Airport bird repelling method and device, storage medium and electronic equipment

Abstract

The invention provides an airport bird repelling method and device, a storage medium and electronic equipment, and relates to the technical field of airport airspace safety, and the method comprises the steps: obtaining a plurality of airspace images collected by a plurality of cameras disposed in an airport range; one camera corresponds to at least one airspace image; performing target identification on each airspace image in the plurality of airspace images, judging whether the airspace images contain a target object, and determining a target camera to which the target airspace image containing the target object belongs under the condition that the target object is identified; and based on the relative position information of the target camera and the target object, determining a target airspace, and controlling the sound wave generator to emit bird repelling sound waves to the target airspace. According to the airport bird repelling method, the airport bird repelling device, the storage medium and the electronic equipment provided by the invention, the birds influencing the flight safety are accurately positioned through the images collected by the camera, and bird repelling is performed in a targeted manner, so that intelligence of airport bird repelling is realized.

Description

Technical Field

[0001] The present application relates to the field of airport airspace safety technology, and in particular to an airport bird-repelling method, device, storage medium and electronic equipment. Background Art

[0002] In the operation of modern airports, bird invasions often pose a serious threat to flight safety. Bird strikes may not only damage aircraft engines, but may also lead to more serious flight accidents. In related technologies, in order to ensure flight safety, airports usually adopt a variety of bird repellent measures, including the use of sonic bird repellents, laser bird repellents, and manual bird repellents.

[0003] However, traditional bird-repelling methods often rely on manual operations, which consumes a lot of manpower and resources. Especially in large airports, manual bird-repelling is costly and inefficient. Secondly, although sonic bird repellents and laser bird repellents can repel birds to a certain extent, birds may adapt to these stimuli during long-term use, resulting in a gradual weakening of the bird-repelling effect. In addition, traditional bird-repelling equipment often lacks intelligence and cannot automatically adjust the bird-repelling strategy according to actual conditions, resulting in less than ideal bird-repelling effects. Summary of the invention

[0004] The purpose of this application is to provide an airport bird-repelling method, device, storage medium and electronic equipment, which can accurately locate birds that affect flight safety through images collected by a camera, and carry out targeted bird repelling, thereby realizing intelligent airport bird repelling.

[0005] The present application provides an airport bird-repelling method, comprising: Acquire multiple airspace images collected by multiple cameras set up within the airport; one camera corresponds to at least airspace images; perform target recognition on each of the multiple airspace images to determine whether the airspace image contains a target object, and when the target object is recognized, determine the target camera to which the target airspace image containing the target object belongs; determine the target airspace based on the relative position information between the target camera and the target object, and control the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0006] Optionally, obtaining multiple airspace images captured by multiple cameras set up within the airport includes: using the DeepStream framework to obtain the video stream of each camera in the multiple cameras, and extracting image frames from the video stream of each camera, and using each image frame as the airspace image.

[0007] Optionally, performing target recognition on each of the multiple spatial domain images to determine whether the spatial domain image contains a target object includes: performing target detection on the spatial domain image captured by the camera using a target detection model, and performing image recognition on the detected spatial domain image using an image recognition model to determine whether the object recognized from the spatial domain image is the target object.

[0008] Optionally, determining the target airspace based on the relative position information between the target camera and the target object includes: obtaining the position information of the target camera based on the airport coordinate system, and calculating the position information of the target object based on the airport coordinate system according to the lens orientation of the target camera and the distance between the target camera and the target object; determining the target airspace according to the position information of the target object based on the airport coordinate system.

[0009] Optionally, the location information includes: horizontal coordinate information and vertical coordinate information; determining the target airspace according to the location information of the target object based on the airport coordinate system includes: acquiring the horizontal coordinate range and the vertical coordinate range of multiple divided airspaces, and matching the horizontal coordinate information of the target object based on the airport coordinate system with the horizontal coordinate range of each divided area, and filtering out at least one first airspace from the multiple divided airspaces; matching the vertical coordinate information of the target object based on the airport coordinate system with the vertical coordinate range of each divided area, filtering out a second airspace from the at least one first airspace, and determining the second airspace as the target airspace.

[0010] Optionally, controlling the sound wave generator to emit bird-repelling sound waves to the target airspace includes: when the target airspace is determined, controlling at least one sound wave generator associated with the target airspace to emit bird-repelling sound waves to the target airspace; wherein the at least one sound wave generator is: a sound wave generator among multiple sound wave generators installed at the airport that can send bird-repelling sound waves to the target airspace.

[0011] The present application also provides an airport bird-repelling device, comprising: An acquisition module is used to acquire multiple airspace images collected by multiple cameras set up within the airport; one camera corresponds to at least one airspace image; an identification module is used to perform target recognition on each of the multiple airspace images to determine whether the airspace image contains a target object; a determination module is used to determine the target camera to which the target airspace image containing the target object belongs when the target object is recognized; the determination module is also used to determine the target airspace based on the relative position information between the target camera and the target object; a control module is used to control the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0012] Optionally, the acquisition module is specifically used to use the DeepStream framework to acquire the video stream of each camera among the multiple cameras, and extract image frames from the video stream of each camera, and use each image frame as a spatial domain image.

[0013] Optionally, the recognition module is specifically used to perform target detection on the spatial image captured by the camera using a target detection model, and to perform image recognition on the detected spatial image using an image recognition model to determine whether the object recognized from the spatial image is a target object.

[0014] Optionally, the determination module is specifically used to obtain the position information of the target camera based on the airport coordinate system, and calculate the position information of the target object based on the airport coordinate system according to the lens direction of the target camera and the distance between the target camera and the target object; the determination module is also specifically used to determine the target airspace according to the position information of the target object based on the airport coordinate system.

[0015] Optionally, the location information includes: horizontal coordinate information and vertical coordinate information; the determination module is specifically used to obtain the horizontal coordinate range and the vertical coordinate range of multiple divided airspaces, and match the horizontal coordinate information of the target object based on the airport coordinate system with the horizontal coordinate range of each divided area, and filter out at least one first airspace from the multiple divided airspaces; the determination module is also specifically used to match the vertical coordinate information of the target object based on the airport coordinate system with the vertical coordinate range of each divided area, filter out a second airspace from the at least one first airspace, and determine the second airspace as the target airspace.

[0016] Optionally, the control module is specifically used to control at least one sound wave generator associated with the target airspace to emit bird-repelling sound waves to the target airspace when the target airspace is determined; wherein the at least one sound wave generator is: a sound wave generator among multiple sound wave generators installed at the airport that can send bird-repelling sound waves to the target airspace.

[0017] The present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of any of the above-mentioned airport bird-repelling methods.

[0018] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned airport bird-repelling methods are implemented.

[0019] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned airport bird-repelling methods are implemented.

[0020] The airport bird-repelling method, device, storage medium and electronic device provided by the present application first obtain multiple airspace images collected by multiple cameras set within the airport; one camera corresponds to at least one airspace image; then, target recognition is performed on each of the multiple airspace images to determine whether the airspace image contains a target object, and when the target object is identified, the target camera to which the target airspace image containing the target object belongs is determined; finally, based on the relative position information between the target camera and the target object, the target airspace is determined, and the sound wave generator is controlled to emit bird-repelling sound waves to the target airspace. In this way, the flying birds that affect flight safety are accurately located through the images collected by the camera, and the birds are driven away in a targeted manner, realizing the intelligentization of airport bird-repelling. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0022] Figure 1 It is a flow chart of the airport bird-repelling method provided by this application; Figure 2 It is a structural schematic diagram of the airport bird repellent device provided by the present application; Figure 3 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0024] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0025] In the operation of modern airports, bird invasions often pose a serious threat to flight safety. Bird strikes may not only damage aircraft engines, but may also lead to more serious flight accidents. In order to ensure flight safety, airports usually adopt a variety of bird repellent measures, including but not limited to the use of sonic bird repellents, laser bird repellents, and manual bird repellents. However, these traditional bird repellent methods have some shortcomings.

[0026] First, traditional bird repellent methods often rely on manual operation, which consumes a lot of manpower and resources. Especially in large airports, manual bird repellent is costly and inefficient. Secondly, although sonic bird repellents and laser bird repellents can repel birds to a certain extent, birds may adapt to these stimuli during long-term use, resulting in a gradual weakening of the bird repellent effect. In addition, traditional bird repellent equipment often lacks intelligence and cannot automatically adjust the bird repellent strategy according to actual conditions, resulting in less than ideal bird repellent effects.

[0027] In recent years, with the development of computer vision and deep learning technologies, intelligent bird-repellent systems based on image recognition have gradually attracted attention. These systems capture real-time images of birds through cameras and use deep learning algorithms for image recognition, which can automatically identify and locate birds. However, most existing intelligent bird-repellent systems are deployed in the cloud and rely on network data transmission. There are problems such as data transmission delays and limited network bandwidth, which affect real-time performance and reliability.

[0028] The airport bird-repelling method provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0029] like Figure 1 As shown, an airport bird-repelling method provided by an embodiment of the present application may include the following steps 101 to 103: Step 101: Acquire multiple airspace images collected by multiple cameras installed within the airport.

[0030] The airport is divided into multiple airspaces, each of which is monitored by at least one camera, and one camera corresponds to at least one airspace image, that is, an image captured by a camera contains at least one airspace.

[0031] For example, multiple cameras are installed in the security area of ​​the airport, each of which can capture video images. After that, the captured video stream is sent to the edge computing device (for example, Jetson, etc.) for target detection and recognition.

[0032] Specifically, the step of acquiring multiple airspace images collected by multiple cameras set within the airport in the above step 101 may also include the following step 101a: Step 101a: Use the DeepStream framework to obtain the video stream of each camera in the multiple cameras, extract image frames from the video stream of each camera, and use each image frame as a spatial domain image.

[0033] Exemplarily, in an embodiment of the present application, the DeepStream framework is used to obtain the video stream captured by the camera, and image recognition is performed on each image frame in the video stream.

[0034] Step 102: Perform target recognition on each of the multiple airspace images to determine whether the airspace image contains a target object, and if the target object is recognized, determine the target camera to which the target airspace image containing the target object belongs.

[0035] Specifically, the step of performing target recognition on each of the plurality of airspace images in step 102 to determine whether the airspace image contains the target object may further include the following step 102a: Step 102a: Use the target detection model to perform target detection on the airspace image collected by the camera, and use the image recognition model to perform image recognition on the detected airspace image to determine whether the object recognized from the airspace image is the target object.

[0036] Exemplarily, after the edge computing device receives the video captured by each camera using the DeepStream framework, it analyzes and identifies each image frame of the video (i.e., the above-mentioned airspace image). First, it performs target detection on the image frame to detect whether the image contains flying birds. Then, it uses image recognition technology to determine the airspace where the flying birds are located.

[0037] Specifically, the step of determining the target airspace based on the relative position information between the target camera and the target object in the above step 102 may further include the following steps 102b and 102c: Step 102b, obtaining the position information of the target camera based on the airport coordinate system, and calculating the position information of the target object based on the airport coordinate system according to the lens orientation of the target camera and the distance between the target camera and the target object.

[0038] Step 102c: determine the target airspace according to the position information of the target object based on the airport coordinate system.

[0039] For example, after obtaining the position information of the target object in the airport coordinate system, the airspace where the target object is located can be determined based on the position information. The position information includes: abscissa information and ordinate information.

[0040] Specifically, the step of determining the target airspace according to the position information of the target object based on the airport coordinate system in the above step 102c may further include the following steps 102c1 and 102c2: Step 102c1, obtain the horizontal coordinate range and the vertical coordinate range of multiple divided airspaces, and match the horizontal coordinate information of the target object based on the airport coordinate system with the horizontal coordinate range of each divided area, and filter out at least one first airspace from the multiple divided airspaces.

[0041] Step 102c2, matching the ordinate information of the target object based on the airport coordinate system with the ordinate range of each divided area, filtering out a second airspace from the at least one first airspace, and determining the second airspace as the target airspace.

[0042] Exemplarily, in an embodiment of the present application, the airspace can be preliminarily screened by the position of the camera to reduce the amount of calculation, and then the target airspace is determined based on the position information of the target object and the horizontal and vertical coordinate ranges contained in the airspace.

[0043] Step 103: determine a target airspace based on the relative position information between the target camera and the target object, and control the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0044] Exemplarily, after the target airspace is determined, a sound wave generator capable of sending bird-repelling sound waves to the target airspace can be controlled to send bird-repelling sound waves to the target airspace.

[0045] Specifically, the above step 103 may further include the following step 103a: Step 103a: When the target airspace is determined, control at least one sound wave generator associated with the target airspace to emit bird-repelling sound waves toward the target airspace.

[0046] Among them, the at least one sound wave generator is: among the multiple sound wave generators installed at the airport, a sound wave generator that can send bird-repelling sound waves to the target airspace.

[0047] In this way, it is possible to avoid the situation in which the birds adapt to the sound waves and the bird-repelling effect is reduced due to the long-term activation of the bird-repelling sound waves when there are no flying birds invading, thereby greatly improving the bird-repelling effect and flight safety.

[0048] It should be noted that in the embodiment of the present application, the hardware and software required to execute the airport bird-repelling method provided in the embodiment of the present application may include the following: 1. Hardware deployment: Consider using GPU acceleration, especially if the deep learning model is complex, which can help increase the speed of object detection. Consider using high-performance cameras to ensure high-quality images to improve detection accuracy. Consider using devices with edge computing capabilities to reduce the performance consumption of central servers, reduce the time consumption caused by network transmission, and improve the real-time performance of the system.

[0049] 2. Data collection: Ensure that camera locations and angles are optimal to cover the surveillance area and minimize blind spots. Consider using multiple cameras to increase surveillance coverage and accuracy.

[0050] 3. Data preprocessing: Add further control and enhancements to image quality to ensure the best quality images fed into the model.

[0051] 4. Target detection and recognition: Consider using more advanced deep learning models to improve detection accuracy. Advanced target detection models include YOLO (You Only Look Once), SSD (Single Shot Multibox Detector), etc. Consider model quantization and optimization to adapt to the limited resources of edge devices and improve real-time performance. Consider applying post-processing techniques on the model output, such as non-maximum suppression (NMS), to filter redundant detection boxes.

[0052] The airport bird-repelling method provided in the embodiment of the present application first obtains multiple airspace images collected by multiple cameras set within the airport; one camera corresponds to at least one airspace image; then, target recognition is performed on each of the multiple airspace images to determine whether the airspace image contains a target object, and when the target object is identified, the target camera to which the target airspace image containing the target object belongs is determined; finally, based on the relative position information between the target camera and the target object, the target airspace is determined, and the sound wave generator is controlled to emit bird-repelling sound waves to the target airspace. In this way, the flying birds that affect flight safety are accurately located through the images collected by the camera, and the birds are driven away in a targeted manner, thereby realizing the intelligentization of airport bird-repelling.

[0053] It should be noted that the airport bird-repelling method provided in the embodiment of the present application can be executed by an airport bird-repelling device, or a control module in the airport bird-repelling device for executing the airport bird-repelling method. In the embodiment of the present application, the airport bird-repelling device executing the airport bird-repelling method is taken as an example to illustrate the airport bird-repelling device provided in the embodiment of the present application.

[0054] It should be noted that, in the embodiments of the present application, the airport bird-repelling method shown in the above-mentioned method drawings is illustrated by taking one of the drawings in the embodiments of the present application as an example. When implemented specifically, the airport bird-repelling method shown in the above-mentioned method drawings can also be implemented in combination with any other drawings that can be combined as illustrated in the above-mentioned embodiments, which will not be described in detail here.

[0055] The airport bird-repelling device provided by the present application is described below, and the airport bird-repelling method described below and above can be referenced to each other.

[0056] Figure 2 The schematic diagram of the structure of the airport bird repellent device provided in the embodiment of the present application is as follows: Figure 2 As shown, specifically including: The acquisition module 201 is used to acquire multiple airspace images collected by multiple cameras set up within the airport; one camera corresponds to at least one airspace image; the recognition module 202 is used to perform target recognition on each airspace image in the multiple airspace images to determine whether the airspace image contains a target object; the determination module 203 is used to determine the target camera to which the target airspace image containing the target object belongs when the target object is recognized; the determination module 203 is also used to determine the target airspace based on the relative position information between the target camera and the target object; the control module 204 is used to control the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0057] Optionally, the acquisition module 201 is specifically used to use the DeepStream framework to acquire the video stream of each camera among the multiple cameras, and extract image frames from the video stream of each camera, and use each image frame as a spatial domain image.

[0058] Optionally, the recognition module 202 is specifically used to perform target detection on the spatial image captured by the camera using a target detection model, and to perform image recognition on the detected spatial image using an image recognition model to determine whether the object recognized from the spatial image is a target object.

[0059] Optionally, the determination module 203 is specifically used to obtain the position information of the target camera based on the airport coordinate system, and calculate the position information of the target object based on the airport coordinate system according to the lens orientation of the target camera and the distance between the target camera and the target object; the determination module 203 is also specifically used to determine the target airspace according to the position information of the target object based on the airport coordinate system.

[0060] Optionally, the location information includes: horizontal coordinate information and vertical coordinate information; the determination module 203 is specifically used to obtain the horizontal coordinate range and the vertical coordinate range of multiple divided airspaces, and match the horizontal coordinate information of the target object based on the airport coordinate system with the horizontal coordinate range of each divided area, and filter out at least one first airspace from the multiple divided airspaces; the determination module 203 is also specifically used to match the vertical coordinate information of the target object based on the airport coordinate system with the vertical coordinate range of each divided area, filter out a second airspace from the at least one first airspace, and determine the second airspace as the target airspace.

[0061] Optionally, the control module 204 is specifically used to control at least one sound wave generator associated with the target airspace to emit bird-repelling sound waves to the target airspace when the target airspace is determined; wherein the at least one sound wave generator is: a sound wave generator among multiple sound wave generators installed at the airport that can send bird-repelling sound waves to the target airspace.

[0062] The airport bird-repelling device provided by the present application first obtains multiple airspace images collected by multiple cameras set within the airport; one camera corresponds to at least one airspace image; then, target recognition is performed on each of the multiple airspace images to determine whether the airspace image contains a target object, and when the target object is identified, the target camera to which the target airspace image containing the target object belongs is determined; finally, based on the relative position information between the target camera and the target object, the target airspace is determined, and the sound wave generator is controlled to emit bird-repelling sound waves to the target airspace. In this way, the flying birds that affect flight safety are accurately located through the images collected by the camera, and the birds are driven away in a targeted manner, realizing the intelligentization of airport bird-repelling.

[0063] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 310, a communication interface 320, a memory 330 and a communication bus 340, wherein the processor 310, the communication interface 320 and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logic instructions in the memory 330 to execute the airport bird-repelling method, which includes: obtaining multiple airspace images collected by multiple cameras set within the airport; one camera corresponds to at least airspace images; performing target recognition on each of the multiple airspace images, judging whether the airspace image contains a target object, and determining the target camera to which the target airspace image containing the target object belongs when the target object is recognized; determining the target airspace based on the relative position information between the target camera and the target object, and controlling the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0064] In addition, the logic instructions in the above-mentioned memory 330 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0065] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the airport bird-repelling method provided by the above-mentioned methods, and the method includes: obtaining multiple airspace images collected by multiple cameras set up within the airport; one camera corresponds to at least airspace images; performing target recognition on each of the multiple airspace images, judging whether the airspace image contains a target object, and when the target object is recognized, determining the target camera to which the target airspace image containing the target object belongs; based on the relative position information of the target camera and the target object, determining the target airspace, and controlling the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0066] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned airport bird-repelling method, the method comprising: acquiring multiple airspace images collected by multiple cameras set up within the airport; one camera corresponds to at least airspace images; performing target recognition on each of the multiple airspace images, determining whether the airspace image contains a target object, and when the target object is recognized, determining the target camera to which the target airspace image containing the target object belongs; determining the target airspace based on the relative position information between the target camera and the target object, and controlling the sound wave generator to emit bird-repelling sound waves to the target airspace.

[0067] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0068] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for driving away birds at an airport, characterized in that: Applied to an edge computer, the method comprises: Acquire multiple airspace images collected by multiple cameras installed within the airport; one camera corresponds to at least airspace images; Performing target recognition on each of the multiple airspace images to determine whether the airspace image contains a target object, and if the target object is recognized, determining a target camera to which the target airspace image containing the target object belongs; Based on the relative position information between the target camera and the target object, a target airspace is determined, and a sound wave generator is controlled to emit bird-repelling sound waves to the target airspace.

2. The method according to claim 1, characterized in that The obtaining of multiple airspace images collected by multiple cameras set within the airport includes: The DeepStream framework is used to obtain the video stream of each camera in the multiple cameras, and an image frame is extracted from the video stream of each camera, and each image frame is used as a spatial domain image.

3. The method according to claim 1, characterized in that The performing target recognition on each of the plurality of airspace images to determine whether the airspace image contains a target object includes: The target detection model is used to perform target detection on the spatial domain image collected by the camera, and the image recognition model is used to perform image recognition on the detected spatial domain image to determine whether the object recognized from the spatial domain image is the target object.

4. The method according to claim 1 or 3, characterized in that: The determining of the target airspace based on the relative position information between the target camera and the target object includes: Acquire the position information of the target camera based on the airport coordinate system, and calculate the position information of the target object based on the airport coordinate system according to the lens orientation of the target camera and the distance between the target camera and the target object; The target airspace is determined according to the position information of the target object based on the airport coordinate system.

5. The method according to claim 4, characterized in that The position information includes: horizontal coordinate information and vertical coordinate information; The step of determining the target airspace according to the position information of the target object based on the airport coordinate system includes: Acquire the horizontal coordinate ranges and vertical coordinate ranges of a plurality of divided airspaces, and match the horizontal coordinate information of the target object based on the airport coordinate system with the horizontal coordinate range of each divided area, and select at least one first airspace from the plurality of divided airspaces; The vertical coordinate information of the target object based on the airport coordinate system is matched with the vertical coordinate range of each divided area, a second airspace is screened out from the at least one first airspace, and the second airspace is determined as the target airspace.

6. The method according to claim 1 or 4, characterized in that: The controlling the sound wave generator to emit the bird-repelling sound wave to the target airspace comprises: When the target airspace is determined, controlling at least one sound wave generator associated with the target airspace to emit bird-repelling sound waves toward the target airspace; Among them, the at least one sound wave generator is: among the multiple sound wave generators installed at the airport, a sound wave generator that can send bird-repelling sound waves to the target airspace.

7. An airport bird repellent device, characterized in that: The device comprises: An acquisition module is used to acquire multiple airspace images collected by multiple cameras set within the airport; one camera corresponds to at least one airspace image; A recognition module, used to perform target recognition on each of the plurality of airspace images to determine whether the airspace image contains a target object; A determination module, configured to determine, when a target object is identified, a target camera to which a target airspace image containing the target object belongs; The determination module is further used to determine the target airspace based on the relative position information between the target camera and the target object; The control module is used to control the sound wave generator to emit bird-repelling sound waves to the target airspace.

8. The device according to claim 7, characterized in that The acquisition module is specifically used to use the DeepStream framework to acquire the video stream of each camera in the multiple cameras, and extract image frames from the video stream of each camera, and use each image frame as a spatial domain image.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the airport bird-repelling method as claimed in any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the airport bird-repelling method as claimed in any one of claims 1 to 6 are implemented.

Images