Airport PAPI lighting anomaly recognition and detection method based on aerial video processing and analysis

Abstract

The present invention discloses a method for identifying and detecting airport PAPI light anomalies based on aerial video processing and analysis. The method comprises: capturing a video image of the airport PAPI light area, inputting it into a YOLOV8 target detector for target detection, and using a ByteTrack algorithm to obtain a target tracking trajectory; calculating the overall mean A of the PAPI lights, the spacing between adjacent PAPI lights, and the mean number of small lights in a full-process monitoring data set, and performing judgments on whether the PAPI lights are too low in brightness, not lit, or not lit; constructing a PAPI light flicker recognition model, utilizing the full-process monitoring data set to identify the flicker frequency characteristics of each PAPI light and finding the characteristic center of all PAPI lights, calculating the Euclidean distance between the flicker frequency characteristics of each PAPI light and the characteristic center, and if the Euclidean distance is greater than a flicker characteristic threshold, determining that a flicker anomaly exists and issuing an alarm. The present invention utilizes a YOLOV8 detector and a ByteTrack algorithm to calculate the trajectory information of the PAPI lights in the video, realizing detection of four abnormal states of the PAPI lights, and having the advantages of high accuracy and high reliability.

Description

Technical Field

[0001] The present invention relates to the field of airport lighting anomaly detection, and in particular to an airport PAPI lighting anomaly recognition and detection method based on aerial video processing and analysis. Background Art

[0002] In the field of modern aviation, the operational safety of airports is of vital importance; the navigation lighting system, especially the precision approach path indicator (PAPI light, usually, each PAPI light contains three to six bulbs side by side) provides visual reference to pilots, helping them maintain the correct descent angle during the approach. The abnormal detection of PAPI lights is an important technical means and step to ensure the stable operation of PAPI lights. It is one of the keys to ensure the stable landing of aircraft and plays an important role in the safety of airports. Specifically, the abnormal detection of PAPI lights refers to the use of technical means to detect PAPI lights that are in poor working condition, including the following four abnormal conditions: abnormal PAPI light brightness (including too high brightness and too low brightness), PAPI lights are not on, some PAPI bulbs are not on, and PAPI lights have abnormal flashing frequency.

[0003] Traditional PAPI lighting anomaly detection relies primarily on periodic manual inspections. This approach is not only inefficient but also difficult to detect in real time. Due to the long intervals between manual inspections, potential faults may pose a threat to flight safety before they are discovered. Driven by advances in electronic technology, automated detection systems based on sensors and monitoring devices have gradually been introduced. These solutions typically use optical sensors or photodetectors to monitor parameters such as light brightness and color. However, these early automated detection systems have numerous limitations. For example, they are sensitive to environmental factors such as dust and electromagnetic interference, which can lead to false or missed alarms. Furthermore, existing detection methods are limited in terms of system data integration and analysis, as well as scalability. Some systems lack effective integration and analysis of collected data, making it difficult to extract valuable information from the large amount of data and accurately determine the cause of lighting anomalies. Furthermore, existing general-purpose detection methods are difficult to fully adapt to various real-world situations, significantly compromising detection accuracy and reliability, and increasing deployment costs. Summary of the Invention

[0004] The purpose of the present invention is to solve the technical problems pointed out by the background technology, and provide an airport PAPI light anomaly recognition and detection method based on aerial video processing and analysis, construct a light label data set to train the YOLOV8 target detector for target detection, and the trained YOLOV8 target detector can realize the target detection of PAPI lights and small lights in PAPI lights. The ByteTrack algorithm associates and attributes PAPI lights and small lights in PAPI lights in a hierarchical manner to form target tracking trajectory data of each PAPI light and internal small light in a hierarchical manner; then the target tracking trajectory data is subjected to target traversal analysis to obtain a full-process monitoring data set. Based on the calculation, analysis and judgment of the full-process monitoring data set, the anomaly detection of PAPI lights and small lights is realized, providing convenient PAPI light anomaly detection technical support for civil airports, and promoting the improvement of the digital level of airport security work.

[0005] The purpose of the present invention is achieved through the following technical solutions:

[0006] A method for identifying and detecting airport PAPI lighting anomalies based on aerial video processing and analysis, the method comprising:

[0007] S1. Construct a light label dataset containing video images of the airport PAPI light area and PAPI light label annotations. Input the light label dataset into the YOLOV8 object detector for target detection training. The targets include PAPI lights and small lights in PAPI lights.

[0008] S2: Shoot a video image of the airport PAPI light area and input it into the YOLOV8 target detector for target detection. Then, use the ByteTrack algorithm to associate the target data and obtain the target tracking trajectory.

[0009] S3, traversing each frame of target tracking trajectory to form a full-process monitoring data set of the target;

[0010] S4. Calculate the overall mean A of the historical brightness average value sequence of the PAPI lamp in the full-process monitoring data set. If the overall mean A is less than the low brightness threshold, determine that the PAPI lamp brightness is too low and issue an alarm.

[0011] S5. Calculate the distance between two adjacent PAPI lights in the full-process monitoring data set. If the distance is greater than the light interval threshold, determine that there is a completely unlit PAPI light between the two adjacent PAPI lights and issue an alarm.

[0012] S6. Calculate the mean of the historical number of small lights in the PAPI lamp in the full-process monitoring data set. If the mean is less than the small light number threshold, determine that there are small lights that are not lit in the PAPI lamp and issue an alarm.

[0013] S7. Construct a PAPI lamp flicker recognition model and use the full-process monitoring data set to identify the flicker frequency characteristics of each PAPI lamp and find the characteristic center of all PAPI lamps. Calculate the Euclidean distance between the flicker frequency characteristics of each PAPI lamp and the characteristic center. If the Euclidean distance is greater than the flicker characteristic threshold, the corresponding PAPI lamp is judged to be flickering abnormally and an alarm is issued.

[0014] In order to better implement the present invention, the image frames of the video image are collected according to the time frame T1; the PAPI light labeling method is as follows: the area boxes of the belonging levels are marked according to the PAPI lights and the small lights in the PAPI lights, and the PAPI lights with too low brightness and too high brightness are marked respectively.

[0015] Preferably, the YOLOV8 target detector performs frame-by-frame target detection on the video image stream F(t), where t represents the sequential number of the video frame; the ByteTrack algorithm performs data association and target tracking based on the targets of the previous and next frames being the PAPI lights, and the ByteTrack algorithm performs data association and target tracking based on the targets of the previous and next frames being the small lights in the PAPI lights, and the small lights in the PAPI lights are hierarchically associated and attributed to the corresponding PAPI lights.

[0016] Preferably, the full-process monitoring data set stores target detection data and trajectory data of n PAPI lights and m small lights according to hierarchical attribution; wherein the i-th PAPI light sequence expression of the n PAPI lights is S(i) = {U(i), X(i), Y(i), Z(i)}, U(i) is the historical trajectory coordinate center position sequence of the i-th PAPI light, X(i) is the historical number sequence of small lights contained in the i-th PAPI light, Y(i) is the historical brightness average value sequence of the i-th PAPI light area, and Z(i) is the missed detection video frame position sequence in which no PAPI light label is detected in the trajectory of the i-th PAPI light; the n PAPI lights are respectively organized into a full-process monitoring data set in chronological order.

[0017] Preferably, in step S4, if the overall mean A is greater than the high brightness threshold, the PAPI light brightness is determined to be too high and an alarm is issued; the PAPI light brightness being too low and the PAPI light brightness being too high are collectively referred to as abnormal PAPI light brightness.

[0018] Preferably, in step S5, the PAPI light information between two adjacent PAPI lights is output along with the alarm prompt.

[0019] Preferably, the PAPI light flicker recognition model extracts the difference sequence between the missed video frame sequence and the adjacent non-missed video frame sequence in the full-process monitoring data set, calculates its mean and variance as the flicker frequency feature, and the adjacent non-missed video frame sequence is the PAPI light target trajectory data that does not belong to the missed video frame sequence and is located before and after in time sequence.

[0020] Preferably, the characteristic center Ra of the characteristic center is expressed as: Where R(i) represents the flicker frequency characteristic of the i-th PAPI lamp, and n represents the total number of PAPI lamps in the full process monitoring data set.

[0021] Preferably, the video images of the airport PAPI light area are captured by a drone flying from the far channel end to the near channel end along the arrangement direction of the PAPI light groups according to the aerial photography route and the aerial photography altitude set to H1; the video images in the light tag dataset cover all weather scenes and all light states of the PAPI light groups, and all light states of the PAPI light groups include all PAPI light groups are normal, the brightness of the PAPI lights is too low, the brightness of the PAPI lights is too high, the PAPI lights are completely off, some small lights in the PAPI lights are off, and the PAPI lights are flashing abnormally.

[0022] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0023] (1) The present invention constructs a light label dataset to train the YOLOV8 target detector for target detection. The trained YOLOV8 target detector can realize target detection of PAPI lights and small lights in PAPI lights. The ByteTrack algorithm associates and attributes PAPI lights and small lights in PAPI lights in a hierarchical manner, forming target tracking trajectory data of each PAPI light and the internal small lights in a hierarchical manner; then, the target tracking trajectory data is subjected to target traversal analysis to obtain a full-process monitoring data set. Based on the computational analysis and judgment of the full-process monitoring data set, anomaly detection of PAPI lights and small lights is realized, providing convenient PAPI light anomaly detection technical support for civil airports, and promoting the improvement of the digital level of airport security work.

[0024] (2) The present invention performs PAPI light recognition, detection, tracking and analysis based on video image capture of the airport PAPI light area, achieving the purpose of detecting abnormalities such as abnormal PAPI light brightness, PAPI light not lighting, partial PAPI bulb not lighting, abnormal PAPI light flickering frequency, etc., without relying on light hardware sensor data, greatly reducing labor costs and sensor hardware deployment costs.

[0025] (3) The present invention uses the YOLOV8 detector and ByteTrack algorithm to calculate the trajectory information of the PAPI light in the video, including the target historical trajectory, average brightness, number of small lights, and flashing frequency. The PAPI light trajectory information analysis based on target detection and data association can simultaneously detect four abnormal states of the PAPI light, with the advantages of high accuracy and high reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 Schematic diagram of the method flow of the present invention;

[0027] Figure 2 Schematic diagram of the YOLOV8 target detector identifying the PAPI light in an embodiment. DETAILED DESCRIPTION

[0028] Below in conjunction with embodiment, the present invention is described in further detail:

[0029] Example

[0030] like Figure 1 As shown, a method for identifying and detecting airport PAPI lighting anomalies based on aerial video processing and analysis includes:

[0031] S1. Construct a light label dataset containing video images of the airport PAPI light area and PAPI light label annotations. Input the light label dataset into the YOLOV8 target detector for target detection training. The targets include PAPI lights and the small lights in the PAPI lights. The video images of the airport PAPI light area are taken by setting an aerial route (the route height is 20 meters) along the arrangement direction of the PAPI light group from the far channel end to the near channel end. Aerial videos under different PAPI light states are collected on this aerial route to ensure that the aerial video scenes cover various scenes (different weather environments or different electromagnetic environments or different working scenes) and different light states of all PAPI light groups (including too dark and too bright states based on brightness grading). Finally, image frames are sampled every 1 second from the aerial video to form the light label dataset D of the PAPI lights. The PAPI light labeling method is as follows: PAPI lights and their sub-lights are labeled with area boxes at the assigned level (to achieve high-precision PAPI light anomaly detection, each complete PAPI light area in the video image and the light area of each sub-light within the PAPI light must be labeled). At the same time, PAPI lights with low and high brightness are labeled separately.

[0032] In some embodiments, video images of the airport PAPI light area are captured by a drone flying along the PAPI light array from the far end to the near end, following an aerial photography route and at an altitude of H1 (typically set at 18-26 meters). The video images in the light tag dataset of the present invention cover all weather scenarios and all PAPI light array light states, including all PAPI light arrays operating normally, PAPI light brightness too low, PAPI light brightness too high, PAPI light completely off, some PAPI light components off, and abnormal PAPI light flickering.

[0033] S2. Shoot the video image of the airport PAPI light area and input it into the YOLOV8 target detector for target detection (the image frames of the video image are collected at a time interval of T1) and use the ByteTrack algorithm to associate the target data and obtain the target tracking trajectory. The complete PAPI light area is labeled, and the PAPI light area with normal brightness is labeled as papi_normal (e.g. Figure 2 As shown in the figure, the YOLOV8 target detector recognizes PAPI lights (schematic diagram of the target). The PAPI light area with too low brightness is labeled as papi_low, and the PAPI light area with too high brightness is labeled as papi_high. The light area of each small light of each PAPI light is labeled and labeled as papi_small. After each video image is labeled according to the above rules, the labeled data L is formed (the labeled data L is part of the light label dataset D). The YOLOV8 target detector uses the labeled data L (including the labeled data L) for training. In the actual scenario involved in this embodiment, the number of small lights contained in each PAPI light is 5.

[0034] S3. Traverse each frame of target tracking trajectory to form a full-process monitoring data set of the target. The YOLOV8 target detector of this embodiment performs frame-by-frame target detection on the video image stream F(t), and t represents the sequential number of the video frame. The ByteTrack algorithm performs data association and target tracking based on the targets of the previous and next frames as the PAPI light. The ByteTrack algorithm performs data association and target tracking based on the targets of the previous and next frames as the small lights in the PAPI light. The small lights in the PAPI light are hierarchically associated and attributed to the corresponding PAPI light (the ByteTrack algorithm is based on the small light targets of the previous and next frames for association, and then the small lights are attributed to the PAPI light according to their attribution hierarchy. At the same time, the PAPI light targets are associated with the previous and next frames, thereby obtaining the target association of the PAPI light before and after frames, and the small lights inside the PAPI light are also associated with the previous and next frames). The ByteTrack algorithm is based on the small lights of the previous and next frames and the targets of the PAPI light for target association according to hierarchical attribution, and obtains the trajectory data of the PAPI light as the target association and the trajectory data of the small lights in the PAPI light as the target association.

[0035] In some embodiments, the full-process monitoring data set stores target detection data and trajectory data of n PAPI lights and m small lights according to their hierarchical attributes; wherein the i-th PAPI light sequence expression of the n PAPI lights is S(i)={U(i), V(i), X(i), Y(i), Z(i)}, U(i) is the historical trajectory coordinate center position sequence of the i-th PAPI light, V(i) is the first time that the horizontal and vertical coordinates of the i-th PAPI light area are greater than the horizontal and vertical coordinate threshold Thr (the coordinate threshold Thr in the video frame of size 1920*1080 is set to 800). Under normal circumstances, the n PAPI lights will be on, that is, the 1st to nth PAPI lights will be on. If the i-th PAPI light is not on, it will be detected that the i+1-th PAPI light is on, and the i+1-th PAPI light is detected to be on. The PAPI light will be recorded as the i-th PAPI light. In this case, the horizontal and vertical coordinates of the i-th PAPI light will be greater than the horizontal and vertical coordinate threshold Thr. At this time, the computer counts the i-th PAPI light. After PAPI light target association in the ByteTrack algorithm, it will be corrected to the i+1-th PAPI light. V(i) will record the video frame position (). The horizontal and vertical coordinates are the horizontal and vertical coordinates corresponding to the coordinate system constructed using the video frame image. X(i) is the historical number sequence of small lights contained in the i-th PAPI light, Y(i) is the historical average brightness sequence of the i-th PAPI light area, and Z(i) is the missed detection video frame position sequence in which no PAPI light tags are detected in the trajectory of the i-th PAPI light. The n PAPI lights are organized into a full-process monitoring data set in time sequence. In this embodiment, the following example method is used: Based on the detection and tracking results in the t-th frame image F(t) of the PAPI light group aerial video, the target trajectory information T(t, i) of each target being a PAPI light is analyzed and associated with the temporary full-process monitoring data corresponding to its tracking tag trk. For each T(t, i) of each frame image, the center coordinate position of its current position is added to the historical trajectory coordinate center position sequence of its corresponding temporary full-process monitoring data. For each T(t, i) of each frame image, the horizontal and vertical coordinates of its current position center are checked. If the horizontal and vertical coordinates are greater than the horizontal and vertical coordinate threshold Thr and its tracking label trk is not recorded, then the V(i) in the corresponding temporary full-process monitoring data is set to the current frame position t, and the label trk is recorded. For each T(t, i) of each frame image, the IoU (intersection over union) of the current area of T(t, i) and the current area of all small light trajectories in the current frame is calculated, and the number of small lights with an IoU greater than 0.5 is added to the small light historical number sequence X(i) in the temporary full-process monitoring data corresponding to T(t, i). For each T(t, i) of each frame image, the regional brightness average of T(t, i) is calculated and added to the regional historical brightness average sequence Y(i) in the temporary full-process monitoring data corresponding to the trajectory.For each T(t, i), if the difference between the current frame position t and the last detected frame position is greater than 1, and the difference between the current frame position t and the last lost frame position is greater than 20, then the current frame position t is added to the missed frame position sequence Z(i) in the temporary full-process monitoring data corresponding to the trajectory. After all video frames are analyzed, the temporary full-process monitoring data is updated to the full-process monitoring data set S. All temporary full-process monitoring data are added to the full-process monitoring data set S in ascending order of tracking number, forming the full-process monitoring data set S for all PAPI lights.

[0036] S4. Calculate the overall mean A of the historical brightness average sequence of the PAPI light in the full-process monitoring data set. If the overall mean A is less than a low brightness threshold thr_low (the low brightness threshold thr_low can be derived from a set value or a historical reference threshold obtained by statistically learning historical data from the light tag dataset), determine that the PAPI light brightness is too low and issue an alarm. Preferably, in some embodiments, it is necessary to simultaneously determine whether the PAPI light brightness is too low and the PAPI light brightness is too high. After the determination is completed, the process proceeds to method S5. The method for determining whether the PAPI light brightness is too high is as follows: If the overall mean A is greater than a high brightness threshold thr_high (the high brightness threshold thr_high can be derived from a set value or a historical reference threshold obtained by statistically learning historical data from the light tag dataset), determine that the PAPI light brightness is too high and issue an alarm. In the present invention, low PAPI light brightness and high PAPI light brightness are collectively referred to as abnormal PAPI light brightness. The alarm is abnormal PAPI light brightness, and further specifically outputs an alarm indicating whether the PAPI light brightness is too low or too high.

[0037] S5. Calculate the distance between two adjacent PAPI lights in the full-process monitoring data set. If the distance is greater than a light interval threshold thr_adj (the light interval threshold thr_adj can be derived from a set value or a historical reference threshold obtained by statistically learning historical data from the light tag dataset), it is determined that a completely unlit PAPI light exists between the two adjacent PAPI lights, and an alarm is issued. The present invention outputs information about the PAPI light located between the two adjacent PAPI lights along with the alarm.

[0038] S6. Calculate the mean of the historical number sequence of small lights in the PAPI lamp in the full-process monitoring data set. If the mean is less than the small light number threshold thr_small (the small light number threshold can be derived from a set value or a historical reference threshold obtained by statistical learning of historical data from the light tag dataset), it is determined that there are small lights that are not lit in the PAPI lamp and an alarm is issued.

[0039] S7. Construct a PAPI lamp flicker recognition model. Use the full-process monitoring data set to identify the flicker frequency characteristics of each PAPI lamp and calculate the characteristic center of all PAPI lamps. The characteristic center Ra is expressed as: Where R(i) represents the flicker frequency characteristic of the i-th PAPI lamp, and n represents the total number of PAPI lamps in the full process monitoring data set.

[0040] Calculate the Euclidean distance between the flicker frequency characteristics and the characteristic center of each PAPI light. If the Euclidean distance is greater than the flicker characteristic threshold thr_flash (the flicker characteristic threshold can be derived from a set value or obtained through deep learning of a light label dataset), the corresponding PAPI light is judged to have a flickering abnormality and an alarm is issued.

[0041] In some embodiments, the PAPI light flicker recognition model extracts the difference sequence between the missed video frame sequence and the adjacent non-missed video frame sequence in the full process monitoring data set, and calculates its mean and variance as the flicker frequency feature. The adjacent non-missed video frame sequence is the PAPI light target trajectory data that does not belong to the missed video frame sequence and is located before and after in time sequence.

[0042] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for identifying and detecting airport PAPI lighting anomalies based on aerial video processing and analysis, characterized by: The methods include: S1. Construct a light label dataset containing video images of the airport PAPI light area and PAPI light label annotations. Input the light label dataset into the YOLOV8 object detector for target detection training. The targets include PAPI lights and small lights in PAPI lights. S2: Shoot a video image of the airport PAPI light area and input it into the YOLOV8 target detector for target detection. Then, use the ByteTrack algorithm to associate the target data and obtain the target tracking trajectory. S3. Traverse the target tracking trajectory of each frame to form a full-process monitoring data set of the target; the full-process monitoring data set stores the target detection data and trajectory data of n PAPI lights and m small lights according to the hierarchy; the i-th PAPI light sequence expression of n PAPI lights is S(i)={U(i), V(i), X(i), Y(i), Z(i)}, where U(i) is the historical trajectory coordinate center position sequence of the i-th PAPI light, V(i) is the video frame position where the horizontal and vertical coordinates of the i-th PAPI light area are greater than the horizontal and vertical coordinate threshold Thr for the first time, X(i) is the historical number sequence of small lights contained in the i-th PAPI light, Y(i) is the historical brightness average sequence of the i-th PAPI light area, and Z(i) is the missed detection video frame position sequence where no PAPI light label is detected in the trajectory of the i-th PAPI light; the n PAPI lights are sorted into a full-process monitoring data set in time sequence; S4. Calculate the overall mean A of the historical brightness average value sequence of the PAPI lamp in the full-process monitoring data set. If the overall mean A is less than the low brightness threshold, determine that the PAPI lamp brightness is too low and issue an alarm. S5. Calculate the distance between two adjacent PAPI lights in the full-process monitoring data set. If the distance is greater than the light interval threshold, determine that there is a completely unlit PAPI light between the two adjacent PAPI lights and issue an alarm. S6. Calculate the mean of the historical number of small lights in the PAPI lamp in the full-process monitoring data set. If the mean is less than the small light number threshold, determine that there are small lights that are not lit in the PAPI lamp and issue an alarm. S7. Construct a PAPI light flicker recognition model and use the full-process monitoring data set to identify the flicker frequency characteristics of each PAPI light and calculate the feature center of all PAPI lights. The PAPI light flicker recognition model extracts the difference sequence between the missed video frame bit sequence and the adjacent unmissed video frame bit sequence in the full-process monitoring data set, and calculates its mean and variance as the flicker frequency feature; calculates the Euclidean distance between the flicker frequency feature and the feature center of each PAPI light. If the Euclidean distance is greater than the flicker feature threshold, the corresponding PAPI light is judged to be flickering abnormal and an alarm prompt is issued.

2. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 1 is characterized by: The image frames of the video image are collected according to the time frame T1; the PAPI light labeling method is as follows: the area boxes of the belonging levels are marked according to the PAPI lights and the small lights in the PAPI lights, and the PAPI lights with too low brightness and too high brightness are marked respectively.

3. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 1 is characterized by: The YOLOV8 object detector performs frame-by-frame object detection on the video image stream F(t), where t represents the sequential number of the video frame. The ByteTrack algorithm performs data association and target tracking based on the targets of the previous and next frames being the PAPI lights. The ByteTrack algorithm performs data association and target tracking based on the targets of the previous and next frames being the small lights within the PAPI lights. The small lights within the PAPI lights are hierarchically associated and assigned to the corresponding PAPI lights.

4. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 1 is characterized by: In step S4, if the overall mean A is greater than the high brightness threshold, the PAPI light brightness is determined to be too high and an alarm is issued; PAPI light brightness that is too low and PAPI light brightness that is too high are collectively referred to as PAPI light brightness abnormality.

5. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 1 is characterized by: In step S5, the PAPI light information between two adjacent PAPI lights is output along with the alarm prompt.

6. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 1 is characterized by: The adjacent non-missed video frame bit sequence is the PAPI light target trajectory data that does not belong to the missed video frame bit sequence and is located before and after in time sequence.

7. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 6 is characterized by: Feature Center Feature Center The expression is: ,in represents the flickering frequency characteristics of the i-th PAPI lamp, Indicates the total number of PAPI lamps in the full process monitoring data set.

8. The method for identifying and detecting anomalies of airport PAPI lighting based on aerial video processing and analysis according to claim 1 is characterized by: The video images of the airport PAPI light area are captured by a drone flying from the far channel end to the near channel end along the arrangement direction of the PAPI light groups according to the aerial photography route and the aerial photography altitude set to H1. The video images in the light label dataset cover all weather scenarios and all light states of the PAPI light groups. All light states of the PAPI light groups include all PAPI light groups are normal, the brightness of the PAPI lights is too low, the brightness of the PAPI lights is too high, the PAPI lights are completely off, some small lights in the PAPI lights are off, and the PAPI lights are flashing abnormally.

Images