CN113014866B - Airport low-altitude bird activity surveillance and risk warning system - Google Patents

Abstract

The invention provides an airport low-altitude bird activity monitoring and risk alarming system, which comprises a radar detection unit: the system is used for detecting the low-altitude flying object and transmitting the coordinates of the detected target to the information processing center in real time; the information processing center: the system comprises a video tracking shooting unit, a coordinate acquisition unit and a coordinate display unit, wherein the video tracking shooting unit is used for sending the coordinates of a target to the video tracking shooting unit; the information processing center is also used for analyzing the coordinates of the target and the shot video to obtain bird activity risks, and sending the bird activity risks to the mobile display terminal; video tracking shooting unit: the bird detection device is used for identifying whether the target is a bird or not within a preset detection error range according to the coordinates of the target; if the birds are the birds, tracking shooting is carried out, and the shot video is transmitted to an information processing center; the mobile display terminal: and the bird activity risk receiving device is used for a worker to check the received bird activity risk. The system can timely cope with the potential safety hazard of bird strike, and the accuracy and timeliness of high-risk bird activity detection are improved.

Description

Airport low-altitude bird activity monitoring and risk alarm system

technical field

The invention belongs to the technical field of airport low-altitude monitoring, in particular to an airport low-altitude bird activity monitoring and risk alarm system.

Background technique

Collision between aircraft and birds (referred to as bird strike) is a problem that human beings have been facing since they flew into the blue sky. With the improvement of the ecological environment, the number of birds around the airport is increasing year by year, and the incidents of bird strikes on aircraft are also increasing year by year. Bird strikes are the largest incident type in civil aviation, and bird strike prevention is one of the main tasks of airport safety management. Bird strikes are most likely to occur during takeoff and landing, so airports and their surrounding airspace are key areas for bird strike prevention and control.

The prevention and control of bird strike accidents requires real-time detection of high-risk bird activities in order to respond and deal with them in a timely manner. However, the detection of high-risk bird activities faces many difficulties: First, the installation of sensors is restricted by management regulations, and it is necessary to realize the detection of bird activities in a large area of the airport within a limited sensor installation range. Second, there is a large amount of bird activity at the airport, only a small amount of which is high-risk. In order to achieve a reliable judgment, it is necessary to collect as detailed and accurate information as possible. Third, birds are animals with a high degree of intelligence, and their activity patterns change frequently, making it difficult to predict activities. The accuracy of bird prediction directly affects the reliability of risk prediction.

Contents of the invention

Aiming at the defects in the prior art, the present invention provides an airport low-altitude bird activity monitoring and risk alarm system, which improves the accuracy and timeliness of high-risk bird activity detection.

An airport low-altitude bird activity monitoring and risk alarm system, including:

At least one radar detection unit: used to detect low-altitude flying objects, and transmit the coordinates of the detected targets to the information processing center in real time;

Information processing center: used to distribute the coordinates of the target to the video tracking and shooting unit; the information processing center is also used to analyze the coordinates of the target and the captured video, obtain the risk of bird activities, and send the risk of bird activities to the mobile display terminal;

At least one video tracking and shooting unit: used to identify whether the target is a bird within the preset detection error range according to the coordinates of the target; if it is a bird, perform tracking and shooting, and send the captured video to the information processing center ;

At least one mobile display terminal: for personnel to view received bird activity risks.

Preferably, the information processing center is specifically used for:

Correlate the coordinates detected multiple times for the same target to obtain the flight trajectory;

Associating the flight trajectory with the corresponding video captured by the video tracking and shooting unit to obtain identification information, and identifying the bird's activity pattern according to the identification information;

Inputting the identification information into the risk prediction function corresponding to the activity pattern to obtain the bird activity risk;

Calculate area risk;

When the bird activity risk or area risk is higher than the preset alarm threshold, a high-risk bird activity risk alarm or a high-risk area risk alarm is issued.

Preferably, the information processing center is specifically used for:

Calculating the similarities of various activity patterns according to the identification information;

Determine whether the similarity of all activity patterns is lower than the preset similarity threshold; if yes, define the bird’s activity pattern as a non-high-risk activity pattern; if not, define the bird’s activity pattern as the maximum similarity corresponding activity mode.

Preferably, the activity pattern includes long-distance migration; the information processing center is specifically used for:

According to the flight trajectory T, a plurality of images A of the area where the birds are located and the total number of coordinates N accumulated are extracted from the corresponding video; respectively, the trajectory similarity f _1-T (T) and appearance Similarity f _1-A (A) and data confidence f _1-N (N);

Define the similarity of long-distance migration as the product of trajectory similarity f _1-T (T), appearance similarity f _1-A (A) and data confidence f _1-N (N);

Among them, the trajectory similarity f _1-T (T) is calculated according to the flight altitude, flight speed and flight direction change; the appearance similarity f _1-A (A) is calculated according to the maximum value of the long-distance migration similarity and the maximum wingspan width obtained, or calculated according to the maximum value of long-distance migration similarity and body length, wherein the maximum value of long-distance migration similarity is the maximum value of multiple similarities calculated under long-distance migration; the maximum wingspan width or body length according to the regional image A The width and distance are calculated; the data confidence f _1-N (N) is calculated based on the total number N of accumulated detected coordinates.

Preferably, the risk prediction function f _1-R (D ₁ , A) of long-distance migration is calculated according to the distance D ₁ and the maximum wingspan width, wherein the distance D ₁ is the straight line fitted by the flight trajectory and The distance of the flight path of the aircraft.

Preferably, the activity mode includes continuous circling in the air; the information processing center is specifically used for:

According to the flight trajectory T, a plurality of images A of the area where the birds are located and the total number of coordinates N accumulated are extracted from the corresponding video; respectively, the trajectory similarity f _2-T (T) and the appearance Similarity f _2-A (A) and data confidence f _2-N (N);

Define the similarity of continuous circling in the air as the product of trajectory similarity f _2-T (T), appearance similarity f _2-A (A) and data confidence f _2-N (N);

Among them, the trajectory similarity f _2-T (T) is calculated according to the flight altitude, flight speed and range of activity dispersion; the appearance similarity f _2-A (A) is calculated according to the maximum similarity of continuous circling in the air and the maximum wingspan width obtained, or calculated according to the maximum similarity value and body length of continuous circling in the air, wherein the maximum similarity value of continuous circling in the air is the maximum value of multiple similarities calculated under continuous circling in the air; the maximum wingspan width or body length is based on the area image A The width and distance are calculated; the data confidence f _2-N (N) is calculated based on the total number N of accumulated detected coordinates.

Preferably, the risk prediction function f _2-R (D ₂ , A) of continuous circling in the air is calculated according to the integration factor D ₂ and the maximum wingspan width, wherein the integration factor D ₂ is the probability model of the distribution space and the aircraft The space range of takeoff and landing routes is calculated.

Preferably, the activity mode includes low-altitude frequent flashes; the information processing center is specifically used for:

According to the flight trajectory _T , a plurality of images A of the area where the birds are located and the total number N of accumulated coordinates are extracted from the corresponding video; Quantitative similarity f _3-A (A) and data confidence f _3-N (N);

Define the similarity of low-altitude frequent flashes as the product of trajectory similarity f _3-T (T), population similarity f _3-A (A) and data confidence f _3-N (N);

Among them, the trajectory similarity f _3-T (T) is based on flight height and flight distance as constraints, and filters out the start and end space or time approximation of all flight trajectories at the preset screening time; the population number similarity f _3-A ( A) Calculated based on the number of birds in the area image A; the data confidence f _3-N (N) is calculated based on the total number N of accumulated detected coordinates.

Preferably, the risk prediction function f _3-R (D ₃ , D ₄ , A) of low-altitude frequent flashes is calculated based on the distance D ₃ , the active factor D ₄ and the number of birds in the area image A, where the distance D ₃ is the distance between the activity distribution range and the runway, and the activity factor D ₄ is calculated based on the number of bird flocks taking off per unit time.

Preferably, the information processing center is also used for:

Calculate the cumulative value of the bird activity risk under each activity mode in the unit time in the area to obtain the regional risk.

It can be seen from the above technical solution that the low-altitude bird activity monitoring and risk alarm system at the airport provided by the present invention realizes the detection of large-scale low-altitude small flying objects through radar, and further realizes the confirmation of birds and detailed information through intelligent video tracking and shooting. Collect, and finally identify bird species and bird activity patterns through intelligent analysis, judge the risk of current and future bird activities, and transmit high-risk bird activities to relevant staff in real time, which can promptly respond to potential safety hazards of bird strikes, Improved accuracy and timeliness of detection of high-risk bird activity.

Description of drawings

In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the specific embodiments or the prior art. Throughout the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, elements or parts are not necessarily drawn in actual scale.

Fig. 1 is a module block diagram of an airport low-altitude bird activity monitoring and risk warning system provided by Embodiment 1 of the present invention.

Detailed ways

Embodiments of the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings. The following examples are only used to illustrate the technical solutions of the present invention more clearly, and therefore are only examples, rather than limiting the protection scope of the present invention. It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application shall have the usual meanings understood by those skilled in the art to which the present invention belongs.

It should be understood that when used in this specification and the appended claims, the terms "comprising" and "comprises" indicate the presence of described features, integers, steps, operations, elements and/or components, but do not exclude one or Presence or addition of multiple other features, integers, steps, operations, elements, components and/or collections thereof.

It should also be understood that the terminology used in the description of the present invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the present invention. As used in this specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural referents unless the context clearly dictates otherwise.

As used in this specification and the appended claims, the term "if" may be construed as "when" or "once" or "in response to determining" or "in response to detecting" depending on the context . Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, to mean "once determined" or "in response to the determination" or "once detected [the described condition or event] ]” or “in response to detection of [described condition or event]”.

Embodiment one:

An airport low-altitude bird activity monitoring and risk warning system, see Figure 1, including:

At least one radar detection unit: used to detect low-altitude flying objects, and transmit the coordinates of the detected targets to the information processing center in real time;

Information processing center: used to distribute the coordinates of the target to the video tracking and shooting unit.

Specifically, the information processing center can integrate the coordinates from multiple radar detection units, distribute the coordinates to each video tracking and shooting unit according to the principle of the shortest distance, and distribute the target to the video tracking and shooting unit closest to the target, so as to capture the Clearer goals.

At least one video tracking and shooting unit: used to identify whether the target is a bird within the preset detection error range according to the coordinates of the target; if it is a bird, perform tracking and shooting, and send the captured video to the information processing center ;

Specifically, when the video tracking and shooting unit cannot identify the target as a bird within the preset detection time (generally 2-10 seconds), it considers that the target is not a bird; When the target is found to be a bird, increase the focal length of the lens in the video tracking and shooting unit to track and shoot the target, so that a clearer target can be captured, and the collected video will be sent to the information processing center, and then continue to detect a goal.

The information processing center is also used to analyze the coordinates of the target and the captured video, obtain the bird activity risk, and send the bird activity risk to the mobile display terminal;

At least one mobile display terminal: for personnel to view received bird activity risks.

Specifically, the signal processing center transmits the risk of bird activities to the mobile display terminal for display in real time. Once it is detected that the risk of bird activities is high, the signal processing center will remind the staff through sound and image, and guide the staff to deal with it in time.

The airport's low-altitude bird activity monitoring and risk alarm system uses radar to detect large-scale low-altitude small flying objects, and further uses video intelligent tracking and shooting to realize bird confirmation and detailed information collection, and finally identify bird species and species through intelligent analysis. The bird activity mode judges the risk of current and future bird activities, and transmits high-risk bird activities to relevant staff in real time, which can promptly respond to potential safety hazards of bird strikes and improves the accuracy of high-risk bird activity detection and timeliness.

Embodiment two:

Embodiment 2 On the basis of Embodiment 1, the following content is added:

The information processing center is specifically used for:

Correlate the coordinates detected multiple times for the same target to obtain the flight trajectory;

Associating the flight trajectory with the corresponding video captured by the video tracking and shooting unit to obtain identification information, and identifying the bird's activity pattern according to the identification information;

The identification information is input into the risk prediction function corresponding to the activity pattern to obtain the bird activity risk.

Specifically, the information processing center associates the coordinates detected multiple times by the target to form a flight trajectory, and then associates the flight trajectory with the video to form identification information. The bird's activity pattern is identified based on the identification information, and the bird's future activity is predicted based on the identified activity pattern, and the bird's activity risk is analyzed.

Calculate area risk;

When the bird activity risk or area risk is higher than the preset alarm threshold, a high-risk bird activity risk alarm or a high-risk area risk alarm is issued.

Specifically, the system not only provides early warning of bird activity risks, but also provides early warning of regional risks.

When identifying the activity pattern of birds, the information processing center is specifically used for:

Calculating the similarities of various activity patterns according to the identification information;

Determine whether the similarity of all activity patterns is lower than the preset similarity threshold; if yes, define the bird’s activity pattern as a non-high-risk activity pattern; if not, define the bird’s activity pattern as the maximum similarity corresponding activity mode.

Specifically, the high-risk bird activity patterns include three patterns: long-distance migration, continuous circling in the air, and frequent low-altitude flashes. Therefore, the system mainly uses these three activity patterns to identify high-risk bird activities. When identifying activity patterns, the similarities of the three activity patterns are calculated separately. If the similarities of the obtained three activity patterns are all lower than the similarity threshold, it is considered that the current bird’s activity pattern does not belong to the above three patterns, and it is not a high-risk activity; otherwise, it is determined that the activity pattern corresponds to the maximum value among the three similarities. mode.

1. Long distance migration

According to the flight trajectory T, multiple images A of the bird's area extracted from the video, and the total number of coordinates N accumulated, calculate the trajectory similarity f _1-T (T) and appearance similarity f _1-A (A) and data confidence f _1-N (N).

The trajectory similarity f _1-T (T) of the long-distance migration is calculated according to the flight altitude, flight speed and flight direction change range; the appearance similarity f _1-A (A) is calculated according to the maximum value of the long-distance migration similarity and The maximum wingspan width is calculated, or calculated based on the maximum similarity of long-distance migration and body length, where the maximum similarity of long-distance migration is the maximum value of multiple similarities calculated under long-distance migration; the maximum wingspan width or The body length is calculated based on the width and distance of the area image A; the data confidence f _1-N (N) is calculated based on the total number of accumulated coordinates N, and the larger N is, the higher the data confidence.

The product of the three is the similarity S1 of the long-distance migration pattern, S ₁ =f _1-T (T)f _1-A (A)f _1-N (N).

2. Continuous hovering in the air

According to the flight trajectory T, multiple images A of the bird's area extracted from the video, and the total number of coordinates N accumulated, calculate the trajectory similarity f _2-T (T) and appearance similarity f _2-A (A) and data confidence f _2-N (N).

The trajectory similarity f _2-T (T) of the continuous circling in the air is calculated according to the flight altitude, flight speed and dispersion range of the activity; the appearance similarity f _2-A (A) is calculated according to the maximum value and the maximum Wingspan width is calculated, or calculated based on the maximum similarity of continuous circling in the air and body length, wherein the maximum similarity of continuous circling in the air is the maximum value of multiple similarities calculated under continuous circling in the air; the data confidence f _{2- N} (N) is calculated based on the total number N of accumulated coordinates detected. The larger N is, the higher the data confidence is.

The product of the three is the similarity S2 of the continuous hovering mode in the air, S ₂ =f _2-T (T)f _2-A (A)f _2-N (N).

3. Frequent flashes at low altitude

According to the flight trajectory T, multiple images A of the bird's area extracted from the video, and the total number of coordinates N accumulated, the trajectory similarity f _3-T (T) and the species population similarity f _3-A ( A) and data confidence f _3-N (N).

The trajectory similarity f _3-T (T) of the low-altitude frequent flashes is based on the flight height and flight distance as the restriction conditions, and the start and end space or time approximation of all flight trajectories in the preset screening time (which can be in the near future) are screened out. degree; the population similarity f _3-A (A) is calculated based on the number of birds in the area image A; the data confidence f _3-N (N) is calculated based on the total number of coordinates N accumulated, the greater the N, the greater the data confidence higher.

The product of the three is the similarity S3 of the low-altitude frequent flashing mode, S ₃ =f _3-T (T)f _3-A (A)f _3-N (N).

When the system recognizes the bird's activity pattern, it inputs the identification information into the risk prediction function corresponding to the activity pattern to obtain the bird's activity risk.

The risk prediction function f _1-R (D ₁ ,A) for long-distance migration is calculated based on the distance D ₁ and the maximum wingspan width, where the distance D ₁ is the straight line fitted by the flight trajectory and the aircraft take-off and landing the distance of the route;

The risk prediction function f _2-R (D ₂ ,A) of continuous circling in the air is calculated according to the integral factor D ₂ and the maximum wingspan width, where the integral factor D ₂ is the probability model of passing through the distribution space and the aircraft take-off and landing route The spatial range is calculated;

The risk prediction function f _3-R (D ₃ , D ₄ , A) of low-altitude frequent flashes is calculated based on the distance D ₃ , activity factor D ₄ and the number of birds in the area image A, where the distance D ₃ is the activity The distance between the distribution range and the runway, the active factor D ₄ is calculated based on the number of bird flocks taking off per unit time.

Preferably, the information processing center is also used for:

Calculate the cumulative value of the bird activity risk under each activity mode in the unit time in the area to obtain the regional risk.

Specifically, the system accumulates the bird activity risks of the three activity modes within a certain period of time in the region to obtain the regional risk, expressed as ∑f _1-R (D ₁ ,A)+∑f _2-R (D ₂ ,A)+∑f _3-R (D ₃ ,D ₄ ,A).

The system provided by the embodiments of the present invention is for brief description, and for the parts not mentioned in the embodiments, reference may be made to the corresponding content in the foregoing embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. All of them should be covered by the scope of the claims and description of the present invention.

Claims (7)

1. An airport low-altitude bird activity monitoring and risk warning system is characterized in that it comprises: At least one radar detection unit: used to detect low-altitude flying objects, and transmit the coordinates of the detected targets to the information processing center in real time; Information processing center: used to distribute the coordinates of the target to the video tracking and shooting unit; the information processing center is also used to analyze the coordinates of the target and the captured video, obtain the risk of bird activities, and send the risk of bird activities to the mobile display terminal; At least one video tracking and shooting unit: used to identify whether the target is a bird within the preset detection error range according to the coordinates of the target; if it is a bird, perform tracking and shooting, and send the captured video to the information processing center ; At least one mobile display terminal: for staff to view received bird activity risks; The information processing center is specifically used for: Correlate the coordinates detected multiple times for the same target to obtain the flight trajectory; Associating the flight trajectory with the corresponding video captured by the video tracking and shooting unit to obtain identification information, and identifying the bird's activity pattern according to the identification information; Inputting the identification information into the risk prediction function corresponding to the activity pattern to obtain the bird activity risk; Calculate area risk; When the bird activity risk or area risk is higher than the preset alarm threshold, a high-risk bird activity risk alarm or a high-risk area risk alarm is issued; The information processing center is specifically used for: Calculating the similarities of various activity patterns according to the identification information; Determine whether the similarity of all activity patterns is lower than the preset similarity threshold; if yes, define the bird’s activity pattern as a non-high-risk activity pattern; if not, define the bird’s activity pattern as the maximum similarity The corresponding activity mode; The activity pattern includes long-distance migration; the information processing center is specifically used for: According to the flight trajectory T, a plurality of images A of the area where the birds are located and the total number of coordinates N accumulated are extracted from the corresponding video; respectively, the trajectory similarity f _1-T (T) and appearance Similarity f _1-A (A) and data confidence f _1-N (N); Define the similarity of long-distance migration as the product of trajectory similarity f _1-T (T), appearance similarity f _1-A (A) and data confidence f _1-N (N); Among them, the trajectory similarity f _1-T (T) is calculated according to the flight altitude, flight speed and flight direction change; the appearance similarity f _1-A (A) is calculated according to the maximum value of long-distance migration similarity and the maximum wingspan width obtained, or calculated according to the maximum value of long-distance migration similarity and body length, wherein the maximum value of long-distance migration similarity is the maximum value of multiple similarities calculated under long-distance migration; the maximum wingspan width or body length according to the regional image A The width and distance are calculated; the data confidence f _1-N (N) is calculated based on the total number N of accumulated detected coordinates. 2. according to the described airport low-altitude bird activity monitoring and risk warning system of claim 1, it is characterized in that, The risk prediction function f _1-R (D ₁ ,A) for long-distance migration is calculated based on the distance D ₁ and the maximum wingspan width, where the distance D ₁ is the straight line fitted by the flight trajectory and the aircraft take-off and landing The distance of the route. 3. according to the described airport low-altitude bird activity monitoring and risk warning system of claim 1, it is characterized in that, described activity mode comprises air continuous circling; Described information processing center is specifically used for: According to the flight trajectory T, a plurality of images A of the area where the birds are located and the total number of coordinates N accumulated are extracted from the corresponding video; respectively, the trajectory similarity f _2-T (T) and the appearance Similarity f _2-A (A) and data confidence f _2-N (N); Define the similarity of continuous circling in the air as the product of trajectory similarity f _2-T (T), appearance similarity f _2-A (A) and data confidence f _2-N (N); Among them, the trajectory similarity f _2-T (T) is calculated according to the flight altitude, flight speed and range of activity dispersion; the appearance similarity f _2-A (A) is calculated according to the maximum similarity of continuous circling in the air and the maximum wingspan width obtained, or calculated according to the maximum similarity value and body length of continuous circling in the air, wherein the maximum similarity value of continuous circling in the air is the maximum value of multiple similarities calculated under continuous circling in the air; the maximum wingspan width or body length is based on the area image A The width and distance are calculated; the data confidence f _2-N (N) is calculated based on the total number N of accumulated detected coordinates. 4. according to the described airport low-altitude bird activity monitoring and risk warning system of claim 3, it is characterized in that, The risk prediction function f _2-R (D ₂ ,A) of continuous circling in the air is calculated according to the integral factor D ₂ and the maximum wingspan width, where the integral factor D ₂ is the probability model of passing through the distribution space and the aircraft take-off and landing route The spatial extent is calculated. 5. according to the described airport low-altitude bird activity monitoring and risk warning system of claim 1, it is characterized in that, described activity mode comprises low-altitude frequent flashing; Described information processing center is specifically used for: According to the flight trajectory _T , a plurality of images A of the area where the birds are located and the total number N of accumulated coordinates are extracted from the corresponding video; Quantitative similarity f _3-A (A) and data confidence f _3-N (N); Define the similarity of low-altitude frequent flashes as the product of trajectory similarity f _3-T (T), population similarity f _3-A (A) and data confidence f _3-N (N); Among them, the trajectory similarity f _3-T (T) is based on flight height and flight distance as constraints, and filters out the start and end space or time approximation of all flight trajectories at the preset screening time; the population number similarity f _3-A ( A) Calculated based on the number of birds in the area image A; the data confidence f _3-N (N) is calculated based on the total number N of accumulated detected coordinates. 6. according to the described airport low-altitude bird activity monitoring and risk warning system of claim 5, it is characterized in that, The risk prediction function f _3-R (D ₃ , D ₄ , A) of low-altitude frequent flashes is calculated based on the distance D ₃ , activity factor D ₄ and the number of birds in the area image A, where the distance D ₃ is the activity The distance between the distribution range and the runway, the active factor D ₄ is calculated based on the number of bird flocks taking off per unit time. 7. according to the described airport low-altitude bird activity monitoring and risk warning system of claim 1, it is characterized in that, described information processing center is also used for: Calculate the cumulative value of the bird activity risk under each activity mode in the unit time in the area to obtain the regional risk.

Images