Infrared three-dimensional accurate imaging method and system for power equipment

Abstract

The invention discloses an infrared three-dimensional accurate imaging method and system for power equipment, and is applied to the technical field of infrared imaging. The method comprises the following steps: acquiring three-dimensional point cloud data of power equipment, and establishing a three-dimensional model; three-dimensional model projection drawings at different angles are generated, and the corresponding relation between the three-dimensional model projection drawings and the three-dimensional point cloud is recorded; obtaining two-dimensional infrared images of the power equipment at different angles, and matching the two-dimensional infrared images with the three-dimensional model projection drawing to obtain a mapping relation between the two-dimensional infrared images and the three-dimensional point cloud; calculating the measurement distance of the power equipment in all the two-dimensional infrared images, and obtaining the environment temperature when the two-dimensional infrared images are collected; establishing a temperature compensation model, and compensating the two-dimensional infrared image; and mapping the compensated temperature of the power equipment to the three-dimensional point cloud to obtain an infrared three-dimensional model. The temperature of the power equipment is mapped to the three-dimensional model through infrared three-dimensional accurate imaging, and the operation state of the power equipment can be monitored more visually.

Description

Technical Field

[0001] The present invention relates to the field of infrared imaging technology, and more particularly to a method and system for accurate three-dimensional infrared imaging of electric power equipment. Background Art

[0002] Damage or functional failure of power equipment often causes heating. Therefore, temperature is a key performance parameter monitored in predictive maintenance of power equipment. By collecting temperature data of power equipment through infrared thermal imaging technology and regularly checking the temperature of key equipment, the operating status of the equipment can be tracked over time, and abnormal readings can be quickly discovered for further inspection, thereby reducing the possibility of unplanned shutdowns due to equipment failure, reducing maintenance costs and equipment repair costs, extending the life of equipment assets, and maximizing maintenance effects and production capacity. Infrared thermal imaging technology detects the temperature distribution of an object by sensing the infrared radiation of the object, thereby forming a thermal image. As a non-contact, image-based temperature measurement technology, infrared thermal imaging can quickly and accurately detect the temperature of the target object without direct contact with it. Therefore, it is regarded as a very efficient non-destructive testing technology and has been widely used in temperature measurement of power equipment. However, in the existing power equipment temperature monitoring scheme, two-dimensional infrared images are used. Two-dimensional images cannot fully reflect the temperature distribution of power equipment, and monitoring personnel need to make judgments through multiple two-dimensional images. Therefore, how to provide a three-dimensional infrared accurate imaging method and system for power equipment is a problem that technicians in this field need to solve urgently. Summary of the invention

[0003] In view of this, the present invention provides a method and system for accurate three-dimensional infrared imaging of electric power equipment, which maps the infrared image of the electric power equipment to a three-dimensional model and intuitively displays the monitoring results.

[0004] In order to achieve the above object, the present invention provides the following technical solutions:

[0005] A method for accurate three-dimensional infrared imaging of electric power equipment comprises the following steps:

[0006] S1. Acquire three-dimensional point cloud data of the power equipment and establish a three-dimensional model based on the three-dimensional point cloud data;

[0007] S2, generating projection images of the three-dimensional model at different angles, and recording the corresponding relationship between the projection images of the three-dimensional model and the three-dimensional point cloud;

[0008] S3, obtaining two-dimensional infrared images of the power equipment at different angles, matching the two-dimensional infrared images with the three-dimensional model projection images, and recording the matching relationship between the two-dimensional infrared images and the three-dimensional model projection images;

[0009] S4, combining the matching relationship between the two-dimensional infrared image and the three-dimensional model projection image, and the corresponding relationship between the three-dimensional model projection image and the three-dimensional point cloud to obtain a mapping relationship between the two-dimensional infrared image and the three-dimensional point cloud;

[0010] S5, calculating the measurement distance of all power equipment in the two-dimensional infrared images, and obtaining the ambient temperature when the two-dimensional infrared images are collected;

[0011] S6, establishing a temperature compensation model based on the measured ambient temperature and the measured distance to compensate the two-dimensional infrared image;

[0012] S7. According to the mapping relationship between the three-dimensional point cloud and the two-dimensional infrared image, the temperature of the compensated power equipment is mapped to the three-dimensional point cloud to obtain an infrared three-dimensional model.

[0013] Optionally, the angle at which the projection image of the three-dimensional model is generated in S2 corresponds to the angle at which the two-dimensional infrared image of the electric power equipment is collected in S3.

[0014] Optionally, S3 specifically includes: collecting two-dimensional infrared images of power equipment through infrared imaging equipment at different angles, extracting the contours of the power equipment in the two-dimensional infrared image and the three-dimensional model projection map through an edge detection algorithm; selecting a two-dimensional infrared image, and comparing its contours of power equipment with the contours of power equipment in all three-dimensional model projection maps, taking the three-dimensional model projection map with the greatest repetition as the matching image of this two-dimensional infrared image, and adjusting the size of the two-dimensional infrared image so that the pixels in the two-dimensional infrared image correspond one-to-one with the pixels in the three-dimensional model projection map; performing contour comparison and size adjustment on all two-dimensional infrared images to obtain the matching relationship between all two-dimensional infrared images and the three-dimensional model projection map.

[0015] Optionally, S5 is specifically:

[0016] S51, performing power equipment target detection on the two-dimensional infrared image, and extracting the power equipment part in the two-dimensional infrared image;

[0017] S52, performing denoising processing on the two-dimensional infrared image of the power equipment part to eliminate the influence of environmental factors;

[0018] S53, obtaining the minimum bounding rectangle of the power equipment through a contour recognition algorithm, and obtaining the vertex coordinates of the minimum bounding rectangle;

[0019] S54. Calculate the measured distance of the electric equipment based on the vertex coordinates of the minimum circumscribed rectangle.

[0020] Optionally, S54 is specifically:

[0021]

[0022] Where L is the measurement distance of the power equipment, D is the width of the power equipment, f is the focal length, and d is the x ,d y It represents the size of the pixel point in the x and y directions of the imaging plane coordinate system, x1 and y1 represent the coordinates of one vertex of the minimum circumscribed rectangle, and x2 and y2 represent the coordinates of another vertex adjacent to it in the width direction.

[0023] Optionally, the temperature compensation model in S6 is specifically:

[0024] T1=T0-a1exp(a2T a )-a3

[0025] T=T1-b1x 2 +b1x+c

[0026] Where, T is the temperature value after measuring distance compensation, T1 is the temperature value after ambient temperature compensation, T0 is the initial temperature value, T a is the ambient temperature, x is the measurement distance, a1, a2, a3 are the ambient temperature compensation coefficients, b1, b2, c are the measurement distance compensation coefficients.

[0027] An infrared three-dimensional precise imaging system for electric power equipment executes the above-mentioned infrared three-dimensional precise imaging method for electric power equipment, comprising: a point cloud acquisition device for acquiring three-dimensional point cloud data of electric power equipment and establishing a three-dimensional model; an infrared acquisition device for acquiring a two-dimensional infrared image of the electric power equipment; an image matching module for acquiring a mapping relationship between the two-dimensional infrared image and the three-dimensional point cloud; a distance calculation module for calculating the measurement distance of the electric power equipment in the two-dimensional infrared image; a temperature compensation module for compensating the two-dimensional infrared image based on the measurement environment temperature and the measurement distance; and a point cloud mapping module for mapping the temperature of the electric power equipment to the three-dimensional point cloud.

[0028] It can be seen from the above technical scheme that, compared with the prior art, the present invention provides a method and system for accurate three-dimensional infrared imaging of power equipment, which has the following beneficial effects: the present invention establishes a three-dimensional point cloud model and maps it with a two-dimensional infrared image to obtain an infrared three-dimensional model, which can intuitively display the temperature distribution of the power equipment, assist staff in judging the operation status of the power equipment, and reduce the risk of failure of the power equipment; the present invention makes the projection map of the three-dimensional point cloud model correspond to the three-dimensional model, and matches the two-dimensional infrared image with the projection map to obtain a mapping relationship, which can accurately reflect the temperature conditions of each point of the power equipment; the present invention compensates for the temperature data collected by the infrared imaging device, improves the accuracy of temperature monitoring, and can better reflect the actual situation of the power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0030] Figure 1 This is a flow chart of the infrared three-dimensional precise imaging method for power equipment of the present invention;

[0031] Figure 2 It is a flow chart of distance calculation for electric power equipment of the present invention;

[0032] Figure 3 This is a flow chart of temperature compensation for power equipment measurement according to the present invention. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] The embodiment of the present invention discloses a method for accurate three-dimensional infrared imaging of electric power equipment. Figure 1 As shown, the following steps are included:

[0035] S1. Acquire three-dimensional point cloud data of the power equipment and establish a three-dimensional model based on the three-dimensional point cloud data;

[0036] S2, generating projection images of the three-dimensional model at different angles, and recording the corresponding relationship between the projection images of the three-dimensional model and the three-dimensional point cloud;

[0037] S3, obtaining two-dimensional infrared images of the power equipment at different angles, matching the two-dimensional infrared images with the three-dimensional model projection images, and recording the matching relationship between the two-dimensional infrared images and the three-dimensional model projection images;

[0038] S4, combining the matching relationship between the two-dimensional infrared image and the three-dimensional model projection image, and the corresponding relationship between the three-dimensional model projection image and the three-dimensional point cloud to obtain a mapping relationship between the two-dimensional infrared image and the three-dimensional point cloud;

[0039] S5, calculating the measurement distance of all power equipment in the two-dimensional infrared images, and obtaining the ambient temperature when the two-dimensional infrared images are collected;

[0040] S6, establishing a temperature compensation model based on the measured ambient temperature and the measured distance to compensate the two-dimensional infrared image;

[0041] S7. According to the mapping relationship between the three-dimensional point cloud and the two-dimensional infrared image, the temperature of the compensated power equipment is mapped to the three-dimensional point cloud to obtain an infrared three-dimensional model.

[0042] Furthermore, the angle at which the projection image of the three-dimensional model is generated in S2 corresponds to the angle at which the two-dimensional infrared image of the power equipment is collected in S3.

[0043] In the embodiment of the present invention, in S2, the world coordinates of the midpoint of the point cloud are converted into camera coordinates, and then the camera coordinates are converted into plane pixel coordinates through the camera intrinsic parameters to obtain the corresponding relationship between the three-dimensional model projection image and the three-dimensional point cloud.

[0044] In an embodiment of the present invention, a three-dimensional model projection image is generated at a certain angle with the three-dimensional model of the power equipment as the center, and all pixel points in the three-dimensional model projection image have corresponding three-dimensional point clouds, and all three-dimensional point clouds have corresponding pixel points.

[0045] Furthermore, S3 is specifically as follows: collecting two-dimensional infrared images of power equipment through infrared imaging equipment at different angles, extracting the contours of the power equipment in the two-dimensional infrared image and the three-dimensional model projection map through an edge detection algorithm; selecting a two-dimensional infrared image, and comparing its contours of power equipment with the contours of power equipment in all three-dimensional model projection maps, taking the three-dimensional model projection map with the greatest repetition as the matching image of this two-dimensional infrared image, and adjusting the size of the two-dimensional infrared image so that the pixels in the two-dimensional infrared image correspond one-to-one with the pixels in the three-dimensional model projection map; performing contour comparison and size adjustment on all two-dimensional infrared images to obtain the matching relationship between all two-dimensional infrared images and the three-dimensional model projection map.

[0046] In an embodiment of the present invention, the edge detection algorithm adopts the Canny algorithm, firstly, the image is smoothed and converted into grayscale, and the noise in the image is removed by using a Gaussian filter, and then the Sobel kernel is applied in the horizontal and vertical directions to obtain the first-order derivatives in the horizontal and vertical directions on the smoothed image, and then the edge gradient and angle are calculated, and the angle is rounded to one of four angles representing the vertical, horizontal and two diagonal directions; all pixels that may not constitute an edge are deleted, if each pixel is a local maximum in its neighborhood, it is checked in the gradient direction, if it is a local maximum, it is used for the next stage, otherwise it is set to 0, and the edge pixels with weak gradient values ​​are filtered out, and the edge pixels with high gradient values ​​are retained. For pixels located at high gradient values ​​and weak gradient values, if one of the 8 pixels around it has a pixel value of 255, it is set to a strong pixel, otherwise it is set to 0.

[0047] Further, such as Figure 2 As shown, S5 is specifically:

[0048] S51, performing power equipment target detection on the two-dimensional infrared image, and extracting the power equipment part in the two-dimensional infrared image;

[0049] S52, performing denoising processing on the two-dimensional infrared image of the power equipment part to eliminate the influence of environmental factors;

[0050] S53, obtaining the minimum bounding rectangle of the power equipment through a contour recognition algorithm, and obtaining the vertex coordinates of the minimum bounding rectangle;

[0051] S54. Calculate the measured distance of the electric equipment based on the vertex coordinates of the minimum circumscribed rectangle.

[0052] In the embodiment of the present invention, in S51, target detection is performed on the power equipment through the R-CNN network, and in S52, corrosion and expansion operations are performed on the two-dimensional infrared image in sequence.

[0053] Furthermore, S54 is specifically:

[0054]

[0055] Where L is the measurement distance of the power equipment, D is the width of the power equipment, f is the focal length, and d is the x ,d y It represents the size of the pixel point in the x and y directions of the imaging plane coordinate system, x1 and y1 represent the coordinates of one vertex of the minimum circumscribed rectangle, and x2 and y2 represent the coordinates of another vertex adjacent to it in the width direction.

[0056] Furthermore, the temperature compensation model in S6 is specifically:

[0057] T1=T0-a1exp(a2T a )-a3

[0058] T=T1-b1x 2 +b1x+c

[0059] Where, T is the temperature value after measuring distance compensation, T1 is the temperature value after ambient temperature compensation, T0 is the initial temperature value, T a is the ambient temperature, x is the measurement distance, a1, a2, a3 are the ambient temperature compensation coefficients, b1, b2, c are the measurement distance compensation coefficients. The temperature compensation process is as follows: Figure 3 shown.

[0060] In the embodiment of the present invention, the temperature compensation model compensates for the ambient temperature and the measurement distance. When the difference between the ambient temperature and the temperature of the power equipment is too large, the measurement result will produce a large error. In this embodiment, infrared imaging experiments are carried out at different temperatures, actual measurement data are collected, and the measurement data is plotted along with the change of the ambient temperature. After multiple experiments, curve fitting is performed to establish a nonlinear model of the fitted curve as the ambient temperature compensation model: T1=T0-a1exp(a2T a )-a3.

[0061] As the measuring distance increases, the measured temperature will be slightly lower than the actual temperature. Similarly, by changing the measuring distance through multiple experiments, the error between the actual temperature and the measured temperature is obtained, and then the error value at different measuring distances is obtained. The error value is fitted by second order to obtain the measuring distance temperature compensation model: T = T1-b1x 2 +b1x+c. The compensation coefficients in the ambient temperature compensation model and the measurement distance temperature compensation model are determined by experimental data.

[0062] and Figure 1 Corresponding to the method described above, an embodiment of the present invention further discloses an infrared three-dimensional precise imaging system for electric power equipment, which executes the above-mentioned infrared three-dimensional precise imaging method for electric power equipment, including: a point cloud acquisition device, used to acquire three-dimensional point cloud data of electric power equipment and establish a three-dimensional model; an infrared acquisition device, used to acquire a two-dimensional infrared image of the electric power equipment; an image matching module, used to obtain the mapping relationship between the two-dimensional infrared image and the three-dimensional point cloud; a distance calculation module, used to calculate the measurement distance of the electric power equipment in the two-dimensional infrared image; a temperature compensation module, which compensates the two-dimensional infrared image based on the measurement environment temperature and the measurement distance; and a point cloud mapping module, used to map the temperature of the electric power equipment to the three-dimensional point cloud.

[0063] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0064] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for accurate three-dimensional infrared imaging of power equipment, characterized in that: The following steps are involved: S1. Acquire three-dimensional point cloud data of the power equipment and establish a three-dimensional model based on the three-dimensional point cloud data; S2, generating projection images of the three-dimensional model at different angles, and recording the corresponding relationship between the projection images of the three-dimensional model and the three-dimensional point cloud; S3, obtaining two-dimensional infrared images of the power equipment at different angles, matching the two-dimensional infrared images with the three-dimensional model projection images, and recording the matching relationship between the two-dimensional infrared images and the three-dimensional model projection images; S4, combining the matching relationship between the two-dimensional infrared image and the three-dimensional model projection image, and the corresponding relationship between the three-dimensional model projection image and the three-dimensional point cloud to obtain a mapping relationship between the two-dimensional infrared image and the three-dimensional point cloud; S5, calculating the measurement distance of all power equipment in the two-dimensional infrared images, and obtaining the ambient temperature when the two-dimensional infrared images are collected; S6, establishing a temperature compensation model based on the measured ambient temperature and the measured distance to compensate the two-dimensional infrared image; S7. According to the mapping relationship between the three-dimensional point cloud and the two-dimensional infrared image, the temperature of the compensated power equipment is mapped to the three-dimensional point cloud to obtain an infrared three-dimensional model.

2. The method for accurate three-dimensional infrared imaging of electric power equipment according to claim 1, characterized in that: The angle at which the projection image of the three-dimensional model is generated in S2 corresponds to the angle at which the two-dimensional infrared image of the power equipment is collected in S3.

3. The method for accurate three-dimensional infrared imaging of electric power equipment according to claim 2, characterized in that: S3 is specifically as follows: collecting two-dimensional infrared images of power equipment through infrared imaging equipment at different angles, extracting the contours of the power equipment in the two-dimensional infrared image and the three-dimensional model projection map through an edge detection algorithm; selecting a two-dimensional infrared image, comparing its contour of power equipment with the contours of power equipment in all three-dimensional model projection maps, taking the three-dimensional model projection map with the greatest repetition as the matching image of this two-dimensional infrared image, adjusting the size of the two-dimensional infrared image so that the pixels in the two-dimensional infrared image correspond one-to-one with the pixels in the three-dimensional model projection map; performing contour comparison and size adjustment on all two-dimensional infrared images to obtain the matching relationship between all two-dimensional infrared images and the three-dimensional model projection map.

4. The method for accurate three-dimensional infrared imaging of electric power equipment according to claim 1, characterized in that: S5 is specifically: S51, performing power equipment target detection on the two-dimensional infrared image, and extracting the power equipment part in the two-dimensional infrared image; S52, performing denoising processing on the two-dimensional infrared image of the power equipment part to eliminate the influence of environmental factors; S53, obtaining the minimum circumscribed rectangle of the electric power equipment through a contour recognition algorithm, and acquiring the vertex coordinates of the minimum circumscribed rectangle; S54. Calculate the measurement distance of the electric equipment based on the vertex coordinates of the minimum circumscribed rectangle.

5. The method for accurate three-dimensional infrared imaging of electric power equipment according to claim 4, characterized in that: S54 is as follows: Where L is the measurement distance of the power equipment, D is the width of the power equipment, f is the focal length, and d is the x d y It represents the size of the pixel point in the x and y directions of the imaging plane coordinate system, x1 and y1 represent the coordinates of one vertex of the minimum circumscribed rectangle, and x2 and y2 represent the coordinates of another vertex adjacent to it in the width direction.

6. The method for accurate three-dimensional infrared imaging of electric power equipment according to claim 1, characterized in that: The temperature compensation model in S6 is as follows: <h2 style=";text-align:left;direction:ltr">T1 = T0 - a1exp(a2T<h2 style=";text-align:left;direction:ltr"> a <h2 style=";text-align:left;direction:ltr"> )-a3 T=T1-b1x 2 +b1x+c Where, T is the temperature value after measuring distance compensation, T1 is the temperature value after ambient temperature compensation, T0 is the initial temperature value, T a is the ambient temperature, x is the measurement distance, a1, a2, a3 are the ambient temperature compensation coefficients, b1, b2, c are the measurement distance compensation coefficients.

7. An infrared three-dimensional precise imaging system for power equipment, characterized in that: The method for infrared three-dimensional precise imaging of electric power equipment as described in any one of claims 1 to 6 comprises: a point cloud acquisition device for acquiring three-dimensional point cloud data of electric power equipment and establishing a three-dimensional model; an infrared acquisition device for acquiring two-dimensional infrared images of electric power equipment; an image matching module for acquiring a mapping relationship between a two-dimensional infrared image and a three-dimensional point cloud; a distance calculation module for calculating a measurement distance of the electric power equipment in a two-dimensional infrared image; a temperature compensation module for compensating the two-dimensional infrared image based on the measurement ambient temperature and the measurement distance; and a point cloud mapping module for mapping the temperature of the electric power equipment to a three-dimensional point cloud.

Images