Method for detecting and monitoring low altitude unmanned aerial vehicles above highways

Abstract

The present application relates to a kind of high-speed road upper low altitude unmanned aerial vehicle detection and monitoring method, belong to low altitude target detection field.The present application is to overcome the current low altitude detection system, the problem that low altitude unmanned aerial vehicle cannot be accurately detected on high-speed road upper flight, by distributed detection method, using widely distributed camera to detect unmanned aerial vehicle, and form track information.The present application uses the photoelectric camera widely distributed on high-speed road, adjusts camera posture when needed, uses camera to detect low altitude unmanned aerial vehicle, uses camera networking information to form unmanned aerial vehicle flight track, supports airspace control and military operation needs.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of low-altitude target detection, and particularly relates to a method for detecting and monitoring low-altitude unmanned aerial vehicles above highways. BACKGROUND

[0002] In the field of air target detection, through various ground radars and air radars, the effective detection of medium-high altitude, high altitude targets and low altitude fast targets can be basically realized. However, for unmanned aerial vehicles flying along highways, due to the similarity of their speed and flight path to ground vehicles, it is difficult for existing means to distinguish between the two when both the unmanned aerial vehicle and the vehicle appear in the same beam and distance unit, which is a difficulty in the field of air target detection. The present application uses the idea of distributed detection to detect unmanned aerial vehicles flying above highways through widely distributed cameras.

[0003] Highway cameras are generally divided into three types. The first type is a speed camera combined with a radar module. The radar module is used to detect high-speed vehicles, and the camera is used to take photos. The second type is a security checkpoint camera, which is used to take photos of vehicles and personnel entering and leaving, and to investigate suspicious vehicles and personnel. The third type is a monitoring camera with LED light devices that can remain on at night to ensure clear camera vision. In recent years, various multifunctional cameras have become increasingly widespread. As of the end of 2021, the total length of highways in China was 169,000 kilometers, and the total length of high-speed railways was 40,000 kilometers. There are approximately 24 million cameras distributed on various types of highways, with a shooting speed of 10 ms. The speed detection distance is 300 meters, and the detection distance of high-magnification zoom cameras can reach 500 to 2000 meters, which can be used to detect low-altitude flying unmanned aerial vehicles.

[0004] The present application uses widely distributed cameras on highways to detect and identify unmanned aerial vehicles through camera networks to achieve information networking and form target track information, which helps to detect and monitor low-altitude unmanned aerial vehicles above highways. The present application can be used in the fields of airspace management and military operations. SUMMARY

[0005] (I) Technical problems to be solved

[0006] The technical problem to be solved by the present application is how to provide a method for detecting and monitoring low-altitude unmanned aerial vehicles above highways to solve the problem of low-altitude detection of special targets in the field of air target detection.

[0007] (II) Technical solutions

[0008] In order to solve the above technical problems, the present application provides a method for detecting and monitoring low-altitude unmanned aerial vehicles above highways, which comprises the following steps:

[0009] S1, camera air monitoring

[0010] At the required moment, the designated area camera is selected to turn into an air monitoring mode for work; when the UAV approaches the highway, the camera is remotely controlled through the network to turn into an air detection mode, according to the position information of the UAV and the designated camera, the camera detection elevation angle is calculated in real time, the camera and its associated equipment are guided to automatically adjust according to the guided elevation angle, and the air detection working mode is turned into;

[0011] S2, UAV detection and identification

[0012] When the camera works in the UAV detection mode, once the UAV enters the camera monitoring range, the camera performs image detection and target identification according to the pre-set detection rules, and when the target is identified as a UAV, it is tracked and photographed for evidence; when the calculation power is allowed and the calculation parameters meet the conditions, the precise orientation of the UAV is realized according to the pre-stored camera position and attitude and the position information of the target in the image;

[0013] S3, information networking fusion

[0014] Under the networking of the camera, if multiple cameras in the network observe the UAV target at the same time, the camera information in the network is fused, the UAV position is calculated through the cross positioning of the double cameras according to the position information of each camera and the direction information of the UAV detected by each camera;

[0015] If only a single camera in the network observes the target at the same time, the distance of the UAV is estimated through the detection ability of the single camera.

[0016] (Three) beneficial effects

[0017] The present application provides a kind of low altitude UAV detection and monitoring method above highway, the present application provides a kind of low altitude UAV detection and monitoring method above highway, which can be used for UAV detection, tracking and identification.The method mainly proposes two points, one is to use the camera deployed on the highway for detecting ground target, if necessary, change its working mode, execute the detection, tracking and identification function of unmanned aerial vehicle in the air;Two is to use distributed camera, network fusion, multi-station cross positioning, same identification, clustering, batch, continuous tracking and type and model identification are carried out to the UAV target detection information.The method can be used in low altitude target detection and airspace supervision fields, and can solve the detection problem of low altitude UAV flying along the highway. DETAILED DESCRIPTION

[0018] Figure 1 The flow chart of the low altitude UAV detection and monitoring method above highway of the present application. DETAILED DESCRIPTION

[0019] In order to make the purpose, content and advantages of the present application more clear, the specific embodiments of the present application are described in further detail below in combination with the drawings and examples.

[0020] The present application relates to a method for detecting and monitoring low-altitude unmanned aerial vehicles above highways, and belongs to the field of low-altitude target detection. In order to overcome the problem that the current low-altitude detection system cannot accurately detect low-altitude unmanned aerial vehicles above highways, the present application uses a distributed detection method to detect unmanned aerial vehicles by using widely distributed cameras (including radar speed measurement systems) and forms flight path information. Because traditional low-altitude and ultra-low-altitude flying unmanned aerial vehicles mainly rely on ground radars, air radars, and special photoelectric imaging and laser ranging equipment, and military equipment is most common. Among them, when radars detect low-altitude flying unmanned aerial vehicles above highways, the cars driving on the highway will cause false alarm points in the radar detection process, making it difficult to distinguish the unmanned aerial vehicle points, resulting in flight path correlation errors and eventually breaking off the flight; special photoelectric imaging and laser ranging equipment are not conducive to widespread deployment due to short detection distance and high cost. Traditional special radars and photoelectric equipment cannot effectively solve the problem of detecting low-altitude unmanned aerial vehicles above highways. The present application uses photoelectric cameras widely distributed on highways to adjust the camera attitude when needed, detects low-altitude flying unmanned aerial vehicles by using cameras, forms the flight path of unmanned aerial vehicles by using camera networking information, and supports the need for airspace control and military operations.

[0021] The basic process of the present application includes three basic steps, namely camera air monitoring, unmanned aerial vehicle detection and identification, and information networking fusion.

[0022] S1, camera air monitoring

[0023] At the required moment, the specified area camera is selected to enter the air monitoring mode for work. The normal working mode of the camera on the highway is the ground detection working mode, which is mainly used for shooting ground vehicles or pedestrians. When the unmanned aerial vehicle approaches the highway, the camera is remotely controlled by the network to enter the air detection mode. According to the position information of the unmanned aerial vehicle and the specified camera, the camera detection elevation angle is calculated in real time, and the camera is guided to automatically adjust together with its associated equipment such as the lighting lamp and the speed radar according to the guided elevation angle, and enters the air detection working mode.

[0024] The selection of the camera can be based on the pre-set area, extracting all or part of the cameras in the area, or setting an interception zone according to the direction of the unmanned aerial vehicle attack using special rules.

[0025] S2, unmanned aerial vehicle detection and identification

[0026] When the camera works in the unmanned aerial vehicle detection mode, once the unmanned aerial vehicle enters the monitoring range of the camera, the camera carries out image detection and target identification according to the pre-set detection rule, and when the unmanned aerial vehicle is identified, the camera carries out tracking and photographing. When the calculation power is allowed and the calculation parameters meet the conditions, the precise orientation (azimuth, pitch) of the unmanned aerial vehicle can be realized according to the pre-stored camera position and attitude and the position information of the target in the image; if the speed measuring radar can detect the unmanned aerial vehicle, the position and speed information of the unmanned aerial vehicle can be further calculated.

[0027] S3, information networking fusion

[0028] When the camera is networked, if multiple cameras in the network observe the unmanned aerial vehicle target at the same time, the information of the cameras in the network can be fused, the position of the unmanned aerial vehicle is calculated through the cross positioning of the double cameras according to the position information of each camera and the direction information of the unmanned aerial vehicle detected by each camera; if only a single camera in the network observes the target at the same time, the distance of the unmanned aerial vehicle is estimated through the detection capability of the single camera (since the detection distance of the camera is short, the distance error of the unmanned aerial vehicle is small after the information networking). The camera networking information can identify, cluster, batch and continuously track the unmanned aerial vehicle target in the networking area, and further form a relatively stable track for the target, and if necessary, the type and model of the unmanned aerial vehicle can be identified.

[0029] Embodiment 1:

[0030] The basic flow of the application is shown in the following figure, which includes three basic steps, namely camera air monitoring, unmanned aerial vehicle detection and identification, and information networking fusion.

[0031] S1, camera air monitoring

[0032] S11, military radar, photoelectric equipment capture and tracking of unmanned aerial vehicle;

[0033] S12, judging whether the unmanned aerial vehicle is flying along the highway or is about to enter the area near the highway by using a digital map;

[0034] S13, if the judgment condition is met, before the radar detection is invalid, part or all of the cameras in the nearby area are remotely controlled through the network to turn into air detection mode, or an interception zone is set according to the direction of the unmanned aerial vehicle attack;

[0035] S14, according to the position of the unmanned aerial vehicle and the position information of the camera itself, the detection angle of the camera is calculated in real time, and the camera is guided to adjust the angle together with the associated lighting lamp, speed measuring radar and the like according to the guide information;

[0036] In the absence of information guidance of the special radar and photoelectric equipment in S11, the interception area is detected and identified when the unmanned aerial vehicle enters the area by setting the camera on the highway.

[0037] S2, the unmanned aerial vehicle is detected and identified

[0038] S21, the camera works in the unmanned aerial vehicle detection mode, once the unmanned aerial vehicle enters the camera monitoring range, the camera carries out image detection, and adopts neural network algorithm for target identification;

[0039] S22, when the target is identified as an unmanned aerial vehicle, the target is tracked and photographed for evidence;

[0040] S23, if the calculation parameter meets the condition, according to the position and attitude of the camera and the position information of the target in the image, the accurate orientation (azimuth, pitch) of the unmanned aerial vehicle can be realized;

[0041] S24, if the speed radar can detect the unmanned aerial vehicle, the position and speed information of the unmanned aerial vehicle can be further calculated;

[0042] S25, while continuing to track the target, uploading the position, heading, speed, model, time, picture and other information of the unmanned aerial vehicle.

[0043] S3, information networking fusion

[0044] S31, if multiple cameras in the network observe the unmanned aerial vehicle target at the same time, the command center will receive the unmanned aerial vehicle information reported by multiple cameras;

[0045] S32, the same target is identified by using image information;

[0046] S33, if it is the same target, the cross positioning is carried out by using the target direction information uploaded by multiple cameras, and the positioning result of single camera is fused to improve the positioning accuracy;

[0047] S34, the track is started by using the point trail information fused by multiple cameras;

[0048] S35, the angle of the camera is adjusted to keep continuous tracking, the stable track is formed by using the camera networking, and the formed track information is sent to the special radar, photoelectric detection equipment or monitoring system to ensure the accuracy and continuity of the unmanned aerial vehicle detection track;

[0049] S36, the pictures taken by multiple cameras and the identification results of single camera are fused for further identification.

[0050] The application provides a highway upper low-altitude unmanned aerial vehicle detection and monitoring method, which can be used for unmanned aerial vehicle detection, tracking and identification. The method mainly proposes two points: one is to use the camera arranged on the upper part of the highway for detecting ground targets, and to change the working mode of the camera when necessary, so as to perform the functions of detecting, tracking and identifying the unmanned aerial vehicles in the air; the other is to use the distributed cameras to perform network fusion, multi-station cross positioning, same identity identification, clustering, batch, continuous tracking and type and model identification on the unmanned aerial vehicle target detection information. The method can be used in the fields of low-altitude target detection and airspace supervision, and can solve the problem of detecting the unmanned aerial vehicles flying along the highway at low altitudes.

[0051] The above only describes the preferred embodiments of the application, and it should be noted that those skilled in the art can make some improvements and modifications without departing from the technical principles of the application, and these improvements and modifications should also be considered as the protection scope of the application.

Claims

1. A method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways, characterized in that, The method includes the following steps: S1, Camera aerial surveillance When needed, the camera in the designated area is selected to switch to the air surveillance mode; when the drone approaches the highway, the camera is remotely controlled via the network to switch to the air detection mode. Based on the drone's position and the position information of the designated camera, the camera's detection elevation angle is calculated in real time, and the camera and its associated equipment are guided to automatically adjust according to the guided elevation angle and switch to the air detection mode. S2, Unmanned Aerial Vehicle Detection and Identification When the camera is in drone detection mode, once a drone enters the camera's monitoring range, the camera performs image detection and target recognition according to pre-set detection rules. When it is identified as a drone-type target, it tracks it and takes pictures for evidence. When computing power allows and computing parameters are met, the drone can be precisely oriented based on pre-stored camera position and attitude, as well as the target's position information in the image. S3, Information Network Integration When cameras are connected to the network, if multiple cameras in the network simultaneously observe the drone target, the information from the cameras in the network will be fused. Based on the position information of each camera and the direction information of the drone it detects, the position of the drone will be calculated by cross-positioning of the two cameras. If only a single camera observes the target within the network at any given time, the distance to the drone can be estimated using the detection capability of that single camera.

2. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 1, characterized in that, In step S1, the associated equipment includes: lighting and speed radar.

3. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 1, characterized in that, In step S1, the camera selects a pre-defined area and extracts all or part of the cameras in that area, or sets an interception zone according to special rules based on the direction of the incoming drone.

4. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 3, characterized in that, In step S2, if the speed measuring radar can detect the drone, then the drone's position and speed information are calculated.

5. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 1, characterized in that, In step S3, when the camera is connected to the network, it performs identity recognition, clustering, batching, and continuous tracking of UAV targets within the network area, thereby forming a relatively stable flight path for the target and also identifying the type and model of the UAV.

6. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in any one of claims 1-5, characterized in that, Step S1 specifically includes: S11, military radar, and optoelectronic equipment are used to capture and track drones; S12. Use digital maps to determine whether the drone is flying along a highway or about to enter the vicinity of a highway. S13. If the judgment conditions are met, before the radar detection fails, remotely control some or all cameras in the nearby area to switch to air detection mode via the network, or set up an interception zone according to special rules based on the direction of the incoming drone. S14. Based on the drone's location and the camera's own location information, calculate the camera's detection elevation angle in real time, and guide the camera and its associated equipment to adjust the elevation angle according to the guidance information.

7. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 6, characterized in that, In step S11, without the guidance of dedicated radar or optoelectronic equipment, a self-detection and interception zone is set up using cameras on the highway. When a drone enters this zone, it is detected and identified.

8. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 6, characterized in that, Step S2 specifically includes: S21. When the camera is operating in drone detection mode, once the drone enters the camera's monitoring range, the camera performs image detection and uses a neural network algorithm for target recognition. S22. When a target is identified as a drone, track it and take photos as evidence. S23. When computing power allows and calculation parameters are satisfied, the drone can be accurately oriented based on the camera position and attitude and the target's position information in the image. S24. If the speed measuring radar can detect the drone, then further calculate the drone's position and speed information.

9. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 8, characterized in that, Step S2 further includes: S25, while continuing to track the target, uploading information on the drone's location, heading, speed, model, time, and images.

10. The method for detecting and monitoring low-altitude unmanned aerial vehicles (UAVs) above highways as described in claim 8 or 9, characterized in that, Step S3 specifically includes: S31. If multiple cameras in the network simultaneously observe the drone target, the command center will receive drone information reported by multiple cameras. S32. Use image information to identify the identity of targets; S33. If it is the same target, use the target direction information uploaded by multiple cameras to perform cross-positioning, and fuse it with the positioning result of a single camera to improve positioning accuracy. S34. Use the point information fused from multiple cameras to initiate the flight path batching; S35. Guide the camera to adjust its angle to maintain continuous tracking, use the camera network to form a stable track, and send the track information to a dedicated radar, photoelectric detection equipment or monitoring system to ensure the accuracy and continuity of the UAV's track detection. S36. Further identification is performed by fusing images captured by multiple cameras with the recognition results from a single camera.

Images