Method, device, equipment and storage medium for obstacle investigation in airport clearance area

Abstract

An embodiment of the present application provides a method, device, equipment and storage medium for detecting obstacles in the airport clearance area, belonging to the technical field of airport safety monitoring, and can be applied in the low-altitude economy field. The method includes: obtaining the shielding parameter of the airport surveillance radar; controlling the pan-tilt head to move to the target posture according to the shielding parameter, wherein the installation position of the pan-tilt head is determined based on the installation position of the airport surveillance radar, and the pan-tilt head is used to carry the imaging device; controlling the pan-tilt head to stop moving to take a picture through the imaging device to obtain a target image; performing segmentation processing on the target image through a pre-trained image segmentation model to obtain a foreground pixel point set of the target image; performing obstacle detection in the clearance area on the foreground pixel point set. The embodiment of the present application can reduce the cost of detecting obstacles in the airport clearance area and improve the accuracy, simplicity and automation degree of detecting obstacles in the airport clearance area.

Description

Technical Field

[0001] This application relates to the technical fields of airport security monitoring and low-altitude economy, and particularly to a method, device, equipment, and storage medium for detecting obstacles in the airport clearance area. Background Art

[0002] The airport clearance area refers to the airspace and area specified to ensure that aircraft are not interfered by obstacles (such as buildings, towers, hills, trees, etc.) during takeoff, landing, and other flight operations. In the airport clearance area, no obstacle can exceed a certain height.

[0003] Currently, in the aviation field, the detection of obstacles in the airport clearance area generally adopts the method of manual inspection of obstacles, which is time-consuming and laborious and difficult to meet the real-time detection requirements.

[0004] In related technologies, lidar is also used to perform spatial scanning of the airport clearance area to collect spatial data (such as point cloud data) for complex three-dimensional modeling to detect possible obstacles. However, due to the short scanning distance of lidar, it is necessary to use drones or special vehicles to carry lidar for scanning, which is costly and time-consuming. It depends on manual operation to plan and deploy the scanning of lidar, and any update or change requires manual re-planning of a new scanning task and re-modeling, and each modeling also consumes a large amount of computing resources.

[0005] In related technologies, a multi-view stereo vision system is also used to collect three-dimensional images or depth images of the airport clearance area for analysis to detect possible obstacles. However, the multi-view stereo vision system requires the coordinated work of multiple cameras. It not only cannot cover a long distance, affecting the detection accuracy, but also involves complex installation, synchronization, calibration, image processing, and data fusion, and the maintenance work is also relatively cumbersome.

[0006] Therefore, how to reduce the cost of detecting obstacles in the airport clearance area, improve the accuracy, simplicity, and automation of detecting obstacles in the airport clearance area has become an urgent technical problem to be solved. Summary of the Invention

[0007] The main purpose of the embodiments of this application is to propose a method, device, equipment, and storage medium for detecting obstacles in the airport clearance area, aiming to reduce the cost of detecting obstacles in the airport clearance area and improve the accuracy, simplicity, and automation of detecting obstacles in the airport clearance area.

[0008] To achieve the above object, in the first aspect of the embodiments of this application, a method for detecting obstacles in the airport clearance area is proposed, and the method includes:

[0009] Obtain the occlusion parameters of the airport surveillance radar;

[0010] Control the pan-tilt to move to the target pose according to the occlusion parameter, where the installation position of the pan-tilt is determined based on the installation position of the airport surveillance radar, and the pan-tilt is used to carry a photographing device;

[0011] Control the pan-tilt to stop moving and take a photograph through the photographing device to obtain a target image;

[0012] Perform segmentation processing on the target image through a pre-trained image segmentation model to obtain the foreground pixel point set of the target image;

[0013] Perform clearance obstacle investigation on the foreground pixel point set.

[0014] To achieve the above object, a second aspect of the embodiments of the present application provides an airport clearance obstacle investigation device, and the device includes:

[0015] A parameter acquisition module, configured to acquire the occlusion parameter of the airport surveillance radar;

[0016] A pan-tilt control module, configured to control the pan-tilt to move to the target pose according to the occlusion parameter, where the installation position of the pan-tilt is determined based on the installation position of the airport surveillance radar, and the pan-tilt is used to carry a photographing device;

[0017] An image photographing module, configured to control the pan-tilt to stop moving and take a photograph through the photographing device to obtain a target image;

[0018] An image segmentation module, configured to perform segmentation processing on the target image through a pre-trained image segmentation model to obtain the foreground pixel point set of the target image;

[0019] An obstacle investigation module, configured to perform clearance obstacle investigation on the foreground pixel point set.

[0020] To achieve the above object, a third aspect of the embodiments of the present application provides a computer device, and the computer device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method described in the first aspect above is implemented.

[0021] To achieve the above object, a fourth aspect of the embodiments of the present application provides a computer-readable storage medium, and the computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the method described in the first aspect above is implemented.

[0022] In the solution implemented by the method, device, equipment and storage medium for detecting obstacles in the airport clearance area proposed in this application, the shielding parameter of the airport surveillance radar is obtained; according to the shielding parameter, the pan-tilt is controlled to move to the target posture, where the installation position of the pan-tilt is determined based on the installation position of the airport surveillance radar, and the pan-tilt is used to carry a photographing device; the pan-tilt is controlled to stop moving to take a photograph through the photographing device to obtain a target image; the target image is segmented through a pre-trained image segmentation model to obtain a foreground pixel point set of the target image; the foreground pixel point set is checked for obstacles in the clearance area. In this way, on the one hand, through the shielding parameter of the airport surveillance radar, the pan-tilt is reasonably guided to accurately move to the target posture, so that the photographing device carried by the pan-tilt can take a target image that can cover the area that may be blocked by obstacles in real time; on the other hand, through the pre-trained image segmentation model, the foreground pixel point set is accurately segmented from the target image, and the irrelevant interference factors in the target image can be effectively excluded, so as to only focus on checking for obstacles in the foreground pixel point set, improving the efficiency and accuracy of obstacle detection in the clearance area. Therefore, through pan-tilt control, intelligent and automatic obstacle detection in the airport clearance area is realized, thereby reducing the cost of obstacle detection in the airport clearance area and improving the accuracy, simplicity and automation of obstacle detection in the airport clearance area. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flowchart of a method for detecting obstacles in the airport clearance area provided by an embodiment of the present application;

[0024] Figure 2 is an example diagram of an application scenario for detecting obstacles in the airport clearance area provided by an embodiment of the present application;

[0025] Figure 3 is an example diagram of a target image provided by an embodiment of the present application;

[0026] Figure 4 is a schematic block diagram of a device for detecting obstacles in the airport clearance area provided by an embodiment of the present application;

[0027] Figure 5 is a schematic block diagram of the structure of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] It should be noted that although the functional modules are divided in the schematic diagram of the device and the logical sequence is shown in the flowchart, in some cases, the steps shown or described can be executed in a different module division from that in the device or a different sequence from that in the flowchart. Terms such as "first" and "second" in the description, claims, and the above-mentioned drawings are used to distinguish similar objects and do not necessarily describe a specific order or sequence.

[0030] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0031] First, the nouns involved in this application are analyzed as follows:

[0032] Airport Surveillance Radar (ASR): It refers to a radar system used to monitor the positions of aircraft in the airport and the airspace around the airport. The main function of the airport surveillance radar is to provide real-time monitoring and tracking of aircraft in the airport's clear airspace to ensure the safety of aircraft during takeoff and landing.

[0033] Obscuration parameter: It refers to the factors that affect the signal propagation or coverage range of the airport surveillance radar and can be used to quantify or evaluate whether certain areas cannot be effectively monitored by the airport surveillance radar. It reflects the situation where the monitoring ability of the airport surveillance radar is limited due to the influence of obstacles on the signal propagation of the airport surveillance radar.

[0034] Obscuration angle: It can also be called the blind area angle or occlusion angle. It refers to the specific angular range where obstacles around the airport (such as buildings, towers, hills, trees, etc.) cause the airport surveillance radar to be unable to effectively monitor.

[0035] Target obscuration angle: It can also be called the limit angle of the obscuration angle. It refers to the upper threshold angle of the obscuration angle caused by obstacles around the airport to the airport surveillance radar. That is to say, the obscuration angle caused by obstacles around the airport to the airport surveillance radar shall not exceed the target obscuration angle. Once it exceeds the target obscuration angle, it will cause a blind area in the airport surveillance radar and affect the monitoring of aircraft by the airport surveillance radar.

[0036] Among them, the obscuration parameter includes the target obscuration angle.

[0037] Pan-tilt head: It refers to a pan-tilt head system that can carry a shooting device or an integrated pan-tilt head camera with a shooting device. The pan-tilt head carries the shooting device and is used to fix the shooting device and change the height, pitch angle, or direction of the shooting device to stably hold the shooting device in a certain posture for the shooting device to take pictures.

[0038] Among them, the shooting device can be a monocular camera. Compared with lidar and multi-camera stereo vision systems, the pan-tilt system equipped with a monocular camera has obvious advantages of low cost, small volume, easy maintenance, simplicity, flexibility, and stability, and can quickly capture stable images of different angles of the airport surrounding environment at any time.

[0039] YOLOv8 Segmentation network: It is an efficient and advanced deep network model in the field of object detection and belongs to a new version of the YOLO (You Only Look Once) series of models. The YOLOv8 Segmentation network inherits the advantages of YOLOv8 and is optimized to perform pixel-level classification on images, thereby achieving more refined image understanding.

[0040] Based on this, the embodiments of the present application provide a method, device, equipment, and storage medium for detecting obstacles in the airport clearance area, aiming to reduce the cost of detecting obstacles in the airport clearance area and improve the accuracy, simplicity, and automation of detecting obstacles in the airport clearance area.

[0041] The method, device, equipment, and storage medium for detecting obstacles in the airport clearance area provided by the embodiments of the present application are specifically described through the following embodiments. First, the method for detecting obstacles in the airport clearance area in the embodiments of the present application is described.

[0042] The method for detecting obstacles in the airport clearance area provided by the embodiments of the present application relates to the technical fields of airport safety monitoring and low-altitude economy. The method for detecting obstacles in the airport clearance area provided by the embodiments of the present application can be applied to a terminal, a server, or software running on a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the method for detecting obstacles in the airport clearance area, such as software for detecting obstacles in the airport clearance area, but is not limited to the above forms. Among them, the terminal or the server communicates with the pan-tilt through a network.

[0043] This application can be used in numerous general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer computing devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0044] Figure 1 FIG. 4 is an alternative flowchart of the method for detecting obstacles in the airport clearance area provided by an embodiment of the present application. Figure 1 The method in FIG. 4 may include, but is not limited to, steps S101 to S105.

[0045] Step S101, obtaining the shielding parameter of the airport surveillance radar.

[0046] To facilitate the rapid and automated detection of obstacles in the airport clearance area, the shielding parameter of the airport surveillance radar is obtained as the basis for detection.

[0047] Step S102, controlling the pan-tilt head to move to the target posture according to the shielding parameter, wherein the installation position of the pan-tilt head is determined based on the installation position of the airport surveillance radar, and the pan-tilt head is used to carry a photographing device.

[0048] By setting the pan-tilt head at an appropriate position, the photographing device can photograph obstacles with a shielding angle greater than the target shielding angle for the airport surveillance radar. Among them, the installation position of the pan-tilt head is determined by the installation position of the airport surveillance radar.

[0049] Exemplarily, taking the pan-tilt camera as an example, if the airport surveillance radar is located in the radar tower, specifically, the pan-tilt camera can be installed at the base of the radar tower, and the installation position is horizontal or at the same height as the bottom of the airport surveillance radar. The installation is simple and easy to maintain, and the occupied area is also small.

[0050] In this way, based on the shielding parameter of the airport surveillance radar, the pan-tilt head can be reasonably guided to accurately move to the target posture so that the photographing device can perform high-precision photographing on the area that may be blocked by obstacles.

[0051] Before step S102 of some embodiments, the zero position of the pan-tilt head can also be calibrated, and the shooting angle of the shooting device can be calibrated.

[0052] To ensure that the images captured by the shooting device are stable and accurate, after installing the pan-tilt head, the zero position of the pan-tilt head can be calibrated, that is, the initial position of the pan-tilt head is set to zero, and the installation angle of the camera can be checked and adjusted through a level to calibrate the shooting angle of the shooting device, so that the visual center line of the shooting device is aligned with the zero line of the level, ensuring that the lens of the shooting device is parallel to the horizontal plane. In this way, the zero position of the pan-tilt head is aligned with the zero degree of the horizontal viewing angle of the shooting device, that is to say, when the pan-tilt head is at zero degree, its rotation axis and the visual axis of the shooting device are both parallel to the horizontal plane, and the shooting angle of the shooting device is exactly horizontal.

[0053] In some embodiments, in order to improve the accuracy and simplicity of obstacle detection in the airport clearance area, the occlusion parameter can be the target occlusion angle. Among them, according to relevant flight safety regulations, the occlusion angle of obstacles to the airport radar shall not exceed 0.25 degrees. Therefore, the target occlusion angle can be set to 0.25 degrees.

[0054] In step S102 of some embodiments, the pan-tilt head can be controlled to rotate at the target motion speed until the pitch angle of the pan-tilt head is the target occlusion angle.

[0055] The target posture can specifically be that the pitch angle of the pan-tilt head is equal to the target occlusion angle.

[0056] The pan-tilt head can have multiple motion modes. To avoid errors in the pan-tilt head moving to the target posture, the pan-tilt head is controlled to rotate at the target motion speed until the pitch angle of the pan-tilt head is the target occlusion angle.

[0057] The target motion speed can be a fixed motion speed. Among them, in order to facilitate accurately adjusting the pitch angle of the pan-tilt head to the target occlusion angle, the target motion speed can be a relatively small fixed motion speed. Exemplarily, for example, the pan-tilt head is controlled to start from the zero position and rotate at a relatively small fixed motion speed of 0.01 degrees / s until the pitch angle of the pan-tilt head reaches 0.25 degrees.

[0058] In this way, through this extremely detailed and slow motion control of the pan-tilt head, it is convenient to accurately adjust the pitch angle of the pan-tilt head to the target occlusion angle.

[0059] Step S103, control the pan-tilt head to stop moving to capture a target image through the shooting device.

[0060] When the pitching angle of the pan-tilt is adjusted to the target shielding angle, control the pan-tilt to stop moving and control the shooting device to take a picture to obtain a target image, so as to quickly implement the investigation of obstacles in the clearance area based on the target image.

[0061] It should be noted that when the pan-tilt is in the target posture, the target image captured by the shooting device can cover the picture of obstacles with a shielding angle greater than the target shielding angle for the airport surveillance radar.

[0062] Step S104: Perform segmentation processing on the target image through a pre-trained image segmentation model to obtain the foreground pixel point set of the target image.

[0063] The target image can be segmented through a pre-trained image segmentation model to obtain the foreground pixel point set of the target image, thereby improving the segmentation accuracy of the foreground pixel point set.

[0064] Exemplarily, the pre-trained image segmentation model can be a pre-trained YOLOv8Segmentation network.

[0065] Before step S104 in some embodiments, the untrained image segmentation model can be trained.

[0066] Exemplarily, the untrained image segmentation model can be the YOLOv8 Segmentation network. Specifically, the YOLOv8 Segmentation network can be iteratively trained using a preset image sample and its actual pixel-level label of the foreground. Effectively learn the predicted foreground pixel points of the image sample, where the image sample contains different foreground objects in the airport environment (such as trees, buildings, etc.), and the actual pixel-level label of the foreground refers to the pixel points of the foreground object marked for the image sample in a mask (mask) manner; thereby calculating the loss between the actual pixel-level label of the foreground and the predicted foreground pixel points, calculating the loss function of the YOLOv8 Segmentation network according to the loss, and then updating the parameters of the YOLOv8Segmentation network according to the loss function until the number of iterations is greater than the preset number threshold, and stopping the training of the YOLOv8 Segmentation network to obtain the trained YOLOv8 Segmentation network. The trained YOLOv8 Segmentation network can accurately segment the foreground pixel point set in the complex background of the airport environment.

[0067] In this way, by segmenting the foreground pixel point set from the target image, irrelevant interference factors in the target image can be effectively excluded. Subsequently, obstacle detection will become simpler and clearer. Compared with performing obstacle detection on the entire target image, the computational complexity is greatly reduced, thus significantly reducing the computational complexity of obstacle detection and improving the detection speed while saving computational resources.

[0068] Step S105: Perform obstacle detection in the clearance area on the foreground pixel point set.

[0069] The foreground pixel point set contains the main information of the obstacles. By focusing only on the foreground pixel point set for obstacle detection in the clearance area, irrelevant background information can be ignored, thereby providing more accurate and rapid obstacle detection and improving the efficiency and accuracy of obstacle detection.

[0070] In step S105 of some embodiments, the target image can be processed by detecting the midline to determine the horizontal midline of the target image; determining whether there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline; in the case where there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline, determining that there are obstacles that damage the airport clearance area; in the case where there are no foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline, determining that there are no obstacles that damage the airport clearance area.

[0071] When the pitching angle of the pan-tilt is the target shielding angle of the airport surveillance radar, it means that the horizontal center line of the visual imaging of the shooting device coincides with the boundary of the target shielding angle. The boundary of the target shielding angle refers to the ray emitted from the installation position point of the pan-tilt and having an angle with the horizontal reference line equal to the target shielding angle. At this time, the objects above the horizontal center line of the visual imaging exceed the boundary of the target shielding angle, that is, exceed the allowable range of the shielding angle of the airport surveillance radar, and are thus obstacles that damage the airport clearance area.

[0072] Based on this, the target image is processed by detecting the midline to determine the horizontal midline of the target image. The horizontal midline is the axis of symmetry of the target image in the horizontal direction; then it is detected whether there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline; in the case where there are no foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline, determining that there are no obstacles that damage the airport clearance area; in the case where there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline, the foreground pixel points whose height exceeds the horizontal midline are determined as obstacles that damage the airport clearance area.

[0073] For a better understanding of the above embodiments, please refer to Figure 2 , Figure 2 which is an application scenario example diagram for airport clearance area obstacle detection. In Figure 2In the schematic illustration, taking the scenario where there are woods in the surrounding environment of the airport as an example, the pan-tilt camera is installed at the base of the radar tower. The installation position is at the same horizontal level or the same height as the bottom of the airport surveillance radar. The allowable range of the shielding angle of the airport surveillance radar is <0.25 degrees, that is, the target shielding angle value is 0.25 degrees. Then, when the pitch angle of the pan-tilt camera is 0.25 degrees, the horizontal center line of the visual imaging of the pan-tilt camera coincides with the ray of 0.25 degrees. Trees with a height exceeding the horizontal center line of the visual imaging of the pan-tilt camera will exceed the ray of 0.25 degrees, which are obstacles that damage the airport clearance area. At this time, the target image captured by the pan-tilt camera is as Figure 3 shown. In the target image Figure 3 shown, the trees are the foreground objects and the background is the airspace. By using a pre-trained image segmentation model to perform segmentation processing on the target image, it is possible to distinguish the pixel point set {F} of the trees from the pixel point set {B} of the background airspace. Perform midline detection processing on the target image to determine the horizontal midline of the target image, and perform segmentation processing on the pixel point set {F} of the trees with the horizontal midline as the dividing line, obtaining the pixel points {F+} above the horizontal midline and the pixel points {F-} below the horizontal midline in the pixel point set {F} of the trees. The pixel points {F+} are the pixel points of the trees in the woods that exceed the ray of 0.25 degrees, representing obstacles that damage the airport clearance area, and the pixel points {F-} are the pixel points of the safe trees in the woods that do not damage the airport clearance area.

[0074] In this way, by deploying the pan-tilt with the shooting device at an appropriate specific position and adjusting the pitch angle of the pan-tilt to the target shielding angle of the airport surveillance radar, it is possible to enable the shooting device to collect target images from a specific perspective in real time, and through the trained image segmentation model, segment the foreground pixel point set of the target image, so as to directly perform accurate obstacle detection on the foreground pixel point set based on the horizontal midline of the target image, thereby providing a more convenient and accurate obstacle detection with lower detection costs.

[0075] In the case of detecting obstacles that damage the airport clearance area, the foreground pixel points with a height exceeding the horizontal midline can be marked in the target image in a masking manner, so as to send an alarm message indicating that there are obstacles in the airport clearance area, helping airport staff, pilots or air traffic controllers to timely discover and eliminate potential flight safety hazards, and avoiding accidents caused by the presence of obstacles, thereby ensuring the normal operation and flight safety of the airport.

[0076] Therefore, the method for detecting obstacles in the airport clearance area provided by the above embodiment realizes real-time intelligent detection of obstacles in the clearance area in an automated manner, without manual intervention, can be detected all-weather at any time, and is particularly suitable for complex airport environments, and can better cope with changes in different times, weather, lighting, etc., continuously ensuring flight safety.

[0077] The method for detecting obstacles in the airport clearance area provided by the above embodiments can be applied in the low-altitude economy field, for example, in flight activities of the low-altitude economy such as drone flight, air logistics distribution, and agricultural spraying. Through accurate obstacle detection, this method can provide clearer obstacle details for the flight activities of the low-altitude economy, which not only helps to effectively reduce accidents in flight activities, but also can optimize flight paths and provide technical support for the development of the low-altitude economy.

[0078] The method for detecting obstacles in the airport clearance area provided by the above embodiments obtains the shielding parameters of the airport surveillance radar; according to the shielding parameters, controls the pan-tilt to move to the target posture, wherein the installation position of the pan-tilt is determined based on the installation position of the airport surveillance radar, and the pan-tilt is used to carry a photographing device; controls the pan-tilt to stop moving to take a photograph through the photographing device to obtain a target image; performs segmentation processing on the target image through a pre-trained image segmentation model to obtain a foreground pixel point set of the target image; performs obstacle detection on the foreground pixel point set. On the one hand, through the shielding parameters of the airport surveillance radar, reasonably guides the pan-tilt to accurately move to the target posture, so that the photographing device carried by the pan-tilt can take a target image that can cover the area that may be blocked by obstacles in real time; on the other hand, through the pre-trained image segmentation model, accurately segments the foreground pixel point set from the target image, which can effectively eliminate irrelevant interference factors in the target image, so as to only focus on the foreground pixel point set for obstacle detection, improving the efficiency and accuracy of obstacle detection in the clearance area. Thus, through pan-tilt control, intelligent and automatic obstacle detection in the airport clearance area is realized, thereby reducing the cost of obstacle detection in the airport clearance area and improving the accuracy, simplicity and automation of obstacle detection in the airport clearance area.

[0079] Please refer to Figure 4 , Figure 4 which is a schematic block diagram of an obstacle detection device in the airport clearance area provided by an embodiment of the present application. The obstacle detection device in the airport clearance area can be configured in a computer device and is used to execute the aforementioned method for detecting obstacles in the airport clearance area.

[0080] As Figure 4 shown, the obstacle detection device 400 in the airport clearance area includes: a parameter acquisition module 401, a pan-tilt control module 402, an image capture module 403, an image segmentation module 404, and an obstacle detection module 405.

[0081] The parameter acquisition module 401 is used to obtain the shielding parameters of the airport surveillance radar;

[0082] The pan-tilt control module 402 is used to control the pan-tilt to move to the target posture according to the shielding parameter, wherein the installation position of the pan-tilt is determined based on the installation position of the airport surveillance radar, and the pan-tilt is used to carry a photographing device;

[0083] The image capturing module 403 is used to control the pan-tilt to stop moving and capture a target image through the photographing device;

[0084] The image segmentation module 404 is used to perform segmentation processing on the target image through a pre-trained image segmentation model to obtain a foreground pixel point set of the target image;

[0085] The obstacle detection module 405 is used to detect obstacles in the clearance area for the foreground pixel point set.

[0086] In one embodiment, the shielding parameter includes a target shielding angle.

[0087] In one embodiment, the pan-tilt control module 402 is specifically configured to:

[0088] Control the pan-tilt to perform rotational movement at a target movement speed until the pitch angle of the pan-tilt is the target shielding angle.

[0089] In one embodiment, the obstacle detection module 405 is specifically configured to:

[0090] Perform center line detection processing on the target image to determine the horizontal center line of the target image;

[0091] Detect whether there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal center line;

[0092] In the case that there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal center line, it is determined that there are obstacles damaging the airport clearance area;

[0093] In the case that there are no foreground pixel points in the foreground pixel point set whose height exceeds the horizontal center line, it is determined that there are no obstacles damaging the airport clearance area.

[0094] In one embodiment, the airport clearance area obstacle detection device 400 further includes an alarm information sending module, and the alarm information sending module is used to:

[0095] Send an alarm information indicating that there are obstacles in the airport clearance area.

[0096] In one embodiment, the trained image segmentation model includes a trained YOLOv8Segmentation network.

[0097] In one embodiment, the airport clearance area obstacle detection device 400 further includes a calibration module, and the calibration module is configured to:

[0098] Calibrate the zero-degree position of the pan-tilt head and calibrate the shooting angle of the shooting device.

[0099] Among them, each module in the above-mentioned airport clearance area obstacle detection device 400 corresponds to each step in the above-mentioned embodiment of the airport clearance area obstacle detection method, and its functions and implementation processes will not be elaborated here one by one.

[0100] The airport clearance area obstacle detection device 400 can execute the airport clearance area obstacle detection method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved by the airport clearance area obstacle detection method provided in the embodiments of the present application can be realized. For details, please refer to the previous embodiments and will not be elaborated here.

[0101] The methods and devices of the present application can be used in many general-purpose or special-purpose computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that execute specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment, where tasks are executed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0102] Exemplarily, the above methods and devices can be implemented in the form of a computer program, and the computer program can run on a computer device as shown in Figure 5 the following figure.

[0103] Please refer to Figure 5 , Figure 5 which is a schematic block diagram of the structure of a computer device provided in the embodiments of the present application.

[0104] Please refer to Figure 5 , the computer device includes a processor and a memory connected through a system bus. Among them, the memory can include a non-volatile storage medium and an internal memory.

[0105] The processor is used to provide computing and control capabilities to support the operation of the entire computer device.

[0106] The internal memory provides an environment for the operation of a computer program in a non-volatile storage medium. When the computer program is executed by a processor, the processor can execute any one of the methods for detecting obstacles in the airport clearance area.

[0107] It should be understood that the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0108] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0109] Obtain the shielding parameters of the airport surveillance radar;

[0110] According to the shielding parameters, control the pan-tilt to move to the target posture. Among them, the installation position of the pan-tilt is determined based on the installation position of the airport surveillance radar, and the pan-tilt is used to carry a photographing device;

[0111] Control the pan-tilt to stop moving to take a photograph through the photographing device to obtain a target image;

[0112] Through a pre-trained image segmentation model, perform segmentation processing on the target image to obtain a foreground pixel point set of the target image;

[0113] Perform an obstacle search in the clearance area on the foreground pixel point set.

[0114] In one embodiment, the shielding parameter includes a target shielding angle.

[0115] In one embodiment, when the processor implements controlling the pan-tilt to move to the target posture according to the shielding parameters, it is used to implement:

[0116] Control the pan-tilt to rotate at a target moving speed until the pitch angle of the pan-tilt is the target shielding angle.

[0117] In one embodiment, when the processor implements the clearance area obstacle detection for the foreground pixel point set, it is used to implement:

[0118] Perform a midline detection process on the target image to determine the horizontal midline of the target image;

[0119] Detect whether there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline;

[0120] In the case where there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline, determine that there are obstacles damaging the airport clearance area;

[0121] In the case where there are no foreground pixel points in the foreground pixel point set whose height exceeds the horizontal midline, determine that there are no obstacles damaging the airport clearance area.

[0122] In one embodiment, after the processor implements the determination that there are obstacles damaging the airport clearance area, it is further used to implement:

[0123] Send an alarm message indicating that there are obstacles in the airport clearance area.

[0124] In one embodiment, the trained image segmentation model includes a trained YOLOv8Segmentation network.

[0125] In one embodiment, before the processor implements the control of the pan-tilt to move to the target pose according to the shielding parameter, it is further used to implement:

[0126] Calibrate the zero-degree position of the pan-tilt and calibrate the shooting angle of the shooting device.

[0127] This computer device can execute the airport clearance area obstacle detection method provided in the embodiments of the present application. Therefore, the beneficial effects that can be achieved by the airport clearance area obstacle detection method provided in the embodiments of the present application can be realized. For details, please refer to the previous embodiments and will not be elaborated here.

[0128] The embodiments of the present application further provide a computer-readable storage medium.

[0129] A computer program is stored on the computer-readable storage medium of the present application. When the computer program is executed by a processor, the steps of the airport clearance area obstacle detection method as described above are implemented.

[0130] Among them, the computer-readable storage medium may be the internal storage unit of the airport clearance obstacle detection device or computer equipment described in the foregoing embodiments, such as the hard disk or memory of the airport clearance obstacle detection device or computer equipment. The computer-readable storage medium may also be an external storage device of the airport clearance obstacle detection device or computer equipment, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital Card (SDCard), a Flash Card, etc. equipped on the airport clearance obstacle detection device or computer equipment.

[0131] Since the computer program stored in the computer-readable storage medium can execute any one of the airport clearance obstacle detection methods provided in the embodiments of the present application, the beneficial effects that can be achieved by any one of the airport clearance obstacle detection methods provided in the embodiments of the present application can be realized. For details, see the foregoing embodiments and will not be elaborated herein.

[0132] Furthermore, the computer-readable storage medium may mainly include a storage program area and a storage data area. Among them, the storage program area may store an operating system, application programs required for at least one function, etc.; the storage data area may store data created according to the use of blockchain nodes, etc.

[0133] The blockchain referred to in the present application is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm. Blockchain, in essence, is a decentralized database, a string of data blocks generated by using cryptographic methods. Each data block contains information about a batch of network transactions, which is used to verify the validity (anti-counterfeiting) of the information and generate the next block. The blockchain may include a blockchain underlying platform, a platform product service layer, an application service layer, etc.

[0134] It should be noted that in this article, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or system. Without further limitations, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or system including the element.

[0135] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present application.

Claims

1. A method for checking obstacles in an airport clear area, characterized in that: The method comprises: Obtain the shielding parameters of the airport surveillance radar; According to the shielding parameter, control the gimbal to move to a target posture, wherein the setting position of the gimbal is determined based on the setting position of the airport surveillance radar, and the gimbal is used to carry a shooting device; Controlling the pan / tilt head to stop moving so as to shoot with the shooting device to obtain a target image; Segmenting the target image using a pre-trained image segmentation model to obtain a foreground pixel point set of the target image; Checking the foreground pixel set for obstacles in the clear area; Wherein, the shielding parameters include a target shielding angle; The step of controlling the pan / tilt platform to move to a target posture according to the shielding parameter comprises: Controlling the pan / tilt platform to rotate at a target movement speed until the pitch angle of the pan / tilt platform reaches the target shielding angle; The checking of obstacles in the clear area of ​​the foreground pixel set includes: Performing centerline detection processing on the target image to determine the horizontal centerline of the target image; Detecting whether there is a foreground pixel point in the foreground pixel point set whose height exceeds the horizontal center line; In the case where there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal center line, it is determined that there is an obstacle that destroys the airport clear zone; In the case that there is no foreground pixel point in the foreground pixel point set whose height exceeds the horizontal center line, it is determined that there is no obstacle that damages the airport clear zone.

2. The method according to claim 1, characterized in that After determining that there are obstacles that damage the airport clear zone, the method further includes: Issue a warning message that there are obstacles in the airport clear area.

3. The method according to any one of claims 1 to 2, characterized in that: The trained image segmentation model includes a trained YOLOv8 Segmentation network.

4. The method according to any one of claims 1 to 2, characterized in that: Before controlling the pan / tilt platform to move to the target posture according to the shielding parameter, the method further includes: The zero-degree position of the pan / tilt is calibrated, and the shooting angle of the shooting device is calibrated.

5. An obstacle detection device for an airport clear area, characterized in that: The device comprises: A parameter acquisition module is used to obtain the shielding parameters of the airport surveillance radar; A gimbal control module, used for controlling the gimbal to move to a target posture according to the shielding parameter, wherein the setting position of the gimbal is determined based on the setting position of the airport surveillance radar, and the gimbal is used to carry a shooting device; An image shooting module, used for controlling the pan / tilt head to stop moving so as to shoot through the shooting device to obtain a target image; An image segmentation module is used to segment the target image using a pre-trained image segmentation model to obtain a foreground pixel point set of the target image; An obstacle detection module is used to detect obstacles in the clear area of ​​the foreground pixel set; Wherein, the shielding parameters include a target shielding angle; The pan / tilt control module is further used to control the pan / tilt to rotate at a target movement speed until the pitch angle of the pan / tilt is the target shielding angle; The obstacle detection module is also used to perform centerline detection processing on the target image to determine the horizontal centerline of the target image; detect whether there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal centerline; if there are foreground pixel points in the foreground pixel point set whose height exceeds the horizontal centerline, determine that there are obstacles that damage the airport's clear zone; if there are no foreground pixel points in the foreground pixel point set whose height exceeds the horizontal centerline, determine that there are no obstacles that damage the airport's clear zone.

6. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the airport clear zone obstacle detection method according to any one of claims 1 to 4 when executing the computer program.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the airport clearance zone obstacle detection method described in any one of claims 1 to 4 is implemented.

Images