprocessed image to be calibrated through the common network to obtain a first feature map;

[0016] Process the first feature map through the first recognition network to obtain the recognition result of the target object, and process the first feature map through the second recognition network to obtain the recognition result of the reference object;

[0017] Calculate the error information between the target object and the reference object in the image to be calibrated according to the recognition result of the target object and the recognition result of the reference object.

[0018] Further, the recognition result of the target object includes target object box information, and the reference object includes reference object box information. The step of calculating the error information between the target object and the reference object in the image to be calibrated according to the recognition result of the target object and the recognition result of the reference object includes:

[0019] Calculate the distance from the center point of the target object box to the center point of the reference object box according to the target object box information and the reference object box information;

[0020] Obtain the error information between the target object and the reference object in the image to be calibrated according to the distance from the center point of the target object box to the center point of the reference object box.

[0021] Further, the recognition result of the target object includes target object box information, and the reference object includes reference object box information. The step of calculating the error information between the target object and the reference object in the image to be calibrated according to the recognition result of the target object and the recognition result of the reference object includes:

[0022] Calculate the intersection over union (IoU) of the target object bounding box and the reference object bounding box based on the target object bounding box information and the reference object bounding box information;

[0023] Calculate the error information of the target object and the reference object in the image to be calibrated based on the IoU of the target object bounding box and the reference object bounding box.

[0024] Further, the step of calibrating the rangefinder according to the error information includes:

[0025] Generate an adjustment instruction according to the error information;

[0026] Adjust the jig through the adjustment instruction so that the jig calibrates the rangefinder.

[0027] In a second aspect, a calibration device is provided, and the device includes:

[0028] An acquisition module, configured to acquire an image to be calibrated, where the image to be calibrated is an image obtained through an eyepiece in the rangefinder, and a reference object is provided in the eyepiece;

[0029] A processing module, configured to perform image processing on the image to be calibrated to obtain error information of a target object and the reference object in the image to be calibrated;

[0030] A calibration module, configured to calibrate the rangefinder according to the error information.

[0031] In a third aspect, an electronic device is provided, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the calibration method according to any one of the embodiments of the present invention are implemented.

[0032] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps in the calibration method according to any one of the embodiments of the present invention are implemented.

[0033] In an embodiment of the present invention, a to-be-calibrated image is obtained. The to-be-calibrated image is an image obtained through an eyepiece in the rangefinder, and a reference object is provided in the eyepiece. Image processing is performed on the to-be-calibrated image to obtain error information of a target object and the reference object in the to-be-calibrated image. The rangefinder is calibrated according to the error information. By performing image processing on the to-be-calibrated image obtained from the eyepiece to obtain the error information of the target object and the reference object in the to-be-calibrated image, and then calibrating the rangefinder according to the error information, manual calibration is not required, the calibration efficiency of the rangefinder is improved, and thus the production efficiency of the laser rangefinder is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0035] Figure 1 is a flowchart of a calibration method.

[0036] Figure 2 is a structural diagram of a calibration device. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0037] The following details the embodiments of the present invention. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are intended to explain the present invention, and should not be construed as a limitation of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "circumferential", "radial", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation of the present invention.

[0039] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality of" means two or more unless specifically defined otherwise.

[0040] In the present invention, unless otherwise clearly specified and defined, terms such as "mounted", "connected", "coupled", "fixed", etc. shall be construed in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] In the present invention, unless otherwise clearly specified and defined, the first feature being "on" or "under" the second feature may include the direct contact between the first and second features, or may include the situation where the first and second features are not in direct contact but in contact through additional features therebetween. Moreover, the first feature being "above", "over" and "on top of" the second feature includes that the first feature is directly above and obliquely above the second feature, or merely means that the horizontal height of the first feature is higher than that of the second feature. The first feature being "under", "beneath" and "underneath" the second feature includes that the first feature is directly below and obliquely below the second feature, or merely means that the horizontal height of the first feature is lower than that of the second feature.

[0042] Please refer to Figure 1 , Figure 1 a calibration method provided for this application, the method comprising:

[0043] 101. Obtain an image to be calibrated.

[0044] In an embodiment of the present invention, the above-mentioned image to be calibrated is an image obtained through an eyepiece in a rangefinder, and a reference object is provided in the eyepiece.

[0045] Specifically, the above-mentioned rangefinder may include an objective lens and an eyepiece. Among them, the objective lens is arranged at the front end of the rangefinder, and the eyepiece is arranged at the rear end of the rangefinder. A user can observe the area where the target to be measured is located through the eyepiece.

[0046] More specifically, the above-mentioned rangefinder includes a housing and a movement. The movement includes an objective lens and an eyepiece. Before the rangefinder leaves the factory, it is necessary to calibrate the movement to ensure the accuracy of the rangefinder.

[0047] The above-mentioned image to be calibrated can be an image obtained by shooting through a camera aimed at the eyepiece. A reference object is set in the eyepiece, and the reference object can be a crosshair.

[0048] In a possible embodiment, the above-mentioned camera is a dedicated camera. The camera uses the eyepiece of the rangefinder as a lens to collect images, so that the image to be calibrated is consistent with the picture observed by the user through the eyepiece.

[0049] 102. Perform image processing on the image to be calibrated to obtain the error information between the target object and the reference object in the image to be calibrated.

[0050] In the embodiment of the present invention, the above-mentioned image to be calibrated further includes a target object, and the target object can be a bull's-eye. In this way, the crosshair of the eyepiece and the bull's-eye of the object can be included in the image to be calibrated.

[0051] Among them, the crosshair of the eyepiece is used to mark the target position aimed at by the current rangefinder, and the distance between the rangefinder and the bull's-eye of the object is preset.

[0052] The above-mentioned image processing of the image to be calibrated can be to perform target recognition on the image to be calibrated, recognize the target object information and the reference object information in the image to be calibrated, and calculate the error information between the target object and the reference object according to the target object information and the reference object information.

[0053] 103. Calibrate the rangefinder according to the error information.

[0054] In the embodiment of the present invention, the above-mentioned calibration includes calibrating the eyepiece and the objective lens. The eyepiece and the objective lens of the rangefinder can be continuously calibrated by continuously performing steps 101 and 102, so that the crosshair can be aligned with the bull's-eye.

[0055] In the embodiment of the present invention, an image to be calibrated is obtained. The image to be calibrated is an image obtained through the eyepiece in the rangefinder, and a reference object is set in the eyepiece; image processing is performed on the image to be calibrated to obtain the error information between the target object and the reference object in the image to be calibrated; the rangefinder is calibrated according to the error information. By performing image processing on the image to be calibrated obtained from the eyepiece to obtain the error information between the target object and the reference object in the image to be calibrated, and then calibrating the rangefinder according to the error information, manual calibration is not required, the calibration efficiency of the rangefinder is improved, and the production efficiency of the laser rangefinder is further improved.

[0056] Optionally, in the step of obtaining the image to be calibrated, the rangefinder can be installed on an adjusted fixture; the eyepiece of the rangefinder is image-captured by an image device to obtain the image to be calibrated.

[0057] In an embodiment of the present invention, the above-mentioned jig is a jig that has been adjusted. The adjustment of the jig is performed according to the model parameters of the rangefinder. For rangefinders with different model parameters, the adjustment range of the corresponding jig is different.

[0058] A rangefinder that has been manually calibrated can be used to adjust the jig so that when the manually calibrated rangefinder is fixed by the jig, its aiming center coincides with the target center. The manually calibrated rangefinder and the rangefinder to be calibrated have the same model parameters.

[0059] Furthermore, a dedicated image device is provided on the jig. The dedicated image device can be a dedicated camera. The dedicated camera uses the eyepiece of the rangefinder to be calibrated as the lens. When the rangefinder is installed on the jig, at the same time, the lens part of the camera is installed on the eyepiece of the rangefinder to be calibrated, so that the eyepiece of the rangefinder to be calibrated serves as the lens of the camera, thereby ensuring the consistency between the image captured by the camera and the picture observed by the user through the eyepiece.

[0060] During calibration, image information in the eyepiece is collected through the image device to obtain the image to be calibrated. The image to be calibrated includes at least a reference object, and the reference object can be the aiming center in the eyepiece.

[0061] Optionally, in the step of performing image processing on the image to be calibrated to obtain the error information between the target object and the reference object in the image to be calibrated, the image to be calibrated can be preprocessed; the preprocessed image to be calibrated is subjected to recognition processing through a preset image recognition model to obtain the error information between the target object and the reference object in the image to be calibrated.

[0062] In an embodiment of the present invention, image processing of the image to be calibrated can be performed using a preset image recognition model. The preset image recognition model can also be referred to as a pre-trained image recognition model. The image recognition model used for recognizing the image to be calibrated can be an image recognition model based on a convolutional neural network.

[0063] Furthermore, the image to be calibrated can also be preprocessed. The preprocessing can be denoising, normalizing, scaling, and cropping the image to obtain an image to be calibrated that meets the input size of the image recognition model.

[0064] After preprocessing the image to be calibrated, the image to be calibrated is input into the preset image recognition model. Since the image recognition model is pre-trained and learns the error information between the target object and the reference object during the training process, the image recognition model can automatically output the error information between the target object and the reference object in the image to be calibrated.

[0065] By using a preset image recognition model to perform recognition processing on the image to be calibrated, the error information between the target object and the reference object in the image to be calibrated can be obtained, which can improve the calibration efficiency of the rangefinder and thus improve the production efficiency of the laser rangefinder.

[0066] Optionally, the image recognition model includes a common network, a first recognition network, and a second recognition network. The input of the first recognition network and the input of the second recognition network are both connected to the output of the common network. In the step of performing recognition processing on the preprocessed image to be calibrated through the preset image recognition model to obtain the error information between the target object and the reference object in the image to be calibrated, the preprocessed image to be calibrated can be processed through the common network to obtain a first feature map; the first feature map can be processed through the first recognition network to obtain the recognition result of the target object, and the first feature map can be processed through the second recognition network to obtain the recognition result of the reference object; according to the recognition result of the target object and the recognition result of the reference object, the error information between the target object and the reference object in the image to be calibrated is calculated.

[0067] In the embodiment of the present invention, the image recognition model includes three parts of networks. The common network can be a shallow neural network, which is used to extract the general features of the target object and the reference object. After processing the image to be calibrated through the common network, the first feature map obtained contains the primary features of the target object and the reference object. The first recognition network is required to extract the high-level features of the target object from the first feature map, and the second recognition network is required to extract the high-level features of the reference object from the first feature map.

[0068] The first recognition network and the second recognition network can be deep neural networks. It should be noted that the first recognition network and the second recognition network can be the same or different in structure. Even if the first recognition network and the second recognition network are the same in structure, their network parameters are different.

[0069] Before training the image recognition model, a data set is constructed, and the image recognition model is trained through the data set. The data set includes sample images of the rangefinder. The acquisition method of the sample images is the same as that of the image to be calibrated. The sample images are marked with the target object, the reference object, and the error information as training guidance.

[0070] During the training process of the image recognition model, the first loss function of the first recognition network and the second loss function of the second recognition network are calculated. The parameters of the first recognition network are adjusted by backpropagation through the first loss function, the parameters of the second recognition network are adjusted by backpropagation through the second loss function, and the parameters of the common network are adjusted by backpropagation through the total loss of the first loss function and the second loss function.

[0071] In a possible embodiment, an error processing network is further included in the image recognition model. The input of the error processing network is the outputs of the first recognition network and the second recognition network, that is, the recognition results of the target object and the reference object are input into the error processing network, and the error information between the target object and the reference object is obtained through the processing of the error processing network. The error processing network can be a fully convolutional neural network, and the parameters in the error processing network are also obtained through training.

[0072] Optionally, the recognition result of the target object includes target object box information, and the reference object includes reference object box information. In the step of calculating the error information between the target object and the reference object in the to-be-calibrated image according to the recognition results of the target object and the reference object, the distance from the center point of the target object box to the center point of the reference object box can be calculated according to the target object box information and the reference object box information; according to the distance from the center point of the target object box to the center point of the reference object box, the error information between the target object and the reference object in the to-be-calibrated image is obtained.

[0073] In the embodiment of the present invention, the recognition result of the target object includes target object box information, and the target object box information can be five-tuple information such as (x1, y1, w1, h1, c1), where x1 and y1 are the center point coordinates of the target object box, w1 is the width of the target object box, h1 is the height of the target object box, and c1 is the class confidence of the target object box.

[0074] Similarly, the recognition result of the reference object includes reference object box information, and the reference object box information can be five-tuple information such as (x2, y2, w2, h2, c2), where x2 and y2 are the center point coordinates of the reference object box, w2 is the width of the reference object box, h2 is the height of the reference object box, and c2 is the class confidence of the reference object box.

[0075] Among them, both c1 and c2 are values between [0, 1].

[0076] The error information between the target object and the reference object can be the distance from the center point of the target object box to the center point of the reference object box. Specifically, the distance from the center point of the target object box to the center point of the reference object box can be calculated by using the Euclidean distance through the center point (x1, y1) of the target object box and the center point (x2, y2) of the reference object box. The smaller the distance from the center point of the target object box to the center point of the reference object box, the smaller the deviation between the aiming point and the bull's-eye, and the smaller the error.

[0077] In a possible embodiment, after obtaining the distance from the center point of the target object box to the center point of the reference object box, the error information can be calculated by the following formula:

[0078]

[0079] Wherein, D is the distance from the center point of the target object box to the center point of the reference object box, and s is the error. It can be seen that when the distance D from the center point of the target object box to the center point of the reference object box is fixed, the higher the class confidence c1 of the target object box and the class confidence c2 of the reference object box, the smaller the error. Conversely, the larger the error.

[0080] Optionally, the recognition result of the target object includes target object box information, and the reference object includes reference object box information. In the step of calculating the error information of the target object and the reference object in the image to be calibrated according to the recognition results of the target object and the reference object, the intersection over union of the target object box and the reference object box can be calculated based on the target object box information and the reference object box information; and the error information of the target object and the reference object in the image to be calibrated can be calculated based on the intersection over union of the target object box and the reference object box.

[0081] In the embodiment of the present invention, the recognition result of the target object includes target object box information, and the target object box information may be five - tuple information such as (x1, y1, w1, h1, c1). Among them, x1 and y1 are the center point coordinates of the target object box, w1 is the width of the target object box, h1 is the height of the target object box, and c1 is the class confidence of the target object box.

[0082] Similarly, the recognition result of the reference object includes reference object box information, and the reference object box information may be five - tuple information such as (x2, y2, w2, h2, c2). Among them, x2 and y2 are the center point coordinates of the reference object box, w2 is the width of the reference object box, h2 is the height of the reference object box, and c2 is the class confidence of the reference object box.

[0083] The intersection over union of the target object box and the reference object box can be obtained by dividing the intersection area of the target object box and the reference object box by the union area of the target object box and the reference object box. Specifically, it can be shown as the following formula:

[0084]

[0085] Among them, r is the intersection over union of the target object box and the reference object box, A is the target object box, and B is the reference object box. The minimum value of the intersection over union of the target object box and the reference object box is 0, indicating that there is no intersection between the target object box and the reference object box; the maximum value of the intersection over union of the target object box and the reference object box is 1, indicating that the target object box and the reference object box are of the same size and completely overlap.

[0086] In a possible embodiment, after obtaining the intersection over union of the target object box and the reference object box, the error information can be calculated by the following formula:

[0087]

[0088] It can be seen that the higher the class confidence c1 of the target object box and the class confidence c2 of the reference object box are, the smaller the error is. On the contrary, the larger the error is.

[0089] Optionally, in the step of calibrating the rangefinder according to the error information, an adjustment instruction can be generated according to the error information; through the adjustment instruction, the jig is adjusted so that the jig calibrates the rangefinder.

[0090] In the embodiment of the present invention, an adjustment instruction can be generated according to the error information. The greater the error information is, the greater the adjustment range of the adjustment instruction is. The jig is controlled according to the adjustment instruction to calibrate the objective lens or the eyepiece of the rangefinder.

[0091] After one calibration, the above calibration method is used for the next calibration until the error information for two or more consecutive times is less than a preset value, and the calibration of the rangefinder is ended to obtain the calibrated rangefinder.

[0092] Please refer to Figure 2 , Figure 2 which is a calibration device provided by the present application. The device includes:

[0093] An acquisition module 201, configured to acquire a to-be-calibrated image, where the to-be-calibrated image is an image obtained through an eyepiece in the rangefinder, and a reference object is arranged in the eyepiece;

[0094] A processing module 202, configured to perform image processing on the to-be-calibrated image to obtain error information between a target object and the reference object in the to-be-calibrated image;

[0095] A calibration module 203, configured to calibrate the rangefinder according to the error information.

[0096] Further, the acquisition module 201 includes:

[0097] An installation sub-module, configured to install the rangefinder on a jig that has been adjusted;

[0098] An acquisition sub-module, configured to acquire an image of the eyepiece of the rangefinder through an image device to obtain the to-be-calibrated image.

[0099] Further, the processing module 202 includes:

[0100] A first processing sub-module, configured to preprocess the to-be-calibrated image;

[0101] A second processing sub-module, configured to perform recognition processing on the preprocessed to-be-calibrated image through a preset image recognition model to obtain error information between the target object and the reference object in the to-be-calibrated image.

[0102] Further, the image recognition model includes a common network, a first recognition network, and a second recognition network. The inputs of the first recognition network and the second recognition network are both connected to the output of the common network. The second processing sub-module includes:

[0103] A first processing unit for processing the preprocessed image to be calibrated through the common network to obtain a first feature map;

[0104] A second processing unit for processing the first feature map through the first recognition network to obtain the recognition result of the target object, and processing the first feature map through the second recognition network to obtain the recognition result of the reference object;

[0105] A calculation unit for calculating the error information between the target object and the reference object in the image to be calibrated according to the recognition result of the target object and the recognition result of the reference object.

[0106] Further, the recognition result of the target object includes target object box information, the reference object includes reference object box information, and the calculation unit includes:

[0107] A first calculation sub-unit for calculating the distance from the center point of the target object box to the center point of the reference object box according to the target object box information and the reference object box information;

[0108] A processing sub-unit for obtaining the error information between the target object and the reference object in the image to be calibrated according to the distance from the center point of the target object box to the center point of the reference object box.

[0109] Further, the recognition result of the target object includes target object box information, the reference object includes reference object box information, and the calculation unit further includes:

[0110] A second calculation sub-unit for calculating the intersection over union of the target object box and the reference object box according to the target object box information and the reference object box information;

[0111] A third calculation sub-unit for calculating the error information between the target object and the reference object in the image to be calibrated according to the intersection over union of the target object box and the reference object box.

[0112] Further, the calibration module 203 includes:

[0113] A generation sub-module for generating an adjustment instruction according to the error information;

[0114] A calibration sub-module, configured to adjust the jig according to the adjustment instruction, so that the jig calibrates the rangefinder.

[0115] An embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, and the computer program enables a computer to execute some or all of the steps of any calibration method described in the above method embodiments.

[0116] An embodiment of the present invention further provides an electronic device, where the electronic device includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute some or all of the steps of any calibration method described in the above method embodiments.

[0117] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0118] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0119] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0120] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0121] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software program module.

[0122] If the above-mentioned integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned memory includes: USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical disks, etc., which can store program codes.

[0123] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (abbreviation: ROM), random access memories (abbreviation: RAM), magnetic disks, or optical disks, etc.

[0124] The above has introduced the embodiments of the present invention in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A calibration method, characterized in that, For rangefinder calibration, the rangefinder includes a housing and a movement, and the movement includes an objective lens and an eyepiece. Specifically, it is used to calibrate the movement before the rangefinder leaves the factory. The method includes: Install the rangefinder on the adjusted fixture; Align the eyepiece of the rangefinder through an image device to collect images, using the eyepiece of the rangefinder as a lens to collect images, and obtain a to-be-calibrated image. The to-be-calibrated image includes a target object and a reference object. The target object is the bull's-eye of an object, and the reference object is the crosshair in the eyepiece; Preprocess the to-be-calibrated image; Process the preprocessed to-be-calibrated image through a preset image recognition model to obtain the error information between the target object and the reference object in the to-be-calibrated image. The image recognition model includes a common network, a first recognition network, and a second recognition network. The inputs of the first recognition network and the second recognition network are both connected to the output of the common network; Specifically, process the preprocessed to-be-calibrated image through the common network to obtain a first feature map; Process the first feature map through the first recognition network to obtain the recognition result of the target object, and process the first feature map through the second recognition network to obtain the recognition result of the reference object; Calculate the error information between the target object and the reference object in the to-be-calibrated image according to the recognition result of the target object and the recognition result of the reference object; Calibrate the movement of the rangefinder according to the error information.

2. The method according to claim 1, characterized in that, The recognition result of the target object includes target object box information, and the reference object includes reference object box information. The step of calculating the error information between the target object and the reference object in the to-be-calibrated image according to the recognition result of the target object and the recognition result of the reference object includes: Calculate the distance from the center point of the target object box to the center point of the reference object box according to the target object box information and the reference object box information; Obtain the error information between the target object and the reference object in the to-be-calibrated image according to the distance from the center point of the target object box to the center point of the reference object box.

3. The method according to claim 1, characterized in that, The recognition result of the target object includes target object box information, and the reference object includes reference object box information. The step of calculating the error information between the target object and the reference object in the to-be-calibrated image according to the recognition result of the target object and the recognition result of the reference object includes: Calculate the intersection over union (IoU) of the target object box and the reference object box according to the target object box information and the reference object box information; Calculate the error information between the target object and the reference object in the to-be-calibrated image according to the intersection over union (IoU) of the target object box and the reference object box.

4. The method according to claim 1, characterized in that, The step of calibrating the rangefinder according to the error information includes: Generate an adjustment instruction according to the error information; Adjust the fixture through the adjustment instruction so that the fixture calibrates the rangefinder.

5. A calibration device, characterized in that, The device includes: An acquisition module, configured to mount a rangefinder on an adjusted fixture; perform image acquisition by aligning an image device with the eyepiece of the rangefinder, use the eyepiece of the rangefinder as a lens to perform image acquisition, obtain a to-be-calibrated image, the to-be-calibrated image includes a target object and a reference object, the target object is the bull's-eye of an object, and the reference object is the crosshair in the eyepiece; A processing module, configured to preprocess the to-be-calibrated image; perform recognition processing on the preprocessed to-be-calibrated image through a preset image recognition model to obtain error information of the target object and the reference object in the to-be-calibrated image, the image recognition model includes a common network, a first recognition network and a second recognition network, the input of the first recognition network and the input of the second recognition network are both connected to the output of the common network; specifically, process the preprocessed to-be-calibrated image through the common network to obtain a first feature map; process the first feature map through the first recognition network to obtain a recognition result of the target object, and process the first feature map through the second recognition network to obtain a recognition result of the reference object; calculate the error information of the target object and the reference object in the to-be-calibrated image according to the recognition result of the target object and the recognition result of the reference object; A calibration module, configured to calibrate the rangefinder according to the error information.

6. An electronic device, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the steps in the calibration method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps in the calibration method according to any one of claims 1 to 4 are implemented.

Images