Vibration detection method and device, medium, equipment and product

Abstract

The invention relates to a vibration detection method and device, a medium, equipment and a product, and the method comprises the steps: obtaining a to-be-detected candidate image which is an image containing a tower drum object; edge detection is carried out on the candidate image, a target area image of the candidate image is determined, and the target area image is an image comprising a structure edge area of the tower drum object; determining a vibration displacement signal of the target area image according to the phase of the detection point in the target area image; and determining a vibration detection result of the candidate image according to the vibration displacement signal.

Description

Technical Field

[0001] The present disclosure relates to the field of power generation technology, and in particular, to a vibration detection method, device, medium, equipment and product. Background Art

[0002] The tower is the pole of wind power generation, which mainly plays a supporting role in wind turbines. Due to the influence of human or environmental factors such as variable load, salt spray erosion, installation defects, etc., the tower is prone to cracks, deformation or flange loosening, causing the tower to deviate from the healthy operating state, which seriously threatens the safe operation of wind turbines. Therefore, in order to ensure the long-term safe and normal operation of wind turbines, it is necessary to measure the vibration of the tower.

[0003] In the prior art, acceleration or velocity sensors are usually installed in the tower to measure the vibration of the tower. However, acceleration or velocity sensors have certain inconveniences in installation and operation, and can only measure a few points in the measurement of large structures, and may change the inherent characteristics of the structure in the measurement of small structures, resulting in inaccurate vibration data. On the other hand, the acceleration or velocity sensors installed in the tower can only provide sparse, discrete point direction measurements, and the resulting spatial perception resolution is low. Summary of the invention

[0004] In order to solve the above problems, the present disclosure provides a vibration detection method, device, medium, equipment and product.

[0005] In a first aspect, the present disclosure provides a vibration detection method, the method comprising: Acquire a candidate image to be detected, where the candidate image is an image containing a tower object; Performing edge detection on the candidate image to determine a target area image of the candidate image, wherein the target area image is an image of a structural edge area including the tower object; determining a vibration displacement signal of the target area image according to a phase of a detection point in the target area image; A vibration detection result of the candidate image is determined according to the vibration displacement signal.

[0006] Optionally, performing edge detection on the candidate image to determine the target area image of the candidate image includes: The candidate image is used as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image, wherein the edge detection result includes the target area image of the candidate image.

[0007] Optionally, taking the candidate image as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image includes: Acquire feature maps of multiple preset scales of the candidate image; The feature maps of each preset scale are fused to obtain a fused feature map, wherein the pixel information of each pixel point on the fused feature map is fused pixel information of multiple preset scales; Performing a convolution operation on the fused feature map through a preset classification network to obtain probability information corresponding to each pixel point on the fused feature map; The edge detection result of the candidate image is obtained according to the probability information corresponding to each pixel and the preset edge threshold.

[0008] Optionally, determining the vibration displacement signal of the target area image according to the phase of the detection point in the target area image includes: Determine the detection point from a plurality of pixel points corresponding to the target area image according to probability information corresponding to each pixel point; The phase of the detection point is acquired, and the vibration displacement signal of the target area image is determined according to the phase.

[0009] Optionally, determining the detection point from a plurality of pixel points corresponding to the target area image according to probability information corresponding to each pixel point includes: For the probability information corresponding to each pixel point, the pixel point corresponding to the target probability information is used as the target pixel point; The point corresponding to the target pixel point on the edge area of ​​the structure is used as the detection point.

[0010] Optionally, determining the vibration detection result of the candidate image according to the vibration displacement signal includes: When it is determined that the vibration displacement signal is greater than or equal to a preset vibration displacement threshold, it is determined that the tower object in the candidate image is vibrating.

[0011] In a second aspect, the present disclosure provides a vibration detection device, the device comprising: An acquisition module, used for acquiring a candidate image to be detected, wherein the candidate image is an image containing a tower object; A detection module, configured to perform edge detection on the candidate image to determine a target area image of the candidate image, wherein the target area image is an image of a structural edge area including a wind turbine tower; A first determination module, configured to determine a vibration displacement signal of the target area image according to a phase of a detection point in the target area image; The second determination module is used to determine the vibration detection result of the candidate image according to the vibration displacement signal.

[0012] Optionally, the detection module is used to use the candidate image as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image, wherein the edge detection result includes the target area image of the candidate image.

[0013] Optionally, the detection module includes: A first acquisition submodule, used to acquire feature maps of multiple preset scales of the candidate image; A first determination submodule is used to fuse the feature maps of each preset scale to obtain a fused feature map, wherein the pixel information of each pixel point on the fused feature map is fused pixel information of multiple preset scales; A second determination submodule is used to perform a convolution operation on the fused feature map through a preset classification network to obtain probability information corresponding to each pixel point on the fused feature map; The third determination submodule is used to obtain the edge detection result of the candidate image according to the probability information corresponding to each pixel point and a preset edge threshold.

[0014] Optionally, the first determining module includes: A fourth determination submodule, configured to determine the detection point from a plurality of pixel points corresponding to the target area image according to probability information corresponding to each pixel point; The fifth determination submodule is used to obtain the phase of the detection point and determine the vibration displacement signal of the target area image according to the phase.

[0015] Optionally, the fourth determination submodule is used to take the pixel point corresponding to the target probability information as the target pixel point based on the probability information corresponding to each pixel point; and take the point corresponding to the target pixel point on the edge area of ​​the structure as the detection point.

[0016] Optionally, the second determination module is used to determine that the tower object in the candidate image is vibrating when it is determined that the vibration displacement signal is greater than or equal to a preset vibration displacement threshold.

[0017] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.

[0018] In a fourth aspect, the present disclosure provides an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of the method described in the first aspect of the present disclosure.

[0019] In a fifth aspect, the present disclosure provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method described in the first aspect of the present disclosure.

[0020] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects: By acquiring a candidate image to be detected, the candidate image is an image containing a tower object; performing edge detection on the candidate image to determine a target area image of the candidate image, the target area image is an image of a structural edge area including the tower object; determining a vibration displacement signal of the target area image according to the phase of the detection point in the target area image; and determining a vibration detection result of the candidate image according to the vibration displacement signal. In this way, vibration detection of the tower object can be performed according to the vibration displacement signal in the acquired image including the tower object, which can avoid the problem of changing the inherent characteristics of the structure caused by installing a sensor alone, and the acquired image can increase the resolution of spatial perception and improve the accuracy of vibration detection.

[0021] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are used to provide further understanding of the present disclosure and constitute a part of the specification. They are used to explain the present disclosure together with the following detailed description, but do not constitute a limitation of the present disclosure.

[0023] Figure 1 The figure is a flow chart of a vibration detection method according to an exemplary embodiment.

[0024] Figure 2 is a structural diagram of an edge detection model according to an exemplary embodiment.

[0025] Figure 3 is a block diagram of a vibration detection device according to an exemplary embodiment.

[0026] Figure 4 is based on Figure 3 The illustrated embodiment shows a block diagram of a detection module.

[0027] Figure 5 is based on Figure 3 The illustrated embodiment shows a block diagram of a first determination module.

[0028] Figure 6It is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0029] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.

[0030] It should be noted that all actions of acquiring signals, information or data in the present disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the device is located and with the authorization given by the owner of the corresponding device.

[0031] The embodiments described in some embodiments of the present disclosure below do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0032] Before introducing the specific implementation methods of the present disclosure in detail, the application scenarios of the present disclosure are first described. The present disclosure can be applied to the vibration measurement scenario of the tower of wind power generation. The tower is the tower pole of wind power generation, which mainly plays a supporting role in the wind turbine generator set. Due to the long-term influence of human or environmental factors such as variable load, salt spray erosion, installation defects, etc., the tower is prone to cracks, deformation or flange loosening, causing the tower to deviate from the healthy operating state, which seriously threatens the operation safety of the wind turbine generator set. Therefore, in order to ensure the long-term safe and normal operation of the wind turbine generator set, it is necessary to measure the vibration of the tower so that maintenance can be carried out in a planned manner according to the actual situation.

[0033] In the prior art, acceleration or velocity sensors are usually installed in the tower to measure the vibration of the tower. However, acceleration or velocity sensors have certain inconveniences in installation and operation, and can only measure a few points in the measurement of large structures, and may change the inherent characteristics of the structure in the measurement of small structures, resulting in inaccurate vibration data. On the other hand, the acceleration or velocity sensors installed in the tower can only provide sparse, discrete point direction measurements, and the resulting spatial perception resolution is low.

[0034] In order to overcome the technical problems existing in the above related technologies, the present disclosure provides a vibration detection method, device, medium, equipment and product, which obtains a candidate image to be detected, which is an image containing a tower object; performs edge detection on the candidate image to determine a target area image of the candidate image, which is an image of a structural edge area including the tower object; determines a vibration displacement signal of the target area image according to the phase of the detection point in the target area image; and determines a vibration detection result of the candidate image according to the vibration displacement signal. In this way, vibration detection of the tower object can be performed according to the vibration displacement signal in the acquired image including the tower object, which can avoid the problem of changing the inherent characteristics of the structure caused by installing a sensor alone, and the resolution of spatial perception can be increased through the acquired image, thereby improving the accuracy of vibration detection.

[0035] The present disclosure is described below in conjunction with specific embodiments.

[0036] Figure 1 is a flow chart of a vibration detection method according to an exemplary embodiment. Figure 1 As shown, the method can be applied to a control device, which can be a common computer, a server, etc., or a vehicle-mounted control device such as a vehicle-mounted computer or a vehicle-mounted industrial personal computer (IPC), or a vehicle controller. The method can include the following steps.

[0037] In step S101, a candidate image to be detected is obtained.

[0038] The candidate image is an image containing a tower object.

[0039] In this step, a high-speed camera may be used to shoot the tower object to obtain a video file, and then multiple image frames may be obtained from the video file, and the multiple image frames may be used as candidate images to be processed. In another possible implementation, the high-speed camera may be used to shoot photos of the tower object according to a preset shooting cycle to obtain multiple photos, and the multiple photos may be used as candidate images to be processed.

[0040] In step S102, edge detection is performed on the candidate image to determine a target area image of the candidate image.

[0041] The target area image is an image of a structural edge area including the tower object.

[0042] The boundary or contour in the candidate image can be detected by edge detection. Among them, the edge in the candidate image generally refers to the area with large grayscale or color changes in the candidate image, indicating the boundary between objects or the texture change inside the object. The goal of edge detection is to find the location where the pixel value changes significantly in the image and mark it as the boundary. In the present disclosure, edge detection can be performed by an edge detection model, which detects the edge of the structure by establishing a neural network using richer convolution features, can output high-quality structural edges, and automatically determine the location of the measuring point.

[0043] Optionally, the candidate image may be used as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image, where the edge detection result includes the target area image of the candidate image.

[0044] In a possible implementation, multiple feature maps of preset scales of the candidate image can be first obtained; then the feature maps of each preset scale are fused to obtain a fused feature map, and the pixel information of each pixel point on the fused feature map is the fused pixel information of multiple preset scales; then a convolution operation is performed on the fused feature map through a preset classification network to obtain probability information corresponding to each pixel point on the fused feature map; and based on the probability information corresponding to each pixel point and a preset edge threshold, an edge detection result of the candidate image is obtained.

[0045] For example, Figure 2As shown, the edge detection model can include module 1_C64, module 1_C128, module 2_C256, and two modules 2_C512. The five modules are divided into a five-layer structure, and each module is a one-layer structure. Among them, type 1 includes two layers of modules, and type 2 includes three layers of modules. Among them, module 1_C64 represents a convolution block of type 1 with an output channel of 64, and module 2_C256 represents a convolution block of type 2 with an output channel of 256. Module 1 contains two convolution layers with a kernel size of 3×3, and each convolution layer is followed by a convolution layer with a kernel size of 1×1 and an output channel of 21. The output fusion of the 1×1-21 convolution layer is then used as the input to the convolution layer with a kernel size of 1×1 and an output channel of 1 (1×1-1). Module 2 contains three convolutional layers with a kernel size of 3×3. Each convolutional layer is followed by a convolutional layer with a kernel size of 1×1 and an output channel of 21. The output of the 1×1-21 convolutional layer is fused and then used as the input to the convolutional layer with a kernel size of 1×1 and an output channel of 1 (1×1-1). The deconvolution layer performs upsampling to map the image size back to the original size. Finally, the output of each module is superimposed in the fusion part, and a 1×1-1 convolution is performed again to merge multiple channels to achieve the ability to obtain multiple mixed information. In addition, a cross-entropy loss / sigmoid layer can be added at the end of each module to calculate the loss and update the parameters. In this way, by constructing a fully convolutional neural network structure, the lightweight network structure can meet the requirements of the edge detection task of the structure and reduce the computing time.

[0046] In step S103, the vibration displacement signal of the target area image is determined according to the phase of the detection point in the target area image.

[0047] Optionally, the detection point may be determined from a plurality of pixel points corresponding to the target area image according to probability information corresponding to each pixel point; then the phase of the detection point is acquired, and the vibration displacement signal of the target area image is determined according to the phase.

[0048] In a possible implementation, with respect to the probability information corresponding to each pixel point, the pixel point corresponding to the target probability information may be used as the target pixel point; and then the point corresponding to the target pixel point on the edge area of ​​the structure may be used as the detection point.

[0049] In some embodiments, the phase of the detection point may be acquired in the following manner.

[0050] For example, a two-dimensional Gabor filter may be used to calculate the phase of the detection point, and the phase change of the detection point may be calculated based on the calculated detection point position to obtain the image phase, that is, to obtain the vibration displacement signal.

[0051] In step S104, a vibration detection result of the candidate image is determined according to the vibration displacement signal.

[0052] Optionally, when it is determined that the vibration displacement signal is greater than or equal to a preset vibration displacement threshold, it is determined that the tower object in the candidate image is vibrating.

[0053] By adopting the above technical solution, a candidate image to be detected can be obtained, which is an image containing a tower object; edge detection can be performed on the candidate image to determine a target area image of the candidate image, which is an image of a structural edge area including the tower object; a vibration displacement signal of the target area image can be determined according to the phase of the detection point in the target area image; and a vibration detection result of the candidate image can be determined according to the vibration displacement signal. In this way, vibration detection of the tower object can be performed according to the vibration displacement signal in the image including the tower object obtained, which can avoid the problem of changing the inherent characteristics of the structure caused by installing a sensor alone, and the resolution of spatial perception can be increased through the acquired image, thereby improving the accuracy of vibration detection.

[0054] Figure 3 is a block diagram of a vibration detection device according to an exemplary embodiment. Figure 3 The vibration detection device 200 includes an acquisition module 201 , a detection module 202 , a first determination module 203 and a second determination module 204 .

[0055] An acquisition module 201 is used to acquire a candidate image to be detected, where the candidate image is an image containing a tower object; A detection module 202 is used to perform edge detection on the candidate image to determine a target area image of the candidate image, where the target area image is an image of a structural edge area including a wind turbine tower; A first determination module 203, configured to determine a vibration displacement signal of the target area image according to a phase of a detection point in the target area image; The second determination module 204 is configured to determine a vibration detection result of the candidate image according to the vibration displacement signal.

[0056] Optionally, the detection module 202 is used to use the candidate image as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image, where the edge detection result includes the target area image of the candidate image.

[0057] Figure 4 is based on Figure 3 The embodiment shown is a block diagram of a detection module, such as Figure 4 As shown, the detection module 202 includes: A first acquisition submodule 2021 is used to acquire feature maps of multiple preset scales of the candidate image; The first determination submodule 2022 is used to fuse the feature maps of each preset scale to obtain a fused feature map, where the pixel information of each pixel point on the fused feature map is fused pixel information of multiple preset scales; The second determination submodule 2023 is used to perform a convolution operation on the fused feature map through a preset classification network to obtain probability information corresponding to each pixel point on the fused feature map; The third determination submodule 2024 is used to obtain the edge detection result of the candidate image according to the probability information corresponding to each pixel point and the preset edge threshold.

[0058] Figure 5 is based on Figure 3 The embodiment shown is a block diagram of a first determination module, such as Figure 5 As shown, the first determination module 203 includes: The fourth determination submodule 2031 is used to determine the detection point from a plurality of pixel points corresponding to the target area image according to the probability information corresponding to each pixel point; The fifth determination submodule 2032 is used to obtain the phase of the detection point and determine the vibration displacement signal of the target area image according to the phase.

[0059] Optionally, the fourth determination submodule 2031 is used to take the pixel corresponding to the target probability information as the target pixel for the probability information corresponding to each pixel; and take the point corresponding to the target pixel on the edge area of ​​the structure as the detection point.

[0060] Optionally, the second determination module 204 is configured to determine that the tower object in the candidate image is vibrating when it is determined that the vibration displacement signal is greater than or equal to a preset vibration displacement threshold.

[0061] The above device is used to obtain a candidate image to be detected, which is an image containing a tower object; edge detection is performed on the candidate image to determine a target area image of the candidate image, which is an image of a structural edge area including the tower object; the vibration displacement signal of the target area image is determined according to the phase of the detection point in the target area image; and the vibration detection result of the candidate image is determined according to the vibration displacement signal. In this way, vibration detection of the tower object can be performed according to the vibration displacement signal in the image including the tower object obtained, which can avoid the problem of changing the inherent characteristics of the structure caused by installing a sensor alone, and the resolution of spatial perception can be increased through the acquired image, thereby improving the accuracy of vibration detection.

[0062] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0063] Figure 6 FIG. 1 is a block diagram of an electronic device 300 according to an exemplary embodiment. Figure 6 As shown, the electronic device 300 may include: a processor 301 , a memory 302 . The electronic device 300 may also include one or more of a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .

[0064] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned vibration detection method. The memory 302 is used to store various types of data to support the operation of the electronic device 300. For example, these data may include instructions for any application or method used to operate on the electronic device 300, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, magnetic disk or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 302 or sent through the communication component 305. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 305 may include: Wi-Fi module, Bluetooth module, NFC module, etc.

[0065] In an exemplary embodiment, the electronic device 300 may be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to perform the above-mentioned vibration detection method.

[0066] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned vibration detection method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned vibration detection method.

[0067] In another exemplary embodiment, a computer program product is also provided. The computer program product includes a computer program executable by a programmable device, and has a code portion for performing the above-mentioned vibration detection method when the computer program is executed by the programmable device.

[0068] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0069] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present disclosure will not further describe various possible combinations.

[0070] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.

Claims

1. A vibration detection method, characterized in that: The method comprises: Acquire a candidate image to be detected, where the candidate image is an image containing a tower object; Performing edge detection on the candidate image to determine a target area image of the candidate image, wherein the target area image is an image of a structural edge area including the tower object; determining a vibration displacement signal of the target area image according to a phase of a detection point in the target area image; A vibration detection result of the candidate image is determined according to the vibration displacement signal.

2. The method according to claim 1, characterized in that The performing edge detection on the candidate image to determine the target area image of the candidate image comprises: The candidate image is used as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image, wherein the edge detection result includes the target area image of the candidate image.

3. The method according to claim 2, characterized in that The step of using the candidate image as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image includes: Acquire feature maps of multiple preset scales of the candidate image; The feature maps of each preset scale are fused to obtain a fused feature map, wherein the pixel information of each pixel point on the fused feature map is fused pixel information of multiple preset scales; Performing a convolution operation on the fused feature map through a preset classification network to obtain probability information corresponding to each pixel point on the fused feature map; The edge detection result of the candidate image is obtained according to the probability information corresponding to each pixel and the preset edge threshold.

4. The method according to claim 3, characterized in that Determining the vibration displacement signal of the target area image according to the phase of the detection point in the target area image includes: Determine the detection point from a plurality of pixel points corresponding to the target area image according to probability information corresponding to each pixel point; The phase of the detection point is acquired, and the vibration displacement signal of the target area image is determined according to the phase.

5. The method according to claim 4, characterized in that The determining the detection point from a plurality of pixel points corresponding to the target area image according to the probability information corresponding to each pixel point comprises: For the probability information corresponding to each pixel point, the pixel point corresponding to the target probability information is used as the target pixel point; The point corresponding to the target pixel point on the edge area of ​​the structure is used as the detection point.

6. The method according to any one of claims 1 to 5, characterized in that The step of determining the vibration detection result of the candidate image according to the vibration displacement signal comprises: When it is determined that the vibration displacement signal is greater than or equal to a preset vibration displacement threshold, it is determined that the tower object in the candidate image is vibrating.

7. A vibration detection device, characterized in that: The device comprises: An acquisition module, used for acquiring a candidate image to be detected, wherein the candidate image is an image containing a tower object; A detection module, configured to perform edge detection on the candidate image to determine a target area image of the candidate image, wherein the target area image is an image of a structural edge area including a wind turbine tower; A first determination module, configured to determine a vibration displacement signal of the target area image according to a phase of a detection point in the target area image; The second determination module is used to determine the vibration detection result of the candidate image according to the vibration displacement signal.

8. The device according to claim 7, characterized in that The detection module is used to use the candidate image as an input of a pre-generated edge detection model to obtain an edge detection result of the candidate image, wherein the edge detection result includes the target area image of the candidate image.

9. The device according to claim 8, characterized in that The detection module comprises: A first acquisition submodule, used to acquire feature maps of multiple preset scales of the candidate image; A first determination submodule is used to fuse the feature maps of each preset scale to obtain a fused feature map, wherein the pixel information of each pixel point on the fused feature map is fused pixel information of multiple preset scales; A second determination submodule is used to perform a convolution operation on the fused feature map through a preset classification network to obtain probability information corresponding to each pixel point on the fused feature map; The third determination submodule is used to obtain the edge detection result of the candidate image according to the probability information corresponding to each pixel point and a preset edge threshold.

10. The device according to claim 9, characterized in that The first determining module includes: A fourth determination submodule, configured to determine the detection point from a plurality of pixel points corresponding to the target area image according to probability information corresponding to each pixel point; The fifth determination submodule is used to obtain the phase of the detection point and determine the vibration displacement signal of the target area image according to the phase.

11. The device according to claim 10, characterized in that The fourth determination submodule is used to use the pixel corresponding to the target probability information as the target pixel for the probability information corresponding to each pixel; and use the point corresponding to the target pixel on the edge area of ​​the structure as the detection point.

12. The device according to any one of claims 7 to 10, characterized in that The second determination module is configured to determine that the tower object in the candidate image is vibrating when it is determined that the vibration displacement signal is greater than or equal to a preset vibration displacement threshold.

13. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

14. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images