Automated Detection and Intelligent Bird Deterrence Device and Method for Airport Bird Situation

Abstract

The present invention discloses an automatic detection and intelligent bird-repelling device and method for airport birds, wherein an automatic detection method for airport birds comprises: collecting airport airspace environment data in real time through a multi-source sensor array, and preprocessing the environment data to generate a fused data set; constructing a target detection model based on a deep learning algorithm to identify bird targets on the fused data set, extracting target feature information, the target feature information including the location, movement trajectory, number and type of birds; combining the airport flight take-off and landing time series data with the target feature information, calculating the threat level of bird activities to flights through a risk assessment model established based on fuzzy logic and Bayesian network; triggering a graded warning signal according to the threat level, and linking the bird-repelling device to perform a directional bird-repelling operation. The present invention forms an automatic detection and emergency prevention and control system for airport birds, improves the detection accuracy, warning accuracy and bird-repelling efficiency of bird strike risks, and ensures the safety of aviation operations.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic detection and risk prevention and control of bird conditions at airports, and in particular to an automatic detection and intelligent bird repelling device and method for bird conditions at airports. Background Art

[0002] In recent years, with the rapid development of the global air transportation industry, the flight volume at airports has continued to increase, and flight safety accidents caused by bird strikes have occurred frequently. Bird condition monitoring and prevention have gradually become one of the core issues in airport safety management; traditional airport bird condition monitoring methods generally use manual inspections, ground telescope observations, single radar or single camera detection means, which have problems such as limited detection range, weak target recognition ability, insufficient real-time performance, and low monitoring accuracy, and are difficult to meet the high standards of safety requirements for modern aviation operations.

[0003] To cope with the increasingly complex and variable laws of bird activities, the existing technology has gradually developed towards multi-sensor fusion detection, and some bird monitoring technologies combining radar and optical devices or based on machine vision algorithms have emerged. Although the ability to detect bird targets has been improved to a certain extent, there is still a large room for improvement in the information fusion accuracy, complex scene recognition ability, and accuracy of risk assessment in the existing technical solutions.

[0004] Specifically, the existing airport bird condition monitoring technologies generally have the following deficiencies: First, the multi-source sensor data fusion is not deep enough, and the multi-modal data cannot be fully coordinated, resulting in low comprehensive utilization efficiency of environmental data and affecting the accuracy of target detection; second, in the process of target recognition, there is a lack of accurate extraction of comprehensive feature information such as the flight trajectory, species, and quantity of birds, and it is impossible to effectively predict bird behavior and accurately divide the risk level; third, in the aspect of bird activity risk assessment, most methods only use simple rule models, and fail to effectively integrate airport flight takeoff and landing data for real-time threat assessment, and cannot accurately and quickly form an effective early warning for flight safety.

[0005] Therefore, how to effectively improve the accuracy of automatic detection of bird conditions at airports and the accuracy of bird strike risk prediction, and further realize efficient early warning and bird repelling linkage is an important technical problem that needs to be solved urgently at present.

[0006] In summary, the existing airport bird condition detection technologies have problems such as insufficient detection accuracy, low data fusion efficiency, and untimely risk early warning. The present invention improves the accuracy of airport bird condition detection and risk assessment by using multi-source sensor fusion, deep learning target recognition, and a risk assessment model combining fuzzy logic and Bayesian network, and realizes timely and effective hierarchical early warning and bird repelling linkage. Summary of the Invention

[0007] The purpose of this section is to outline some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Simplifications or omissions may be made in this section, the abstract of the specification, and the title of the invention to avoid obscuring the purpose of this section, the abstract of the specification, and the title of the invention, but such simplifications or omissions shall not be used to limit the scope of the present invention.

[0008] In view of the above existing problems, the present invention is proposed.

[0009] To solve the above technical problems, the present invention provides the following technical solution: An automated bird situation detection and intelligent bird repelling method for airports, including: real-time collecting airport airspace environment data through a multi-source sensor array, and preprocessing the environment data to generate a fused data set;

[0010] Constructing an object detection model based on a deep learning algorithm to identify bird targets in the fused data set and extract target feature information, where the target feature information includes bird position, movement trajectory, quantity, and species;

[0011] Combining the airport flight takeoff and landing timing data with the target feature information, and calculating the threat level of bird activities to flights through a risk assessment model established based on fuzzy logic and Bayesian network;

[0012] Triggering a hierarchical warning signal according to the threat level, and linking with bird repelling equipment to perform directional bird repelling operations.

[0013] As a preferred solution of the automated bird situation detection method for airports of the present invention, the multi-source sensor array includes radar equipment, visible light cameras, infrared thermal imagers, and sonar detectors, and the airport airspace environment data collected in real time by the multi-source sensor array includes radar data, visible light image data, infrared thermal imaging data, sonar data, and meteorological information around the airport runway;

[0014] Among them, the radar data includes distance, radial velocity, and azimuth angle, the visible light image data includes frame sequence images, target pixel coordinates, and color texture features, the infrared thermal imaging data includes target thermal radiation intensity and thermal imaging coordinates, the sonar data includes echo intensity, delay time, and target azimuth, and the meteorological information around the airport runway includes wind direction, wind speed, and visibility.

[0015] As a preferred solution of the automated bird situation detection method for airports of the present invention, preprocessing the environment data to generate a fused data set includes:

[0016] Performing unified time calibration on the environment data;

[0017] Perform band-pass filtering and background noise suppression on radar, infrared, and sonar data, and perform background modeling and moving target segmentation on visible light images;

[0018] According to the coordinate systems of different sensors, convert the target detection results to a unified spatial coordinate system, and perform association and redundancy removal processing on the multi-source tracking results through the Kalman filtering algorithm;

[0019] Perform secondary screening on targets with low confidence and eliminate duplicate targets;

[0020] Perform bounding box annotation on birds in visible light images and infrared thermal images;

[0021] Enhance visible light and infrared data by using image flipping, rotation, brightness adjustment, and noise addition methods;

[0022] Match the processed data with the annotation information according to the time stamp to form a unified sequential data set, which is the fusion data set.

[0023] As a preferred solution of the airport bird situation automatic detection method of the present invention, a target detection model is constructed based on a deep learning algorithm to identify bird targets in the fusion data set and extract target feature information, including:

[0024] Use a bidirectional long short-term memory network to perform multi-level fusion on radar, infrared, and visible light features;

[0025] For the small-scale and easily overlapping features of bird targets, set an attention mechanism to enhance the features of key regions;

[0026] Use the labeled fusion data set for supervised training, and the training loss function adopts a multi-task weighted form:

[0027]

[0028] Among them, is the classification loss, is the bounding box regression loss, is the multi-modal consistency loss; , , are the weighting coefficients of the classification loss, the bounding box regression loss, and the multi-modal consistency loss respectively;

[0029] Perform multi-modal matching on the preprocessed video frames, infrared thermal imaging frames, and radar / sonar data, and the network outputs the predicted positions, species, and confidence levels of bird targets;

[0030] If the confidence level is higher than the threshold , it is determined as a valid bird target, and its flight trajectory, quantity, and shape characteristics are further extracted;

[0031] Index the recognized target information by the target ID to generate a target feature information set including the position, movement trajectory, quantity, and species of birds.

[0032] As a preferred solution of the airport bird situation automatic detection method described in the present invention, the recognition and extraction of the target detection model include:

[0033] Track the same target detected in consecutive video frames or by radar, and use the Kalman filtering algorithm to obtain an accurate movement trajectory;

[0034] The position at each moment in the trajectory and speed are discretely stored to form a trajectory sequence;

[0035] Statistically analyze the flight speed, flight altitude, and direction to determine whether there are behavioral patterns of birds quickly skimming over the runway or flying in groups;

[0036] Combine the deep learning classification network with biological prior knowledge to classify and identify the body shape, feather characteristics, and thermal distribution information of birds in visible light and infrared images;

[0037] According to the recognition results, classify the bird species into different categories such as small finches, raptors, gulls, wading birds, etc., and label them with cluster behavior labels or night activity frequency labels.

[0038] As a preferred solution of the airport bird situation automatic detection method described in the present invention, combine the airport flight takeoff and landing time sequence data with the target feature information, and calculate the threat level of bird activities to flights through a risk assessment model established based on fuzzy logic and Bayesian network, including:

[0039] Set key indicators such as the number of birds n, population density , the distance d from the nearest runway center, and the flight altitude h, and establish corresponding fuzzy sets for each indicator;

[0040] Use the membership function to perform fuzzy processing on each indicator:

[0041]

[0042] where a and b are interval thresholds;

[0043] Input the fuzzified indicators into the Bayesian network nodes to form event conditions;

[0044] Combine the aircraft takeoff and landing frequency and takeoff and landing time information in the flight takeoff and landing time sequence data to calculate the posterior probability of bird strike risk;

[0045] The evaluation values ​​of each indicator output by fuzzy logic and the posterior probability of Bayesian network are combined to determine the threat level of bird activities to flights according to the weighted rule;

[0046] If the comprehensive score exceeds the preset upper threshold, it is judged as high risk or extremely high risk;

[0047] If the comprehensive score is in the middle range, it is judged as medium risk;

[0048] If the comprehensive score is below the lower threshold, it is judged as low risk.

[0049] As a preferred solution of the automatic detection method for bird situation at an airport according to the present invention, the threat levels include:

[0050] When the comprehensive score is in the range of [0, 0.3), it is judged as low threat level L1, which means that the number of birds is very small and far away from the critical areas of the runway, and basically does not pose a safety impact on aircraft takeoff and landing;

[0051] When the comprehensive score is in [0.3, 0.5), it is judged as medium threat level L2, then the number of birds is moderate or occasionally enters the runway safety buffer zone, and monitoring and regular warning are required;

[0052] When the comprehensive score is between [0.5, 0.7), it is judged as a high threat level L3, which means that the bird activities are frequent and have obviously approached the flight path, posing a potential risk to flights that are taking off or about to take off or land.

[0053] When the comprehensive score is ≥0.7, it is judged as an extremely high threat level L4, then large flocks of birds repeatedly appear on the runway and its surroundings, posing a serious threat to flight safety.

[0054] As a preferred solution of the automatic detection method for bird situation at an airport of the present invention, a graded warning signal is triggered according to the threat level, and a bird-repelling device is linked to perform a directional bird-repelling operation, including:

[0055] When the threat level is L1, only text / voice reminders are sent to tower personnel to remind them to stay focused;

[0056] When the threat level is L2, an audio signal or light flashing warning is triggered to remind ground and flight crews to pay close attention to the bird situation at the airport;

[0057] When the threat level is L3, a high-frequency harsh sound wave or strong light warning is triggered, and real-time risk warnings are issued to flights about to take off and land;

[0058] When the threat level is L4, the highest level emergency alarm is triggered, and the control department is advised to delay flight takeoff and landing, and immediately activate a linkage mechanism of multiple bird-repelling measures.

[0059] As a preferred solution of the automatic detection method for bird situation at an airport according to the present invention, the linked bird-repelling device performs a directional bird-repelling operation, including:

[0060] When the threat level is ≥ L2, the sonic repelling device will be automatically activated to send out adjustable frequency high-decibel sonic interference;

[0061] When the threat level is ≥ L3, in addition to sound wave interference, laser or strong beam bird repellent devices are turned on, and bionic sounds such as the calls of birds of prey can be played to repel them;

[0062] When the threat level is L4, multiple devices are activated simultaneously to implement a comprehensive bird repellent solution including laser, strong light beam, bionic natural enemy and aerosol.

[0063] The present invention also discloses an intelligent bird-repelling device based on the aforementioned automatic detection method for bird conditions at an airport, comprising a monitoring module arranged on a runway, the monitoring module comprising a radar device, a visible light camera, an infrared thermal imager and a sonar detector, and the monitoring modules are all connected to a control host;

[0064] It also includes an early warning module, which includes a tower display screen, a voice player, and warning lights arranged on both sides of the runway;

[0065] The device also includes a bird-repelling execution module, which includes a frequency-adjustable sound wave transmitter, a strong light, a bionic sound player and an aerosol generator.

[0066] Beneficial effects of the present invention:

[0067] 1. The radar equipment, visible light camera, infrared thermal imager and sonar detector work together to realize multi-dimensional and multi-modal comprehensive perception of airport bird information, which effectively makes up for the problem of limited detection range of a single sensor or missed target detection and false alarm. The pre-processed data fusion process further eliminates the data inconsistency between sensors, provides higher quality and more reliable environmental data, and thus improves the accuracy and stability of subsequent bird target detection;

[0068] 2. Through the precise identification and dynamic tracking of bird targets under complex backgrounds and multi-target interference conditions, the accuracy and reliability of bird activity identification are effectively improved. At the same time, the bird activity tracks, quantity and bird species characteristics are accurately extracted, which further provides a sufficient and accurate data basis for subsequent risk assessment, helps to accurately judge bird behavior patterns and clarify the potential risk types posed to airport flight safety;

[0069] 3. By incorporating flight departure and arrival time data into the risk assessment process, the intersection of aircraft operating status with the spatial and temporal activities of birds is effectively considered. The uncertainty issues of qualitative and quantitative indicators are processed through fuzzy logic, and Bayesian networks are used to quantitatively infer risk probabilities. Thus, a refined and real-time analysis of the impact of bird activities on airport flight safety is comprehensively achieved, the risk levels are accurately classified, and the timeliness of early warning judgments for bird strike events is greatly improved.

[0070] 4. Through the direct linkage between the risk assessment results and the actual prevention and control measures at the airport, different levels of early warning signals are automatically triggered in real time according to the risk levels, and corresponding bird repelling measures are implemented, thereby achieving the optimal scheduling and precise implementation of airport bird repelling resources, and avoiding the defects of slow response and resource waste in traditional manual inspections or single early warning methods; further enhancing the airport's rapid response and efficient disposal capabilities for sudden bird strike risks, and significantly improving the airport's flight safety prevention and control level. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. Among them:

[0072] Figure 1 It is a schematic flowchart of the airport bird situation automatic detection method shown in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0073] To make the above objects, features, and advantages of the present invention more obvious and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings of the specification. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0074] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0075] Many specific details are set forth in the following description to facilitate a thorough understanding of the present invention, but the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0076] According to an embodiment of the present invention, in combination with Figure 1 the flowchart shown, an airport bird situation automatic detection and intelligent bird repelling method includes:

[0077] S1. Real-time collect the airport airspace environment data through a multi-source sensor array, and preprocess the environment data to generate a fusion dataset. It should be noted in this step that:

[0078] The multi-source sensor array includes radar equipment, visible light cameras, infrared thermal imagers, and sonar detectors. The airport airspace environment data collected in real-time by the multi-source sensor array includes radar data, visible light image data, infrared thermal imaging data, sonar data, and meteorological information around the airport runway;

[0079] Among them, the radar data includes distance, radial velocity, and azimuth angle. The visible light image data includes frame sequence images, target pixel coordinates, and color texture features. The infrared thermal imaging data includes target thermal radiation intensity and thermal imaging coordinates. The sonar data includes echo intensity, delay time, and target azimuth. The meteorological information around the airport runway includes wind direction, wind speed, and visibility;

[0080] As an example, the radar equipment includes multi-beam scanning radar and pulsed Doppler radar, which are used to detect the flight speed, distance, and azimuth of bird targets within a range of 0.5 km to 10 km;

[0081] As an example, the visible light camera includes a high-resolution dynamic imaging module, which is used to obtain the morphological characteristics and activity videos of birds within a visible range of 0 to 2 km;

[0082] As an example, the infrared thermal imager includes mid-wave infrared and long-wave infrared imaging modules, which are used to detect the thermal signal characteristics of birds within a range of 0 to 1.5 km under night / low light conditions;

[0083] As an example, the sonar detector includes sonar transmitting and receiving units distributed in the horizontal and vertical directions, which are used to identify and locate the acoustic echo characteristics of birds within a range of 0 to 1 km.

[0084] In an alternative embodiment, by preprocessing the environment data, a fusion dataset is generated, including:

[0085] Perform unified time calibration on the environment data;

[0086] Perform band-pass filtering and background noise suppression on radar, infrared, and sonar data, and perform background modeling and moving target segmentation on visible light images;

[0087] According to the coordinate systems of different sensors, convert the target detection results to a unified spatial coordinate system, and implement the association and redundancy removal processing of multi-source tracking results through the Kalman filtering algorithm;

[0088] Perform secondary screening on targets with low confidence, and eliminate duplicate targets;

[0089] Perform bounding box annotation on birds in visible light images and infrared thermal images;

[0090] Enhance visible light and infrared data using methods such as image flipping, rotation, brightness adjustment, and noise addition;

[0091] Match the processed data with the annotation information according to the timestamp to form a unified sequential dataset, which is the fusion dataset.

[0092] S2. Construct an object detection model based on a deep learning algorithm to identify bird targets in the fusion dataset and extract target feature information, where the target feature information includes the position, movement trajectory, quantity, and species of the birds. Among them, it should be noted in this step that:

[0093] Use a bidirectional long short-term memory network to perform multi-level fusion of radar, infrared, and visible light features;

[0094] For the small-scale and easily overlapping features of bird targets, set an attention mechanism to enhance the features of key regions;

[0095] Use the annotated fusion dataset for supervised training, and the training loss function adopts a multi-task weighted form:

[0096]

[0097] Among them, is the classification loss, is the bounding box regression loss, is the multi-modal consistency loss; , , are the weighting coefficients of the classification loss, bounding box regression loss, and multi-modal consistency loss respectively;

[0098] Perform multi-modal matching on the preprocessed video frames, infrared thermal imaging frames, and radar / sonar data, and the network outputs the predicted position, species, and confidence of the bird targets;

[0099] If the confidence is higher than the threshold , it is determined as a valid bird target, and further extract its flight trajectory, quantity, and shape features;

[0100] Index the identified target information through the target ID to generate a target feature information set including the position, movement trajectory, quantity, and species of the birds.

[0101] Furthermore, the identification and extraction of the object detection model include:

[0102] Track the trajectory of the same target detected in consecutive video frames or by radar, and use the Kalman filter algorithm to obtain an accurate movement trajectory;

[0103] Discretize and store the positions and velocities at each moment in the trajectory to form a trajectory sequence;

[0104] Statistically analyze the flight speed, flight altitude, and direction to determine whether there are behavioral patterns such as birds quickly skimming over the runway and forming flock flights;

[0105] Combine a deep learning classification network with prior biological knowledge to classify and identify the body size, feather characteristics, and thermal distribution information of birds in visible light and infrared images;

[0106] According to the recognition results, classify bird species into different categories such as small finches, raptors, gulls, wading birds, etc., and label them with flock behavior labels or nocturnal activity frequency labels.

[0107] Specifically, each detected bird target is assigned a unique ID;

[0108] For the same target detected in different frames or by different sensors, match and merge them into different time records under the same ID;

[0109] For each target ID, record the key information of position, movement trajectory, quantity, and species, and output it as a unified data structure. For example:

[0110]

[0111] Among them, represents the position of the target at the current moment in the spatial coordinate system, represents the movement trajectory sequence from the initial detection to the current moment, represents the number of birds in the same group or within the same frame, represents the specific bird species classification, such as finches, raptors, gulls, wading birds, then includes additional labels such as whether it is a flock flight and nocturnal activity.

[0112] As an example, use the Kalman filter algorithm to track the same gull target in consecutive frames to obtain the positions and velocities at each moment within 5 seconds. If the average speed is 12 m / s and the direction is stable, it is judged that its flight is normal and has not changed significantly;

[0113] If more than 10 gull targets are continuously detected in the same area and gather in a similar flight direction and altitude, label it as "gull flock activity" to remind subsequent risk assessment to pay attention to the possible phenomenon of flock skimming near the runway safety area;

[0114] Use a deep learning classification network to perform secondary recognition on high-resolution captured images, confirm the body size characteristics and feather colors of the birds, and match them with the infrared thermal distribution. If the characteristics match those of a raptor, update the label to Hawk;

[0115] If a large number of infrared thermal targets are detected moving during the night time period (e.g., 23:00~05:00), append the "night activity frequency" label;

[0116] Exemplarily, the generated data record is:

[0117]

[0118] Among them, Indicates that the category is seagull, Indicates the night activity frequency;

[0119] The above information indicates that the target with ID = 0027 is a single seagull, whose position has changed sequentially in the past 2 seconds and there is no group flight behavior.

[0120] S3. Combine the airport flight takeoff and landing timing data with the target feature information, and calculate the threat level of bird activities to flights through a risk assessment model established based on fuzzy logic and Bayesian network. Among them, it should be noted in this step that:

[0121] Set key indicators such as the number of birds n, population density , the distance d to the nearest runway center, and the flight height h, and establish corresponding fuzzy sets for each indicator;

[0122] Exemplarily, taking the number of birds n as an example, it is set as:

[0123] : The number of birds is very small;

[0124] : The number of birds is medium;

[0125] : The number of birds is huge;

[0126] Adopt the membership function to perform fuzzy processing on each indicator:

[0127]

[0128] Among them, a and b are interval thresholds;

[0129] It should be noted that for the four key indicators calculate the fuzzy membership degree values respectively, and convert each indicator into the corresponding fuzzy linguistic variable to form the fuzzy bird activity information ;

[0130] For example, if and the preset interval threshold is , then , which means a large number of birds;

[0131] Let represent the condition of the bird activity event comprehensively obtained from the fuzzy inference result of ;

[0132] Let represent the airport flight take-off and landing time series data, including the take-off and landing frequencies and times of flights within the current or future time;

[0133] Let represent the bird strike threat event level, taking ;

[0134] In the embodiments of the present invention, through a risk assessment model, the posterior probability of a specific threat level occurring under given bird activity conditions and flight take-off and landing time series information is calculated, and the following mathematical expression formula is exemplarily given:

[0135]

[0136]

[0137]

[0138] Among them, represents the prior probability of observing specific bird activities under given threat levels and flight time series conditions, represents the prior probability of a certain threat level occurring under given flight take-off and landing frequencies, is the normalization term, corresponding to the overall probability of a certain bird activity occurring under given flight conditions;

[0139] By integrating the evaluation values of each index output by fuzzy logic and the posterior probability of the Bayesian network, the threat level of bird activities to flights is determined according to the weighting rule; that is, on the basis of fuzzy membership processing and the posterior probability of the Bayesian network, the results are further weighted and combined to obtain the final comprehensive score S:

[0140]

[0141] Among them, is the weighted average value obtained by comprehensively calculating the fuzzy index, , is the weight factor, which is used to find a balance between the fuzzy logic score and the probability inference result;

[0142] When S is relatively high, it indicates that the overlap between bird activities and flight operations is significant, and the risk increases accordingly.

[0143] Combined with the value of the final score S, map it to the interval [0, 1]. Further, the threat levels include:

[0144] When the comprehensive score is in the range of [0, 0.3), it is determined as the low threat level L1, which means that the number of birds is extremely small and far from the critical runway area, and basically has no safety impact on aircraft takeoff and landing.

[0145] When the comprehensive score is in the range of [0.3, 0.5), it is determined as the medium threat level L2, which means that the number of birds is moderate or they occasionally enter the runway safety buffer zone, and monitoring and regular early warnings are required.

[0146] When the comprehensive score is in the range of [0.5, 0.7), it is determined as the high threat level L3, which means that bird activities are frequent and they have clearly approached the airway, posing a potential risk to flights taking off or landing.

[0147] When the comprehensive score ≥ 0.7, it is determined as the extremely high threat level L4, which means that large flocks of birds repeatedly appear on and around the runway, posing a serious threat to flight safety.

[0148] S4. Trigger graded early warning signals according to the threat level and link the bird repellent equipment to perform directional bird repellent operations. Among them, it should be noted in this step that:

[0149] When the threat level is L1, only send text / voice reminders to the tower personnel to prompt them to stay vigilant.

[0150] When the threat level is L2, trigger an audio signal or a warning of flashing lights to remind the ground and flight crew to focus on observing the bird situation at the airport.

[0151] When the threat level is L3, trigger high-frequency harsh sound waves or strong light warnings, and give real-time risk warnings to flights about to take off or land.

[0152] When the threat level is L4, trigger the highest-level emergency alarm, recommend that the air traffic control department delay flight takeoff and landing, and immediately activate the linkage mechanism of multiple bird repellent measures.

[0153] In an alternative implementation, the linkage of the bird repellent equipment includes:

[0154] When the threat level ≥ L2, automatically activate the sonic bird repellent equipment and send adjustable-frequency high-decibel sound waves for interference.

[0155] When the threat level ≥ L3, in addition to sonic interference, turn on the laser or strong light beam bird repellent device, and can play bionic sounds such as the calls of raptors to drive them away.

[0156] When the threat level is L4, multiple devices are activated simultaneously to implement a comprehensive bird repellent solution including laser, strong light beam, bionic natural enemy and aerosol.

[0157] In an optional embodiment, the directional bird-repelling operation includes:

[0158] Automatically adjust the scanning direction and angle of the sound wave or light beam based on the real-time detected bird target location information;

[0159] When large-scale flocks of birds appear, multiple bird-repelling devices are coordinated to operate synchronously according to multiple target locations to maximize the dispersal effect;

[0160] Dynamically monitor the effectiveness of the dispersal operation. If the birds still pose an obvious threat, maintain high-intensity joint operations. If the birds have left the critical airspace, automatically downgrade to low intensity and stop dispersing to avoid unnecessary resource consumption.

[0161] In an optional implementation, the linkage with flight takeoff and landing includes:

[0162] When the threat level is ≥ L3 and the bird-repelling effect is poor, a high-risk alert will be automatically sent to the aviation control department, suggesting delaying or changing the take-off and landing time;

[0163] After the bird-scaring is completed and the threat level is reduced to L1, the warning status will be automatically lifted and the tower will be notified to resume normal flight scheduling.

[0164] The aforementioned preprocessing method and feature extraction method for collecting environmental data can be performed using methods and means in the prior art and will not be described in detail in this example.

[0165] Furthermore, the present embodiment discloses an intelligent bird-repelling device based on the aforementioned automatic detection method for bird conditions at an airport, including a monitoring module, wherein the monitoring module includes a radar device, a visible light camera, an infrared thermal imager and a sonar detector, and the monitoring modules are all connected to a control host. Specifically, the radar device may be a multi-beam scanning radar and a pulse Doppler radar, which are deployed at commanding heights around the airport, covering a range of 0.5-10 kilometers, and detecting the distance, speed and direction of birds. The visible light camera may be a high-resolution dynamic camera module, which is installed on lamp poles on both sides of the runway, covering a range of 0-2 kilometers, and collecting bird morphological characteristics and activity videos.

[0166] The infrared thermal imager can be a medium / long wave infrared imaging module, deployed on a low-light area bracket, covering 0-1.5 kilometers, and detecting bird heat signals at night; the sonar detector may include horizontal and vertical sonar arrays, distributed on the ground outside the runway, covering 0-1 kilometers, and locating the position of birds through echoes; it also includes meteorological sensors installed around the runway to monitor meteorological data such as wind direction, wind speed, and visibility in real time.

[0167] It also includes a central processing unit, including a control host and a data storage server, etc. The control host is deployed in the airport control room, integrating a data fusion module, a deep learning target detection model (such as BiLSTM + attention mechanism), and a risk assessment model (fuzzy logic and Bayesian network), responsible for processing sensor data, generating threat levels, and outputting control instructions; the data storage server is used to store the fusion data set, flight takeoff and landing timing data, and historical threat records.

[0168] It also includes a warning device,

[0169] : a tower display screen for real-time display of bird positions, threat levels, and bird repelling status, a voice broadcast module for sending voice alerts (such as L1 - L4 level prompts) to tower personnel, and warning lights distributed on both sides of the runway to trigger flashing strong light (L2 and above levels).

[0170] It also includes a bird repelling execution module, including a frequency - adjustable sound wave emitter installed on the periphery of the runway for directionally emitting high - decibel sound waves, a strong light lamp deployed in key areas of the runway for emitting laser beams or strong light interference, a bionic sound player for playing bird repelling audio such as the calls of raptors, and an aerosol generator located around the runway for releasing irritating aerosols.

[0171] Furthermore, the placement positions of each module are as follows: the radar device is set on the airport perimeter tower or high point to achieve 360° airspace coverage; the visible light / infrared cameras are set on the lamp posts on both sides of the runway, staggered at intervals of 200 meters; the sonar detectors are set on the ground outside the runway, arranged in a circular array; the meteorological sensors are set in the middle and at both ends of the runway to monitor local meteorological changes; the sound wave emitters are set at the four corners of the runway to cover the near - field area (0 - 1 km); the strong light lamps are set on both sides of the runway center line for directional scanning of the takeoff and landing channels; the aerosol generators are set outside the runway safety buffer zone to avoid affecting the flight line of sight; the central processing unit and the data server are located in the airport control room and are directly connected to the tower console.

[0172] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. An automatic detection and intelligent bird-repelling method for airport birds, characterized in that: include: Collect airport airspace environment data in real time through a multi-source sensor array, and pre-process the environment data to generate a fused data set; Building a target detection model based on a deep learning algorithm to identify bird targets in the fused data set and extract target feature information, wherein the target feature information includes the location, movement trajectory, number and type of birds; Combining the airport flight take-off and landing time series data with the target feature information, the threat level of bird activities to flights is calculated through a risk assessment model based on fuzzy logic and Bayesian network; Triggering a graded warning signal according to the threat level, and linking the bird-repelling equipment to perform a directional bird-repelling operation; A target detection model is constructed based on a deep learning algorithm to identify bird targets in the fused data set and extract target feature information, including: A bidirectional long short-term memory network is used to perform multi-level fusion of radar, infrared and visible light features; For the small-scale and easily overlapping features of bird targets, an attention mechanism is set to enhance the key area features; Use the labeled fusion data set for supervised training, and the training loss function adopts a multi-task weighted form: in, is the classification loss, is the bounding box regression loss, is the multimodal consistency loss; , , They are the weighted coefficients for classification loss, bounding box regression loss, and multimodal consistency loss respectively; Perform multimodal matching on the pre-processed video frames, infrared thermal imaging frames and radar / sonar data, and the network outputs the predicted position, type and confidence of the bird target; If the confidence level is higher than the threshold , it is determined to be a valid bird target, and its flight trajectory, number and appearance characteristics are further extracted; The identified target information is indexed by the target ID to generate a target feature information set including the bird's location, movement trajectory, number and type; The identification and extraction of the target detection model includes: Track the trajectory of the same target detected by continuous video frames or radar, and use the Kalman filter algorithm to obtain the precise motion trajectory; The position of each moment in the trajectory and speed Discretized storage is performed to form a trajectory sequence; Conduct statistical analysis on flight speed, altitude and direction to determine whether birds have behavioral patterns of flying quickly across the runway or forming flocks; Combining deep learning classification networks with biological prior knowledge, the body shape, feather characteristics and thermal distribution information of birds in visible light and infrared images are classified and identified; Classify bird species into different categories based on the identification results, and label them with clustering behavior labels or nocturnal activity frequency labels; Combining the airport flight take-off and landing time sequence data with the target feature information, the threat level of bird activities to flights is calculated through a risk assessment model based on fuzzy logic and Bayesian network, including: Set the number of birds n and population density , the distance d from the center of the runway and the flight altitude h are the key indicators, and a corresponding fuzzy set is established for each indicator; Using membership function Fuzzy processing of each indicator: Among them, a and b are interval thresholds; Input the fuzzified indicators into the Bayesian network nodes to form event conditions; Combined with the aircraft take-off and landing frequency and take-off and landing time information in the flight take-off and landing time series data, the posterior probability of bird strike risk is calculated; The evaluation values ​​of each indicator output by fuzzy logic and the posterior probability of Bayesian network are combined to determine the threat level of bird activities to flights according to the weighted rule; If the comprehensive score exceeds the preset upper threshold, it is judged as high risk or extremely high risk; If the comprehensive score is in the middle range, it is judged as medium risk; If the comprehensive score is below the lower threshold, it is judged as low risk.

2. The method for automatically detecting and intelligently driving away birds at an airport according to claim 1, characterized in that: The multi-source sensor array includes radar equipment, visible light cameras, infrared thermal imagers and sonar detectors. The airport airspace environment data collected in real time by the multi-source sensor array includes radar data, visible light image data, infrared thermal imaging data, sonar data and meteorological information around the airport runway; Among them, the radar data includes distance, radial velocity and azimuth, the visible light image data includes frame sequence images, target pixel coordinates and color texture features, the infrared thermal imaging data includes target thermal radiation intensity and thermal imaging coordinates, the sonar data includes echo intensity, delay time and target azimuth, and the meteorological information around the airport runway includes wind direction, wind speed and visibility.

3. The method for automatic detection of bird conditions and intelligent bird repelling at an airport according to claim 1 or 2, characterized in that: Preprocessing the environmental data to generate a fused data set includes: Performing unified time calibration on the environmental data; Perform bandpass filtering and background noise suppression on radar, infrared and sonar data, and perform background modeling and moving target segmentation on visible light images; According to the coordinate systems of different sensors, the target detection results are converted into a unified spatial coordinate system, and the Kalman filter algorithm is used to realize the association and redundancy removal of multi-source tracking results; Conduct secondary screening on targets with low confidence and eliminate duplicate targets; Annotate the bounding boxes of birds in visible light and infrared thermal images; Visible light and infrared data are enhanced by image flipping, rotation, brightness adjustment and noise addition methods; The processed data and the annotation information are matched according to the timestamp to form a unified serial data set, which is the fused data set.

4. The method for automatic detection of bird conditions and intelligent bird repelling at an airport according to claim 3, characterized in that: The threat levels include: When the comprehensive score is in the range of [0, 0.3), it is judged as low threat level L1, which means that the number of birds is very small and far away from the critical areas of the runway, and basically does not pose a safety impact on aircraft takeoff and landing; When the comprehensive score is in [0.3, 0.5), it is judged as medium threat level L2, then the number of birds is moderate or occasionally enters the runway safety buffer zone, and monitoring and regular warning are required; When the comprehensive score is between [0.5, 0.7), it is judged as a high threat level L3, which means that the bird activities are frequent and have obviously approached the flight path, posing a potential risk to flights that are taking off or about to take off or land. When the comprehensive score is ≥0.7, it is judged as an extremely high threat level L4, then large flocks of birds repeatedly appear on the runway and its surroundings, posing a serious threat to flight safety.

5. The method for automatic detection of bird conditions and intelligent bird repelling at an airport according to claim 4, characterized in that: According to the threat level, a graded warning signal is triggered, and the bird-repelling device is linked to perform a directional bird-repelling operation, including: When the threat level is L1, only text / voice reminders are sent to tower personnel to remind them to stay focused; When the threat level is L2, an audio signal or light flashing warning is triggered to remind ground and flight crews to pay close attention to the bird situation at the airport; When the threat level is L3, a high-frequency harsh sound wave or strong light warning is triggered, and real-time risk warnings are issued to flights about to take off and land; When the threat level is L4, the highest level emergency alarm is triggered, and the control department is advised to delay flight takeoff and landing, and immediately activate a linkage mechanism of multiple bird-repelling measures.

6. The method for automatic detection of bird conditions and intelligent bird repelling at an airport according to claim 5, characterized in that: The linked bird-repelling device performs a directional bird-repelling operation, including: When the threat level is ≥ L2, the sonic repelling device will be automatically activated to send out adjustable frequency high-decibel sonic interference; When the threat level is ≥ L3, in addition to sound wave interference, turn on the laser or strong beam bird repellent device and play bionic sound to repel the birds; When the threat level is L4, multiple devices are activated simultaneously to implement a comprehensive bird repellent solution including laser, strong light beam, bionic natural enemy and aerosol.

7. An intelligent bird-repelling device based on the automatic detection of bird conditions at an airport and the intelligent bird-repelling method according to any one of claims 1 to 6, characterized in that: It includes a monitoring module arranged on the runway, the monitoring module includes a radar device, a visible light camera, an infrared thermal imager and a sonar detector, and the monitoring modules are connected to the control host; It also includes an early warning module, which includes a tower display screen, a voice player, and warning lights arranged on both sides of the runway; It also includes a bird-repelling execution module, which includes a frequency-adjustable sound wave transmitter, a strong light, a bionic sound player and an aerosol generator.

Images