Visual Localization Method of Underwater Robot in Nuclear Environment

Abstract

The present invention provides a visual positioning method for an underwater robot in a nuclear environment. The visual positioning method includes: setting an underwater camera and a target at an underwater working position, and calibrating the camera parameters and the camera position of the underwater camera, wherein the target is within the field of view of the underwater camera; processing the target images captured by the underwater camera to extract the contours of all the images; matching the contours of all the images with the image template of the target to judge and extract the correct target pattern; extracting the coordinates of the feature points for the correct target pattern, calculating the coordinates of the target relative to the underwater camera according to the coordinates of the feature points and the target image, and performing coordinate system transformation to obtain the coordinates of the target relative to the pool, thereby completing the visual positioning of the underwater robot. The visual positioning method of the present invention omits irradiation-sensitive devices such as depth pressure sensors and the requirement for the camera to be radiation-resistant, can achieve higher positioning accuracy, and has good economy.

Description

Technical Field

[0001] The present invention relates to a positioning method, and in particular to a visual positioning method for an underwater robot in a nuclear environment. Background Art

[0002] A thin stainless steel plate is laid on the inner wall of the spent fuel pool in a nuclear power plant, which is called a clad plate. The clad plates are spliced by welding. Since the spent fuel has high radioactivity, if there are quality problems in the welds spliced between the clad plates, radioactive cooling water in the spent fuel pool may leak out of the clad plate, endangering the safety of the nuclear power plant. Developing an underwater monitoring and operation robot in a nuclear environment to inspect the welds of the clad plates of the spent fuel pool and perform operations such as grinding and welding, the accurate positioning of the robot in the pool is the key to ensuring the normal operation of the robot. In addition, underwater robot technology has gradually been applied to assist in monitoring and performing operations during the major overhaul of nuclear power plant pressure vessels and steam generators, so as to improve work efficiency and reduce personnel irradiation. The accurate positioning of the robot is also a prerequisite for the robot to carry out monitoring and operations.

[0003] Currently, most commonly used underwater positioning methods are based on information collected by sensors such as depth (pressure) sensors, ultrasonic sensors, pose sensors, or underwater acoustic communication. However, the above sensors are not suitable for high-irradiation environments. The development of radiation-resistant sensors requires a long cycle and high cost, and cannot meet the positioning requirements of underwater robots in the nuclear environment at the present stage. Underwater robots in the sea area mostly use long and short baseline acoustic positioning, which is not suitable for the positioning requirements of the small environment of nuclear power plants. Summary of the Invention

[0004] In view of the above problems, there is an urgent need for an optical underwater positioning method based on image recognition. Therefore, the present application proposes a visual positioning method for an underwater robot in a nuclear environment.

[0005] It should be understood that the above general description and the following detailed description of the present disclosure are both exemplary and explanatory, and are intended to provide further explanation of the present disclosure.

[0006] To solve the above technical problems, the present invention provides a visual positioning method for an underwater robot in a nuclear environment. The visual positioning method includes:

[0007] Step S1, an underwater camera and a target are arranged at an underwater working position, and the camera parameters and the camera position of the underwater camera are calibrated, wherein the target is within the field of view of the underwater camera;

[0008] Step S2, the target images captured by the underwater camera are processed to extract the contours of all the images;

[0009] Step S3: Match the contours of all images with the image template of the target, and judge and extract the correct target pattern;

[0010] Step S4: Extract the coordinates of the feature points for the correct target pattern, calculate the coordinates of the target relative to the underwater camera based on the coordinates of the feature points and the target image, and perform coordinate system transformation to obtain the coordinates of the target relative to the pool, thus completing the visual positioning of the underwater robot.

[0011] Preferably, the present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein the method for extracting the contours of all images in step S2 includes a contour extraction algorithm.

[0012] Preferably, the present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein the matching in step S3 further includes:

[0013] Read the image template of the target and extract the template edge;

[0014] Perform binarization processing on the contours of all images and then extract the image edge;

[0015] Match the template edge and the image edge obtained in the above two steps, calculate the similarity between the target and the target image, search for the object in the image to be matched through a sliding window, and extract the corresponding relationship of the image edge feature points, so as to identify the scale change and rotation change of the target image.

[0016] Preferably, the present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein the processing in step S2 includes: removing noise from the target image and extracting the contours of all images, wherein the method for removing noise includes mean filtering.

[0017] Preferably, the present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein the method for removing noise further includes:

[0018] Perform dilation processing of formula (1) and erosion processing of formula (2) on the target image after mean filtering:

[0019] dst(x, y) = max src(x + x1, y + y1) Formula (1)

[0020] dst(x, y) = min src(x + x1, y + y1) Formula (2)

[0021] where (x1, y1) ∈ convolution kernel.

[0022] The present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein the calibration method in step S1 includes Zhang Zhengyou calibration method.

[0023] Preferably, the present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein in steps S2 and S3, the extraction method includes any one of the Sobel edge extraction method and the Canny edge extraction method.

[0024] Preferably, the present invention further provides a visual positioning method for an underwater robot in a nuclear environment, wherein in step S4, the coordinate system transformation is performed according to the following formula:

[0025] p C = R * P W + T

[0026] Assume that the coordinates of the target in the camera coordinate system are P = (X, Y, Z). Therefore, the coordinates of the target relative to the pool are obtained according to the following formula:

[0027] p w = R T (P - T)

[0028] where p C represents the coordinates of the target in the camera coordinate system; p w represents the coordinates of the target in the world coordinate system; R is the rotation matrix, T is the translation matrix, and R and T are obtained by the PnP function.

[0029] Compared with the prior art, the visual positioning method of the present invention not only omits irradiation-sensitive devices such as depth pressure sensors, and there is no requirement for the radiation resistance of the camera, but also can achieve higher positioning accuracy and has good economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Embodiments of the present disclosure will now be described in detail with reference to the drawings. Preferred embodiments of the present disclosure will now be described in detail, examples of which are illustrated in the drawings. Whenever possible, the same reference numerals will be used throughout the drawings to refer to the same or like parts. In addition, although the terms used in the present disclosure are selected from well-known and commonly used terms, some of the terms mentioned in the description of the present disclosure may be selected by the applicant according to his or her judgment, and the detailed meanings thereof are described in the relevant parts of the description herein. In addition, it is required to understand the present disclosure not only by the actual terms used, but also by the meaning implied by each term.

[0031] Hereinafter, with reference to the drawings, for those skilled in the art of the present technology, from the detailed description of the present invention, the above and other objects, features, and advantages of the present invention will be apparent.

[0032] Figure 1 The flowchart of the visual positioning method for an underwater robot in a nuclear environment according to the present invention is shown;

[0033] Figure 2 Shown as Figure 1 The schematic diagram of the target image in step S1;

[0034] Figure 3 Shown as the schematic diagram of the camera coordinate system;

[0035] Figure 4 Shown as the comparison schematic diagram of the target image after mean filtering after step S2;

[0036] Figure 5 Shown as the erosion and dilation diagram of the target image;

[0037] Figure 6 Shown as the schematic diagram of the template matching process in step S3. Detailed implementation manners

[0038] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following-described drawings are only some examples or embodiments of the present application. For those of ordinary skill in the art, without creative efforts, the present application can also be applied to other similar scenarios based on these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structure or operation.

[0039] As shown in the present application and the claims, unless the context clearly indicates an exception, words such as "a", "an", "one", and / or "the" are not specifically singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0040] Unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps described in these embodiments do not limit the scope of the present application. At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship. Technologies, methods, and devices known to those of ordinary skill in the relevant fields may not be discussed in detail, but where appropriate, the said technologies, methods, and devices should be regarded as part of the authorization specification. In all the examples shown and discussed here, any specific value should be interpreted as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that similar reference numerals and letters represent similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0041] In addition, it should be noted that the use of words such as "first" and "second" to define components is only for the convenience of distinguishing the corresponding components. If not otherwise stated, the above words have no special meaning and cannot be understood as limiting the scope of protection of this application. In addition, although the terms used in this application are selected from well-known and commonly used terms, some terms mentioned in the specification of this application may be selected by the applicant at his or her discretion, and their detailed meanings are explained in the relevant parts of the description of this article. In addition, it is required to understand this application not only by the actual terms used, but also by the meaning implied by each term.

[0042] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0043] The present invention provides a visual positioning method for an underwater robot in a nuclear environment, the process of which is as follows: Figure 1 The specific steps include:

[0044] Step S1, setting an underwater camera and Figure 2 The target shown in the figure is used to calibrate the camera parameters and the camera position of the underwater camera, wherein the target is located within the field of view of the underwater camera; illustratively, the camera parameters and the camera position are calibrated using the Zhang Zhengyou calibration method;

[0045] Step S2, processing the target images obtained by the underwater camera to extract the contours of all images;

[0046] Step S3, matching the contours of all images with the image template of the target, determining and extracting the correct target pattern;

[0047] Step S4, for the correct target image, the coordinates of the feature points are extracted, and the coordinates of the target relative to the underwater camera are calculated based on the coordinates of the feature points and the target image, and the coordinate system is transformed to obtain the coordinates of the target relative to the pool, thereby completing the visual positioning of the underwater robot.

[0048] The following is a detailed description of the above steps:

[0049] In step S1, the camera is calibrated.

[0050] Specifically, the camera is placed at a predetermined working position, and the Zhang Zhengyou calibration method is used to calibrate the camera's internal and external parameters.

[0051] according to Figure 2Make a checkerboard calibration board and obtain a set of images of the calibration board by moving the calibration board. Use an image detection algorithm to obtain the pixel coordinates (u, v) of each corner point.

[0052] In a preferred embodiment, the image edge monitoring algorithm includes Sobel edge extraction, Canny edge extraction algorithm, etc.

[0053] In the Zhang-Zhengyou calibration method, the world coordinate system is fixed on the checkerboard, then the physical coordinate W of any point on the checkerboard is 0. Since the world coordinate system of the calibration board is defined artificially in advance and the size of the calibration board grid is known, the physical coordinates (U, V, W) of each corner point in the world coordinate system can be calculated. The positioning method of the present invention uses the pixel coordinates (u, v) of each corner point and the physical coordinates (U, V, W) of each corner point in the world coordinate system to calibrate the camera and obtain the internal and external parameter matrices and distortion parameters of the camera.

[0054] In the above process, the calculation idea of the internal and external parameters of the camera includes: first, solving the product of the internal parameter matrix and the external parameter matrix; second, solving the internal parameter matrix; third, solving the external parameter matrix.

[0055] The original single-point undistorted imaging model can be transformed into the following formula (1), where R1 and R2 are the first two columns of the rotation matrix R. For simplicity, the internal parameter matrix is denoted as A. For different images, the internal parameter matrix A is a constant value. For the same image, the internal parameter matrix A and the external parameter matrix (R1 R2 T) are constant values. For a single point on the same image, the internal parameter matrix A, the external parameter matrix (R1 R2 T), and the scale factor Z are constant values.

[0056]

[0057] Among them, A(R1 R2 T) is denoted as matrix H, and H is the product of the internal parameter matrix and the external parameter matrix. Denote the three columns of matrix H as (H1, H2, H3), then there are:

[0058]

[0059] Using the above formula (2) to eliminate the scale factor Z, we can get:

[0060]

[0061]

[0062] At this time, the scale factor Z has been eliminated, so the above formula holds for all corner points on the same image. (u, v) are the coordinates of the calibration board corner points in the pixel coordinate system, and the pixel coordinate system can be understood as the intuitive coordinate system on the target image obtained by shooting.

[0063] Such asFigure 3 As shown, it is the camera coordinate system. (U, V) are the coordinates of the calibration plate corner points in the world coordinate system. Through the image recognition algorithm, the pixel coordinates (u, v) of the calibration plate corner points can be obtained; also, since the world coordinate system of the calibration plate is predefined and the size of each grid on the calibration plate is known, the (U, V) in the world coordinate system can be calculated.

[0064] Among them, H is the homography matrix with 8 independent unknown elements. Each calibration plate corner point can provide two constraint equations. Therefore, when the number of calibration plate corner points on an image is equal to 4, the matrix H corresponding to this image can be obtained.

[0065] When the number of calibration plate corner points on an image is more than 4, the optimized matrix H is obtained by least squares regression. Thus, the internal parameter matrix A of the camera is:

[0066]

[0067] The external parameter matrix reflects the positional relationship between the calibration plate and the camera.

[0068] For different images, the positional relationship between the calibration plate and the camera has changed. At this time, the external parameter matrix corresponding to each image is different. The matrix H and the matrix A have been solved above.

[0069] Through formula (5):

[0070] (R1 R2 T) = A -1 H, formula (5)

[0071] The external parameter matrix (R1 R2 T) corresponding to each image can be obtained.

[0072] Enter step S2, target image processing, including removing noise from the target image taken underwater and extracting the contours of all images using the contour extraction algorithm.

[0073] First, remove image noise.

[0074] The original grayscale image taken has a lot of noise (patterns). The noise in the original image can be removed through filtering. Mean filtering is adopted, and the kernel size can be adjusted according to the actual situation to smooth the image. Remove noise from the target image taken underwater, extract the contours of all images using the contour extraction algorithm, match the contours, and determine whether it is the correct target pattern. For the correct target pattern, extract the coordinates of the feature points, and calculate the relative coordinates between the camera and the target according to the obtained coordinates and the target data.

[0075] Erode and then dilate the image after mean filtering to further remove noise and make the edges of the image shape smoother.

[0076] Specifically, the expressions for erosion and dilation are shown in Equations (6) and (7) respectively. After erosion and dilation, the image is as Figure 5 shown.

[0077] The mathematical expression for dilation is as follows:

[0078] dst(x, y) = max src(x + x1, y + y1) Equation (6)

[0079] The mathematical expression for erosion is as follows:

[0080] dst(x, y) = min src(x + x1, y + y1) Equation (7)

[0081] where src is the source image, dst is the target image, and (x1, y1) ∈ the convolution kernel.

[0082] In step S3, the contour is matched to determine whether it is the correct target pattern;

[0083] Specifically, in this step, the improved Canny algorithm is used to extract the edges of the template (the image template of the target) and the edges of the target image to intercept the target object image; the template edges and the image edges are matched, the similarity between the target and the target image captured by the camera is calculated, the object is searched in the image to be matched through a sliding window, and the corresponding relationship is obtained through the image edge feature points, so as to identify the scale change (such as the degree of size change) and rotation change (such as the rotation angle) of the target image.

[0084] The specific flowchart is as Figure 6 shown. The details are described as follows in combination with this figure:

[0085] Step S61, obtain the contours of all images;

[0086] Step S62, read the image template of the target;

[0087] Step S63, extract the template edges through the Canny algorithm;

[0088] Step S64, perform binary processing on all captured target images;

[0089] Step S65, extract the image edges through the Canny algorithm;

[0090] Step S66, match the template edges and the image edges obtained in steps S63 and S65, calculate the similarity, and obtain the corresponding relationship of the image feature points;

[0091] Step S67, calculate the centroid size and angle of the image.

[0092] Then, enter step S4. For the correct target pattern, extract the coordinates of the feature points. Calculate the relative coordinates between the underwater camera and the target based on the obtained coordinates and the target image. Transform the coordinates to obtain the position coordinates of the target relative to the pool, thus completing the visual positioning of the underwater robot.

[0093] In this step, target positioning is first performed, that is, the feature point data, image data, camera internal parameter matrix, camera distortion parameters, etc. of the template target are sent into the PnP function. The rotation matrix R matrix and translation matrix T matrix of the transformation between camera coordinate systems can be obtained. This is a relative transformation, and the calibration data of the camera needs to be fused to obtain the absolute value of the transformation. Use the obtained R matrix and T matrix to position the tracked target points.

[0094] The PnP function (Perspective-n-Point) in the above process is used to estimate the relative pose between the target image and the camera. The PnP function can calculate the mutual mapping problem between the three-dimensional spatial positions of the feature points of the image and the external parameters of the camera.

[0095] The PnP function is based on the three-dimensional spatial feature points corresponding to the target detected in the image to perform three-dimensional external parameter recovery, and can project the feature points in the image into three-dimensional space.

[0096] It is necessary to prepare the target first, that is, the feature points on the image. Set the position parameters and rotation matrix of the camera and the target, use the external parameters to project the three-dimensional spatial points to the projection positions on the image, and calculate the projection error. Minimize the projection error to solve the pose parameters. When the projection error reaches the minimum value, the pose parameters converge, that is, the solution is completed.

[0097] From camera calibration, the internal parameters of the camera can be calculated. Through the PnP function, the external parameters of the camera can be obtained. Let the coordinates of the target in the camera coordinate system be p c , and the coordinates of the target in the world coordinate system be p w . From the external parameters, the transformation formula of the target between the camera coordinate system and the world coordinate system is:

[0098] p C = R * P W + T Equation (8)

[0099] where R is the rotation matrix and T is the translation matrix.

[0100] The coordinates of the target in the camera coordinate system are P = (X, Y, Z). Therefore, according to the formula:

[0101] p w = R T (P - T) Equation (9)

[0102] Among them, R and T are obtained by the PnP function, so the pool coordinates of the target can be obtained.

[0103] Using the visual positioning method of the underwater robot in a nuclear environment of the present invention, the following technical effects are achieved:

[0104] (1) The underwater positioning method based on image recognition proposed by the invention is applicable to the underwater environment with high irradiation in nuclear power plants. During operation, only the target needs to be fixed on the robot, and irradiation-sensitive devices such as depth pressure sensors do not need to be installed.

[0105] (2) In this positioning method, the camera only needs to be arranged in the shallow water layer. Due to the shielding effect of water on the high radioactivity at the bottom of the spent fuel pool, the irradiation dose in the shallow water layer has been greatly reduced, and the camera is not required to have radiation resistance.

[0106] (3) Compared with depth pressure sensors, long or short baseline positioning methods, etc., the optical underwater positioning method based on image recognition proposed by the present invention can achieve higher positioning accuracy. According to the prototype test, millimeter-level positioning accuracy can be achieved within 10 meters.

[0107] (4) Since high-radiation-dose-resistant components do not need to be used in this underwater positioning scheme, the positioning scheme has good economy and can be applied during the operation and maintenance of equipment such as pressure vessels and refueling pools in addition to spent fuel pools.

[0108] The basic concepts have been described above. Obviously, for those skilled in the art, the above invention disclosure is only an example and does not constitute a limitation to this application. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are proposed in this application, so such modifications, improvements, and corrections still belong to the spirit and scope of the exemplary embodiments of this application.

[0109] At the same time, specific words are used in this application to describe the embodiments of this application. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification is not necessarily the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be combined appropriately.

[0110] The basic concepts have been described above. Obviously, for those skilled in the art, the above invention disclosure is only an example and does not constitute a limitation to this application. Although not explicitly stated here, those skilled in the art may make various modifications, improvements, and corrections to this application. Such modifications, improvements, and corrections are proposed in this application, so such modifications, improvements, and corrections still fall within the spirit and scope of the exemplary embodiments of this application.

[0111] Meanwhile, this application uses specific terms to describe the embodiments of this application. Such as "one embodiment", "an embodiment", and / or "some embodiments" mean a certain feature, structure, or characteristic related to at least one embodiment of this application. Therefore, it should be emphasized and noted that the "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more at different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures, or characteristics in one or more embodiments of this application can be appropriately combined.

[0112] Similarly, it should be noted that, in order to simplify the expression of the disclosure of this application and thus help the understanding of one or more invention embodiments, in the previous description of the embodiments of this application, sometimes multiple features are grouped into one embodiment, drawing, or the description thereof. However, this disclosure method does not mean that the features required by the subject matter of this application are more than those mentioned in the claims. In fact, the features of the embodiment are fewer than all the features of the single embodiment disclosed above.

[0113] In some embodiments, numbers are used to describe components and the quantity of attributes. It should be understood that such numbers used for the description of embodiments are, in some examples, modified by the modifiers "about", "approximately", or "substantially". Unless otherwise stated, "about", "approximately", or "substantially" indicate that the said numbers allow a variation of ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, and such approximate values may change according to the characteristics required by individual embodiments. In some embodiments, the numerical parameters should consider the specified significant digits and adopt the method of retaining the general number of digits. Although the numerical ranges and parameters used in some embodiments of this application to confirm the breadth of their scope are approximate values, in specific embodiments, such numerical settings are as precise as possible within the feasible range.

[0114] Although this application has been described with reference to the current specific embodiments, those of ordinary skill in the art should recognize that the above embodiments are only used to illustrate this application, and various equivalent changes or substitutions can be made without departing from the spirit of this application. Therefore, as long as the changes and variations of the above embodiments are within the scope of the spirit of this application, they will fall within the scope of the claims of this application.

Claims

1. A visual positioning method for an underwater robot in a nuclear environment, characterized in that, The visual positioning method includes: Step S1: Set an underwater camera and a target at the underwater working position, and calibrate the camera parameters and the camera position of the underwater camera, where the target is within the field of view of the underwater camera; Step S2: Process the target images captured by the underwater camera to extract the contours of all the images; Step S3: Match the contours of all the images with the image template of the target, and judge and extract the correct target pattern; wherein, the matching in Step S3 further includes: Read the image template of the target and extract the template edge; Perform binarization processing on the contours of all the images and then extract the image edge; Match the template edge and the image edge obtained in the above two steps, calculate the similarity between the target and the target image, search for the object in the image to be matched through a sliding window, extract the image edge feature points to obtain the corresponding relationship, so as to identify the scale change and rotation change of the target image; Step S4: Extract the coordinates of the feature points for the correct target pattern, calculate the coordinates of the target relative to the underwater camera according to the coordinates of the feature points and the target image, and perform coordinate system transformation to obtain the coordinates of the target relative to the pool, thus completing the visual positioning of the underwater robot.

2. The visual positioning method of the underwater robot in the nuclear environment according to claim 1, wherein The method for extracting the contours of all the images in Step S2 includes a contour extraction algorithm.

3. The visual positioning method of the underwater robot in the nuclear environment according to claim 1, characterized in that, The processing of Step S2 includes: Remove the noise from the target image and extract the contours of all the images, wherein the method for removing the noise includes mean filtering.

4. The visual positioning method of the underwater robot in the nuclear environment according to claim 3, wherein The method for removing the noise further includes: Perform dilation processing of Equation (1) and erosion processing of Equation (2) on the target image after mean filtering: dst(x,y) = maxsrc(x + x1, y + y1) Equation (1) dst(x,y) = minsrc(x + x1, y + y1) Equation (2) where (x1, y1) ∈ convolution kernel.

5. The visual positioning method of the underwater robot in the nuclear environment according to claim 1, wherein The calibration method in Step S1 includes Zhang Zhengyou calibration method.

6. The visual positioning method of the underwater robot in the nuclear environment according to claim 1, wherein The extraction methods in Steps S2 and S3 include any one of Sobel edge extraction method and Canny edge extraction method.

7. The visual positioning method of the underwater robot in the nuclear environment according to claim 1, characterized in that, In Step S4, the coordinate system transformation is performed according to the following formula: p C = R * P W + T Let the coordinates of the target in the camera coordinate system be P = (X, Y, Z), so the coordinates of the target relative to the pool are obtained according to the following formula: p w = R T (P - T) where p C represents the coordinates of the target in the camera coordinate system; p w represents the coordinates of the target in the world coordinate system; R is the rotation matrix, T is the translation matrix, and R and T are obtained by the PnP function.

Images