Low-altitude aircraft regional channel monitoring method and device, aircraft and storage medium

Abstract

The invention relates to the technical field of monitoring, in particular to a low-altitude aircraft regional channel monitoring method and device, an aircraft and a storage medium. When it is detected that the aircraft flies according to the target flight route, the channel photo of the target channel area is collected according to the target time period, anomaly recognition is performed on the channel photo, and when it is determined that abnormal data exists in the channel photo, an alarm is given according to the abnormal data, so that the channel area monitoring efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of monitoring technology, and in particular to a method, device, aircraft and storage medium for monitoring a low-altitude aircraft area channel. Background Art

[0002] As an important part of the airspace, low-altitude airspace plays an irreplaceable role in general aviation activities such as agricultural production, ocean monitoring, remote sensing mapping, meteorological detection, emergency rescue, disaster relief, education and training, culture and sports, and tourism.

[0003] At present, waterway monitoring mostly uses fixed camera monitoring or manual inspections. Due to the limitations of the inspectors' work attitude and experience, there is a problem of low monitoring efficiency. Summary of the invention

[0004] In view of the above, the present application provides a method, device, aircraft and storage medium for monitoring the regional channel of low-altitude aircraft to improve monitoring efficiency and accuracy.

[0005] The first aspect of the present application provides a method for monitoring a low-altitude aircraft regional channel, the method comprising: When the aircraft is detected to be flying according to the target flight route, the channel photos of the target channel area are collected according to the target time period; Performing anomaly identification on the waterway photo to determine whether there is abnormal data in the waterway photo; When it is determined that the abnormal data exists in the channel photo, an alarm is issued according to the abnormal data.

[0006] In an optional implementation, when the abnormal data is waterway congestion, the performing abnormality identification on the waterway photo includes: Determining the waterway traffic data of the target waterway area in the waterway photo and the clustering evaluation index of the waterway traffic data; Constructing an evaluation sample matrix based on the waterway traffic data and the cluster evaluation index; Calculating a cluster evaluation value for each evaluation sample in the evaluation sample matrix; The maximum evaluation value among the cluster evaluation values ​​is obtained, and it is determined whether the waterway traffic data has waterway congestion according to the maximum evaluation value.

[0007] In an optional implementation, the calculating the cluster evaluation value of each evaluation sample in the evaluation sample matrix based on the cluster evaluation index includes: Determine a plurality of cluster centers of the evaluation sample matrix, and a membership value between each evaluation sample and each of the cluster centers; The weight of each of the cluster centers is determined, and the cluster evaluation value of each evaluation sample is determined according to the membership value and the weight.

[0008] In an optional implementation, when the abnormal data is an obstacle, the performing abnormality identification on the waterway photo includes: Determine the sea surface area and non-sea surface area in the channel photo according to the target channel area; Extracting first obstacle information of the sea surface area and second obstacle information of the non-sea surface area according to a preset obstacle database; It is determined whether the obstacle exists in the sea surface area according to the first obstacle information, and it is determined whether the obstacle exists in the non-sponge area according to the second obstacle information.

[0009] In an optional implementation, when the abnormal data is a hidden danger in the external environment, the abnormality identification of the waterway photo includes: Extracting features from the waterway photo to obtain a feature set; The target feature is compared with a preset environmental data set, wherein the target feature is any feature in the feature set; when it is determined that the target feature matches any environmental data in the preset environmental data set, it is determined that the waterway photo contains the external environmental hidden danger.

[0010] In an optional embodiment, the method further comprises: Obtaining the real-time flight trajectory, real-time flight speed and real-time flight attitude of the aircraft; Determining whether the aircraft is in an abnormal flight state according to the real-time flight trajectory, the real-time flight speed, and the real-time flight attitude; When it is determined that the aircraft is in the abnormal flight state, determining target flight data corresponding to the abnormal flight state, the target flight data being any one of the real-time flight trajectory, the real-time flight speed, and the real-time flight attitude; An alarm is issued according to the target flight data.

[0011] In an optional implementation, when it is determined that the abnormal data exists in the waterway photograph, the method further includes: Generate warning information according to the abnormal data, and determine a set of waterway photos corresponding to the abnormal data according to a preset time range; The warning information and the waterway photo set are sent to a terminal monitoring device.

[0012] A second aspect of the present application provides a low-altitude aircraft regional channel monitoring device, the device comprising: A collection module, for collecting channel photos of the target channel area according to a target time period when it is detected that the aircraft is flying according to the target flight route; The identification module is used to identify abnormalities in the channel photo to determine whether there is abnormal data in the channel photo; the alarm module is used to issue an alarm based on the abnormal data when it is determined that the abnormal data exists in the channel photo.

[0013] A third aspect of the present application provides an aircraft, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the low-altitude aircraft regional channel monitoring method when executing the computer program.

[0014] A fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-mentioned low-altitude aircraft regional channel monitoring method.

[0015] In summary, the low-altitude aircraft area channel monitoring method, device, aircraft and storage medium provided in the present application realize real-time monitoring of the channel area by collecting channel photos of the target channel area according to the target time period. Combined with the abnormality identification of the channel photos, abnormal data in the channel photos can be discovered in time and the alarm mechanism can be triggered, effectively improving the efficiency and accuracy of channel area monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a structural schematic diagram of a low-altitude aircraft regional channel monitoring system shown in an embodiment of the present application; Figure 2 is a flow chart of a method for monitoring a low-altitude aircraft regional channel shown in an embodiment of the present application; Figure 3 It is a functional module diagram of a low-altitude aircraft regional channel monitoring device shown in an embodiment of the present application; Figure 4 It is a structural diagram of a data processing unit shown in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "said", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0018] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0019] Reference Figure 1 , which is a schematic diagram of the structure of a low-altitude aircraft regional channel monitoring system shown in an embodiment of the present application.

[0020] The low-altitude aircraft area channel monitoring system 1 includes an aircraft 10 and a terminal monitoring device 20. The aircraft 10 includes a drone 11 and a collection device 12. The aircraft 11 is used to fly according to a preset route, and the collection device 12 is used to collect channel photos of the monitoring area according to a preset time period. The collection device 12 can be an ultra-light high-definition AI camera, etc.

[0021] The aircraft 10 also includes a data processing unit 13, which is used to process and analyze the channel photos when receiving the channel photos collected by the collection device 12 according to a preset time period, so as to determine whether there is abnormal data in the channel photos, so as to further determine whether there is any abnormality in the monitored channel area.

[0022] The aircraft 10 further includes an alarm device 14, which is used to generate an alarm signal according to the abnormal data when receiving the alarm signal generated by the data processing unit 13. The alarm device 14 can be a speaker, a broadcaster, etc.

[0023] In some embodiments, the data processing unit 13 is also used to send the corresponding waterway photos / videos to the terminal monitoring device 20 according to a preset time range (X minutes before and after the abnormal moment, X is greater than 0) when it is determined that there is an abnormality in the waterway area, so that the terminal monitoring device 20 can perform data processing and data analysis on the waterway photos / videos to determine the corresponding processing plan for the abnormality.

[0024] In some embodiments, the aircraft 10 is also integrated with an infrared sensor for auxiliary detection, so that the aircraft 10 can still work normally at night or in low light conditions, thereby improving the all-weather working capability of the low-altitude aircraft area channel monitoring system 1.

[0025] Reference Figure 2 As shown, it is a flow chart of a method for monitoring the channel of a low-altitude aircraft area shown in an embodiment of the present application, and the method for monitoring the channel of a low-altitude aircraft area includes the following steps.

[0026] S21, when it is detected that the aircraft is flying according to the target flight route, a channel photo of the target channel area is collected according to the target time period.

[0027] In some embodiments, the aircraft can set a flight route (target flight route) and set a time period (target time period) for collecting channel photos in advance according to the route of the channel area to be monitored. After determining the target flight route and target time period of the aircraft, the aircraft is controlled to fly according to the target flight route, and the flight trajectory (real-time flight trajectory) of the drone is monitored in real time to see if it is consistent with the target flight route. When the real-time flight trajectory is consistent with the target flight route, it can be determined that the aircraft has not experienced a flight deviation event, so the collection device in the aircraft can be controlled to collect channel photos of the target channel area according to the target time period, and the channel area being monitored is called the target channel area.

[0028] In some embodiments, the aircraft can also automatically adjust the flight route and collection time period according to changes in the monitored waterway area. Secondly, the aircraft can also monitor in real time whether there are obstacles on the flight route, and when an obstacle is identified, automatically adjust the flight route to avoid the obstacle. The aircraft can also shorten the collection time period according to the number of ships in the waterway area when it is determined that the number of ships reaches a preset threshold. In other embodiments, the monitoring personnel can also adjust the flight route and collection time period of the aircraft through the terminal monitoring device according to personal needs / experience. Specifically, the corresponding adjustment instructions can be generated according to the adjusted flight route and collection time period, and the adjustment instructions can be sent to the aircraft through the terminal monitoring device, so that after receiving the adjustment instructions, the aircraft adjusts the pre-stored flight route and collection time period according to the flight route and collection time period carried in the adjustment instructions.

[0029] S22, performing anomaly identification on the channel photo to determine whether there is abnormal data in the channel photo.

[0030] In some embodiments, when a channel photo is obtained, the channel photo is first preprocessed, such as denoising, contrast enhancement, color correction, etc., to improve the image quality of the channel photo. The preprocessing may also include filtering (such as Gaussian filtering), noise reduction (removing isolated or outliers) and thinning (reducing the number of points to speed up processing). Furthermore, the channel photo is identified for anomalies using an anomaly recognition algorithm to determine whether there are anomalies in the target channel area, such as channel congestion, obstacles, and external environmental hazards.

[0031] In an optional implementation, when the abnormal data is waterway congestion, the performing abnormality identification on the waterway photo includes: Determining the waterway traffic data of the target waterway area in the waterway photo and the clustering evaluation index of the waterway traffic data; Constructing an evaluation sample matrix based on the waterway traffic data and the cluster evaluation index; Calculating a cluster evaluation value for each evaluation sample in the evaluation sample matrix; The maximum evaluation value among the cluster evaluation values ​​is obtained, and it is determined whether the waterway traffic data has waterway congestion according to the maximum evaluation value.

[0032] In some embodiments, the aircraft first needs to determine the traffic state index and traffic state level for evaluating the traffic state of the channel in the target channel area, and the traffic state index may include retention, convergence and equivalent traffic volume, etc. Among them, the retention represents the time ratio of the ship stagnation in the channel, which is calculated based on the speed of the ship in the channel and the position of the star flash. Convergence refers to the density of ships in the channel, which is calculated based on the number of ships passing through the target channel area within the statistical unit time and unit length. The traffic state level may include unimpeded, stable, lightly congested and congested, etc. Among them, each traffic state level defines the range of traffic state indicators, for example, the unimpeded state may correspond to the situation of low retention, small convergence and moderate equivalent traffic volume; the congested state corresponds to the situation of high retention, large convergence and large equivalent traffic volume. It should be noted that the corresponding thresholds will be pre-set to evaluate the height of the retention, the size of the convergence and the size of the equivalent traffic volume. Further, the determined traffic state index and traffic state level are integrated together as a cluster evaluation indicator.

[0033] At the same time, the aircraft can also use image processing technology (for example, target detection algorithm and image segmentation algorithm) to extract channel traffic data in the channel from the collected channel photos, where the channel traffic data can include the number of ships, ship speed and ship spacing, etc. And construct an evaluation sample matrix based on the channel traffic data and clustering evaluation indicators, where the rows represent evaluation samples, that is, channel traffic data, and the columns represent clustering evaluation indicators. Then, a clustering algorithm (for example, K-means, hierarchical clustering, etc.) is used to perform cluster analysis on the evaluation sample matrix, and the clustering evaluation value of each evaluation sample is calculated according to the clustering results and clustering evaluation indicators. Among them, the clustering evaluation value reflects the similarity between the evaluation sample and each cluster center, so that the traffic status of the channel can be evaluated. Specifically, the aircraft can randomly determine multiple initial cluster centers, and the number of initial cluster centers can be determined according to the expected number of classifications of the channel traffic status (such as unimpeded, stable, slightly crowded, crowded)), and initialize a membership matrix, which is the same as the evaluation sample matrix, and is used to record the membership of each evaluation sample to each cluster center. For each evaluation sample in the evaluation sample matrix, calculate the distance (other distance measurement methods such as Euclidean distance, Mahalanobis distance) between itself and each cluster center, to quantify the similarity between the evaluation sample and the cluster center. Then, according to the distance between each evaluation sample and the cluster center, use the membership function in fuzzy mathematics (such as Gaussian membership function, trapezoidal membership function, etc.) to calculate the membership of each evaluation sample to each cluster center, and fill the membership value calculated into the corresponding position, update the membership matrix. According to the updated membership matrix, by all evaluation samples belonging to this cluster being carried out weighted average or taking the median and other modes to calculate the new position of each cluster center, that is, obtain new cluster center. After updating the cluster center, according to the same implementation method as above, calculate the distance between each evaluation sample and the new cluster center, and update the membership matrix, until the change of cluster center and membership matrix reaches the preset convergence condition or the preset number of iterations. Finally, according to the final membership matrix, the cluster evaluation value of each evaluation sample is calculated, where the cluster evaluation value reflects the similarity between the evaluation sample and each cluster center, which can be used to judge the congestion level of waterway traffic data.

[0034] In some embodiments, when calculating the cluster evaluation value of each evaluation sample, for each evaluation sample, the importance of each cluster center is first determined, and a weight is assigned to each cluster center according to its importance. If the importance of each cluster center is comparable, the equal weight method is adopted, that is, the same weight is assigned to each cluster center, and the weight vector is [1, 1, . . . , 1], where the length of the weight vector is equal to the number of cluster centers. If the importance of each cluster center is inconsistent, that is, the "crowded" cluster center is more important than other cluster centers, a higher weight is assigned to the cluster center. For each evaluation sample, its membership value to each cluster center is multiplied by the corresponding weight, and then summed to obtain the cluster evaluation value of the evaluation sample.

[0035] The clustering evaluation value of each evaluation sample is determined by the following formula: Among them, the clustering evaluation value i is the clustering evaluation value of the i-th evaluation sample, C is the number of cluster centers, is the membership value of the i-th evaluation sample to the j-th cluster center, and the weight j is the weight of the jth cluster center.

[0036] The higher the cluster evaluation value, the more similar the evaluation sample is to the "congested" cluster center, indicating that the waterway traffic is more congested. Therefore, the maximum evaluation value is determined from the cluster evaluation value of each evaluation sample, and the maximum evaluation value is compared with the preset threshold to determine whether the evaluation sample represents waterway congestion. If the maximum evaluation value meets the preset threshold, it means that the evaluation sample has waterway congestion. Otherwise, it means that there is no waterway congestion, that is, the waterway traffic is normal.

[0037] Through the above-mentioned optional implementation methods, anomalies in traffic data in waterway photos can be effectively identified, especially for waterway congestion, which not only improves the accuracy and efficiency of anomaly identification, but also provides strong technical support for realizing intelligent monitoring and management of waterway traffic.

[0038] In an optional implementation, when the abnormal data is an obstacle, the performing abnormality identification on the waterway photo includes: Determine the sea surface area and non-sea surface area in the channel photo according to the target channel area; Extracting first obstacle information of the sea surface area and second obstacle information of the non-sea surface area according to a preset obstacle database; It is determined whether the obstacle exists in the sea surface area according to the first obstacle information, and it is determined whether the obstacle exists in the non-sponge area according to the second obstacle information.

[0039] In some embodiments, the aircraft can extract the original point cloud data in the channel photo to identify abnormal data in the channel photo, especially obstacles. And further perform point cloud segmentation to determine the sea surface area and the non-sea surface area. In order to identify different types of obstacles, features are extracted from the original point cloud data of different areas, which may include normal features (indicating the direction of the surface), curvature features (indicating the degree of curvature of the surface) and shape features (such as the overall shape of the obstacle), etc., and the first obstacle information of the sea surface area and the second obstacle information of the non-sea surface area can also be determined according to the extracted features. The first obstacle information is obtained by comparing the first output result of the obstacle recognition model obtained by inputting the features of the original point cloud data corresponding to the sea surface area into the pre-trained obstacle recognition model with the preset obstacle database. The second obstacle information is obtained by comparing the second output result of the obstacle recognition model obtained by inputting the features of the original point cloud data corresponding to the non-sea surface area into the pre-trained obstacle recognition model with the preset obstacle database. When it is determined that any one of the data in the preset obstacle database exists in the first obstacle information or any one of the data in the preset obstacle database exists in the second obstacle information, it can be determined that there is an obstacle in the channel photo. When any data in the preset obstacle database exists in the first obstacle information, it means that there is an obstacle in the sea area, and ships in the normal channel area need to pay attention to the obstacle. When any data in the preset obstacle database exists in the second obstacle information, it means that there is an obstacle in the non-sea area. At this time, it is necessary to notify the aircraft to pay attention to the obstacle to avoid collision.

[0040] Among them, the obstacle recognition model is pre-trained based on the historical original point cloud data based on the deep learning network, and each historical original point cloud data includes annotation information. The preset obstacle database is a database that stores information on various obstacles in the waterway, which may include obstacle images (including example images of various obstacles for matching with waterway photos), feature descriptions (detailed feature descriptions of each obstacle, such as color, shape, texture and size, etc.), obstacle types (classification of obstacles, such as floating objects, sunken ships, bridges, docks, etc.), location information (known obstacles often appear in specific locations of the waterway), etc. The preset obstacle database can be subsequently constructed and updated by manual annotation, automatic annotation by machine learning algorithms, or a combination of the two, so as to make the preset obstacle database more accurate and complete.

[0041] Through the above optional implementation, by accurately distinguishing the sea surface area and the non-sea surface area and extracting their obstacle information respectively, it is possible to accurately determine the existence of obstacles in the waterway and surrounding areas, thereby improving the accuracy and reliability of obstacle identification. Secondly, it also helps ships to avoid obstacles in time during navigation, ensures the safe flight of aircraft, and significantly improves the intelligent level of waterway monitoring.

[0042] In some embodiments, after determining that there are obstacles in the waterway photo, the aircraft can also classify the obstacles into different categories (such as ships, buoys, buildings, etc.) and identify the specific type of each obstacle. Secondly, the aircraft can also use pixel coordinates or position coordinates relative to the waterway to determine the position of each obstacle in the waterway photo based on the results of target detection or semantic segmentation, thereby improving the intelligent level of waterway monitoring and providing strong support for the safe and efficient use of waterways by accurately classifying and locating obstacles.

[0043] In other embodiments, the aircraft may also directly acquire original point cloud data related to the target channel area from the acquisition device.

[0044] In an optional implementation, when the abnormal data is a hidden danger in the external environment, the abnormality identification of the waterway photo includes: Extracting features from the waterway photo to obtain a feature set; The target feature is compared with a preset environmental data set, wherein the target feature is any feature in the feature set; when it is determined that the target feature matches any environmental data in the preset environmental data set, it is determined that the waterway photo contains the external environmental hidden danger.

[0045] In some embodiments, the aircraft can make a comprehensive judgment through image analysis technology and a preset environmental data set to determine whether there are external environmental hazards in the route photo. The preset environmental data set is a database that stores various external environmental hazard information in the route.

[0046] Specifically, computer vision technologies such as image segmentation, edge detection, and target recognition are used to extract features related to external hidden dangers from waterway photos, including weather features (such as clouds, heavy rain, snowstorms, etc.), water surface features (such as wave height, water flow speed, oil pollution, algae outbreaks, etc.) and shoreline features (such as landslides, river bank erosion, tree collapse, etc.), and integrate them to obtain a feature set. Further, any feature extracted from the waterway photo is compared with the preset environmental data set. Whenever there is at least one feature that matches any environmental data in the preset environmental data set, it is determined that there are external environmental hidden dangers in the waterway photo, that is, there are external environmental hidden dangers in the target waterway area monitored by the aircraft.

[0047] In other embodiments, the aircraft is also integrated with multiple sensor modules for collecting external environment data, including meteorological data, water surface data, etc.

[0048] Through the above-mentioned optional implementation methods, by accurately identifying hidden dangers of the external environment in waterway photos, potential risks in the waterway can be discovered and determined in a timely manner, thereby improving the efficiency and accuracy of waterway monitoring, helping to prevent safety accidents caused by environmental factors such as bad weather and water pollution, and providing strong guarantees for the safe operation of the waterway.

[0049] S23, when it is determined that the abnormal data exists in the channel photo, an alarm is issued according to the abnormal data.

[0050] When an abnormality is identified, an alarm is sounded through the broadcast loudspeaker on the aircraft, and the alarm information and the channel photo / video data collected within a preset time range are sent to the terminal monitoring device.

[0051] In some embodiments, when it is determined that there is an abnormality in the target channel area, the aircraft can determine the level of the abnormality and perform different levels of alarms according to the abnormality level. Specifically, when it is determined that there is channel congestion in the channel area, the channel congestion level is determined according to the cluster evaluation value, such as mild, moderate, severe, etc. Among them, mild corresponds to the first level of alarm mode, moderate corresponds to the second level of alarm mode, and severe corresponds to the third level of alarm mode. Exemplarily, when the channel congestion level is mild, the aircraft can use the first level of alarm mode to alarm, for example, record abnormal information; when the channel congestion level is moderate, the aircraft uses the second level of alarm mode to alarm, for example, the warning light flashes, and sends warning information to the electronic equipment of the ground personnel (such as a mobile phone); when the channel congestion level is severe, the aircraft can use the third level of alarm mode to alarm, such as emergency broadcast, automatic obstacle avoidance, and notification of the ground control center. In other embodiments, the aircraft can also obtain the number of ships in the channel area and set different levels of alarm modes according to the number of ships.

[0052] In some embodiments, a 5G network can be deployed in the waterway in advance. Through the 5G network, the aircraft can transmit waterway photos and abnormality identification results to the terminal monitoring equipment in real time, so that monitoring personnel can understand the waterway conditions in time and take action, thereby improving the efficiency and accuracy of data feedback.

[0053] Through the above optional implementation, the airway is monitored in real time by an aircraft, which enables a quick response to abnormal situations such as congestion and obstacles. At the same time, the 5G network is used to transmit the airway photos and abnormal identification results in real time, ensuring that the monitoring personnel can quickly obtain accurate information and make timely decisions, further improving the intelligence and real-time nature of airway monitoring.

[0054] In an optional embodiment, the method further comprises: Obtaining the real-time flight trajectory, real-time flight speed and real-time flight attitude of the aircraft; Determining whether the aircraft is in an abnormal flight state according to the real-time flight trajectory, the real-time flight speed, and the real-time flight attitude; When it is determined that the aircraft is in the abnormal flight state, determining target flight data corresponding to the abnormal flight state, the target flight data being any one of the real-time flight trajectory, the real-time flight speed, and the real-time flight attitude; An alarm is issued according to the target flight data.

[0055] In some embodiments, sensors or other data acquisition devices installed on the aircraft can collect flight data of the aircraft in real time, including the flight route (real-time flight trajectory), flight speed (real-time flight speed) and flight attitude (real-time flight attitude), and send the flight data to the data processing unit of the aircraft through the communication bus or wireless transmission technology inside the aircraft. When the data processing unit receives the flight data, it can pre-process the flight data, such as data cleaning and format conversion, and further compare the real-time flight trajectory with the target flight route, the real-time flight speed with the preset speed threshold, and the real-time flight attitude with the preset flight attitude. Whenever any flight data is monitored to be abnormal, that is, the real-time flight trajectory does not conform to the target flight route, and / or the real-time flight speed exceeds the preset speed threshold, and / or the real-time flight attitude does not conform to the preset flight attitude, the aircraft can be in an abnormal flight state, and it can be determined which one or more flight data abnormalities cause the aircraft to be in the abnormal flight state, and the abnormal flight data is determined to be the target flight data. Once the target flight data is determined, the aircraft will trigger the corresponding alarm mechanism according to the preset alarm strategy, such as triggering an audible or visual alarm inside the aircraft to notify ground personnel, or sending the alarm information to the terminal monitoring equipment or the electronic equipment of the monitoring personnel through wireless communication technology. Among them, the alarm information can include a detailed description of the abnormal flight status, including the abnormal type, the target flight data and its abnormal value, the time of occurrence, etc.

[0056] After receiving the alarm information, the terminal monitoring device can take corresponding response measures, such as adjusting the flight plan, starting the emergency procedure, etc. At the same time, the aircraft can also automatically adjust according to the preset automatic response strategy, such as automatically correcting the flight attitude, slowing down, etc.

[0057] In some embodiments, if it is monitored that the real-time flight trajectory does not conform to the target flight route, and / or the real-time flight speed exceeds a preset speed threshold, and / or the real-time flight attitude does not conform to the preset flight attitude, the aircraft's route photo collection work is stopped.

[0058] Through the above optional implementation, by collecting the flight data of the aircraft in real time, and monitoring and comparing it in real time, the abnormal flight status of the aircraft can be quickly discovered. Once an abnormality is detected, not only can the abnormal type and abnormal data be accurately determined, but the alarm mechanism can also be triggered in time to effectively notify ground personnel and take corresponding response measures, which not only improves flight safety and reduces accident risks, but also improves the autonomy and response capabilities of the aircraft through the application of automatic response strategies, providing strong technical guarantees for the safe flight of the aircraft.

[0059] In an optional implementation, when it is determined that the abnormal data exists in the waterway photograph, the method further includes: Generate warning information according to the abnormal data, and determine a set of waterway photos corresponding to the abnormal data according to a preset time range; The warning information and the waterway photo set are sent to a terminal monitoring device.

[0060] In some embodiments, once abnormal data is identified, the aircraft will immediately generate an alarm message based on the abnormal data, where the alarm message may include key information such as the type, location, and time of the abnormality, so that the monitoring personnel of the terminal monitoring device can quickly understand and respond. At the same time, the aircraft can also determine a set of channel photos related to the abnormal data based on a preset time range, where the channel photo set includes multiple channel photos before and after the abnormality occurs, so that the monitoring personnel can understand the abnormality process and surrounding environment. Further, the aircraft will integrate the alarm message and the corresponding channel photo set and send them to the terminal monitoring device.

[0061] Through the above optional implementation methods, by real-time monitoring of abnormal conditions in the waterway and providing intuitive and comprehensive information support to monitoring personnel through alarm information and waterway photo collections, it helps to improve the efficiency and safety of waterway management.

[0062] Reference Figure 3 , which is a functional module diagram of a low-altitude aircraft area channel monitoring device shown in an embodiment of the present application.

[0063] In some embodiments, the low-altitude aircraft area channel monitoring device 30 may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments of the low-altitude aircraft area channel monitoring device 30 may be stored in a memory of an electronic device and executed by at least one processor to execute (see Figure 2 Description) Function of low-altitude aircraft regional channel monitoring.

[0064] In this embodiment, the low-altitude aircraft area channel monitoring device 30 can be divided into multiple functional modules according to the functions it performs. The functional modules may include: an acquisition module 301, an identification module 302, an alarm module 303 and a sending module 304. The module referred to in this application refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0065] The acquisition module 301 is used to acquire channel photos of the target channel area according to a target time period when it is detected that the aircraft is flying according to the target flight route.

[0066] The identification module 302 is used to perform anomaly identification on the waterway photo to determine whether there is abnormal data in the waterway photo.

[0067] The alarm module 303 is used to generate an alarm based on the abnormal data when it is determined that the abnormal data exists in the channel photo.

[0068] The identification module 302 is also specifically used to: determine the channel traffic data of the target channel area in the channel photo, and the clustering evaluation index of the channel traffic data; construct an evaluation sample matrix based on the channel traffic data and the clustering evaluation index; calculate the clustering evaluation value of each evaluation sample in the evaluation sample matrix; obtain the maximum evaluation value among the clustering evaluation values, and judge whether the channel traffic data has the channel congestion according to the maximum evaluation value.

[0069] The identification module 302 is also specifically used to: determine multiple cluster centers of the evaluation sample matrix, and the membership value of each evaluation sample to each cluster center; determine the weight of each cluster center, and determine the cluster evaluation value of each evaluation sample based on the membership value and the weight.

[0070] The identification module 302 is also specifically used to: determine the sea surface area and the non-sea surface area in the channel photo according to the target channel area; extract the first obstacle information of the sea surface area and the second obstacle information of the non-sea surface area according to a preset obstacle database; judge whether the obstacle exists in the sea surface area according to the first obstacle information, and judge whether the obstacle exists in the non-sponge area according to the second obstacle information.

[0071] The identification module 302 is also specifically used to: extract features from the waterway photo to obtain a feature set; compare the target feature with a preset environmental data set, the target feature being any one of the features in the feature set; and when it is determined that the target feature matches any one of the environmental data in the preset environmental data set, it is determined that the waterway photo contains the external environmental hidden danger.

[0072] The alarm module 303 is also used to: obtain the real-time flight trajectory, real-time flight speed and real-time flight attitude of the aircraft; determine whether the aircraft is in an abnormal flight state based on the real-time flight trajectory, the real-time flight speed and the real-time flight attitude; when it is determined that the aircraft is in the abnormal flight state, determine the target flight data corresponding to the abnormal flight state, the target flight data being any one of the real-time flight trajectory, the real-time flight speed and the real-time flight attitude; and issue an alarm based on the target flight data.

[0073] The sending module 304 is used to: generate warning information according to the abnormal data, and determine a set of waterway photos corresponding to the abnormal data according to a preset time range; and send the warning information and the set of waterway photos to a terminal monitoring device.

[0074] It should be understood that the various variations and specific embodiments of the low-altitude aircraft area channel monitoring method provided in the above-mentioned embodiments are also applicable to the low-altitude aircraft area channel monitoring device of the present embodiment. Through the above-mentioned detailed description of the low-altitude aircraft area channel monitoring method, those skilled in the art can clearly know the implementation method of the low-altitude aircraft area channel monitoring device in the present embodiment. For the sake of brevity of the specification, it will not be described in detail here.

[0075] Reference Figure 4 , which is a schematic diagram of a data processing unit according to an embodiment of the present application. In a preferred embodiment of the present application, the data processing unit 13 includes a memory 131 , at least one processor 132 and at least one communication bus 133 .

[0076] Those skilled in the art should understand that Figure 4 The structure of the data processing unit shown does not constitute a limitation of the embodiments of the present application, and can be either a bus structure or a star structure. The data processing unit 13 can also include more or less other hardware or software than shown in the figure, or a different component arrangement.

[0077] In some embodiments, the data processing unit 13 is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application-specific integrated circuits, programmable gate arrays, digital processors, and embedded devices.

[0078] It should be noted that the data processing unit 13 is only an example, and other existing or future electronic products that are suitable for the present application should also be included in the protection scope of the present application and included here by reference.

[0079] In some embodiments, the memory 131 stores a computer program, and when the computer program is executed by the at least one processor 132, all or part of the steps in the low-altitude aircraft regional channel monitoring method as described above are implemented.

[0080] In some embodiments, the at least one processor 132 is the control core (Control Unit) of the data processing unit 13, and uses various interfaces and lines to connect the various components of the entire data processing unit 13, and executes various functions and processes data of the data processing unit 13 by running or executing the program or module stored in the memory 131, and calling the data stored in the memory 131. For example, when the at least one processor 132 executes the computer program stored in the memory, it implements all or part of the steps of the low-altitude aircraft area channel monitoring method described in the embodiment of the present application; or implements all or part of the functions of the low-altitude aircraft area channel monitoring device. The at least one processor 132 can be composed of an integrated circuit, for example, it can be composed of a single packaged integrated circuit, or it can be composed of multiple integrated circuits with the same function or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips.

[0081] In some embodiments, the at least one communication bus 133 is configured to implement connection and communication between the memory 131 and the at least one processor 132, etc.

[0082] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling an electronic device (which can be a personal computer, electronic device, or network device, etc.) or a processor to execute part of the method described in each embodiment of the present application.

[0083] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0084] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0085] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for monitoring the regional channel of low-altitude aircraft, characterized in that: The method comprises: When the aircraft is detected flying along the target flight path, flight path photos of the target flight path area are collected according to the target time period; Performing anomaly recognition on the channel photo to determine whether there is abnormal data in the channel photo; When it is determined that the abnormal data exists in the channel photo, an alarm is issued according to the abnormal data.

2. The low-altitude aircraft regional channel monitoring method according to claim 1, characterized in that: When the abnormal data is waterway congestion, the abnormality identification of the waterway photo includes: Determining waterway traffic data of the target waterway area in the waterway photograph and a clustering evaluation index of the waterway traffic data; Constructing an evaluation sample matrix based on the waterway traffic data and the cluster evaluation index; Calculating a cluster evaluation value for each evaluation sample in the evaluation sample matrix; A maximum evaluation value among the cluster evaluation values ​​is obtained, and whether the waterway traffic data has waterway congestion is determined according to the maximum evaluation value.

3. The low-altitude aircraft regional channel monitoring method according to claim 2, characterized in that: Calculating the cluster evaluation value of each evaluation sample in the evaluation sample matrix based on the cluster evaluation index includes: Determining a plurality of cluster centers of the evaluation sample matrix and a membership value between each evaluation sample and each cluster center; The weight of each cluster center is determined, and the cluster evaluation value of each evaluation sample is determined according to the membership value and the weight.

4. The low-altitude aircraft regional channel monitoring method according to claim 1, characterized in that: When the abnormal data is an obstacle, the abnormality identification of the channel photo includes: determining the sea surface area and the non-sea surface area in the channel photo according to the target channel area; Extracting first obstacle information of the sea surface area and second obstacle information of the non-sea surface area according to a preset obstacle database; It is determined whether the obstacle exists in the sea surface area according to the first obstacle information, and it is determined whether the obstacle exists in the non-sponge area according to the second obstacle information.

5. The low-altitude aircraft regional channel monitoring method according to claim 1, characterized in that: When the abnormal data is a hidden danger in the external environment, the abnormality identification of the waterway photo includes: Performing feature extraction on the waterway photo to obtain a feature set; Comparing a target feature with a preset environmental data set, wherein the target feature is any one feature in the feature set; When it is determined that the target feature matches any one of the environmental data in the preset environmental data set, it is determined that the waterway photo contains the external environmental hidden danger.

6. The method for monitoring the regional channel of low-altitude aircraft according to any one of claims 1 to 5, characterized in that: The method further comprises: Obtaining the real-time flight trajectory, real-time flight speed and real-time flight attitude of the aircraft; determining whether the aircraft is in an abnormal flight state according to the real-time flight trajectory, the real-time flight speed, and the real-time flight attitude; When it is determined that the aircraft is in the abnormal flight state, determining target flight data corresponding to the abnormal flight state, the target flight data being any one of the real-time flight trajectory, the real-time flight speed, and the real-time flight attitude; An alarm is issued according to the target flight data.

7. The method for monitoring the regional channel of low-altitude aircraft according to any one of claims 1 to 5, characterized in that: When it is determined that the abnormal data exists in the channel photograph, the method further includes: Generate an alarm message based on the abnormal data, and determine a set of waterway photos corresponding to the abnormal data according to a preset time range; The warning information and the waterway photo collection are sent to a terminal monitoring device.

8. A low-altitude aircraft area channel monitoring device, characterized in that: The device comprises: The acquisition module is used to acquire channel photos of the target channel area according to the target time period when the aircraft is detected to be flying according to the target flight route; an identification module for performing anomaly identification on the waterway photo to determine whether the waterway photo contains abnormal data; The alarm module is used to generate an alarm based on the abnormal data when it is determined that the abnormal data exists in the channel photo.

9. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method for monitoring the regional channel of low-altitude aircraft according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the low-altitude aircraft regional channel monitoring method according to any one of claims 1 to 7 are implemented.

Images