A low-altitude flying object anti-collision warning system and method

Abstract

The present invention discloses a low-altitude flying object anti-collision warning system and method, including the steps of preliminary detection, target image enhancement, initial value acquisition and obstacle distance calculation. It can optimize the low-altitude specific obstacles (such as electric wires, flagpoles and other slender targets), can timely detect obstacles with a distance greater than 200m, and can timely alarm, reduce the probability of flying objects colliding with obstacles, and reduce property losses. The anti-collision warning system can be installed around and above the low-altitude flying object, and can be determined according to the actual application scenario and the flight characteristics of the low-altitude flying object.

Description

Technical Field

[0001] The present invention relates to the field of radar warning technology, and in particular to a low-altitude flying object anti-collision warning system and method. Background Art

[0002] The anti-collision warning systems currently on the market have a long detection distance for targets on the road (such as vehicles, fences, etc.), but a very short detection distance for some unique obstacles at low altitudes (such as slender targets such as wires and flagpoles), or even fail to detect them. They cannot meet the anti-collision warning requirements for low-altitude flying objects and cannot be directly used as anti-collision warning systems for low-altitude aircraft. In order to accurately detect low-altitude obstacles, it is necessary to improve the existing anti-collision warning systems to improve the recognition accuracy and recognition distance of low-altitude obstacles. Summary of the invention

[0003] In order to overcome the defects in the prior art, an embodiment of the present invention provides a collision avoidance warning method for low-altitude flying objects, which can solve one or more problems in the background technology, can adapt to the working scenarios of low-altitude flying objects, can detect some slender obstacles at low altitudes from a long distance and calculate the distance between the low-altitude flying objects and the obstacles, thereby improving the obstacle avoidance capability of low-altitude flying objects.

[0004] The present application embodiment discloses: a low-altitude flying object anti-collision warning method, comprising the following steps:

[0005] S1. Preliminary detection: Detect multiple target points on the obstacle through radar to form a target point distribution map;

[0006] S2, target image enhancement: repeat step "S1" to obtain a multi-frame target point distribution map, and superimpose the multi-frame target point distribution maps to increase the intensity of the target;

[0007] S3, initial value acquisition: extract the two points closest to the radar in the obstacle, and mark the two points as point A and point B, set the intersection of the central axis of the radar and the low-altitude flying object as point F, obtain the distance AF from point A to point F, the distance BF from point B to point F, the angle α between AF and AB, and the angle β between BF and AB;

[0008] S4. Obstacle distance calculation: obtain the radar distance AF from point A to point F, the distance BF from point B to point F, the angle α between AF and AB, and the angle β between BF and AB, and calculate the straight-line distance from point F to the obstacle.

[0009] Furthermore, in the obstacle calculation step, the following steps are included:

[0010] Calculate the straight-line distance AD ​​from point A to the central axis of the radar based on the distance value AF from point A to point F and the angle α between AF and AB;

[0011] Calculate the straight-line distance BE from point B to the central axis of the radar based on the distance value BF from point B to point F and the angle β between BF and AB;

[0012] The distance AB is calculated according to the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar. The calculation formula is: AB = S (AD + BE) = S (AF × sin α + BF × sin β), where S is the correction coefficient;

[0013] ∠ABF and ∠BAF are calculated according to the sine theorem. The calculation formula is AB÷sin(α+β)=AF÷sin∠ABF=BF÷sin∠BAF;

[0014] Calculate the straight-line distance FC from the radar to the obstacle using the formula FC = AF × sin∠BAF = BF × sin∠ABF.

[0015] Furthermore, it also includes target point filtering, drawing a fitting straight line along multiple target points, filtering out target points that deviate from the fitting straight line and exceed a set threshold, and the drawn fitting straight line is one or more.

[0016] Furthermore, the correction coefficient S is corrected by a recurrent neural network, thereby continuously improving the accuracy of calculating the distance between the radar and the obstacle.

[0017] The present invention also provides a low-altitude flying object anti-collision warning system, which is used for the above anti-collision warning method, and includes a radar, an image enhancement module, a data storage module, a data extraction module and a calculation module, wherein:

[0018] The radar is used to detect multiple target points on the obstacle to form a multi-frame target point distribution map;

[0019] The image enhancement module is used to superimpose target point distribution maps of multiple frames to increase the intensity of target points in the target point distribution maps;

[0020] The data storage module is used to store the target point distribution map of the enhanced processing;

[0021] The data extraction module is used to extract at least two points closest to the radar in the target point distribution map, and send the position information of the two points to the calculation module, and mark the two closest points as point A and point B, set the intersection of the central axis of the radar and the low-altitude flying object as point F, obtain the distance value AF from the radar to point F, the distance value BF from point B to point F, the angle α between AF and AB, and the angle β between BF and AB;

[0022] The calculation module is used to calculate the straight-line distance between the radar and the obstacle according to the position information of the two points.

[0023] Furthermore, it also includes a target point filtering module, which is used to draw a fitting straight line according to multiple target points in the target point distribution map, and filter out target points that deviate from the fitting straight line and exceed a set threshold. The drawn fitting straight line is one or more.

[0024] Furthermore, the calculation module includes a first calculation unit, a second calculation unit and a third calculation unit, the first calculation unit is used to calculate the straight-line distance AD ​​from point A to the central axis of the radar, the second calculation unit is used to calculate the straight-line distance BE from point B to the central axis of the radar; the third calculation unit is used to calculate the straight-line distance from point F to the obstacle based on the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar.

[0025] Furthermore, the straight-line distance FC from point F to the obstacle is calculated as follows:

[0026] The distance AB is calculated according to the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar. The calculation formula is: AB = S (AD + BE) = S (AF × sin α + BF × sin β), where S is the correction coefficient;

[0027] ∠ABF and ∠BAF are calculated according to the sine theorem. The calculation formula is AB÷sin(α+β)=AF÷sin∠ABF=BF÷sin∠BAF;

[0028] Calculate the straight-line distance FC from the radar to the obstacle using the formula FC = AF × sin∠BAF = BF × sin∠ABF.

[0029] Furthermore, it also includes a learning module, which corrects the correction coefficient S through a recurrent neural network, thereby continuously improving the accuracy of calculating the distance between the radar and the obstacle.

[0030] The beneficial effects of the present invention are as follows: the anti-collision warning system and the anti-collision warning method for low-altitude flying objects involved in the present invention are optimized for low-altitude specific obstacles (such as slender targets such as electric wires and flagpoles), can promptly detect obstacles at a distance greater than 200m, and can promptly issue an alarm, thereby reducing the probability of flying objects colliding with obstacles and reducing property losses. The anti-collision warning system can be installed around and above and below the low-altitude flying object, and can be determined according to the actual application scenario and the flight characteristics of the low-altitude flying object. The method for optimizing the anti-collision warning system for low-altitude specific obstacles can also be used for other similar targets, providing ideas for other similar target detection and warning functions.

[0031] In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 It is a schematic diagram of the calculation process of the anti-collision warning method for low-altitude flying objects. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0035] Reference Figure 1 In a preferred embodiment of the present invention, a low-altitude flying object anti-collision warning method comprises the following steps:

[0036] S1. Preliminary detection: Detect multiple target points on the obstacle through radar to form a target point distribution map;

[0037] S2, target image enhancement: repeat step "S1" to obtain a multi-frame target point distribution map, and superimpose the multi-frame target point distribution maps to increase the intensity of the target;

[0038] S3, initial value acquisition: extract the two points closest to the radar in the obstacle, and mark the two points as point A and point B, set the intersection of the central axis of the radar and the low-altitude flying object as point F, obtain the distance AF from point A to point F, the distance BF from point B to point F, the angle α between AF and AB, and the angle β between BF and AB;

[0039] S4. Obstacle distance calculation: obtain the radar distance AF from point A to point F, the distance BF from point B to point F, the angle α between AF and AB, and the angle β between BF and AB, and calculate the straight-line distance from point F to the obstacle.

[0040] In the above embodiment, the obstacle calculation step includes the following steps:

[0041] Calculate the straight-line distance AD ​​from point A to the central axis of the radar based on the distance value AF from point A to point F and the angle α between AF and AB;

[0042] Calculate the straight-line distance BE from point B to the central axis of the radar based on the distance value BF from point B to point F and the angle β between BF and AB;

[0043] The distance AB is calculated according to the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar. The calculation formula is: AB = S (AD + BE) = S (AF × sin α + BF × sin β), where S is the correction coefficient;

[0044] ∠ABF and ∠BAF are calculated according to the sine theorem. The calculation formula is AB÷sin(α+β)=AF÷sin∠ABF=BF÷sin∠BAF;

[0045] Calculate the straight-line distance FC from the radar to the obstacle using the formula FC = AF × sin∠BAF = BF × sin∠ABF.

[0046] In the above embodiment, target point filtering is also included, a fitting straight line is drawn along a plurality of target points, and target points that deviate from the fitting straight line and exceed a set threshold are filtered out, and the drawn fitting straight line is one or more.

[0047] In the above embodiment, the correction coefficient S is also corrected by a recurrent neural network, so as to continuously improve the accuracy of the distance calculation between the radar and the obstacle.

[0048] The present invention also provides a low-altitude flying object anti-collision warning system, which is used for the above anti-collision warning method, and includes a radar, an image enhancement module, a data storage module, a data extraction module and a calculation module, wherein:

[0049] The radar is used to detect multiple target points on the obstacle to form a multi-frame target point distribution map;

[0050] The image enhancement module is used to superimpose target point distribution maps of multiple frames to increase the intensity of target points in the target point distribution maps;

[0051] The data storage module is used to store the target point distribution map of the enhanced processing;

[0052] The data extraction module is used to extract at least two points closest to the radar in the target point distribution map, and send the position information of the two points to the calculation module, and mark the two closest points as point A and point B, set the intersection of the central axis of the radar and the low-altitude flying object as point F, obtain the distance value AF from the radar to point F, the distance value BF from point B to point F, the angle α between AF and AB, and the angle β between BF and AB;

[0053] The calculation module is used to calculate the straight-line distance between the radar and the obstacle according to the position information of the two points.

[0054] In the above embodiment, it also includes a target point filtering module, which is used to draw a fitting straight line according to multiple target points in the target point distribution map, and filter out target points that deviate from the fitting straight line and exceed a set threshold. The drawn fitting straight line is one or more.

[0055] In the above embodiment, the calculation module includes a first calculation unit, a second calculation unit and a third calculation unit. The first calculation unit is used to calculate the straight-line distance AD ​​from point A to the central axis of the radar, and the second calculation unit is used to calculate the straight-line distance BE from point B to the central axis of the radar; the third calculation unit is used to calculate the straight-line distance from point F to the obstacle based on the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar.

[0056] In the above embodiment, the calculation method of the straight-line distance FC from point F to the obstacle is:

[0057] The distance AB is calculated according to the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar. The calculation formula is: AB = S (AD + BE) = S (AF × sin α + BF × sin β), where S is the correction coefficient;

[0058] ∠ABF and ∠BAF are calculated according to the sine theorem. The calculation formula is AB÷sin(α+β)=AF÷sin∠ABF=BF÷sin∠BAF;

[0059] Calculate the straight-line distance FC from the radar to the obstacle using the formula FC = AF × sin∠BAF = BF × sin∠ABF.

[0060] In the above embodiment, a learning module is also included, which corrects the correction coefficient S through a recurrent neural network, thereby continuously improving the accuracy of calculating the distance between the radar and the obstacle. The specific correction process is to compare the calculated result with the actual distance so that the calculated result is continuously close to the actual distance.

[0061] The beneficial effects of the present invention are as follows: the anti-collision warning system and the anti-collision warning method for low-altitude flying objects involved in the present invention are optimized for low-altitude specific obstacles (such as slender targets such as electric wires and flagpoles), can promptly detect obstacles at a distance greater than 200m, and can promptly issue an alarm, thereby reducing the probability of flying objects colliding with obstacles and reducing property losses. The anti-collision warning system can be installed around and above and below the low-altitude flying object, and can be determined according to the actual application scenario and the flight characteristics of the low-altitude flying object. The method for optimizing the anti-collision warning system for low-altitude specific obstacles can also be used for other similar targets, providing ideas for other similar target detection and warning functions.

[0062] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A low-altitude flying object collision prevention and warning method, characterized in that: The following steps are involved: S1. Preliminary detection: Detect multiple target points on the obstacle through radar to form a target point distribution map; S2, target image enhancement: repeat step "S1" to obtain a multi-frame target point distribution map, and superimpose the multi-frame target point distribution maps to increase the intensity of the target; S3, initial value acquisition: extract the two points closest to the radar in the obstacle, and mark the two points as point A and point B, set the intersection of the radar's central axis and the low-altitude flying object as point F, obtain the distance AF from point A to point F, the distance BF from point B to point F, the angle α between AF and the radar's central axis, and the angle β between BF and the radar's central axis; S4. Obstacle distance calculation: obtain the distance AF from point A to point F, the distance BF from point B to point F, the angle α between AF and the central axis of the radar, and the angle β between BF and the central axis of the radar, and calculate the straight-line distance from point F to the obstacle.

2. The low-altitude flying object anti-collision warning method according to claim 1, characterized in that: The obstacle calculation step includes the following steps: Calculate the straight-line distance AD ​​from point A to the central axis of the radar based on the distance value AF from point A to point F and the angle α between AF and the central axis of the radar; Calculate the straight-line distance BE from point B to the central axis of the radar based on the distance value BF from point B to point F and the angle β between BF and the central axis of the radar; The distance AB is calculated according to the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar. The calculation formula is: AB = S (AD + BE) = S (AF × sin α + BF × sin β), where S is the correction coefficient; ∠ABF and ∠BAF are calculated according to the sine theorem. The calculation formula is AB÷sin(α+β)=AF÷sin∠ABF=BF÷sin∠BAF; Calculate the straight-line distance FC from the radar to the obstacle using the formula FC = AF × sin∠BAF = BF × sin∠ABF.

3. The low-altitude flying object anti-collision warning method according to claim 1, characterized in that: It also includes target point filtering, drawing a fitted straight line along multiple target points, filtering out target points that deviate from the fitted straight line and exceed a set threshold, and the drawn fitted straight line is one or more.

4. The low-altitude flying object anti-collision warning method according to claim 1, characterized in that: It also includes correcting the correction coefficient S through a recurrent neural network, thereby continuously improving the accuracy of calculating the distance between the radar and the obstacle.

5. A low-altitude flying object anti-collision warning system, used for the low-altitude flying object anti-collision warning method according to any one of claims 1 to 4, characterized in that: It includes radar, image enhancement module, data storage module, data extraction module and calculation module, among which: The radar is used to detect multiple target points on the obstacle to form a multi-frame target point distribution map; The image enhancement module is used to superimpose target point distribution maps of multiple frames to increase the intensity of target points in the target point distribution maps; The data storage module is used to store the target point distribution map of the enhanced processing; The data extraction module is used to extract at least two points closest to the radar in the target point distribution map, and send the position information of the two points to the calculation module, and mark the two closest points as point A and point B, set the intersection of the central axis of the radar and the low-altitude flying object as point F, obtain the distance value AF from the radar to point F, the distance value BF from point B to point F, the angle α between AF and the central axis of the radar, and the angle β between BF and the central axis of the radar; The calculation module is used to calculate the straight-line distance between the radar and the obstacle according to the position information of the two points.

6. The low-altitude flying object anti-collision warning system according to claim 5, characterized in that: It also includes a target point filtering module, which is used to draw a fitting straight line according to multiple target points in the target point distribution map, and filter out target points that deviate from the fitting straight line and exceed a set threshold. The drawn fitting straight line is one or more.

7. The low-altitude flying object anti-collision warning system according to claim 5, characterized in that: The calculation module includes a first calculation unit, a second calculation unit and a third calculation unit, wherein the first calculation unit is used to calculate the straight-line distance AD ​​from point A to the central axis of the radar, and the second calculation unit is used to calculate the straight-line distance BE from point B to the central axis of the radar; The third calculation unit is used to calculate the straight-line distance from point A to the obstacle according to the straight-line distance AD ​​from point A to the central axis of the radar and the straight-line distance BE from point B to the central axis of the radar.

8. The low-altitude flying object anti-collision warning system according to claim 7, characterized in that: The calculation formula of the straight-line distance AC from point A to the obstacle is AC=S(AD+BE), where S is the correction coefficient and AC is the straight-line distance from point A to the obstacle.

9. The low-altitude flying object anti-collision warning system according to claim 7, characterized in that: It also includes a learning module, which corrects the correction coefficient S through a recurrent neural network, thereby continuously improving the accuracy of calculating the distance between the radar and the obstacle.

Images