An image data processing system for UAV landing light fault diagnosis

Abstract

The present invention relates to the field of image processing technology, and in particular to an image data processing system for diagnosing faults in landing lights of unmanned aerial vehicles. The system uses the brightness value under a fixed gear to statistically calculate the first suspected fault area in the light-emitting element area, analyzes the brightness changes caused by different gear changes at different heights, and further screens out the second suspected fault area through the distribution of the brightness change amplitude. Analyze the correlation of the brightness change amplitudes of areas at different positions in the second suspected fault area, and further correct the fault credibility in combination with the distance between the unmanned aerial vehicle and the landing light image acquisition device at each height. Determine the final fault probability and accurately locate the fault. The present invention effectively analyzes each light-emitting element area based on factors such as brightness changes, the influence of adjacent array brightness, and the distance between the image acquisition device and the landing light to obtain an accurate final fault probability and effectively locate the fault.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to an image data processing system for diagnosing failures of unmanned aerial vehicle landing lights. Background Art

[0002] A drone landing light is a lighting device installed on a drone. It is mainly used to provide auxiliary lighting when the drone is landing. It can provide sufficient brightness under various ambient light conditions and illuminate the landing area under the drone in darker environments or low visibility conditions, helping operators see the drone more clearly and judge the drone's altitude, speed, etc., to ensure the drone lands safely and accurately.

[0003] Drone landing lights are typically composed of multiple light-emitting elements. If a single element fails, it will produce a significantly different brightness than the others. Therefore, existing technologies can use computer vision to automatically and intelligently locate the faulty area by capturing images of the landing light and analyzing the brightness differences between the light-emitting elements. However, in reality, captured images are affected by factors such as ambient lighting, inter-array lighting, and brightness attenuation caused by the distance between the image acquisition device and the landing light. These factors can affect the brightness representation in the image, making fault location inaccurate based on brightness differences between arrays. Summary of the Invention

[0004] In order to solve the technical problem that the existing technology does not consider the influence of ambient lighting, the influence of lighting between arrays, and the brightness attenuation caused by the distance between the image acquisition device and the landing light, resulting in inaccurate fault area positioning based directly on the brightness difference between arrays, the purpose of the present invention is to provide an image data processing system for UAV landing light fault diagnosis. The technical solution adopted is as follows:

[0005] The present invention proposes an image data processing system for UAV landing light fault diagnosis, the system comprising:

[0006] A first fault analysis module is configured to obtain a landing light image of the UAV landing light; the landing light image includes a plurality of light-emitting element regions; and to determine a first suspected fault region based on brightness values ​​of the light-emitting element regions at preset brightness levels at all altitudes;

[0007] The second fault analysis module is configured to change the brightness level at each height, and screen out second suspected fault areas based on the brightness change amplitude of the first suspected fault area before and after the level change and the distribution of the brightness change amplitude; divide the second suspected fault area into a central area and a boundary area, where the boundary area is adjacent to other light-emitting element areas; and obtain the fault credibility of each second suspected fault area at the current height based on the correlation between the brightness change amplitudes of the central area and the boundary area when the brightness level changes;

[0008] A fault probability determination module is configured to obtain a distance weight based on the distance between the UAV and the landing light image acquisition device at each altitude, perform weighted integration of each second suspected fault area at all altitudes using the distance weight, and obtain an initial fault probability for each light-emitting element area; and obtain a final fault probability for each light-emitting element area based on the number of times the light-emitting element area is determined to be a second suspected fault area at all altitudes and the initial fault probability;

[0009] The fault location module is used to screen out the faulty light-emitting element area according to the final fault probability.

[0010] Furthermore, the first method for screening suspected fault areas includes:

[0011] At a certain height, the average brightness of each light-emitting element region at a preset brightness level is obtained, and all the average brightnesses are clustered to obtain a plurality of first clusters; for each first cluster, a first normal probability is obtained based on the number and average brightness of the light-emitting element regions in the first cluster; the light-emitting element region in the first cluster with the highest first normal probability is selected as the first normal light-emitting element region, and the light-emitting element regions other than the first normal light-emitting element region are selected as the third suspected fault regions;

[0012] All heights are counted, and if a light-emitting element area is identified as the third suspected fault area at any height, the light-emitting element area is regarded as the first suspected fault area.

[0013] Furthermore, the second method for screening suspected fault areas includes:

[0014] For each brightness level change process, the first suspected fault areas are clustered according to the brightness change amplitude to obtain a second cluster; a second normal probability is obtained based on the number of first suspected fault areas in the second cluster and the variance of the brightness change amplitude; the first suspected fault area in the second cluster with the largest second normal probability is selected as the second normal light-emitting element area, and the other first suspected fault areas except the second normal light-emitting element area are selected as the fourth suspected fault areas;

[0015] All brightness level change processes are counted. If a first suspected fault area is determined to be the fourth suspected fault area in all brightness level change processes, the first suspected fault area is used as the second suspected fault area.

[0016] Furthermore, the method for obtaining the fault credibility includes:

[0017] For each brightness level change process, for any second suspected fault area, if other light-emitting element areas adjacent to the boundary area are not the second suspected fault area, the boundary area is used as the boundary area to be analyzed; the brightness change amplitude difference between each boundary area to be analyzed and the central area is negatively correlated and normalized to obtain the brightness change amplitude correlation, and the average brightness change amplitude correlation corresponding to all boundary areas to be analyzed is used as the initial fault credibility of the second suspected fault area; if other light-emitting element areas adjacent to all boundary areas are the second suspected fault area, the brightness change amplitude of the central area is negatively correlated and normalized to obtain the initial fault credibility of the second suspected fault area;

[0018] All brightness level change processes are counted, and the average initial fault credibility of the second suspected fault area in all brightness level change processes is used as the fault credibility.

[0019] Furthermore, the distance weight is the reciprocal of the distance between the UAV and the landing light image acquisition device at each altitude.

[0020] Furthermore, the method for obtaining the initial failure probability includes:

[0021] For any light-emitting element area, if the light-emitting element area is not judged as the second suspected fault area at each height, the initial fault probability is set to 0; otherwise, all heights are counted, and the fault credibility corresponding to the light-emitting element area is weighted and averaged using the distance weight to obtain the initial fault probability.

[0022] Furthermore, the method for obtaining the final failure probability includes:

[0023] For any light-emitting element area, the ratio of the number of times the light-emitting element area is judged as the second suspected fault area to the number of heights is used as the adjustment weight; the product of the adjustment weight and the initial fault probability is normalized to obtain the final fault probability.

[0024] Furthermore, the light-emitting element region where the final failure probability is greater than a preset probability threshold is taken as a failed light-emitting element region.

[0025] Furthermore, the method for dividing the central area and the boundary area includes:

[0026] The light emitting element area is a rectangular area;

[0027] For each second suspected fault area, starting from the boundary pixel point of the second suspected fault area, traverse a preset number of pixel points toward the center point of the area to obtain the area boundary pixel points and the center area boundary of the center area; each center area boundary and the nearest and parallel second suspected fault area boundary constitute a boundary area.

[0028] Furthermore, the system also includes a fault degree evaluation module for evaluating the fault degree according to the number of the faulty light-emitting element areas, and feeding back a repair and replacement command if the fault degree is greater than a preset fault degree threshold.

[0029] The present invention has the following beneficial effects:

[0030] The present invention first uses the brightness value under a fixed gear to count the first suspected fault area in the light-emitting element area. The first suspected fault area is an inaccurate fault screening result caused by multiple factors. Therefore, the present invention further analyzes the brightness changes caused by different gear changes at different heights, and further screens the second suspected fault area through the distribution of the brightness change amplitude. In addition, considering the brightness influence between arrays, the correlation of the brightness change amplitude of areas at different positions in the second suspected fault area is analyzed, and then the fault credibility of the second suspected fault area at each height is obtained. By combining the distance between the drone and the landing light image acquisition device at each height, the fault credibility is further corrected to obtain the initial fault probability of each light-emitting element area. By counting the number of times each light-emitting element area is identified as the second suspected fault area during the entire process, the final fault probability can be determined and accurate fault location can be performed. The present invention effectively analyzes each light-emitting element area based on factors such as brightness changes, the influence of adjacent array brightness, and the distance between the image acquisition device and the landing light to obtain an accurate final fault probability and effectively locate the fault. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 any creative work.

[0032] Figure 1 A block diagram of an image data processing system for UAV landing light fault diagnosis provided by one embodiment of the present invention;

[0033] Figure 2A schematic diagram of light emitting element area division provided by an embodiment of the present invention;

[0034] Figure 3 A schematic diagram of dividing a second suspected fault area provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] To further illustrate the technical means and effectiveness of the present invention in achieving its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of an image data processing system for UAV landing light fault diagnosis proposed in accordance with the present invention. In the following description, references to different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0036] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0037] The following describes in detail a specific solution of an image data processing system for UAV landing light fault diagnosis provided by the present invention in conjunction with the accompanying drawings.

[0038] See also Figure 1 , which shows a block diagram of an image data processing system for UAV landing light fault diagnosis provided by an embodiment of the present invention. The system includes: a first fault analysis module 101, a second fault analysis module 102, a fault probability determination module 103 and a fault location module 104.

[0039] Because the embodiment of the present invention aims to analyze the brightness changes of each light-emitting element area during the change of the brightness level of the landing light at different heights by image processing means, and then determine the final failure probability. Therefore, the scenario for the implementation of the present invention can be the working stage of the drone, and the image of the drone in the air is captured by the shooting equipment, and then the landing light image is segmented for processing by the system of the embodiment of the present invention. During the shooting process, it is necessary to ensure that the camera field of view is wide, and to avoid interference from other background factors as much as possible, and the camera parameters of the image acquisition equipment need to ensure that clear and complete details of the landing light can be captured at a certain distance. The landing light in the embodiment of the present invention includes three gears: low, medium, and high. And four heights are set for image acquisition, namely: 3 meters, 7 meters, 9 meters, and 11 meters.

[0040] It should be noted that in the embodiments of the present invention, a pre-trained neural network can be used to segment the landing light image from the image. Specifically, a Mask R-CNN neural network (Mask Region-based Convolutional Neural Network) can be used. The specific network structure and training methods are well known to those skilled in the art and will not be detailed here.

[0041] The first fault analysis module 101 is used to obtain a landing light image of a UAV landing light. Generally, a landing light is composed of a plurality of circular light-emitting elements, so the landing light image includes a plurality of light-emitting element areas.

[0042] In this embodiment of the present invention, because the light-emitting element is the light source of the landing light, its corresponding brightness value has significant characteristics. The Otsu threshold segmentation algorithm can be used to screen out brightly lit connected areas. Each brightly lit connected area represents a light-emitting element. To facilitate subsequent regional analysis, the minimum circumscribed rectangle of the brightly lit connected area is used as the light-emitting element area.

[0043] In another embodiment of the present invention, considering that landing lights are usually devices with regular shapes and light-emitting elements are neatly arranged in the landing lights, after obtaining the landing light image, the landing light image can be evenly segmented according to the specifications of the light-emitting elements in the landing light to directly obtain the light-emitting element areas. Figure 2 , which shows a schematic diagram of light-emitting element region division provided by an embodiment of the present invention. Since the light-emitting elements are arranged uniformly, each light-emitting element region can be directly determined by uniform region division.

[0044] It should be noted that, in the embodiment of the present invention, when performing brightness analysis, the grayscale value in the landing light image is used as the brightness value.

[0045] The embodiment of the present invention addresses the technical problem that the prior art does not consider factors such as the impact of ambient light on the landing light image, the impact of light between arrays, and the brightness attenuation caused by the distance between the image acquisition device and the landing light, which leads to inaccurate fault area positioning based directly on the brightness difference between arrays. The embodiment of the present invention gradually improves the accuracy of screening through three screenings, thereby obtaining an accurate fault area. Therefore, in order to avoid missed detection, the first fault analysis module 101 calculates the first suspected fault area based on the brightness value of the light-emitting element area at a preset brightness level at all heights. That is, compared with the prior art, the first fault analysis module 101 analyzes the brightness of the light-emitting elements at fixed levels at multiple heights, thereby avoiding the inaccurate influence caused by certain factors at a certain height. By counting the brightness values ​​of the light-emitting element area at all heights, the result of the first screening can be obtained. It should be noted that because normal light-emitting elements have fixed and uniform light-emitting characteristics, the brightness and color they produce are relatively stable, and the brightness information on the image is relatively consistent, while faulty light-emitting elements will produce obviously abnormal brightness values. Therefore, the first suspected fault areas are all areas with abnormal brightness at a certain height or multiple heights. However, it is not certain whether these brightness anomalies are caused by real component failures, and further analysis is required in subsequent modules.

[0046] Preferably, in an embodiment of the present invention, the method for screening the first suspected fault area includes:

[0047] At a certain height, the average brightness of each light-emitting element region under a preset brightness level is obtained. That is, the average brightness is the average grayscale value of the current light-emitting element region. In the embodiment of the present invention, the preset brightness level is set to medium.

[0048] At a given altitude, a landing light image is obtained at a preset brightness level. This image contains multiple light-emitting element regions, indicating multiple average brightness levels. If all light-emitting elements are normal, the average brightness will be relatively uniform. Therefore, this embodiment of the present invention employs a classification strategy for the initial anomaly screening.

[0049] All average brightness values ​​are clustered to obtain multiple first clusters. Because a faulty element is a low-probability event in an array of light-emitting elements, the more light-emitting element regions there are in a first cluster and the greater the average brightness, the more likely that the first cluster is a cluster of normal light-emitting element regions. Therefore, for each first cluster, a first normal probability is obtained based on the number of light-emitting element regions and the average brightness in the first cluster.

[0050] In the embodiment of the present invention, the average brightness is divided by 255 to achieve normalization of the average brightness, and the first normal probability can be obtained by multiplying the normalized result by the number of light-emitting element regions.

[0051] In the embodiment of the present invention, the clustering method may be density clustering, which is a technical means well known to those skilled in the art and will not be described in detail here.

[0052] The light emitting element region in the first cluster with the highest first normal probability is selected as the first normal light emitting element region, and the other light emitting element regions except the first normal light emitting element region are selected as the third suspected fault region.

[0053] At this point, there is a set of third suspected fault areas at each altitude. The landing light of a drone is generally located on the front of the nose. Therefore, during the shooting process, the camera and the landing light are not completely parallel and there will be a certain angle difference. Therefore, the altitude affects the image acquisition device's acquisition angle, which in turn causes a certain light reflection deviation. It is possible that the fault area will be missed at a certain altitude. Therefore, this embodiment of the present invention counts all altitudes. If a light-emitting element area is identified as the third suspected fault area at any altitude, then this light-emitting element area is used as the first suspected fault area. In other words, the union of the third suspected fault area sets at all altitudes is selected as the first suspected fault area set.

[0054] The second fault analysis module 102 is used to further analyze the first suspected fault area, perform a second screening process, and do not perform a third screening analysis. Taking into account the influence of light reflection, the accurate fault area cannot be obtained only through the brightness information itself. Therefore, the second fault analysis module 102 changes the brightness level at each height, and further analyzes the brightness change amplitude of the first suspected fault area during the brightness level change process, and then performs a second screening process. Because the normal light-emitting element area operates stably, the brightness change amplitude generated during the level change process should be uniform. Therefore, for all first suspected fault areas, the more the distribution of the brightness change amplitude before and after the level change deviates from the overall distribution, the more likely it is to be a fault area. In this way, the second suspected fault area can be screened out for a second screening process.

[0055] According to the structural characteristics of the landing light, the light-emitting elements can be arranged in an orderly and compact manner in the landing light, so each light-emitting element area will be affected by the brightness of other areas. For example, when a component fails, if it exists alone, the brightness of the corresponding area will not change with the adjustment of the brightness level, or the change will be small; however, if it is adjacent to a normal component, the adjacent normal component will "fill in the light" for it, that is, the brightness of the faulty component will be affected by the adjacent normal component, resulting in synchronous brightness changes. These brightness changes will affect the judgment of the faulty area. Therefore, although the brightness changes of the second suspected fault area have been analyzed, there is still a risk of inaccuracy. Therefore, further analysis of the second suspected fault area is required.

[0056] The second fault analysis module 102 further divides the second suspected fault area into a central area and a boundary area, where the boundary area is adjacent to other light-emitting element areas. That is, during the brightness level change process, the brightness change in the central area represents the brightness change caused by the elements of the second suspected fault area itself, while the brightness change in the boundary area represents the brightness change that may be affected by the adjacent light-emitting element areas. Therefore, by analyzing the correlation between the brightness change amplitudes of the central area and the boundary area, the fault credibility of each second suspected fault area at the current height can be obtained. That is, the greater the correlation of the change amplitude, the more likely it is that the current second suspected fault area is not affected by the fill light of the adjacent elements, and the brightness changes in the area are all caused by the normal level changes of the area itself, and the fault credibility is lower; the smaller the correlation of the change amplitude, the more likely it is that the boundary area is affected by the fill light of the adjacent elements, while the central element area has a small change or no change caused by the fault, thus resulting in a larger change amplitude difference, and the fault credibility of the second suspected fault area is higher.

[0057] It should be noted that, in the embodiment of the present invention, since there are three brightness levels, two brightness level change processes are set, namely, from a low level to a medium level, and from a medium level to a high level.

[0058] In the embodiment of the present invention, the brightness change amplitude of a region is the absolute value of the difference between the average grayscale values ​​of the region before and after the brightness level is changed.

[0059] In another embodiment of the present invention, the brightness variation range is the absolute value of the difference between the lowest brightness value of the low-level gear and the highest brightness value of the high-level gear.

[0060] Preferably, in one embodiment of the present invention, the method for screening the second suspected fault area includes:

[0061] Similar to the first suspected fault area screening method in one embodiment of the present invention described above, since normal components have a uniform brightness change amplitude during the brightness level change process, a clustering classification method can also be used for the second screening.

[0062] For each brightness level change, the first suspected fault areas are clustered according to the brightness variation to obtain a second cluster. The more first suspected fault areas a second cluster contains and the more uniform the distribution of brightness variation, the more likely it is a cluster of normal component areas. Therefore, the second normal probability is obtained based on the number of first suspected fault areas in the second cluster and the variance of the brightness variation.

[0063] In an embodiment of the present invention, the ratio of the number of first suspected fault areas to the variance of the brightness variation is used as the second normal probability of the second cluster. The smaller the variance, the more uniform the brightness variation, and the greater the second normal probability.

[0064] Selecting the first suspected fault region in the second cluster with the largest second normal probability as the second normal light-emitting element region, and the other first suspected fault regions except the second normal light-emitting element region as the fourth suspected fault region;

[0065] Because landing lights have multiple levels, there are multiple brightness level change processes. All brightness level change processes are counted. If a first suspected fault area is identified as a fourth suspected fault area in all brightness level change processes, then that first suspected fault area is considered the second suspected fault area. In other words, each brightness level change process corresponds to a fourth suspected fault area set, and the intersection of all fourth suspected fault area sets is considered the second suspected fault area set.

[0066] Preferably, in one embodiment of the present invention, since the light emitting element area is rectangular, for each second suspected fault area, starting from the boundary pixel point of the second suspected fault area, a preset number of pixel points are traversed in the direction of the center point of the area to obtain the boundary pixel points and the center area boundary of the center area; each center area boundary and the nearest and parallel second suspected fault area boundary constitute a boundary area. Figure 3 , which shows a schematic diagram of the division of the second suspected fault area provided by an embodiment of the present invention. The shaded area in the figure is the central area, and the extended straight lines of the four boundaries of the central area and the nearest and parallel boundaries of the second suspected fault area constitute a boundary area, that is, the four boundary areas are of the same size, and there are partial overlaps of the same size at the four corners.

[0067] Preferably, in one embodiment of the present invention, the method for obtaining fault credibility includes:

[0068] For each brightness level change process, for any second suspected fault area, if the other light-emitting element areas adjacent to the boundary area are not the second suspected fault area, that is, the other adjacent light-emitting element areas are normal element areas determined after two screenings, then the boundary area will be used as the boundary area to be analyzed. The brightness change amplitude difference between each boundary area to be analyzed and the central area is negatively correlated and normalized to obtain the brightness change amplitude correlation. That is, the smaller the difference, the closer the brightness change amplitude between the central area and the boundary area to be analyzed, and the greater the brightness change amplitude correlation. Because there may be multiple boundary areas to be analyzed, the average brightness change amplitude correlation corresponding to all boundary areas to be analyzed is used as the initial fault credibility of the second suspected fault area;

[0069] If all other light-emitting element areas adjacent to the boundary area are the second suspected fault area, it can be considered that the boundary area may not be affected. At this time, the brightness change amplitude of the central area can be directly analyzed. The smaller the brightness change amplitude, the more likely it is a faulty element, and the greater the initial fault credibility. Therefore, the brightness change amplitude of the central area is negatively correlated and normalized to obtain the initial fault credibility of the second suspected fault area.

[0070] It should be noted that the negative correlation mapping method in the embodiment of the present invention can be implemented by first normalizing and then subtracting the normalized result from the positive integer 1. Normalization can be implemented through multiple existing technologies such as linear normalization and function mapping method.

[0071] Because one height includes multiple brightness level change processes, all brightness level change processes are counted, and the average initial fault credibility of the second suspected fault area in all brightness level change processes is used as the fault credibility.

[0072] After screening and analysis by the second fault analysis module 102, each second suspected fault area corresponds to a fault credibility at each height. However, since the shooting distance will affect the image quality, the lower the height of the drone landing light, the higher the confidence of the extracted image features should be. Therefore, the fault probability determination module 103 further obtains the distance weight according to the distance between the drone and the landing light image acquisition device at each height. That is, by characterizing the confidence of the extracted features through the distance weight, the distance weight can be used to perform weighted integration on each second suspected fault area at all heights, and then the initial fault probability of each light-emitting element area can be obtained. Combining the number of times each light-emitting element area is judged as the second suspected fault area at all heights during the entire process, the final fault probability of each light-emitting element area can be obtained. That is, the more times it is judged as the second suspected fault area, the more likely it is to be a real fault, and the greater the final fault probability.

[0073] Preferably, in one embodiment of the present invention, the distance weight is the inverse of the distance between the UAV and the landing light image acquisition device at each altitude. Then, the method for obtaining the initial failure probability is:

[0074] For any light-emitting element area, if the light-emitting element area is not determined to be the second suspected fault area at any height, the initial fault probability is set to 0; otherwise, all heights are counted, and the fault credibility corresponding to the light-emitting element area is weighted and averaged using the distance weight to obtain the initial fault probability. For example, in the embodiment of the present invention, four height levels are set: 3 meters, 7 meters, 9 meters, and 11 meters. After screening and judgment, a light-emitting element area is determined to be the second suspected fault area at heights of 3 meters and 7 meters. The distance weights are respectively multiplied by the fault credibility at the corresponding heights using one-third and one-seventh to achieve weighting. The weighted results are further added and divided by 2 to achieve average to obtain the initial fault probability.

[0075] Preferably, in an embodiment of the present invention, the method for obtaining the final failure probability includes:

[0076] For any light-emitting element region, the ratio of the number of times the light-emitting element region is identified as the second suspected fault region to the number of heights is used as the adjustment weight. That is, a larger adjustment weight indicates that the light-emitting element region is identified as the second suspected fault region more often, and thus its corresponding final failure probability should be higher.

[0077] The product of the adjustment weight and the initial failure probability is normalized to obtain the final failure probability.

[0078] The normalization processing in the embodiments of the present invention can be implemented by using existing technologies such as linear normalization, function mapping method, etc., which will not be elaborated or limited here.

[0079] In an embodiment of the present invention, the light emitting element region whose final failure probability is greater than a preset probability threshold is regarded as a faulty light emitting element region. Because the final failure probability is normalized in an embodiment of the present invention, the probability threshold is set to 0.6.

[0080] Preferably, in one embodiment of the present invention, the image data processing system further includes a fault severity assessment module configured to assess the fault severity based on the number of faulty light-emitting element regions. If the fault severity exceeds a preset fault severity threshold, a repair and replacement command is fed back. In one embodiment of the present invention, the fault severity may be the ratio of the number of faulty light-emitting element regions to the total number of light-emitting element regions, with the fault severity threshold set to 0.5. If the fault severity is not greater than the preset fault severity threshold, the fault location result is fed back to the terminal.

[0081] In summary, the embodiment of the present invention uses the brightness value under a fixed gear to count the first suspected fault area in the light-emitting element area, further analyzes the brightness changes caused by different gear changes at different heights, and further screens out the second suspected fault area through the distribution of the brightness change amplitude. Analyze the correlation between the brightness change amplitudes of areas at different positions in the second suspected fault area, and then obtain the fault credibility of the second suspected fault area at each height. Combined with the distance between the drone and the landing light image acquisition device at each height, the fault credibility is further corrected to obtain the initial fault probability of each light-emitting element area. By counting the number of times each light-emitting element area is identified as the second suspected fault area during the entire process, the final fault probability can be determined and the fault location can be accurately located. The present invention effectively analyzes each light-emitting element area based on factors such as brightness changes, the influence of adjacent array brightness, and the distance between the image acquisition device and the landing light to obtain an accurate final fault probability and effectively locate the fault.

[0082] It should be noted that the order in which the embodiments of the present invention are described above is for illustrative purposes only and does not necessarily represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0083] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An image data processing system for UAV landing light fault diagnosis, characterized in that: The system comprises: A first fault analysis module is configured to obtain a landing light image of the UAV landing light; the landing light image includes a plurality of light-emitting element regions; and to determine a first suspected fault region based on brightness values ​​of the light-emitting element regions at preset brightness levels at all altitudes; The second fault analysis module is configured to change the brightness level at each height, and screen out second suspected fault areas based on the brightness change amplitude of the first suspected fault area before and after the level change and the distribution of the brightness change amplitude; divide the second suspected fault area into a central area and a boundary area, where the boundary area is adjacent to other light-emitting element areas; and obtain the fault credibility of each second suspected fault area at the current height based on the correlation between the brightness change amplitudes of the central area and the boundary area when the brightness level changes; A fault probability determination module is configured to obtain a distance weight based on the distance between the UAV and the landing light image acquisition device at each altitude, and to use the distance weight to perform a weighted integration of the fault credibility corresponding to each second suspected fault area at all altitudes to obtain an initial fault probability for each light-emitting element area. A final fault probability for each light-emitting element area is obtained based on the number of times the light-emitting element area is determined to be a second suspected fault area at all altitudes and the initial fault probability. A fault location module is used to screen out the faulty light-emitting element area based on the final fault probability; The method for obtaining the fault credibility includes: For each brightness level change process, for any second suspected fault area, if other light-emitting element areas adjacent to the boundary area are not the second suspected fault area, the boundary area is used as the boundary area to be analyzed; the brightness change amplitude difference between each boundary area to be analyzed and the central area is negatively correlated and normalized to obtain the brightness change amplitude correlation, and the average brightness change amplitude correlation corresponding to all boundary areas to be analyzed is used as the initial fault credibility of the second suspected fault area; if other light-emitting element areas adjacent to all boundary areas are the second suspected fault area, the brightness change amplitude of the central area is negatively correlated and normalized to obtain the initial fault credibility of the second suspected fault area; All brightness level change processes are counted, and the average initial fault credibility of the second suspected fault area in all brightness level change processes is used as the fault credibility.

2. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The method for screening the first suspected fault area includes: At a certain height, the average brightness of each light-emitting element region at a preset brightness level is obtained, and all the average brightnesses are clustered to obtain a plurality of first clusters; for each first cluster, a first normal probability is obtained based on the number and average brightness of the light-emitting element regions in the first cluster; the light-emitting element region in the first cluster with the highest first normal probability is selected as the first normal light-emitting element region, and the light-emitting element regions other than the first normal light-emitting element region are selected as the third suspected fault regions; All heights are counted, and if a light-emitting element area is identified as the third suspected fault area at any height, the light-emitting element area is regarded as the first suspected fault area.

3. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The second method for screening suspected fault areas includes: For each brightness level change process, the first suspected fault areas are clustered according to the brightness change amplitude to obtain a second cluster; a second normal probability is obtained based on the number of first suspected fault areas in the second cluster and the variance of the brightness change amplitude; the first suspected fault area in the second cluster with the largest second normal probability is selected as the second normal light-emitting element area, and the other first suspected fault areas except the second normal light-emitting element area are selected as the fourth suspected fault areas; All brightness level change processes are counted. If a first suspected fault area is determined to be the fourth suspected fault area in all brightness level change processes, the first suspected fault area is used as the second suspected fault area.

4. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The distance weight is the reciprocal of the distance between the UAV and the landing light image acquisition device at each altitude.

5. The image data processing system for UAV landing light fault diagnosis according to claim 4, characterized in that: The method for obtaining the initial failure probability includes: For any light-emitting element area, if the light-emitting element area is not judged as the second suspected fault area at each height, the initial fault probability is set to 0; otherwise, all heights are counted, and the fault credibility corresponding to the light-emitting element area is weighted and averaged using the distance weight to obtain the initial fault probability.

6. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The method for obtaining the final failure probability includes: For any light-emitting element area, the ratio of the number of times the light-emitting element area is judged as the second suspected fault area to the number of heights is used as the adjustment weight; the product of the adjustment weight and the initial fault probability is normalized to obtain the final fault probability.

7. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The light-emitting element region where the final failure probability is greater than a preset probability threshold is regarded as a failed light-emitting element region.

8. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The method for dividing the central area and the boundary area includes: The light emitting element area is a rectangular area; For each second suspected fault area, starting from the boundary pixel point of the second suspected fault area, traverse a preset number of pixel points toward the center point of the area to obtain the area boundary pixel points and the center area boundary of the center area; each center area boundary and the nearest and parallel second suspected fault area boundary constitute a boundary area.

9. The image data processing system for UAV landing light fault diagnosis according to claim 1, characterized in that: The system further includes a fault degree evaluation module for evaluating the fault degree according to the number of the faulty light emitting element areas, and feeding back a repair and replacement command if the fault degree is greater than a preset fault degree threshold.

Images