阅读说明：本技术 一种故障定位方法、装置及电子设备 (Fault positioning method and device and electronic equipment ) 是由 笪宏志 翁捷 褚兰 于 2021-08-05 设计创作，主要内容包括：本发明提供了一种故障定位方法、装置及电子设备,基于采集的多个图片样本确定待测设备预设范围内的实际高程信息,获取待测设备对应的包括故障点的图片,并确定出图片对应的相机参数信息,基于实际高程信息以及相机参数信息,确定出故障点对应的待测设备的定位坐标,然后从定位坐标中,筛选出满足预设坐标规则的定位坐标,并作为故障点对应的待测设备的实际故障点坐标。通过本发明,能够根据包括故障点的图片中的故障点,定位出设备的故障点的实际坐标。进一步,在确定实际故障点坐标时,还会从定位坐标中,筛选出满足预设坐标规则的定位坐标,并作为故障点对应的待测设备的实际故障点坐标,提高实际故障点坐标的确定精度。(The invention provides a fault positioning method, a fault positioning device and electronic equipment. By the method and the device, the actual coordinate of the fault point of the equipment can be positioned according to the fault point in the picture comprising the fault point. Furthermore, when the actual fault point coordinate is determined, the positioning coordinate meeting the preset coordinate rule is screened out from the positioning coordinates and is used as the actual fault point coordinate of the equipment to be tested corresponding to the fault point, and the determination accuracy of the actual fault point coordinate is improved.)

1. A method of fault location, comprising:

acquiring a plurality of collected picture samples within a preset range of equipment to be tested, and determining actual elevation information within the preset range of the equipment to be tested based on the plurality of picture samples;

acquiring a picture including a fault point corresponding to the equipment to be tested, and determining camera parameter information corresponding to the picture;

determining the positioning coordinate of the equipment to be tested corresponding to the fault point based on the actual elevation information and the camera parameter information;

and screening out positioning coordinates meeting a preset coordinate rule from the positioning coordinates, and taking the positioning coordinates as actual fault point coordinates of the equipment to be tested corresponding to the fault point.

2. The method for locating the fault according to claim 1, wherein determining the actual elevation information within the preset range of the device under test based on the plurality of picture samples comprises:

extracting a camera parameter information sample in the picture sample;

correcting a camera parameter information sample in the picture sample to obtain reference camera parameter information corresponding to the picture sample;

performing global dense matching on reference camera parameter information corresponding to the picture sample to obtain dense three-dimensional point cloud;

and performing inverse distance weight interpolation calculation on the dense three-dimensional point cloud to obtain actual elevation information in a preset range of the equipment to be measured.

3. The method according to claim 1, wherein determining the camera parameter information corresponding to the picture comprises:

performing picture matching on the picture and the plurality of picture samples, determining the picture sample corresponding to the picture, and using the picture sample as a target picture sample;

and acquiring reference camera parameter information corresponding to the target picture sample, and taking the reference camera parameter information as the camera parameter information corresponding to the picture.

4. The method for locating the fault according to claim 1, wherein determining the location coordinates of the device under test corresponding to the fault point based on the actual elevation information and the camera parameter information comprises:

acquiring a collinear equation, wherein the collinear equation comprises the incidence relation between the camera parameter information and the positioning coordinate of the equipment to be tested corresponding to the fault point;

determining an iteration parameter; the iteration parameters comprise a maximum elevation, a minimum elevation and an elevation step length;

and performing iterative computation based on the iterative parameters and the collinear equation to obtain the positioning coordinates of the equipment to be tested corresponding to the fault point.

5. The method of claim 4, wherein obtaining the collinearity equation comprises:

acquiring a basic collinearity equation; the base collinearity equation includes: the image coordinates of the fault points in the picture including the fault points, the camera parameter information, the positioning coordinates of the equipment to be tested corresponding to the fault points and the incidence relation among the designated coefficients;

calculating the numerical value of the specified coefficient according to camera attitude information in the camera parameter information;

and substituting the numerical value of the specified coefficient into the basic collinearity equation to obtain the collinearity equation.

6. The method of claim 4, wherein determining iterative parameters comprises:

determining a position point corresponding to the camera parameter information in the actual elevation information;

screening out the maximum elevation and the minimum elevation in the specified range with the position point as a datum point in the actual elevation information;

and acquiring a preset elevation step length.

7. The method according to claim 4, wherein performing iterative computation based on the iterative parameters and the collinearity equation to obtain the location coordinates of the device under test corresponding to the fault point comprises:

setting a reference elevation to the minimum elevation;

according to the collinearity equation, calculating and obtaining an abscissa and ordinate point of the positioning coordinate corresponding to the reference elevation, and determining a target elevation corresponding to the abscissa and ordinate point in the actual elevation information;

judging whether the elevation difference between the target elevation and the reference elevation is smaller than a preset elevation difference or not;

if the target elevation is smaller than the preset elevation, updating the preset elevation difference into the elevation difference, and taking the target elevation and the position of the equipment to be tested corresponding to the horizontal and vertical coordinate points as positioning coordinates;

and taking the sum of the reference elevation and the elevation step length as a new reference elevation, and returning to execute the step of calculating and obtaining the abscissa and ordinate points of the positioning coordinates corresponding to the reference elevation according to the collinearity equation until the reference elevation is greater than the maximum elevation.

8. The method according to claim 7, wherein determining the target elevation corresponding to the abscissa point in the actual elevation information comprises:

determining whether the abscissa and ordinate points are located on grid points in the actual elevation information;

if not, determining the corresponding target elevation of the abscissa and the ordinate in the actual elevation information by adopting a bilinear interpolation mode.

9. The fault location method according to claim 7, wherein when it is determined that the height difference between the target elevation and the reference elevation is not less than a preset height difference, the method further comprises:

and taking the sum of the reference elevation and the elevation step length as a new reference elevation, and returning to execute the step of calculating and obtaining the abscissa and ordinate points of the positioning coordinates corresponding to the reference elevation according to the collinearity equation until the reference elevation is greater than the maximum elevation.

10. The fault location method according to claim 7, wherein the step of screening out, from the location coordinates, location coordinates that satisfy a preset coordinate rule and serve as actual fault point coordinates of the device under test corresponding to the fault point comprises:

and screening out the positioning coordinates with the minimum height difference or the height ratio of the target elevation and the reference elevation corresponding to the target elevation closest to a specified numerical value from the positioning coordinates.

11. A fault locating device, comprising:

the elevation determination module is used for acquiring a plurality of acquired picture samples within a preset range of the equipment to be tested and determining actual elevation information within the preset range of the equipment to be tested based on the picture samples;

the information determining module is used for acquiring a picture including a fault point corresponding to the equipment to be tested and determining camera parameter information corresponding to the picture;

the fault point determination module is used for determining the positioning coordinate of the equipment to be tested corresponding to the fault point based on the actual elevation information and the camera parameter information;

and the fault point screening module is used for screening out the positioning coordinates meeting the preset coordinate rule from the positioning coordinates and taking the positioning coordinates as the actual fault point coordinates of the equipment to be tested corresponding to the fault point.

12. A storage medium, characterized in that the storage medium comprises a stored program, wherein a device on which the storage medium is located is controlled to perform the fault localization method according to any one of claims 1-10 when the program is run.

13. An electronic device, comprising: a memory and a processor;

wherein the memory is used for storing programs;

a processor calls a program and is adapted to perform the fault localization method of any of claims 1-10.

Technical Field

The invention relates to the field of photovoltaic power station fault location, in particular to a fault location method and device and electronic equipment.

Background

Along with the development of unmanned aerial vehicle technique, photovoltaic power plant's fortune dimension work is patrolled and examined gradually by the manual work and is changed into the picture that gathers equipment through the mode that unmanned aerial vehicle carried on visible light camera and infrared camera to realize the intellectual detection system of equipment (like photovoltaic module) trouble, the fortune dimension efficiency of improvement photovoltaic power plant that this kind of mode can be very big, the resources of using manpower sparingly.

After the picture including the fault point is determined through the acquired picture, how to accurately locate the geographical coordinates of the fault point of the actual device according to the fault point in the picture including the fault point is a technical problem that needs to be solved by those skilled in the art.

Disclosure of Invention

In view of this, the present invention provides a fault location method, an apparatus and an electronic device, so as to solve the problem that it is urgently needed to accurately locate the geographical coordinates of the fault point of the actual device according to the fault point in the picture including the fault point.

In order to solve the technical problems, the invention adopts the following technical scheme:

a fault location method, comprising:

acquiring a plurality of collected picture samples within a preset range of equipment to be tested, and determining actual elevation information within the preset range of the equipment to be tested based on the plurality of picture samples;

acquiring a picture including a fault point corresponding to the equipment to be tested, and determining camera parameter information corresponding to the picture;

determining the positioning coordinate of the equipment to be tested corresponding to the fault point based on the actual elevation information and the camera parameter information;

and screening out positioning coordinates meeting a preset coordinate rule from the positioning coordinates, and taking the positioning coordinates as actual fault point coordinates of the equipment to be tested corresponding to the fault point.

Optionally, determining, based on the plurality of picture samples, actual elevation information within a preset range of the device under test includes:

extracting a camera parameter information sample in the picture sample;

correcting a camera parameter information sample in the picture sample to obtain reference camera parameter information corresponding to the picture sample;

performing global dense matching on reference camera parameter information corresponding to the picture sample to obtain dense three-dimensional point cloud;

and performing inverse distance weight interpolation calculation on the dense three-dimensional point cloud to obtain actual elevation information in a preset range of the equipment to be measured.

Optionally, determining the camera parameter information corresponding to the picture includes:

performing picture matching on the picture and the plurality of picture samples, determining the picture sample corresponding to the picture, and using the picture sample as a target picture sample;

and acquiring reference camera parameter information corresponding to the target picture sample, and taking the reference camera parameter information as the camera parameter information corresponding to the picture.

Optionally, determining, based on the actual elevation information and the camera parameter information, a positioning coordinate of the device to be tested corresponding to the fault point, including:

acquiring a collinear equation, wherein the collinear equation comprises the incidence relation between the camera parameter information and the positioning coordinate of the equipment to be tested corresponding to the fault point;

determining an iteration parameter; the iteration parameters comprise a maximum elevation, a minimum elevation and an elevation step length;

and performing iterative computation based on the iterative parameters and the collinear equation to obtain the positioning coordinates of the equipment to be tested corresponding to the fault point.

Optionally, obtaining a collinearity equation comprises:

acquiring a basic collinearity equation; the base collinearity equation includes: the image coordinates of the fault points in the picture including the fault points, the camera parameter information, the positioning coordinates of the equipment to be tested corresponding to the fault points and the incidence relation among the designated coefficients;

calculating the numerical value of the specified coefficient according to camera attitude information in the camera parameter information;

and substituting the numerical value of the specified coefficient into the basic collinearity equation to obtain the collinearity equation.

Optionally, determining an iteration parameter comprises:

determining a position point corresponding to the camera parameter information in the actual elevation information;

screening out the maximum elevation and the minimum elevation in the specified range with the position point as a datum point in the actual elevation information;

and acquiring a preset elevation step length.

Optionally, performing iterative computation based on the iterative parameters and the collinearity equation to obtain the positioning coordinates of the device to be tested corresponding to the fault point, including:

setting a reference elevation to the minimum elevation;

according to the collinearity equation, calculating and obtaining an abscissa and ordinate point of the positioning coordinate corresponding to the reference elevation, and determining a target elevation corresponding to the abscissa and ordinate point in the actual elevation information;

judging whether the elevation difference between the target elevation and the reference elevation is smaller than a preset elevation difference or not;

if the target elevation is smaller than the preset elevation, updating the preset elevation difference into the elevation difference, and taking the target elevation and the position of the equipment to be tested corresponding to the horizontal and vertical coordinate points as positioning coordinates;

and taking the sum of the reference elevation and the elevation step length as a new reference elevation, and returning to execute the step of calculating and obtaining the abscissa and ordinate points of the positioning coordinates corresponding to the reference elevation according to the collinearity equation until the reference elevation is greater than the maximum elevation.

Optionally, determining a target elevation corresponding to the abscissa and the ordinate in the actual elevation information includes:

determining whether the abscissa and ordinate points are located on grid points in the actual elevation information;

if not, determining the corresponding target elevation of the abscissa and the ordinate in the actual elevation information by adopting a bilinear interpolation mode.

Optionally, when it is determined that the height difference between the target elevation and the reference elevation is not less than the preset height difference, the method further includes:

and taking the sum of the reference elevation and the elevation step length as a new reference elevation, and returning to execute the step of calculating and obtaining the abscissa and ordinate points of the positioning coordinates corresponding to the reference elevation according to the collinearity equation until the reference elevation is greater than the maximum elevation.

Optionally, screening out a positioning coordinate meeting a preset coordinate rule from the positioning coordinates, and using the positioning coordinate as an actual fault point coordinate of the device to be tested corresponding to the fault point, including:

and screening out the positioning coordinates with the minimum height difference or the height ratio of the target elevation and the reference elevation corresponding to the target elevation closest to a specified numerical value from the positioning coordinates.

A fault locating device comprising:

the elevation determination module is used for acquiring a plurality of acquired picture samples within a preset range of the equipment to be tested and determining actual elevation information within the preset range of the equipment to be tested based on the picture samples;

the information determining module is used for acquiring a picture including a fault point corresponding to the equipment to be tested and determining camera parameter information corresponding to the picture;

the fault point determination module is used for determining the positioning coordinate of the equipment to be tested corresponding to the fault point based on the actual elevation information and the camera parameter information;

and the fault point screening module is used for screening out the positioning coordinates meeting the preset coordinate rule from the positioning coordinates and taking the positioning coordinates as the actual fault point coordinates of the equipment to be tested corresponding to the fault point.

A storage medium comprising a stored program, wherein the apparatus on which the storage medium is located is controlled to perform the above-mentioned fault location method when the program is run.

An electronic device, comprising: a memory and a processor;

wherein the memory is used for storing programs;

the processor calls a program and is used to perform the fault location method described above.

Compared with the prior art, the invention has the following beneficial effects:

the invention provides a fault positioning method, a fault positioning device and electronic equipment, wherein a plurality of collected picture samples in a preset range of equipment to be tested are obtained, actual elevation information in the preset range of the equipment to be tested is determined based on the picture samples, a picture corresponding to the equipment to be tested and including a fault point is obtained, camera parameter information corresponding to the picture is determined, positioning coordinates of the equipment to be tested corresponding to the fault point are determined based on the actual elevation information and the camera parameter information, and then the positioning coordinates meeting a preset coordinate rule are screened out from the positioning coordinates and serve as actual fault point coordinates of the equipment to be tested corresponding to the fault point. By the method and the device, the actual coordinate of the fault point of the equipment can be positioned according to the fault point in the picture comprising the fault point. Further, when the actual fault point coordinate is determined, the positioning coordinate meeting the preset coordinate rule is screened out from the positioning coordinates and is used as the actual fault point coordinate of the equipment to be tested corresponding to the fault point, and the determination accuracy of the actual fault point coordinate is improved.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.

Fig. 1 is a flowchart of a method of fault location according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method of another fault location method according to an embodiment of the present invention;

fig. 3 is a flowchart of a method of a further fault location method according to an embodiment of the present invention;

fig. 4 is a flowchart of a method of a further fault location method according to an embodiment of the present invention;

fig. 5 is a flowchart of a method of a fifth fault location method according to an embodiment of the present invention;

fig. 6 is a schematic structural diagram of a fault location device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Along with the development of unmanned aerial vehicle technique, photovoltaic power plant's fortune dimension is patrolled and examined to change into the mode of gathering the photo through unmanned aerial vehicle carried on visible light, infrared camera by the manual work in the past gradually and is realized equipment, like the intellectual detection system of photovoltaic module trouble, the very big improvement of this kind of mode photovoltaic power plant fortune dimension's efficiency, save a large amount of manpower resources.

After the fault detection of the photovoltaic module is completed, the fault of the photovoltaic module needs to be accurately positioned, and the positioned result is marked on a global electronic map to guide operation and maintenance personnel to carry out operation and maintenance.

At present, the accurate positioning of the faults of the photovoltaic module can be realized by the following three methods:

1. the method comprises the steps of carrying out image registration by utilizing a visible light photo and an infrared photo which are shot simultaneously during routing inspection of the unmanned aerial vehicle, determining a pixel coordinate conversion relation between the visible light photo and the infrared photo, converting a pixel coordinate of a fault detected on the infrared photo into a pixel coordinate of the visible light photo, then carrying out registration on the visible light photo and an electronic map of a power station, and finally completing calibration of the fault of the photovoltaic module on the electronic map of the power station.

The disadvantages of this solution are: due to the fact that imaging modes of the visible light photo and the infrared photo are different, the differences of the resolution ratio of the visible light photo and the infrared photo, the shooting range and the like are large, and the texture difference between the strings is small, accurate registration or registration incapability of visible light images and infrared images is difficult to perform in many unmanned aerial vehicle photovoltaic inspection scenes.

2. When the unmanned aerial vehicle is used for shooting a photo, the camera shooting center GPS coordinate provided by the unmanned aerial vehicle system, the attitude parameter (the attitude parameter is mainly yaw angle, pitch angle and roll angle) of the camera and the flight height data are used for calculating the distance from the pixel coordinate of the fault detected on the infrared photo to the center pixel coordinate of the infrared photo, so that the fault point is positioned. The problem that this kind of scheme exists is that the attitude parameter that the unmanned aerial vehicle system provided is not accurate, and the central pixel coordinate of infrared photo has the skew, can not keep invariable at the height data of the big place unmanned aerial vehicle flight of elevation difference, and these can lead to the fault point position to solve and have great skew.

3. The method comprises the steps of reconstructing camera GPS (Global Positioning System) coordinates and camera postures of all photos shot by an unmanned aerial vehicle by utilizing SFM (motion recovery structure), establishing a corresponding relation between a three-dimensional coordinate and a two-dimensional pixel point according to sparse point cloud data generated by the SFM, and finally interpolating the three-dimensional coordinate corresponding to the pixel coordinate of a fault point. The biggest problem of such a scheme is that when there is not enough or no sparse point cloud within a certain range around the pixel coordinate of the fault point, the interpolation is unstable, the error is uncontrollable, and this is common in a photovoltaic scene. In addition, the point cloud data is also required to be the point cloud data of the photovoltaic module, but in practice, the point cloud data may be the point cloud data of trees around the photovoltaic module, and thus fault location cannot be realized.

As can be seen from the above three methods, the actual coordinates of the fault point of the device cannot be accurately located at present, and therefore, a method capable of accurately locating the fault point is needed.

Therefore, the inventor finds out through research that a plurality of collected picture samples in a preset range of equipment to be tested are obtained, actual elevation information in the preset range of the equipment to be tested is determined based on the picture samples, a picture including a fault point corresponding to the equipment to be tested is obtained, camera parameter information corresponding to the picture is determined, a positioning coordinate of the equipment to be tested corresponding to the fault point is determined based on the actual elevation information and the camera parameter information, and then the positioning coordinate meeting a preset coordinate rule is screened out from the positioning coordinate and serves as an actual fault point coordinate of the equipment to be tested corresponding to the fault point. By the method and the device, the actual coordinate of the fault point of the equipment can be positioned according to the fault point in the picture comprising the fault point. Further, when the actual fault point coordinate is determined, the positioning coordinate meeting the preset coordinate rule is screened out from the positioning coordinates and is used as the actual fault point coordinate of the equipment to be tested corresponding to the fault point, and the determination accuracy of the actual fault point coordinate is improved.

On the basis of the above, an embodiment of the present invention provides a fault location method, and with reference to fig. 1, the fault location method may include:

s11, acquiring a plurality of collected picture samples within a preset range of the device to be tested, and determining actual elevation information within the preset range of the device to be tested based on the picture samples.

In this embodiment, the device to be tested may be a device in a photovoltaic power station, such as a photovoltaic module. Specifically, use the equipment to be tested as photovoltaic module for example, in the scene is patrolled and examined to the photovoltaic, can use unmanned aerial vehicle to carry on infrared camera and carry out image acquisition to photovoltaic module, obtain the infrared photo of unmanned aerial vehicle. When a specific image is collected, a higher course and a higher lateral overlapping rate need to be set between the pictures, and it needs to be ensured that all the pictures are spliced to cover all the photovoltaic modules, that is, photos of a plurality of photovoltaic modules need to be collected to cover all the photovoltaic modules. In this embodiment, the collected picture is referred to as a picture sample.

Besides collecting infrared pictures, the unmanned aerial vehicle can be used for collecting visible light pictures.

Then, the actual elevation information of the device to be tested within the preset range may be determined based on the plurality of picture samples, for example, the actual elevation information of the device to be tested within 100 meters is obtained, and the actual elevation information may be digital surface model DSM information in which the actual elevation information of the ground, the number, the devices (such as photovoltaic modules), buildings, and the like of the device to be tested within 100 meters is stored.

And S12, acquiring the picture including the fault point corresponding to the device to be tested, and determining the camera parameter information corresponding to the picture.

In this embodiment, can use unmanned aerial vehicle to gather the picture of the equipment that awaits measuring, can be called unmanned aerial vehicle picture in this embodiment. The unmanned aerial vehicle picture can be the infrared picture or the visible light picture and the like.

Then, a picture including a fault point is screened from the acquired pictures, and then camera parameter information corresponding to the picture is determined, wherein the camera parameter information in the embodiment can be camera GPS coordinates, camera attitude information and camera internal parameters.

In this embodiment, the camera GPS coordinates are represented by (Xa, Ya, Za), and the camera attitude information is represented by three anglesExpressed by the rotation about Y as the principal axisAngle, then angle ω about the X axis, and finally angle k about the Z axis.

The camera internal reference is represented by (f, cx, cy), f represents the focal length of the camera, and cx and cy represent the pixel coordinates of the camera photographing center.

The pixel coordinate of the detected fault point in the picture is (u, v), and the actual three-dimensional coordinate of the fault point is represented by (X, Y, Z). Wherein, X, Y, and Z are data to be solved in this embodiment.

And S13, determining the positioning coordinates of the equipment to be tested corresponding to the fault point based on the actual elevation information and the camera parameter information.

In this embodiment, a plurality of positioning coordinates may be determined according to the actual elevation information and the camera parameter information, where the positioning coordinates in this embodiment are possible positions where the device to be tested has a fault, and a final fault point position needs to be screened out from the positions.

And S14, screening out positioning coordinates meeting a preset coordinate rule from the positioning coordinates, and taking the positioning coordinates as actual fault point coordinates of the equipment to be tested corresponding to the fault point.

Specifically, the positioning coordinates with the target elevation closest to the reference elevation may be screened out from the positioning coordinates, and specifically, the positioning coordinates and the reference elevation may satisfy a preset elevation difference rule or a preset elevation ratio rule, and serve as actual fault point coordinates of the device to be tested corresponding to the fault point; the reference elevation is determined based on the camera parameter information and corresponds to the target elevation.

In this embodiment, a positioning coordinate in which the height difference between the target elevation and the reference elevation corresponding to the target elevation is the smallest or the elevation ratio is closest to 1 (that is, a specified value) may be screened out from the positioning coordinates.

The method comprises the steps of determining a target elevation, wherein the elevation difference between the target elevation and a reference elevation corresponding to the target elevation is the minimum or the elevation ratio is the closest to 1, and then determining that the determined target elevation is closer to the reference elevation, so that the accuracy of determining the elevation of an actual fault point coordinate is improved.

It should be noted that the positioning coordinates with the target elevation closest to the reference elevation may be screened out through the elevation difference or the elevation ratio, and in addition, the positioning coordinates with the target elevation closest to the reference elevation may be determined through the deviation, the similarity, and the like.

On the basis of the above, referring to fig. 2, acquiring actual elevation information of the device under test within the preset range may include:

and S21, extracting the camera parameter information sample in the picture sample.

Specifically, the equipment to be tested is used as a photovoltaic module, and in a photovoltaic patrol inspection scene, an unmanned aerial vehicle can be used for carrying an infrared camera to carry out image acquisition on the photovoltaic module, so that an infrared photo of the unmanned aerial vehicle is obtained as an example. On the picture that infrared camera gathered, can be recorded with camera parameter information sample, it is specific, include: camera GPS coordinates, camera pose information, and camera internal parameters.

And S22, correcting the camera parameter information sample in the picture sample to obtain reference camera parameter information corresponding to the picture sample.

The camera parameter information samples carried in the above-mentioned picture samples can be affected by the flight stability of the unmanned aerial vehicle and the like, and the accuracy is low, so the camera parameter information samples need to be corrected, specifically, the SFM three-dimensional reconstruction technology is adopted to recover the accurate camera GPS coordinates, camera attitude information and camera internal parameters of each picture, and in this embodiment, the corrected camera parameter information samples are referred to as reference camera parameter information.

And S23, carrying out global dense matching on the reference camera parameter information corresponding to the picture sample to obtain dense three-dimensional point cloud.

Specifically, global dense matching is performed by using the accurate camera GPS coordinates, the camera attitude information, and the camera internal parameters, so as to obtain dense three-dimensional point cloud, which is referred to as dense three-dimensional point cloud in this embodiment.

And S24, performing inverse distance weight interpolation calculation on the dense three-dimensional point cloud to obtain actual elevation information within a preset range of the equipment to be measured.

Specifically, a DSM (digital surface model) is generated by adopting an inverse distance weight interpolation method for dense three-dimensional point cloud according to photovoltaic component information. Specifically, when the inverse distance weight interpolation method is adopted, a spatial range, a weighting method, and the like involved in the inverse distance weight interpolation need to be considered.

In this embodiment, the obtained DSM model is actual elevation information.

In the embodiment, when the DSM model is generated based on the three-dimensional point cloud, overall dense matching is performed, so that the dense degree of the three-dimensional point cloud is higher, and the accuracy of the generated DSM is higher.

On the basis of the above embodiment of determining the DSM model, determining the camera parameter information corresponding to the picture may include:

and S31, carrying out picture matching on the picture and the plurality of picture samples, determining the picture sample corresponding to the picture, and taking the picture sample as a target picture sample.

Specifically, the plurality of picture samples are all pictures taken by the photovoltaic module, and the reference camera parameter information is determined, so that the picture samples matched with the pictures taken at this time and including the fault point can be screened out from the plurality of picture samples, and the reference camera parameter information of the picture samples is used as the camera parameter information of the picture at this time.

When the picture is matched with the plurality of picture samples, a picture name matching method can be adopted, or the similarity of the picture is calculated, and the picture sample with the maximum similarity is taken as the picture sample matched with the picture.

It should be noted that, in order to improve the accuracy of picture matching, when the picture and the picture sample are collected, shooting may be performed according to the same shooting manner, such as shooting at the same height.

And S32, acquiring reference camera parameter information corresponding to the target picture sample, and taking the reference camera parameter information as the camera parameter information corresponding to the picture.

In this embodiment, the reference camera parameter information of the plurality of picture samples is predetermined, and the reference camera parameter information is obtained by correcting the camera parameter information samples, so that the accuracy is high. And then, the reference camera parameter information of the picture sample can be used as the camera parameter information of the current picture directly by determining the picture sample matched with the picture, and compared with a mode of directly extracting the camera parameter information of the picture from the picture and then correcting, the efficiency of determining the camera parameter information can be improved.

In another implementation manner of the present invention, a specific implementation process of determining the positioning coordinates of the device to be tested corresponding to the failure point based on the actual elevation information and the camera parameter information is provided, and with reference to fig. 4, the method may include:

and S41, acquiring a collinear equation.

The collinear equation comprises the incidence relation between the camera parameter information and the positioning coordinate of the equipment to be tested corresponding to the fault point.

In practical applications, the collinearity equation also needs to be obtained by calculating the values of the designated coefficients in the basic collinearity equation.

Thus, obtaining the collinearity equation may include:

1) a basic collinearity equation is obtained.

The base collinearity equation includes: and the image coordinates of the fault points in the picture including the fault points, the camera parameter information, the positioning coordinates of the equipment to be tested corresponding to the fault points and the incidence relation among the specified coefficients.

Specifically, the basic collinearity equation is:

where (u, v) is the image coordinate of the failure point in the picture including the failure point, also referred to as pixel coordinate.

The camera GPS coordinates are represented by (Xa, Ya, Za), and the actual three-dimensional coordinates of the failure point are represented by (X, Y, Z). Wherein, X, Y, and Z are data to be solved in this embodiment.

The camera internal reference is represented by (f, cx, cy), f represents the focal length of the camera, and cx and cy represent the pixel coordinates of the camera photographing center.

Three angles for camera pose informationExpressed by the rotation about Y as the principal axisAngle, then angle ω about the X axis, and finally angle k about the Z axis.

a11, a12, a13, a21, a22, a23, a31, a32 and a33 are designated coefficients in the embodiment and can be calculated by using the camera attitude information.

2) And calculating the numerical value of the specified coefficient according to the camera attitude information in the camera parameter information.

The calculation modes of a11, a12, a13, a21, a22, a23, a31, a32 and a33 are as follows:

a11, a12, a13, a21, a22, a23, a31, a32, a33 and camera pose information satisfy the following relationships:

by the present relational expression, the numerical values of a11, a12, a13, a21, a22, a23, a31, a32, a33 can be calculated.

3) And substituting the numerical value of the specified coefficient into the basic collinearity equation to obtain the collinearity equation.

Specifically, the collinear equation can be obtained by substituting the above a11, a12, a13, a21, a22, a23, a31, a32 and a33 into the basic collinear equation, and in the equation, u and v are known, so that the unknowns are only XYZ.

And S42, determining iteration parameters.

In this embodiment, it can be seen from the collinearity equation that the unknowns to be solved are (X, Y, Z), i.e., three unknowns, but the collinearity equation only satisfies 2 equations, and the three unknowns cannot be directly solved. Therefore, it is necessary to provide Z values using DSM data, i.e., actual elevation information, to perform an auxiliary iterative solution.

In this embodiment, the iteration parameters include a maximum elevation, a minimum elevation, and an elevation step length.

Specifically, the iterative parameter determination process is as follows:

1) and determining a position point corresponding to the camera parameter information in the actual elevation information.

Specifically, after the camera parameter information corresponding to the picture is determined, a corresponding position, referred to as a position point in this embodiment, may be determined in the actual elevation information based on the information.

2) And screening out the maximum elevation and the minimum elevation in the specified range by taking the position point as a datum point in the actual elevation information.

Specifically, a region may be screened out by using the position point as a center and using 10 meters as a radius, which is referred to as a region Z. Then, the maximum elevation Zmax and the minimum elevation Zmin the zone Z are acquired.

3) And acquiring a preset elevation step length.

In this embodiment, the elevation step length may be manually set, for example, 0.1 meter.

And S43, performing iterative computation based on the iterative parameters and the collinear equation to obtain the positioning coordinates of the equipment to be tested corresponding to the fault point.

In practical applications, referring to fig. 5, step S43 may include:

and S51, setting the reference elevation as the minimum elevation.

In this embodiment, since the area Z is already defined, an appropriate elevation needs to be selected from the area Z as an actual elevation of the positioning coordinates of the device to be measured. Therefore, in this embodiment, the actual elevation range of the positioning coordinates of the device to be measured is between the minimum elevation and the maximum elevation, and the most appropriate elevation needs to be determined in an iterative manner.

Firstly, the elevation of the positioning coordinate is set as the minimum elevation, and then the value of the elevation is continuously adjusted until the maximum elevation is reached. Iterative calculation is carried out in the whole process, a proper elevation value is selected from the maximum elevation and the minimum elevation and is used as the actual elevation of the positioning coordinate of the equipment to be measured.

In this embodiment, the reference elevation may be set to Zi, that is, Zi is Zmin in this embodiment.

And S52, calculating to obtain the abscissa and ordinate points of the positioning coordinates corresponding to the reference elevation according to the collinear equation, and determining the target elevation corresponding to the abscissa and ordinate points in the actual elevation information.

Specifically, assuming that the elevation of the current iteration is a Zi value, at this time, only two XY unknowns exist in the collinearity equation, and the XY values can be calculated and obtained as Xi and Yi, respectively.

According to the current DSM data, namely the actual elevation information, calculating the grid point position of the DSM data by utilizing Xi and Yi, determining whether the horizontal and vertical coordinate points are positioned on the grid points in the actual elevation information, if so, directly reading the elevation values of the grid points, and taking the elevation values as the target elevation Zt.

If not, determining the target elevation corresponding to the abscissa and the ordinate in the actual elevation information by using a bilinear interpolation mode, namely determining the actual elevation value corresponding to Xi and Yi, namely the target elevation Zt, by using the bilinear interpolation mode.

S53, judging whether the elevation difference between the target elevation and the reference elevation is smaller than a preset elevation difference; if yes, go to step S54; if not, step S55 is executed.

In this embodiment, the height difference Zdiff ═ abs (Zi-Zt) is calculated. And judging whether Zdiff is smaller than a preset elevation difference DIFFZ, wherein in the embodiment, the DIFFZ may be a larger value, such as 999, initially.

And when the height difference between the target elevation and the reference elevation is not less than the preset height difference, the current height difference is too large, namely the difference between the calculated target elevation and the selected reference elevation is too large and does not meet the requirement, Zi is updated to Zi + step, and the next iteration is carried out.

And S54, updating the preset elevation difference into the elevation difference, and taking the target elevation and the position of the equipment to be tested corresponding to the horizontal and vertical coordinate points as positioning coordinates.

If Zdiff is smaller than the preset elevation difference diff, the diff is Zdiff, current Xi and Yi are recorded, the Zt value is X and Xi, Y and Z are Zt, and the position point of the device to be measured corresponding to (Xi, Yi and Zt) is used as the positioning coordinate.

S55, judging whether the reference elevation is larger than the maximum elevation or not; if so, ending the process. If not, go to step S56.

In this embodiment, when the reference elevation is greater than the maximum elevation Zmax, the loop is skipped and the iteration is stopped.

And S56, taking the sum of the reference elevation and the elevation step length as a new reference elevation.

Specifically, Zi + step is updated, and the process returns to step S52. If Zi > Zmax, then the loop is skipped.

In this embodiment, Zi + step is continuously updated, and then it is determined whether there is a corresponding positioning coordinate for Zi at this time, and a plurality of positioning coordinates are obtained when Zi > Zmax is continuously iterated.

In this embodiment, a positioning coordinate with the minimum height difference or the height ratio closest to 1 of the target elevation and the reference elevation corresponding to the target elevation is screened out from the positioning coordinates, and then the determined coordinate of the positioning coordinate, that is, the XYZ value, is output, and specifically, the coordinate may be output to a display interface, or may be output to a preset terminal, such as a mobile phone of an inspector.

The unmanned aerial vehicle photovoltaic inspection data collected at present are subjected to precision verification, the positioning precision error is smaller than 50cm, and the level of accurately positioning the module can be met. (the photovoltaic module is 1.5m long and 1m wide, and the error of the existing fault location for unmanned aerial vehicle photovoltaic inspection is less than 1m at most).

In this embodiment, accurate camera GPS coordinates, camera attitude information, and camera internal parameters are reconstructed through the SFM process, and dense point cloud is generated through dense matching, thereby obtaining the DSM. On the basis of an SFM result, accurate camera GPS coordinates, camera attitude information, camera internal parameters and high-resolution DSM data are utilized, and a collinear equation iterative solution mode is adopted to obtain accurate three-dimensional coordinates of a fault point of the photovoltaic module, so that the accuracy of fault point positioning is improved.

Optionally, on the basis of the above embodiment of the fault location method, another embodiment of the present invention provides a fault location apparatus, including:

the elevation determination module 11 is configured to acquire a plurality of acquired picture samples within a preset range of the device to be tested, and determine actual elevation information within the preset range of the device to be tested based on the plurality of picture samples;

the information determining module 12 is configured to acquire a picture including a fault point corresponding to the device to be tested, and determine camera parameter information corresponding to the picture;

a fault point determination module 13, configured to determine, based on the actual elevation information and the camera parameter information, a positioning coordinate of the device to be tested corresponding to the fault point;

and the fault point screening module 14 is configured to screen out a positioning coordinate meeting a preset coordinate rule from the positioning coordinates, and use the positioning coordinate as an actual fault point coordinate of the device to be tested corresponding to the fault point.

Further, the elevation determination module 11 includes:

the sample processing submodule is used for extracting a camera parameter information sample in the picture sample;

the correction submodule is used for correcting the camera parameter information sample in the picture sample to obtain reference camera parameter information corresponding to the picture sample;

the dense matching sub-module is used for carrying out global dense matching on the reference camera parameter information corresponding to the picture sample to obtain dense three-dimensional point cloud;

and the information calculation submodule is used for performing inverse distance weight interpolation calculation on the dense three-dimensional point cloud to obtain actual elevation information within a preset range of the equipment to be measured.

Further, the information determining module 12 is specifically configured to:

and performing picture matching on the picture and the plurality of picture samples, determining the picture sample corresponding to the picture, taking the picture sample as a target picture sample, acquiring reference camera parameter information corresponding to the target picture sample, and taking the reference camera parameter information as camera parameter information corresponding to the picture.

Further, the failure point determining module 13 includes:

the equation acquisition sub-module is used for acquiring a collinear equation, and the collinear equation comprises the incidence relation between the camera parameter information and the positioning coordinate of the equipment to be tested corresponding to the fault point;

the parameter determination submodule is used for determining iteration parameters; the iteration parameters comprise a maximum elevation, a minimum elevation and an elevation step length;

and the fault point determination submodule is used for carrying out iterative calculation based on the iterative parameters and the collinear equation to obtain the positioning coordinates of the equipment to be tested corresponding to the fault point.

Further, the equation acquisition submodule includes:

the equation acquisition unit is used for acquiring a basic collinear equation; the base collinearity equation includes: the image coordinates of the fault points in the picture including the fault points, the camera parameter information, the positioning coordinates of the equipment to be tested corresponding to the fault points and the incidence relation among the designated coefficients;

a numerical value calculation unit, configured to calculate a numerical value of the specified coefficient according to camera pose information in the camera parameter information;

and the equation determining unit is used for substituting the numerical value of the specified coefficient into the basic collinearity equation to obtain the collinearity equation.

Further, the parameter determination submodule includes:

a position point determining unit, configured to determine a position point corresponding to the camera parameter information in the actual elevation information;

the elevation screening unit is used for screening out the maximum elevation and the minimum elevation in the specified range by taking the position point as a datum point from the actual elevation information;

and the step length acquiring unit is used for acquiring a preset elevation step length.

Further, the failure point determination submodule includes:

an elevation setting unit for setting a reference elevation as the minimum elevation;

the elevation determination unit is used for calculating and obtaining an abscissa and ordinate point of the positioning coordinate corresponding to the reference elevation according to the collinear equation and determining a target elevation corresponding to the abscissa and ordinate point in the actual elevation information;

the first judgment unit is used for judging whether the elevation difference between the target elevation and the reference elevation is smaller than a preset elevation difference;

the fault point determining unit is used for updating the preset elevation difference into the elevation difference if the preset elevation difference is smaller than the preset elevation difference, and taking the target elevation and the position of the equipment to be tested corresponding to the horizontal and vertical coordinate points as positioning coordinates;

the second judgment unit is used for judging whether the reference elevation is larger than the maximum elevation or not;

and the elevation setting unit is further used for taking the sum of the reference elevation and the elevation step length as a new reference elevation under the condition that the reference elevation is not larger than the maximum elevation.

Further, when the elevation determination unit is configured to determine the target elevation corresponding to the abscissa and the ordinate in the actual elevation information, the elevation determination unit is specifically configured to:

determining whether the abscissa and ordinate points are located on grid points in the actual elevation information; if not, determining the corresponding target elevation of the abscissa and the ordinate in the actual elevation information by adopting a bilinear interpolation mode.

Further, the elevation setting unit is further configured to:

and taking the sum of the reference elevation and the elevation step length as a new reference elevation under the condition that the elevation difference between the target elevation and the reference elevation is judged to be not less than the preset elevation difference and the reference elevation is not more than the maximum elevation.

Further, the fault point screening module 14 is specifically configured to:

and screening out the positioning coordinates with the minimum height difference or the height ratio of the target elevation and the reference elevation corresponding to the target elevation closest to a specified numerical value from the positioning coordinates.

In this embodiment, the actual elevation information of the device to be tested within the preset range is determined based on the collected multiple image samples, the image including the fault point corresponding to the device to be tested is obtained, the camera parameter information corresponding to the image is determined, the positioning coordinate of the device to be tested corresponding to the fault point is determined based on the actual elevation information and the camera parameter information, and then the positioning coordinate meeting the preset coordinate rule is selected from the positioning coordinates and is used as the actual fault point coordinate of the device to be tested corresponding to the fault point. By the method and the device, the actual coordinate of the fault point of the equipment can be positioned according to the fault point in the picture comprising the fault point. Furthermore, when the actual fault point coordinate is determined, the positioning coordinate meeting the preset coordinate rule is screened out from the positioning coordinates and is used as the actual fault point coordinate of the equipment to be tested corresponding to the fault point, and the determination accuracy of the actual fault point coordinate is improved.

It should be noted that, for the working processes of each module, sub-module, and unit in this embodiment, please refer to the corresponding description in the above embodiments, which is not described herein again.

Optionally, on the basis of the embodiments of the fault location method and apparatus, another embodiment of the present invention provides a storage medium, where the storage medium includes a stored program, and when the program runs, a device in which the storage medium is located is controlled to execute the fault location method.

Optionally, on the basis of the embodiments of the fault location method and apparatus, another embodiment of the present invention provides an electronic device, including: a memory and a processor;

wherein the memory is used for storing programs;

the processor calls a program and is used to perform the fault location method described above.

In this embodiment, the actual elevation information of the device to be tested within the preset range is determined based on the collected multiple image samples, the image including the fault point corresponding to the device to be tested is obtained, the camera parameter information corresponding to the image is determined, the positioning coordinate of the device to be tested corresponding to the fault point is determined based on the actual elevation information and the camera parameter information, and then the positioning coordinate meeting the preset coordinate rule is selected from the positioning coordinates and is used as the actual fault point coordinate of the device to be tested corresponding to the fault point. By the method and the device, the actual coordinate of the fault point of the equipment can be positioned according to the fault point in the picture comprising the fault point. Furthermore, when the actual fault point coordinate is determined, the positioning coordinate meeting the preset coordinate rule is screened out from the positioning coordinates and is used as the actual fault point coordinate of the equipment to be tested corresponding to the fault point, and the determination accuracy of the actual fault point coordinate is improved.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.