Bird repelling system and method applied to offshore photovoltaic, storage medium and electronic device

Abstract

This disclosure provides a bird deterrence system, a bird deterrence method, a computer-readable storage medium, and an electronic device for use in offshore photovoltaic systems, relating to the field of bird deterrence technology. The bird deterrence system includes multiple laser bird deterrence units and multiple acoustic bird deterrence units, each acoustic bird deterrence unit distributed at different locations within the offshore photovoltaic site. Each acoustic bird deterrence unit includes: a camera for acquiring a first scene image; a sound-emitting array including multiple sound generators; and a first data processor for acquiring the first scene image captured by the camera, identifying the first scene image, performing depth estimation using the first scene image to determine the distance of the bird object relative to the acoustic bird deterrence unit when the distance is less than or equal to a first distance threshold, and controlling the sound-emitting array to emit sound waves. This disclosure enables automatic bird deterrence control in offshore photovoltaic scenarios.

Description

Technical Field

[0001] This disclosure relates to the field of bird deterrence technology, and more specifically, to a bird deterrence system, a bird deterrence method, a computer-readable storage medium, and an electronic device for use in marine photovoltaic systems. Background Technology

[0002] The photovoltaic modules of offshore solar power are installed in an outdoor environment at sea. Birds can easily perch on the photovoltaic modules and build nests on them. Their droppings can also pollute the photovoltaic modules, affecting their normal operation and potentially causing damage to them in severe cases.

[0003] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] The purpose of this disclosure is to provide a bird deterrence system, a bird deterrence method, a computer-readable storage medium, and an electronic device for use in marine photovoltaic systems, thereby at least to some extent overcoming the adverse effects of bird activity on marine photovoltaic systems.

[0005] According to a first aspect of this disclosure, a bird deterrence system for marine photovoltaic applications is provided, comprising multiple laser bird deterrence units and multiple acoustic bird deterrence units. Each laser bird deterrence unit is distributed at different locations around the periphery of the marine photovoltaic site, based on the shape and area of ​​the marine photovoltaic area and the effective working range of the laser in the laser bird deterrence unit. Each acoustic bird deterrence unit is distributed at different locations inside and at the boundary of the marine photovoltaic site, based on the shape and area of ​​the marine photovoltaic area and the effective working range of the sound-emitting array in the acoustic bird deterrence unit. The acoustic bird deterrence unit includes: a camera for acquiring a first scene image; an acoustic array including multiple sound emitters; and a first data processor for acquiring the first scene image acquired by the camera, identifying the first scene image, performing depth estimation using the first scene image when a bird object is identified, determining the distance of the bird object relative to the acoustic bird deterrence unit, and controlling the acoustic array to emit sound waves when the distance is less than or equal to a first distance threshold.

[0006] Optionally, the laser bird deterrent unit includes: a rotating platform for rotating in response to a rotation command; a laser mounted on the rotating platform; a laser driving unit for driving the laser to work; and a second data processor for acquiring a second scene image, recognizing the second scene image, performing depth estimation using the second scene image when a bird object is identified, determining the distance of the bird object relative to the laser bird deterrent unit, and sending a rotation command to the rotating platform to control the laser emitting end of the laser to rotate to match the direction of the bird object, and controlling the laser driving unit to drive the laser to work when the distance is less than or equal to a second distance threshold; wherein the second distance threshold is greater than a first distance threshold.

[0007] Optionally, the second data processor is further configured to send a start command to the target acoustic bird deterrent unit corresponding to the laser bird deterrent unit when the distance between the bird object and the laser bird deterrent unit is determined to be between a first distance threshold and a second distance threshold; the first data processor of the target acoustic bird deterrent unit responds to the start command to control the camera to start, so as to acquire a first scene image.

[0008] Optionally, when the sonic bird deterrent unit emits sonic waves to drive away the target bird, the first data processor of the sonic bird deterrent unit sends an operation stop command to the target laser bird deterrent unit corresponding to the sonic bird deterrent unit; the second data processor of the target laser bird deterrent unit responds to the operation stop command and controls the laser emission operation against the target bird to stop.

[0009] Optionally, the process of the second data processor performing depth estimation using the second scene image includes: the second data processor determining the size of the second scene image; if the size of the second scene image is larger than a first preset size, downsampling the second scene image to obtain a first intermediate image; inputting the second scene image into a trained first neural network to obtain a first depth image; and inputting the first intermediate image into the first neural network to obtain a second depth image; the first neural network is trained using training samples with a size less than or equal to the first preset size; and inputting the first depth image and the second depth image into the second neural network to perform depth image fusion to obtain the depth estimation result of the second scene image.

[0010] Optionally, the size of the training samples of the first neural network is between a first preset size and a second preset size, wherein the first preset size is larger than the second preset size, and the size of the first intermediate image is the midpoint between the first preset size and the second preset size.

[0011] Optionally, if the size of the second scene image is between a first preset size and a second preset size, the second data processor inputs the second scene image into the first neural network and determines the obtained first depth image as the depth estimation result of the second scene image; if the size of the second scene image is smaller than the second preset size, the second data processor upsamples the second scene image to obtain a second intermediate image; wherein the size of the second intermediate image is between the first preset size and the second preset size; the second intermediate image is input into the first neural network to obtain a third depth image; the third depth image is downsampled to obtain the depth estimation result of the second scene image.

[0012] According to a second aspect of this disclosure, a bird deterrence method for marine photovoltaic systems is provided. The bird deterrence system includes multiple laser bird deterrence units and multiple acoustic bird deterrence units. Each laser bird deterrence unit is distributed at different locations around the periphery of the marine photovoltaic site based on the shape and area of ​​the marine photovoltaic area and the effective working range of the laser in the laser bird deterrence unit. Each acoustic bird deterrence unit is distributed at different locations inside and at the boundary of the marine photovoltaic site based on the shape and area of ​​the marine photovoltaic area and the effective working range of the sound-emitting array in the acoustic bird deterrence unit. Each acoustic bird deterrence unit includes a camera and a sound-emitting array. The camera is used to acquire a first scene image, and the sound-emitting array includes multiple sound generators. The bird deterrence method includes: acquiring the first scene image acquired by the camera; identifying the first scene image; if a bird object is identified, performing depth estimation using the first scene image to determine the distance of the bird object relative to the acoustic bird deterrence unit; and controlling the sound-emitting array to emit sound waves if the distance is less than or equal to a first distance threshold.

[0013] According to a third aspect of this disclosure, a bird-repelling device for marine photovoltaic applications is provided. The bird-repelling device is applied to a bird-repelling system for marine photovoltaic applications. The bird-repelling system includes multiple laser bird-repelling units and multiple acoustic bird-repelling units. Each laser bird-repelling unit is distributed at different locations around the periphery of the marine photovoltaic site according to the shape and area of ​​the marine photovoltaic area and the effective working range of the laser in the laser bird-repelling unit. Each acoustic bird-repelling unit is distributed at different locations inside and at the boundary of the marine photovoltaic site according to the shape and area of ​​the marine photovoltaic area and the effective working range of the sound-emitting array in the acoustic bird-repelling unit. Each acoustic bird-repelling unit includes a camera and a sound-emitting array. The camera is used to acquire a first scene image, and the sound-emitting array includes multiple sound generators. The bird-repelling device includes: an image recognition module for acquiring the first scene image acquired by the camera and recognizing the first scene image; a distance determination module for performing depth estimation using the first scene image when a bird object is identified, to determine the distance of the bird object relative to the acoustic bird-repelling unit; and a bird-repelling activation module for controlling the sound-emitting array to emit sound waves when the distance is less than or equal to a first distance threshold.

[0014] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the above-described bird-repelling method applied to marine photovoltaic systems.

[0015] According to a fifth aspect of this disclosure, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; the processor is configured to implement the above-described bird-repelling method applied to marine photovoltaic systems by executing the executable instructions.

[0016] In some embodiments of this disclosure, the technical solutions provided include, on the one hand, a bird deterrence system comprising laser bird deterrence units and acoustic bird deterrence units is deployed for special scenarios such as offshore photovoltaic systems. Combined with image recognition, an automatic bird deterrence strategy is implemented. The entire bird deterrence process is automated, requiring no human control, ensuring timely bird deterrence, protecting the offshore photovoltaic site from bird activity, and ensuring the normal operation of the photovoltaic modules. On the other hand, this disclosure utilizes images for depth estimation and combines the estimated depth to determine the distance to the birds. When the distance is less than a threshold, the sound-emitting array is controlled to emit bird deterrence sound waves. This linked analysis and processing method at least achieves intelligent control of acoustic bird deterrence. Furthermore, this disclosure combines laser and acoustic bird deterrence, fully utilizing the characteristics of each method. Their combined use can significantly improve the bird deterrence effect of offshore photovoltaic systems.

[0017] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0019] Figure 1 A block diagram of a bird deterrent system applied to marine photovoltaic systems according to an exemplary embodiment of the present disclosure is shown schematically.

[0020] Figure 2 A schematic diagram showing the configuration of the laser bird deterrent unit and the acoustic bird deterrent unit according to an embodiment of the present disclosure is provided.

[0021] Figure 3 A block diagram of an acoustic bird-repelling unit according to an exemplary embodiment of the present disclosure is shown schematically.

[0022] Figure 4A block diagram of a laser bird deterrent unit according to an exemplary embodiment of the present disclosure is shown schematically.

[0023] Figure 5 A flowchart illustrating the depth estimation process of an embodiment of this disclosure is shown schematically.

[0024] Figure 6 A flowchart illustrating a bird-repelling method applied to marine photovoltaic systems according to an embodiment of this disclosure is shown.

[0025] Figure 7 A block diagram schematically illustrates a bird deterrent device applied to marine photovoltaic systems according to an embodiment of the present disclosure.

[0026] Figure 8 A block diagram of an electronic device according to an exemplary embodiment of the present disclosure is shown schematically. Detailed Implementation

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0028] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0029] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all steps. For example, some steps may be broken down, while others may be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances. Furthermore, all terms such as "first," "second," and "third" used below are for distinction purposes only and should not be construed as limiting the scope of this disclosure.

[0030] Figure 1 A block diagram schematically illustrates a bird-repelling system applied to marine photovoltaic systems according to an exemplary embodiment of this disclosure. (Reference) Figure 1 The bird deterrence system 1 for marine photovoltaic applications according to this disclosure may include an acoustic bird deterrence unit 11 and a laser bird deterrence unit 12. Given that the area covered by marine photovoltaic systems is typically large, the number of acoustic bird deterrence units 11 and laser bird deterrence units 12 used in this disclosure is usually multiple.

[0031] Specifically, the location and number of each acoustic bird deterrent unit 11 can be determined according to the shape and area of ​​the marine photovoltaic area and the effective working range (i.e., the effective bird deterrent range) of the sound array in the acoustic bird deterrent unit 11. Considering the bird deterrent capability of the acoustic bird deterrent unit 11, the acoustic bird deterrent unit 11 can be distributed in different locations inside and at the boundary of the marine photovoltaic site.

[0032] Each laser bird deterrent unit 12 can be positioned and numbered according to the shape and area of ​​the marine photovoltaic area and the effective working range (i.e., effective bird deterrent range) of the laser in the laser bird deterrent unit 12. Considering the bird deterrent capability of the laser bird deterrent unit 12 and the influence of the laser on the photovoltaic modules, the laser bird deterrent units 12 can be distributed in different locations around the marine photovoltaic site.

[0033] It should be noted that the acoustic bird deterrent unit 11 of this embodiment can be configured at one end of a support pile, and the other end of the support pile can be fixed to the seabed by a pile driving process. Similarly, the laser bird deterrent unit 12 of this embodiment can also be configured at one end of a support pile, and the other end of the support pile can be fixed to the seabed by a pile driving process. Typically, the support pile corresponding to the acoustic bird deterrent unit 11 and the support pile corresponding to the laser bird deterrent unit 12 are not the same support pile.

[0034] refer to Figure 1 The sonic bird deterrent unit 11 can also be connected to the laser bird deterrent unit 12 via wired or wireless means to transmit control commands and thus realize various combined bird deterrent strategies.

[0035] Figure 2 A schematic diagram illustrating the configuration of the laser bird deterrent unit and the acoustic bird deterrent unit according to embodiments of this disclosure is shown. (See reference...) Figure 2 In this exemplary marine photovoltaic scenario, two laser bird deterrent units and 19 acoustic bird deterrent units can be configured using the aforementioned analysis methods.

[0036] Among them, the acoustic bird deterrent unit 11 can be configured at the river channel of the marine photovoltaic project and at the boundary of the marine photovoltaic area. Compared with the acoustic bird deterrent unit 11, the laser bird deterrent unit 12 can be configured at the periphery of the marine photovoltaic site, so as to give full play to the role of laser bird deterrence while minimizing the impact of laser on photovoltaic modules.

[0037] refer to Figure 3 The sound wave bird deterrent unit 11 of the present disclosure may include a camera 131, a sound array 132 and a first data processor 133.

[0038] Camera 131 can be used to capture images of the first scene.

[0039] The sound-emitting array 132 may include multiple sound generators. The sound pressure level of the sound-emitting array 132 is required to reach 100 to 130 decibels at a distance of 1 meter. This disclosure does not limit the number of sound generators, for example, it may include 20 or 48.

[0040] The first data processor 133 can be used to acquire a first scene image captured by the camera 131, identify the first scene image, and if a bird object is identified, use the first scene image to perform depth estimation to determine the distance of the bird object relative to the sound wave bird deterrent unit. If the distance is less than or equal to a first distance threshold, control the sound-emitting array 132 to emit sound waves.

[0041] refer to Figure 4 The laser bird deterrent unit 12 of this embodiment may include a rotating table 141, a laser 142, a laser driving unit 143, and a second data processor 144.

[0042] The rotary table 141 can rotate in response to a rotation command.

[0043] Laser 142 can be mounted on a rotating stage. Specifically, a 520nm green laser can be used, for example. In conjunction with the rotation of the rotating stage 141, the continuous rotation angle achieved by the laser 142 of this disclosure includes horizontal rotation from 0° to 360° and vertical rotation from -85° to 20°.

[0044] The laser driving unit 143 can be used to drive the laser 142 to work.

[0045] The second data processor 144 performs data analysis and processing operations to control the bird-repelling operation of the laser bird-repelling unit 12. Specifically, the second data processor 144 can acquire a second scene image, identify the second scene image, and, if a bird object is identified, perform depth estimation using the second scene image to determine the distance of the bird object relative to the laser bird-repelling unit 12. If the distance is less than or equal to a second distance threshold, a rotation command is sent to the rotating stage 141 to control the laser emitting end of the laser 142 to rotate to match the direction of the bird object, and the laser driving unit 143 is controlled to drive the laser 142 to work. The second distance threshold is greater than the aforementioned first distance threshold.

[0046] In addition, both the acoustic bird deterrent unit 11 and the laser bird deterrent unit 12 may include an energy storage unit, a power management unit, and a housing. The energy storage unit stores the electrical energy required for the unit's operation; this energy source may include a marine photovoltaic power generation system or a power supply specifically configured for the unit. The power management unit controls the power supply mode. The housing has a structure that encloses the other modules of the unit. To meet the requirements of marine photovoltaic systems for exposure to sunlight, waterproofing, and corrosion resistance, the selection of the housing material must at least consider these factors; for example, an aluminum alloy housing can be used, and this disclosure does not impose any limitations on this.

[0047] According to some embodiments of this disclosure, the second data processor 144 can also be used to send a start command to the target acoustic bird deterrent unit corresponding to the laser bird deterrent unit 12 when it is determined that the distance between the bird object and the laser bird deterrent unit 12 is between a first distance threshold and a second distance threshold. The first data processor of the target acoustic bird deterrent unit can respond to the start command to control the camera to start, so as to acquire a first scene image.

[0048] According to some embodiments of this disclosure, when the acoustic bird deterrent unit 11 emits acoustic waves to drive away target birds, the first data processor of the acoustic bird deterrent unit 11 sends an operation stop command to the target laser bird deterrent unit corresponding to the acoustic bird deterrent unit 11. The second data processor of the target laser bird deterrent unit responds to the operation stop command and controls the laser emission operation against the target birds to stop. This avoids potential damage to photovoltaic modules caused by the laser, such as decreased photoelectric efficiency and damage to the photovoltaic modules.

[0049] The data processing procedure of the second data processor 144 is described below.

[0050] First, a second scene image can be acquired and then the second scene image can be recognized.

[0051] According to some embodiments of this disclosure, the laser bird deterrent unit 12 may further include a camera, and the second scene image acquired by the second data processor 144 is the image captured by the camera.

[0052] According to other embodiments of this disclosure, in a marine photovoltaic scenario, the laser bird deterrent unit 12 can correspond to one or more monitoring cameras, each monitoring camera being configured on a photovoltaic support. Specifically, the monitoring cameras are distributed on the same or different photovoltaic supports. It is understood that the monitoring cameras are pre-installed cameras used to monitor the on-site environment in a marine photovoltaic scenario. Furthermore, monitoring cameras within a predetermined distance from the laser bird deterrent unit 12 can be identified as the corresponding monitoring cameras; this disclosure does not limit the specific value of the predetermined distance.

[0053] In this case, the second scene image can be an image captured by the aforementioned surveillance camera.

[0054] Recognizing the second scene image includes determining whether the second scene image contains bird images. This process can be implemented using a classification model based on a convolutional neural network or through template comparison; this disclosure does not impose any limitations on this. Furthermore, the recognition algorithm of the first data processor 133 can be the same as the recognition algorithm of the second data processor 144.

[0055] If the second scene image is found not to contain bird objects, it can be discarded.

[0056] If the second scene image is found to contain a bird object, the second scene image can be used to perform depth estimation to determine the distance of the bird object relative to the laser bird deterrence unit 12.

[0057] Specifically, in the embodiment where the second scene image comes from the aforementioned surveillance camera, on the one hand, depth estimation can be performed using the second scene image to determine the distance of the bird object relative to the surveillance camera. On the other hand, given that the installation positions of the laser bird deterrent unit 12 and the surveillance camera are fixed, the distance of the laser bird deterrent unit 12 relative to the surveillance camera can be obtained. Therefore, the distance of the bird object relative to the laser bird deterrent unit 12 can be determined based on the distance of the bird object relative to the surveillance camera and the distance of the laser bird deterrent unit 12 relative to the surveillance camera.

[0058] If the determined distance is less than or equal to a second distance threshold, the second data processor 144 can send a rotation command to the turntable 141 to control the laser emitting end of the laser 142 to rotate to match the direction of the bird object, i.e., the laser emitting end is aligned with the bird object. Next, the second data processor 144 can control the laser driving unit 143 to drive the laser 142 to operate and emit laser light. This disclosure does not limit the specific value of the second distance threshold.

[0059] If the distance is determined to be greater than the second distance threshold, the camera is controlled to track the bird until the bird exceeds the predetermined range or the distance is less than or equal to the second distance threshold.

[0060] Depth estimation can be implemented using neural networks. However, a discrepancy may arise between the image size used for neural network training and the current image size of the second scene, especially in scenarios where the surveillance camera and the laser bird deterrent unit 12 are independently configured, making perfect matching difficult. This can lead to inaccurate depth estimation. To at least improve the accuracy of depth estimation, this disclosure also provides a depth estimation scheme.

[0061] First, the second data processor 144 determines the size of the second scene image. If the size of the second scene image is larger than a first preset size, the second scene image is downsampled to obtain a first intermediate image. The second scene image is then input into a trained first neural network to obtain a first depth image. The first intermediate image is then input into the first neural network to obtain a second depth image. The first neural network is trained using training samples with a size less than or equal to the first preset size. Next, the first depth image and the second depth image can be input into the second neural network for depth image fusion to obtain the depth estimation result of the second scene image. Both the first neural network and the second neural network can be based on a convolutional neural network structure; this disclosure does not limit the specific model structure and training process of either.

[0062] According to some embodiments of this disclosure, the size of the training samples of the first neural network is between a first preset size and a second preset size, wherein the first preset size is larger than the second preset size. For example, the first preset size is 512×512, and the second preset size is 256×256. The size of the aforementioned first intermediate image is the midpoint between the first preset size and the second preset size.

[0063] If the size of the second scene image is between the first preset size and the second preset size, the second data processor 144 can input the second scene image into the first neural network and determine the obtained first depth image as the depth estimation result of the second scene image.

[0064] If the size of the second scene image is smaller than the second preset size, the second data processor 144 can upsample the second scene image to obtain a second intermediate image; wherein the size of the second intermediate image is between the first preset size and the second preset size. Next, the second intermediate image can be input into the first neural network to obtain a third depth image. Then, the third depth image is downsampled to obtain the depth estimation result of the second scene image.

[0065] refer to Figure 5 The process of depth estimation described above is illustrated by example.

[0066] In step S502, a second scene image can be acquired.

[0067] In step S504, the size of the second scene image can be determined.

[0068] In step S506, the relationship between the size of the second scene image and the preset size can be determined. The preset size can be understood as the aforementioned first preset size, or a size range formed by the first preset size and the second preset size. When the preset size is understood as a size range formed by the first preset size and the second preset size, "less than the preset size" means less than the second preset size, "greater than the preset size" means greater than the first preset size, and "equal to the preset size" means between the first preset size and the second preset size.

[0069] If the size of the second scene image is larger than the preset size, proceed to step S508; if the size of the second scene image is equal to the preset size, proceed to step S512. If the size of the second scene image is smaller than the preset size, proceed to step S514.

[0070] In step S508, the second scene image can be input into the first neural network to obtain the first depth image; and the second scene image can be downsampled and then input into the first neural network to obtain the second depth image.

[0071] In step S510, the first depth image and the second depth image can be input into the second neural network to obtain a depth image corresponding to the second scene image.

[0072] In step S512, the second scene image can be input into the first neural network to obtain a depth image corresponding to the second scene image.

[0073] In step S514, the second scene image can be upsampled and then input into the first neural network, and the output of the model can be downsampled to obtain a depth image corresponding to the second scene image.

[0074] In addition to the depth estimation methods described above, this disclosure may also employ other ranging schemes that combine deep learning, and this disclosure does not impose any restrictions on such schemes.

[0075] It should be noted that the depth estimation scheme executed by the first data processor 133 in the acoustic bird deterrence unit 11 can also be executed in the same manner as the second data processor 144, which will not be elaborated further in this disclosure.

[0076] Furthermore, this disclosure also provides a bird deterrence method for marine photovoltaic applications. This bird deterrence method is applied to a bird deterrence system for marine photovoltaic applications. The bird deterrence system includes multiple laser bird deterrence units and multiple acoustic bird deterrence units. Each laser bird deterrence unit is distributed at different locations around the periphery of the marine photovoltaic site according to the shape and area of ​​the marine photovoltaic area and the effective working range of the laser in the laser bird deterrence unit. Each acoustic bird deterrence unit is distributed at different locations inside and at the boundary of the marine photovoltaic site according to the shape and area of ​​the marine photovoltaic area and the effective working range of the sound-emitting array in the acoustic bird deterrence unit. The acoustic bird deterrence unit includes a camera and a sound-emitting array. The camera is used to acquire images of a first scene, and the sound-emitting array includes multiple sound generators.

[0077] Figure 6 A flowchart illustrating a bird-repelling method applied to marine photovoltaic systems according to an embodiment of this disclosure is shown schematically. (Reference) Figure 6 The bird-repelling method of this disclosure may include:

[0078] S62. Acquire the first scene image captured by the camera and perform recognition on the first scene image.

[0079] S64. If a bird object is identified, depth estimation is performed using the first scene image to determine the distance of the bird object relative to the acoustic bird deterrent unit.

[0080] S66. When the distance is less than or equal to the first distance threshold, control the sound-emitting array to emit sound waves.

[0081] According to an exemplary embodiment of this disclosure, a laser bird deterrent unit includes: a rotating platform for rotating in response to a rotation command; a laser mounted on the rotating platform; a laser driving unit for driving the laser to operate; and a second data processor for acquiring a second scene image, recognizing the second scene image, performing depth estimation using the second scene image when a bird object is identified, determining the distance of the bird object relative to the laser bird deterrent unit, and sending a rotation command to the rotating platform to control the laser emitting end of the laser to rotate to match the direction of the bird object when the distance is less than or equal to a second distance threshold, and controlling the laser driving unit to drive the laser to operate; wherein the second distance threshold is greater than a first distance threshold.

[0082] According to an exemplary embodiment of this disclosure, the second data processor is further configured to send a start command to the target acoustic bird deterrent unit corresponding to the laser bird deterrent unit when it is determined that the distance between the bird object and the laser bird deterrent unit is between a first distance threshold and a second distance threshold; the first data processor of the target acoustic bird deterrent unit responds to the start command to control the camera to start so as to acquire a first scene image.

[0083] According to an exemplary embodiment of this disclosure, when the acoustic bird deterrent unit emits acoustic waves to drive away the target bird object, the first data processor of the acoustic bird deterrent unit sends an operation stop command to the target laser bird deterrent unit corresponding to the acoustic bird deterrent unit; the second data processor of the target laser bird deterrent unit responds to the operation stop command and controls the laser emission operation against the target bird object to stop.

[0084] According to an exemplary embodiment of this disclosure, the process of the second data processor performing depth estimation using the second scene image includes: the second data processor determining the size of the second scene image; if the size of the second scene image is larger than a first preset size, downsampling the second scene image to obtain a first intermediate image; inputting the second scene image into a trained first neural network to obtain a first depth image; and inputting the first intermediate image into the first neural network to obtain a second depth image; the first neural network is trained using training samples with a size less than or equal to the first preset size; and inputting the first depth image and the second depth image into the second neural network to perform depth image fusion to obtain a depth estimation result of the second scene image.

[0085] According to an exemplary embodiment of the present disclosure, the size of the training samples of the first neural network is between a first preset size and a second preset size, wherein the first preset size is larger than the second preset size, and the size of the first intermediate image is the midpoint between the first preset size and the second preset size.

[0086] According to an exemplary embodiment of this disclosure, if the size of the second scene image is between a first preset size and a second preset size, the second data processor inputs the second scene image into the first neural network and determines the obtained first depth image as the depth estimation result of the second scene image; if the size of the second scene image is smaller than the second preset size, the second data processor upsamples the second scene image to obtain a second intermediate image; wherein the size of the second intermediate image is between the first preset size and the second preset size; the second intermediate image is input into the first neural network to obtain a third depth image; the third depth image is downsampled to obtain the depth estimation result of the second scene image.

[0087] Since the steps of the bird-repelling method applied to marine photovoltaics in this embodiment are the same as those in the above-described system embodiment, they will not be repeated here.

[0088] It should be noted that although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0089] Furthermore, this disclosure also provides a bird deterrent device for marine photovoltaic applications. This bird deterrent device is applied to a bird deterrent system for marine photovoltaic applications. The bird deterrent system includes multiple laser bird deterrent units and multiple acoustic bird deterrent units. Each laser bird deterrent unit is distributed at different locations around the periphery of the marine photovoltaic site according to the shape and area of ​​the marine photovoltaic area and the effective working range of the laser in the laser bird deterrent unit. Each acoustic bird deterrent unit is distributed at different locations inside and at the boundary of the marine photovoltaic site according to the shape and area of ​​the marine photovoltaic area and the effective working range of the sound-emitting array in the acoustic bird deterrent unit. The acoustic bird deterrent unit includes a camera and a sound-emitting array. The camera is used to acquire images of a first scene, and the sound-emitting array includes multiple sound generators.

[0090] Figure 7 A block diagram schematically illustrates a bird-repelling device applied to marine photovoltaic systems according to an embodiment of this disclosure. (Reference) Figure 7 The bird deterrent device 7 for marine photovoltaic applications according to the present disclosure may include an image recognition module 71, a distance determination module 73, and a bird deterrent activation module 75.

[0091] Specifically, the image recognition module 71 can be used to acquire a first scene image captured by the camera and recognize the first scene image; the distance determination module 73 can be used to perform depth estimation using the first scene image when a bird object is identified, so as to determine the distance of the bird object relative to the sound wave bird deterrence unit; the bird deterrence activation module 75 can be used to control the sound-emitting array to emit sound waves when the distance is less than or equal to a first distance threshold.

[0092] Since the functional modules of the bird deterrent device applied to marine photovoltaics in this embodiment are the same as those in the above-described system embodiment, they will not be described again here.

[0093] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0094] The program product for implementing the above-described method according to embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0095] The program product may take the form of any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), an optical disk, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0096] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0097] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0098] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0099] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0100] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0101] The following reference Figure 8 To describe an electronic device 800 according to such an embodiment of the present disclosure. Figure 8 The illustrated electronic device 800 is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein. The aforementioned first data processor and / or second data processor may be configured as in the form of electronic device 800.

[0102] like Figure 8 As shown, the electronic device 800 is presented in the form of a general-purpose computing device. The components of the electronic device 800 may include, but are not limited to: at least one processing unit 810, at least one storage unit 820, a bus 830 connecting different system components (including storage unit 820 and processing unit 810), and a display unit 840.

[0103] The storage unit stores program code that can be executed by the processing unit 810, causing the processing unit 810 to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this disclosure. For example, the processing unit 810 can perform various steps of the bird-repelling method applied to marine photovoltaic systems according to embodiments of this disclosure.

[0104] Storage unit 820 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 8201 and / or cache memory 8202, and may further include a read-only memory (ROM) 8203.

[0105] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0106] Bus 830 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0107] Electronic device 800 can also communicate with one or more external devices 900 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with the electronic device 800, and / or with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed through input / output (I / O) interface 850. Furthermore, electronic device 800 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 860. Figure 8 As shown, network adapter 860 communicates with other modules of electronic device 800 via bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0108] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0109] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0110] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0111] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

[0112] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A bird-repelling system for marine photovoltaic applications, characterized in that, The system includes multiple laser bird-repelling units and multiple acoustic bird-repelling units. The laser bird-repelling units are distributed at different locations around the periphery of the marine photovoltaic site, based on the shape and area of ​​the marine photovoltaic area and the effective working range of the lasers within the laser units. The acoustic bird-repelling units are distributed at different locations inside and at the boundaries of the marine photovoltaic site, based on the shape and area of ​​the marine photovoltaic area and the effective working range of the sound-emitting arrays within the acoustic bird-repelling units. The acoustic bird-repelling units include: The camera is used to capture images of the first scene. A sound array, comprising multiple sound generators; A first data processor is configured to acquire the first scene image captured by the camera, identify the first scene image, and, if a bird object is identified, perform depth estimation using the first scene image to determine the distance of the bird object relative to the sound wave bird deterrent unit. If the distance is less than or equal to a first distance threshold, control the sound-emitting array to emit sound waves. The laser bird deterrence unit includes: A rotary table is used to rotate in response to a rotation command. The laser is mounted on the rotating platform; A laser driving unit is used to drive the laser to work. The second data processor is used to acquire a second scene image, identify the second scene image, and, if a bird object is identified, perform depth estimation using the second scene image to determine the distance of the bird object relative to the laser bird deterrent unit. If the distance is less than or equal to a second distance threshold, a rotation command is sent to the rotating platform to control the laser emitting end of the laser to rotate to match the direction of the bird object, and the laser driving unit is controlled to drive the laser to work; wherein, the second distance threshold is greater than the first distance threshold. The second data processor is further configured to, when determining that the distance between the bird object and the laser bird deterrent unit is between the first distance threshold and the second distance threshold, send a start command to the target acoustic bird deterrent unit corresponding to the laser bird deterrent unit; the first data processor of the target acoustic bird deterrent unit responds to the start command to control the camera to start, so as to acquire the first scene image; In the case where the sonic bird deterrent unit emits sonic waves to drive away the target bird, the first data processor of the sonic bird deterrent unit sends an operation stop command to the target laser bird deterrent unit corresponding to the sonic bird deterrent unit. The second data processor of the target laser bird deterrent unit responds to the operation stop command and controls the laser emission operation against the target bird to stop.

2. The bird-repelling system according to claim 1, characterized in that, The process by which the second data processor performs depth estimation using the second scene image includes: The second data processor determines the size of the second scene image. If the size of the second scene image is larger than a first preset size, the second scene image is downsampled to obtain a first intermediate image. The second scene image is then input into a trained first neural network to obtain a first depth image. The first intermediate image is then input into the first neural network to obtain a second depth image. The first neural network is trained using training samples with a size less than or equal to the first preset size. The first depth image and the second depth image are then input into the second neural network for depth image fusion to obtain a depth estimation result for the second scene image.

3. The bird-repelling system according to claim 2, characterized in that, The size of the training samples of the first neural network is between the first preset size and the second preset size, the first preset size is larger than the second preset size, and the size of the first intermediate image is the midpoint between the first preset size and the second preset size.

4. The bird-repelling system according to claim 3, characterized in that, If the size of the second scene image is between the first preset size and the second preset size, the second data processor inputs the second scene image into the first neural network and determines the obtained first depth image as the depth estimation result of the second scene image; If the size of the second scene image is smaller than the second preset size, the second data processor upsamples the second scene image to obtain a second intermediate image; wherein the size of the second intermediate image is between the first preset size and the second preset size; the second intermediate image is input into the first neural network to obtain a third depth image; the third depth image is downsampled to obtain the depth estimation result of the second scene image.

5. A bird-repelling method applied to marine photovoltaic applications, characterized in that, The bird-repelling method is applied to a bird-repelling system for offshore photovoltaic (PV) projects. The system includes multiple laser bird-repelling units and multiple acoustic bird-repelling units. Each laser bird-repelling unit is distributed at different locations around the periphery of the PV site, based on the shape and area of ​​the PV area and the effective working range of its laser. Each acoustic bird-repelling unit is distributed at different locations inside and at the boundary of the PV site, based on the shape and area of ​​the PV area and the effective working range of its sound-emitting array. Each acoustic bird-repelling unit includes a camera and a sound-emitting array. The camera is used to capture images of a first scene, and the sound-emitting array includes multiple sound generators. The bird-repelling method includes: Acquire the first scene image captured by the camera, and identify the first scene image; If a bird is identified, depth estimation is performed using the scene image to determine the distance of the bird relative to the acoustic bird deterrent unit; When the distance is less than or equal to a first distance threshold, the sound-emitting array is controlled to emit sound waves; The laser bird deterrent unit performs the following steps: A second scene image is acquired, and the second scene image is identified. If a bird object is identified, depth estimation is performed using the second scene image to determine the distance of the bird object relative to the laser bird deterrent unit. If the distance is less than or equal to a second distance threshold, the rotating platform is controlled to rotate so that the laser emitting end of the laser is rotated to match the direction of the bird object, and the laser driving unit is controlled to drive the laser to work. Wherein, the second distance threshold is greater than the first distance threshold. If the distance between the bird object and the laser bird deterrent unit is determined to be between the first distance threshold and the second distance threshold, a start command is sent to the corresponding target acoustic bird deterrent unit to control the camera of the target acoustic bird deterrent unit to start and acquire the first scene image; When the sonic bird deterrent unit emits sonic waves to drive away the target bird, the corresponding target laser bird deterrent unit is controlled to stop laser emission operations targeting the target bird.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the bird-repelling method for marine photovoltaic applications as described in claim 5.

7. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to implement the bird-repelling method for marine photovoltaic applications as described in claim 5 by executing the executable instructions.

Images