Sky light source analysis method and sky light source analysis system

Abstract

The invention discloses a sky light source analysis method and system, and the method comprises the steps: carrying out the continuous long-exposure time-delay photographing of the sky, and obtaining a real-time photographed sky image; the method comprises the following steps: processing a sky image, extracting visible light source information, calculating a motion vector of a light source according to the sky image shot in real time to form a motion track of the light source, analyzing characteristics of the light source, and identifying, classifying and recording the light source according to the motion track and an analysis result to form a light source database. All-weather and all-time-period sky monitoring is carried out through long-exposure time-delay photography, light source changes in different time periods can be captured, light sources in the sky can be recorded, recognized, classified and marked, a light source database is formed through continuous monitoring and data collection, a manager can backtrack related data at any time, and the management efficiency is improved. The high-risk time period and the abnormal light source are deeply analyzed, accurate monitoring and effective management of disturbance flight or black flight of the unmanned aerial vehicle can be achieved, and therefore economic losses are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of urban management, and in particular to a sky light source analysis method and an analysis system thereof. Background Art

[0002] Illegal drone flights refer to the illegal flight of drones into controlled airspace (such as around airports). This behavior not only violates aviation regulations, but may also pose a serious threat to flight safety. In recent years, with the popularity of drones, the frequency of illegal flight incidents has increased dramatically. Many illegal drone flight incidents have led airport management departments to take grounding measures to ensure flight safety. Although this decision is made for safety reasons, it is often due to the inability to provide accurate light source information or specific evidence. The grounding not only directly affects air travel operations, causing flight delays or cancellations, but may also cause economic losses to airlines and passengers. In addition, due to the sensitivity of air transportation, frequent grounding incidents may also have a long-term impact on the airport's reputation and customer trust.

[0003] Observations of abnormal light sources by on-site staff or onlookers are mostly sporadic. They may see spots of light or flashes of light, but lack the professional knowledge and skills to identify the specific nature of the light source (such as whether it is a drone, bird or other aircraft). There are many different light sources in the night sky, including aircraft navigation lights, stars, and even city building lights. The similarity of these light sources makes it difficult for witnesses to make accurate judgments. At critical moments, witnesses may have lost part of the information about the light source. Coupled with the delay in information transmission, subsequent event judgments become more complicated. When management departments are faced with multiple pieces of fragmented information, it is often difficult to make scientific and accurate judgments. This uncertainty leads to overreaction, which ultimately affects flight scheduling and airport operations. Summary of the invention

[0004] The object of the present invention is to provide a sky light source analysis method and an analysis system thereof to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a sky light source analysis method, the method comprising:

[0006] Conduct continuous long-exposure time-lapse photography of the sky to obtain real-time images of the sky;

[0007] The sky image is processed to extract visible light source information. The motion vector of the light source is calculated based on the real-time sky image to form the motion trajectory of the light source. The characteristics of the light source are analyzed. According to the motion trajectory and analysis results, the light source is identified, classified, and recorded to form a light source database.

[0008] Furthermore, performing continuous long-exposure time-lapse photography on the sky to obtain a real-time captured sky image includes: dividing the sky into multiple sky sectors, setting up multiple observation points, performing continuous long-exposure time-lapse photography on each sky sector to obtain a real-time captured sky image, and classifying the sky images according to different time periods and sky sectors.

[0009] Furthermore, the characteristics of the light source include one or more of the color, stroboscopic frequency, moving speed, brightness, and position of the light source.

[0010] Furthermore, the types of light sources include passenger aircraft navigation lights, drone signal lights and starlight. The motion trajectory is judged to be the motion trajectory of a passenger aircraft, the motion trajectory of a drone or the motion trajectory of starlight based on the characteristics of the motion trajectory and the light source. The judgment result is classified and stored in the light source database.

[0011] Furthermore, the abnormal light source is obtained and compared with the light source information in the light source database. When the abnormal light source is determined to be a drone signal light, the motion trajectory of the passenger plane, the motion trajectory of the drone and the motion trajectory of the starlight in the light source database are combined to determine whether it is an illegal or disruptive drone.

[0012] Furthermore, the obtaining of the abnormal light source includes: monitoring a sky image captured in real time to obtain the abnormal light source.

[0013] Furthermore, the obtaining of the abnormal light source includes: judging whether the light source is an abnormal light source according to the external input light source.

[0014] Furthermore, the determining whether it is an abnormal light source includes:

[0015] Display the real-time images and the time-lapse images within the preset time on the display screen;

[0016] Analyze the changes between the current image and the image within the preset time period in the past based on the real-time image and the delayed image, analyze the feature differences between the real-time image and the delayed image based on the changes, and determine whether it is an abnormal light source based on the feature differences.

[0017] A sky light source analysis system, the analysis system comprising:

[0018] The acquisition module is used to perform continuous long-exposure time-lapse photography of the sky to obtain real-time sky images;

[0019] The processing module is connected to the acquisition module signal, and is used to process the sky image, extract visible light source information, calculate the motion vector of the light source according to the real-time sky image to form the motion trajectory of the light source, and analyze the characteristics of the light source. According to the motion trajectory and analysis results, the light source is identified, classified, and recorded to form a light source database.

[0020] Furthermore, the analysis system also includes an acquisition module and an analysis module. The acquisition module is used to acquire abnormal light sources, and the analysis module is used to compare the abnormal light sources with the light source information in the light source database. When the abnormal light source is determined to be a drone signal light, the motion trajectory of the passenger plane, the motion trajectory of the drone and the motion trajectory of the starlight in the light source database are combined to determine whether it is an illegal or disruptive drone.

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention utilizes long-exposure time-lapse photography to conduct all-weather and all-time sky monitoring, can capture changes in light sources in different time periods, record light sources in the sky, and identify, classify and mark them, and accumulate a large amount of light source data through continuous monitoring and data collection to form a light source database. In this way, once an abnormal situation occurs, managers can trace back relevant data at any time and conduct in-depth analysis of high-risk time periods and abnormal light sources, so as to achieve accurate monitoring and effective management of drone interference or illegal flights, thereby reducing economic losses and improving overall aviation safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a schematic diagram of the flow of the sky light source analysis method of the present invention;

[0023] Figure 2 This is a block diagram of the sky light source analysis system of the present invention. DETAILED DESCRIPTION

[0024] 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.

[0025] like Figure 1 As shown, this embodiment provides a sky light source analysis method, the method comprising the following steps:

[0026] S1: Take continuous long-exposure time-lapse photography of the sky to obtain a real-time sky image;

[0027] S2: Process the sky image, extract the visible light source information, calculate the motion vector of the light source based on the real-time sky image to form the motion trajectory of the light source, analyze the characteristics of the light source, identify, classify and record the light source based on the motion trajectory and analysis results to form a light source database.

[0028] Specifically, the sky is divided into multiple sky sectors, multiple observation points are arranged, and multiple optical devices are arranged at each observation point. A time-lapse camera is mainly used to perform continuous long-exposure time-lapse photography of each sky sector, and multi-spectral cameras, panoramic cameras, lidars, etc. are used for auxiliary shooting to obtain real-time sky images, and the sky images are classified according to different time periods and sky sectors. The sky images are processed, for example, using Gaussian filters or median filters to remove image noise, converting images from RGB to HSV or LAB color space to facilitate color analysis, setting a threshold range according to known light source colors for color segmentation, extracting the contour of the segmented image, obtaining the light source position and color information, and calculating the displacement and time interval of the light source in adjacent frames by analyzing continuous image frames, thereby obtaining the moving speed, recording the light source position of each frame, and calculating the movement of the light source according to the position and moving speed. The motion vector forms a motion trajectory. The brightness information of the light source is obtained by calculating the average brightness or grayscale value within the contour. The appearance time of the light source is recorded in continuous image frames, and then the stroboscopic frequency is calculated. The motion trajectory and characteristics of the light source (such as the color, stroboscopic frequency, moving speed, brightness, and position of the light source) are analyzed for preliminary identification. In this way, based on the light source characteristics and motion trajectory, it is possible to distinguish and classify which is starlight, which is flight light, and which may be a drone. For example, the trajectory of the stars is in an arc shape, and the navigation lights of civil airliners are in a continuous straight line trajectory, while the light source trajectory of a drone may be relatively irregular. The navigation lights of civil aviation flights generally have specific flashing and color patterns, while the lights of drones may be more random and changeable. In this way, the light source is classified using a machine learning classifier (such as SVM, random forest) based on the motion trajectory and light source characteristics, and the light source information is recorded in the database to form a light source database;

[0029] Monitor the sky image captured in real time to determine whether there is an abnormal light source, or determine whether it is an abnormal light source based on the light source input externally, such as the light source information provided by the public report. When judging, display the real-time picture taken and the time-lapse picture taken in the past half hour on the display screen, analyze the changes between the current picture and the picture in the past preset time period based on the real-time picture and the time-lapse picture, analyze the feature differences between the real-time picture and the time-lapse picture based on the changes, and determine whether it is an abnormal light source based on the feature differences. For example, compare the position difference of the light source in the real-time picture and the time-lapse picture taken in the past half hour, analyze the change of the brightness of the light source, compare the stroboscopic mode of the light source, compare whether the color of the light source has changed significantly, calculate the feature difference value between the real-time picture and the time-lapse picture taken in the past half hour, determine whether it is an abnormal light source based on the preset threshold, compare the abnormal light source with the light source information in the light source database, and when it is determined that the abnormal light source is a drone signal light, combine the customer information in the light source database The motion trajectory of the aircraft, the motion trajectory of the UAV and the motion trajectory of the starlight can be used to determine whether it is an illegal flight or a disruptive flight UAV. For example, the abnormal light source can be compared with the motion trajectory of the passenger plane in the database. If the motion trajectory of a certain light source overlaps with the motion trajectory of the passenger plane, it can be reasonably inferred that the light source is a civil airliner, otherwise it may be a UAV. Combined with the motion trajectory of the starlight and the motion trajectory of the UAV in the database, the behavior pattern of the abnormal light source is further analyzed. For example, the rapid and nonlinear movement of a single light source in a short period of time may indicate that it is a UAV rather than a star. When determining that the abnormal light source is a UAV signal light, combined with its flight path, speed, flight altitude and other data, if the UAV light source is within the airspace permitted by law and does not conflict with the flight trajectory, the possibility of illegal flight can be ruled out. If the UAV overlaps with the flight trajectory in terms of flight altitude and time, it can be preliminarily determined as a potential illegal flight behavior. The UAV light source is compared with the motion trajectory of the UAV in the database to confirm whether it is a disruptive flight or illegal flight.

[0030] Application scenario 1:

[0031] An airport hopes to establish a sky light source analysis system in its surrounding area to monitor air traffic in real time, especially to identify and track drones to prevent illegal intrusion or interference with normal aviation flights.

[0032] Multiple time-lapse cameras, multispectral cameras and lidars are installed around the airport, responsible for a specific sky sector. These devices continuously perform long-exposure time-lapse photography to generate real-time high-quality sky images. The images are classified and stored according to time and sector for subsequent processing and analysis. The light source information in the image is extracted through image processing algorithms. According to the continuous image sequence, the motion vector of the light source is calculated to form their motion trajectory at each time point. The characteristics of the light source, such as color, strobe frequency, moving speed, brightness and position, are analyzed, and the type of light source is preliminarily identified based on these characteristics. According to the motion trajectory and characteristic analysis results of the light source, it is determined whether the light source is a passenger aircraft navigation light, a drone signal light or starlight. For example, a fast-moving light with a high strobe frequency may be a drone, while a slow-moving light with a constant brightness may be a passenger aircraft. The identification and classification results are recorded in the light source database to provide data support for subsequent analysis and decision-making. The system monitors the sky image in real time and identifies any abnormal light sources that suddenly appear (such as new light sources that have not been recorded). The information of the abnormal light source is compared with the standard light source information in the light source database to determine whether it is a drone signal light. Combined with the movement trajectories of passenger aircraft and starlight in the light source database, the movement pattern of the abnormal light source is analyzed to determine whether it is a "black flying" or "disrupting flying" drone.

[0033] For example: after receiving a report from the public, a light source video is received, and it is determined whether the light source video is an abnormal light source. When judging, the real-time picture taken and the time-lapse picture taken in the past half hour are displayed on the display screen. The changes between the current picture and the picture in the past preset time period are analyzed based on the real-time picture and the time-lapse picture. It is found that the light source has a high strobe frequency and a fast moving speed, which is highly matched with the characteristics of the drone signal light in the database. Combined with its flight path, speed, flight altitude and other data, if the drone light source is within the airspace permitted by law and does not conflict with the flight trajectory, the possibility of illegal flight can be ruled out. If the drone overlaps with the flight trajectory in terms of flight altitude and time, it can be preliminarily determined as a potential illegal flight behavior. The drone light source is compared with the movement trajectory of the drone in the database to confirm whether it is a disruptive flight or an illegal flight. After confirmation, the personnel are notified to handle it, such as activating the drone interception mechanism.

[0034] Application scenario 2:

[0035] A city hopes to establish a sky light source analysis system to monitor and identify sky light sources at night, especially drones, to prevent illegal intrusion or interference with public activities in the city.

[0036] Time-lapse cameras, panoramic cameras and lidar are installed on the tops of several high-rise buildings in the city center to cover the night sky of the entire city. The equipment continuously performs long-exposure time-lapse photography to obtain real-time images of the city's night sky. The images are classified and stored according to time and location for subsequent processing and analysis. The acquired night sky images are processed to extract highlight areas and potential light source information. According to the continuous image sequence, the motion vector of the light source is calculated to form their motion trajectory in the night sky. The color, stroboscopic frequency, moving speed, brightness and position of the light source are analyzed. According to the motion trajectory and feature analysis results of the light source, it is determined whether the light source is a passenger aircraft navigation light, a drone signal light or starlight. For example, a fast-moving light with a high stroboscopic frequency may be a drone. The identification and classification results are recorded in the light source database for subsequent analysis and decision-making. The system monitors the night sky images in real time and identifies any abnormal light sources that suddenly appear (such as new light sources that have not been recorded). The information of the abnormal light source is compared with the standard light source information in the light source database to determine whether it is a drone signal light. Combined with the motion trajectories of passenger aircraft and starlight already in the light source database, the motion pattern of the abnormal light source is analyzed to determine whether it is a "black flight" or "disturbance" drone.

[0037] For example, the system uses continuous long-exposure time-lapse photography to find that a fast-moving light source suddenly appears in the night sky of the city center in the real-time picture, and determines whether the light source video is an abnormal light source. When judging, the real-time picture taken and the time-lapse picture taken in the past half an hour are displayed on the display screen. According to the real-time picture and the time-lapse picture, the changes between the current picture and the picture in the past preset time period are analyzed, and it is found that the light source has a high strobe frequency and a fast moving speed, which is highly matched with the characteristics of the drone signal light in the database. Combined with its flight path, speed, flight altitude and other data, if the drone light source is within the airspace permitted by law and does not conflict with the flight trajectory, the possibility of illegal flight can be ruled out. If the drone overlaps with the flight trajectory in terms of flight altitude and time, it can be preliminarily judged as a potential illegal flight. The drone light source is compared with the movement trajectory of the drone in the database to confirm whether it is a disturbing flight or illegal flight, and the city security department is notified for further confirmation and processing, such as using a signal jammer to force the drone to land.

[0038] like Figure 2 As shown, this embodiment also provides a sky light source analysis system, the analysis system comprising:

[0039] The acquisition module 1 is used to perform continuous long-exposure time-lapse photography of the sky to obtain a real-time sky image. A time-lapse photography camera, a multi-spectral camera, a panoramic camera, a laser radar, etc. can be used. The time-lapse photography camera is mainly used to perform continuous long-exposure time-lapse photography of each sky sector, and is supplemented by a multi-spectral camera, a panoramic camera, a laser radar, etc. for auxiliary shooting;

[0040] The processing module 2 is connected to the acquisition module 1 signal, and is used to process the sky image, extract the visible light source information, calculate the motion vector of the light source according to the real-time sky image to form the motion trajectory of the light source, and analyze the characteristics of the light source. According to the motion trajectory and analysis results, the light source is identified, classified, and recorded to form a light source database.

[0041] Acquisition module 3, used to acquire abnormal light source;

[0042] The analysis module 4 is connected to the acquisition module 3 and the processing module 2 for signal connection, and is used to compare the abnormal light source with the light source information in the light source database. When determining that the abnormal light source is a drone signal light, the motion trajectory of the passenger plane, the motion trajectory of the drone and the motion trajectory of the starlight in the light source database are combined to determine whether it is an illegal or disruptive drone.

[0043] The present invention utilizes long-exposure time-lapse photography to conduct all-weather, all-time sky monitoring. It can capture changes in light sources in different time periods, record light sources in the sky, and identify, classify and mark them. Through continuous monitoring and data collection, a large amount of light source data is accumulated to form a light source database. In this way, once an abnormal situation occurs, managers can trace back relevant data at any time and conduct in-depth analysis of high-risk time periods and abnormal light sources. Accurate monitoring and effective management of drone interference or illegal flights can be achieved, thereby reducing economic losses and improving overall aviation safety.

[0044] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A sky light source analysis method, characterized in that: The method comprises: Conduct continuous long-exposure time-lapse photography of the sky to obtain real-time images of the sky; The sky image is processed to extract visible light source information. The motion vector of the light source is calculated based on the real-time sky image to form the motion trajectory of the light source. The characteristics of the light source are analyzed. According to the motion trajectory and analysis results, the light source is identified, classified, and recorded to form a light source database.

2. The sky light source analysis method according to claim 1, characterized in that: Performing continuous long-exposure time-lapse photography of the sky to obtain a real-time captured sky image includes: dividing the sky into multiple sky sectors, deploying multiple observation points, performing continuous long-exposure time-lapse photography on each sky sector to obtain a real-time captured sky image, and classifying the sky images according to different time periods and sky sectors.

3. The sky light source analysis method according to claim 1, characterized in that: The characteristics of the light source include one or more of the color, strobe frequency, moving speed, brightness, and position of the light source.

4. The sky light source analysis method according to claim 1 or 3, characterized in that: The types of light sources include passenger aircraft navigation lights, drone signal lights and starlight. The motion trajectory is judged as the motion trajectory of a passenger aircraft, the motion trajectory of a drone or the motion trajectory of starlight based on the motion trajectory and the characteristics of the light source. The judgment result is classified and stored in the light source database.

5. The sky light source analysis method according to claim 4, characterized in that: The method also includes: obtaining an abnormal light source, comparing it with the light source information in a light source database, and when determining that the abnormal light source is a drone signal light, combining the motion trajectory of the passenger plane, the motion trajectory of the drone and the motion trajectory of the starlight in the light source database to determine whether it is an illegal or disruptive drone.

6. The sky light source analysis method according to claim 5, characterized in that: The obtaining of the abnormal light source includes: monitoring a sky image captured in real time to obtain the abnormal light source.

7. The sky light source analysis method according to claim 5, characterized in that: The obtaining of the abnormal light source includes: judging whether the light source input from the outside is an abnormal light source.

8. The sky light source analysis method according to claim 5 or 6, characterized in that: The determining whether it is an abnormal light source comprises: Display the real-time images and the time-lapse images within the preset time on the display screen; Analyze the changes between the current image and the image within the preset time period in the past based on the real-time image and the delayed image, analyze the feature differences between the real-time image and the delayed image based on the changes, and determine whether it is an abnormal light source based on the feature differences.

9. A sky light source analysis system, characterized in that: The analysis system comprises: The acquisition module is used to perform continuous long-exposure time-lapse photography of the sky to obtain real-time sky images; The processing module is connected to the acquisition module signal, and is used to process the sky image, extract visible light source information, calculate the motion vector of the light source according to the real-time sky image to form the motion trajectory of the light source, and analyze the characteristics of the light source. According to the motion trajectory and analysis results, the light source is identified, classified, and recorded to form a light source database.

10. The sky light source analysis system according to claim 9, characterized in that: The analysis system also includes an acquisition module and an analysis module. The acquisition module is used to acquire abnormal light sources, and the analysis module is used to compare the abnormal light sources with the light source information in the light source database. When the abnormal light source is determined to be a drone signal light, the motion trajectory of the passenger plane, the motion trajectory of the drone and the motion trajectory of the starlight in the light source database are combined to determine whether it is an illegal or disruptive drone.

Images