Method, device, electronic device and storage medium for determining flight guarantee nodes

Abstract

The present application provides a method, apparatus, electronic device and storage medium for determining a flight guarantee node. The method includes: detecting whether there is an aircraft in the current image information; if the detection result is that there is no aircraft, determining whether the first flight guarantee node is the departure of the aircraft; if the first flight guarantee node is the departure of the aircraft, determining the first flight guarantee node as the current flight guarantee node; if the detection result is that there is an aircraft, comparing the current image information with the template image of the flight guarantee node to obtain a second flight guarantee node; according to the historical flight guarantee node information, determining whether the first flight guarantee node is the arrival of the aircraft; if the first flight guarantee node is the arrival of the aircraft, determining both the first flight guarantee node and the second flight guarantee node as the current flight guarantee node; otherwise, determining the second flight guarantee node as the current flight guarantee node. By means of the present application, the current flight guarantee node can be determined, improving the accuracy and determination efficiency.

Description

Technical Field

[0001] The present invention relates to the field of aviation technology, and in particular, to a method, device, electronic device and storage medium for determining flight guarantee nodes. Background Art

[0002] Flight ground service guarantee is a core and key link in the whole operation chain of civil aviation airports. Flight guarantee nodes are an important part of flight ground service guarantee, mainly referring to all ground guarantee nodes involved in the whole process from the landing to the takeoff of a flight. The ground guarantee nodes include nodes such as the arrival of the guiding vehicle, the departure of the guiding vehicle, the aircraft parking in place, and the aircraft leaving the place.

[0003] Currently, most airports determine the current flight guarantee nodes manually. However, the manual method has low efficiency and problems such as missed reports and misreports. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, device, electronic device and storage medium for determining flight guarantee nodes, which can determine the current flight guarantee nodes and improve the accuracy and determination efficiency.

[0005] In a first aspect, an embodiment of this application provides a method for determining flight guarantee nodes. The method for determining flight guarantee nodes includes:

[0006] Detect whether there is an aircraft in the current image information monitored at the parking position to obtain a detection result;

[0007] If the detection result is that there is no aircraft, then according to the historical flight guarantee node information of the parking position, determine whether the first flight guarantee node of the parking position is the aircraft leaving the place;

[0008] If the first flight guarantee node of the parking position is the aircraft leaving the place, then determine the first flight guarantee node as the current flight guarantee node of the parking position;

[0009] If the detection result is that there is an aircraft, then compare the current image information with the flight guarantee node template image to obtain a second flight guarantee node; and according to the historical flight guarantee node information of the parking position, determine whether the first flight guarantee node of the parking position is the aircraft parking in place;

[0010] If the first flight guarantee node is the aircraft parking in place, then determine the first flight guarantee node and the second flight guarantee node as the current flight guarantee node of the parking position; otherwise, determine the second flight guarantee node as the current flight guarantee node of the parking position.

[0011] In a possible implementation manner, detecting whether there is an aircraft in the current image information monitored at the parking position includes:

[0012] Identify the current image information and the aircraft area where the aircraft is located in the historical image information within a preset duration from the current time;

[0013] Determine the intersection over union (IoU) between each aircraft area in the current image information or historical image information and the aircraft area of the aircraft docking image corresponding to the parking position, and determine the maximum value among all the IoUs as the target IoU of the current image information or historical image information;

[0014] Input the current image information and the historical image information into an aircraft detection model respectively to obtain the aircraft presence probability of the parking position; the aircraft detection model is trained by sample image information and the corresponding aircraft presence probability;

[0015] Determine the detection result according to all the target IoUs and the aircraft presence probabilities of all the parking positions.

[0016] In a possible implementation manner, determining the detection result includes:

[0017] Calculate the average values of all the target IoUs and all the aircraft presence probabilities respectively to obtain a first average value and a second average value;

[0018] If the first average value is greater than or equal to a first preset threshold and the second average value is greater than or equal to a second preset threshold, the detection result is that there is an aircraft;

[0019] Otherwise, the detection result is that there is no aircraft.

[0020] In a possible implementation manner, comparing the current image information with the flight support node template image includes:

[0021] Calculate the first similarity between the current image information and a first template image; the flight support node template image includes at least one first template image with flight support equipment and a second template image without flight support equipment;

[0022] Calculate the second similarity between the current image information and the second template image;

[0023] Compare the maximum value among all the first similarities with the second similarity to obtain a second flight support node.

[0024] In a possible implementation manner, comparing the maximum value among all the first similarities with the second similarity to obtain a second flight support node includes:

[0025] If the maximum value is greater than the second similarity, determine whether the flight support node information in the historical flight support node information contains the flight support node of the flight support node template image corresponding to the maximum value;

[0026] If the historical flight guarantee node information contains the flight guarantee node corresponding to the flight guarantee node template image with the maximum value, the second flight guarantee node is empty;

[0027] If the historical flight guarantee node information does not contain the flight guarantee node corresponding to the flight guarantee node template image with the maximum value, determine the flight guarantee node corresponding to the flight guarantee node template image with the maximum value as the second flight guarantee node;

[0028] If the maximum value is less than the second similarity, use all the flight guarantee nodes without end nodes in the historical flight guarantee node information as the target flight guarantee nodes; and determine the second flight guarantee node as the end node of the target flight guarantee nodes.

[0029] In a possible implementation manner, the method further includes:

[0030] If the historical flight guarantee node information contains a jet bridge docking node and does not contain the end node of the jet bridge docking node, extract the moving area image in the current image information;

[0031] Calculate the similarity between the moving area image and the cabin door template image;

[0032] If the similarity is greater than the third preset threshold and the historical flight guarantee node information contains a cabin door opening node without a cabin door closing node, determine the cabin door closing node as the current flight guarantee node of the parking position;

[0033] If the similarity is greater than the third preset threshold and all the cabin door opening nodes in the historical flight guarantee node information correspond to cabin door closing nodes, determine the cabin door opening node as the current flight guarantee node of the parking position.

[0034] In a possible implementation manner, determining whether the first flight guarantee node of the parking position is an aircraft leaving or entering the position includes:

[0035] If the detection result is that there is an aircraft and all the aircraft entering positions in the historical flight guarantee node information correspond to aircraft leaving positions, the first flight guarantee node is the aircraft entering position;

[0036] If the detection result is that there is no aircraft and the historical flight guarantee nodes contain a target aircraft entering position without an aircraft leaving position, the first flight guarantee node is the aircraft leaving position corresponding to the target aircraft entering position.

[0037] In a second aspect, an embodiment of the present application further provides a device for determining a flight guarantee node, and the device for determining a flight guarantee node includes:

[0038] A detection module, configured to detect whether there is an aircraft in the current image information monitored at the parking position to obtain a detection result;

[0039] A judgment module, configured to, if the detection result is that there is no aircraft, determine whether the first flight support node of the parking bay is the aircraft departure according to the historical flight support node information of the parking bay;

[0040] A determination module, configured to, if the first flight support node of the parking bay is the aircraft departure, determine the first flight support node as the current flight support node of the parking bay;

[0041] A comparison module, configured to, if the detection result is that there is an aircraft, compare the current image information with the flight support node template image to obtain a second flight support node; and determine whether the first flight support node of the parking bay is the aircraft arrival according to the historical flight support node information of the parking bay;

[0042] The determination module is further configured to, if the first flight support node is the aircraft arrival, determine the first flight support node and the second flight support node as the current flight support node of the parking bay; otherwise, determine the second flight support node as the current flight support node of the parking bay.

[0043] In a possible implementation manner, the detection module is specifically configured to: identify the aircraft areas where the aircraft is located in the current image information and the historical image information within a current preset time period; determine the intersection-over-union ratio between each aircraft area in the current image information or the historical image information and the aircraft area of the aircraft arrival image corresponding to the parking bay, and determine the maximum value among all the intersection-over-union ratios as the target intersection-over-union ratio of the current image information or the historical image information; input the current image information and the historical image information into the aircraft detection model respectively to obtain the aircraft presence probability of the parking bay; the aircraft detection model is trained by sample image information and the corresponding aircraft presence probability; determine the detection result according to all the target intersection-over-union ratios and all the aircraft presence probabilities of the parking bays.

[0044] In a possible implementation manner, the detection module is further configured to:

[0045] Calculate the average values of all the target intersection-over-union ratios and all the aircraft presence probabilities respectively to obtain a first average value and a second average value;

[0046] If the first average value is greater than or equal to a first preset threshold and the second average value is greater than or equal to a second preset threshold, the detection result is that there is an aircraft;

[0047] Otherwise, the detection result is that there is no aircraft.

[0048] In a possible implementation, the comparison module is specifically configured to: calculate a first similarity between the current image information and the first template image; the flight guarantee node template image includes at least one first template image with flight guarantee equipment and a second template image without flight guarantee equipment; calculate a second similarity between the current image information and the second template image; compare the maximum value among all the first similarities with the second similarity to obtain the second flight guarantee node.

[0049] In a possible implementation, the comparison module is further configured to:

[0050] If the maximum value is greater than the second similarity, determine whether the flight guarantee node corresponding to the flight guarantee node template image with the maximum value is included in the historical flight guarantee node information;

[0051] If the flight guarantee node corresponding to the flight guarantee node template image with the maximum value is included in the historical flight guarantee node information, the second flight guarantee node is empty;

[0052] If the flight guarantee node corresponding to the flight guarantee node template image with the maximum value is not included in the historical flight guarantee node information, determine the flight guarantee node corresponding to the flight guarantee node template image with the maximum value as the second flight guarantee node;

[0053] If the maximum value is less than the second similarity, use all the flight guarantee nodes without end nodes in the historical flight guarantee node information as the target flight guarantee nodes; and determine the second flight guarantee node as the end node of the target flight guarantee nodes.

[0054] In a possible implementation, the device further includes: an extraction module and a calculation module;

[0055] The extraction module is configured to extract the moving area image in the current image information if the historical flight guarantee node information includes a jet bridge docking node and does not include the end node of the jet bridge docking node;

[0056] The calculation module is configured to calculate the similarity between the moving area image and the cabin door template image;

[0057] The determination module is further configured to determine the cabin door closing node as the current flight guarantee node of the parking position if the similarity is greater than a third preset threshold and the historical flight guarantee node information includes a cabin door opening node without a cabin door closing node;

[0058] The determination module is further configured to determine the cabin door opening node as the current flight guarantee node of the parking position if the similarity is greater than a third preset threshold and all the cabin door opening nodes in the historical flight guarantee node information correspond to cabin door closing nodes.

[0059] In a possible implementation, the determination module is specifically configured to: if the detection result is that an aircraft exists and all aircraft parking positions in the historical flight support node information correspond to aircraft departure positions, then the first flight support node is the aircraft parking position; if the detection result is that no aircraft exists and there is a target aircraft parking position without an aircraft departure position in the historical flight support nodes, then the first flight support node is the aircraft departure position corresponding to the target aircraft parking position.

[0060] In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus, and the processor executes the machine-readable instructions to perform the steps of the method for determining a flight support node according to any one of the first aspects.

[0061] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, it performs the steps of the method for determining a flight support node according to any one of the first aspects.

[0062] An embodiment of the present application provides a method, device, electronic device, and storage medium for determining a flight support node. The method for determining a flight support node includes: detecting whether an aircraft exists in the current image information monitored at the parking position to obtain a detection result; if the detection result is that no aircraft exists, then according to the historical flight support node information of the parking position, determining whether the first flight support node of the parking position is an aircraft departure position; if the first flight support node of the parking position is an aircraft departure position, then determining the first flight support node as the current flight support node of the parking position; if the detection result is that an aircraft exists, then comparing the current image information with the flight support node template image to obtain a second flight support node; and according to the historical flight support node information of the parking position, determining whether the first flight support node of the parking position is an aircraft parking position; if the first flight support node is an aircraft parking position, then determining the first flight support node and the second flight support node as the current flight support node of the parking position; otherwise, determining the second flight support node as the current flight support node of the parking position. By detecting the detection result of whether an aircraft exists in the current image information monitored at the parking position, the present application determines the current flight support node of the parking position, can determine the current flight support node, and improves the accuracy and determination efficiency. Description of the Drawings

[0063] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the embodiments will be briefly introduced below. It should be understood that the following accompanying drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related accompanying drawings can also be obtained based on these drawings.

[0064] Figure 1 It shows a flowchart of a method for determining a flight guarantee node provided by an embodiment of the present application;

[0065] Figure 2 It shows a flowchart of another method for determining a flight guarantee node provided by an embodiment of the present application;

[0066] Figure 3 It shows a schematic structural diagram of a device for determining a flight guarantee node provided by an embodiment of the present application;

[0067] Figure 4 It shows a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0068] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. It should be understood that the accompanying drawings in the present application only serve for illustration and description purposes and are not used to limit the protection scope of the present application. Additionally, it should be understood that the schematic accompanying drawings are not drawn to actual scale. The flowcharts used in the present application show the operations implemented according to some embodiments of the present application. It should be understood that the operations in the flowchart may not be implemented in sequence, and steps without logical context relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart or remove one or more operations from the flowchart under the guidance of the content of the present application.

[0069] In addition, the described embodiments are only some embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application usually described and shown in the accompanying drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application claimed, but only represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts fall within the protection scope of the present application.

[0070] In order to enable those skilled in the art to use the content of this application, the following embodiments are given in combination with a specific application scenario, namely, the "aviation technology field". For those skilled in the art, without departing from the spirit and scope of this application, the general principles defined here can be applied to other embodiments and application scenarios. Although this application is mainly described around the "automatic driving field", it should be understood that this is only an exemplary embodiment.

[0071] It should be noted that the term "including" will be used in the embodiments of this application to indicate the existence of the features stated thereafter, but does not exclude the addition of other features.

[0072] The following will provide a detailed description of a method for determining a flight guarantee node provided by an embodiment of this application.

[0073] Refer to Figure 1 As shown, it is a schematic flowchart of a method for determining a flight guarantee node provided by an embodiment of this application. The specific execution process of this method for determining a flight guarantee node is as follows:

[0074] S101. Detect whether there is an aircraft in the current image information monitored at the parking position to obtain a detection result.

[0075] S102. If the detection result is that there is no aircraft, then determine whether the first flight guarantee node of the parking position is the aircraft leaving the position according to the historical flight guarantee node information of the parking position.

[0076] S103. If the first flight guarantee node of the parking position is the aircraft leaving the position, then determine the first flight guarantee node as the current flight guarantee node of the parking position.

[0077] S104. If the detection result is that there is an aircraft, then compare the current image information with the flight guarantee node template image to obtain a second flight guarantee node; and determine whether the first flight guarantee node of the parking position is the aircraft entering the position according to the historical flight guarantee node information of the parking position.

[0078] S105. If the first flight guarantee node is the aircraft entering the position, then determine the first flight guarantee node and the second flight guarantee node as the current flight guarantee node of the parking position; otherwise, determine the second flight guarantee node as the current flight guarantee node of the parking position.

[0079] An embodiment of the present application provides a method for determining a flight guarantee node. The method for determining the flight guarantee node includes: detecting whether there is an aircraft in the current image information monitored at the parking position to obtain a detection result; if the detection result is that there is no aircraft, then according to the historical flight guarantee node information of the parking position, determining whether the first flight guarantee node of the parking position is the departure of the aircraft; if the first flight guarantee node of the parking position is the departure of the aircraft, then determining the first flight guarantee node as the current flight guarantee node of the parking position; if the detection result is that there is an aircraft, then comparing the current image information with the flight guarantee node template image to obtain a second flight guarantee node; and according to the historical flight guarantee node information of the parking position, determining whether the first flight guarantee node of the parking position is the arrival of the aircraft; if the first flight guarantee node is the arrival of the aircraft, then determining the first flight guarantee node and the second flight guarantee node as the current flight guarantee node of the parking position; otherwise, determining the second flight guarantee node as the current flight guarantee node of the parking position. By detecting the detection result of whether there is an aircraft in the current image information monitored at the parking position, the present application determines the current flight guarantee node of the parking position, can determine the current flight guarantee node, and improves the accuracy and determination efficiency.

[0080] The following describes the exemplary steps of the embodiments of the present application:

[0081] S101. Detect whether there is an aircraft in the current image information monitored at the parking position to obtain a detection result.

[0082] In the embodiment of the present application, at least one monitoring device is provided at each parking position, and the monitoring device can monitor the parking position to obtain the current image information. Detect whether there is an aircraft parked in the pre-image information of the parking position to obtain a detection result. The detection result includes two detection results: there is an aircraft and there is no aircraft. If the detection result is that there is an aircraft, it means that there is an aircraft parked in the parking position; if the detection result is that there is no aircraft, it means that there is no aircraft parked in the parking position.

[0083] The following steps are used to detect whether there is an aircraft in the current image information monitored at the parking position:

[0084] I. Identify the aircraft area where the aircraft is located in the current image information and the historical image information within a preset duration from the current time.

[0085] In the embodiment of the present application, the historical image information refers to the historical image information within a preset duration before the current image information, and the value of the preset duration needs to be set very small. The historical image information can also be several frame image information taken before the current image information, which can be preset to 10 frames, 11 frames, etc., and no specific limitation is made here.

[0086] Here, due to the limitation of the installation height of the apron monitoring, there is a possibility that passing aircraft and aircraft at adjacent positions can be monitored. Therefore, simply identifying the presence of an aircraft in the image information cannot directly determine the presence of an aircraft in the current image information. Thus, other technical means are needed to confirm the detection result. Network factors can affect the shooting effect, and detecting only through a single-frame image is also inaccurate. Therefore, by using the current image information and historical image information, it is to detect whether there is an aircraft at the parking position currently in terms of time, avoiding the influence of network and other factors on the detection result.

[0087] II. Determine the intersection over union (IoU) between each aircraft region in the current image information or historical image information and the aircraft region in the aircraft parking-in image corresponding to the parking position, and determine the maximum value among all the IoUs as the target IoU of the current image information or historical image information.

[0088] In the embodiment of the present application, due to the limitation of the installation height of the apron monitoring, there is a possibility that passing aircraft and aircraft at adjacent positions can be monitored. Therefore, there may be multiple aircraft regions in the current image information and historical image information. Different parking positions have different environments, so the aircraft parking-in images corresponding to different parking positions are also different. The aircraft parking-in image refers to the aircraft parking-in image taken at the corresponding parking position. Calculating the IoU is to detect whether there is an aircraft at the parking position currently in terms of space. The larger the IoU, the greater the possibility that there is an aircraft in the current image information or historical image information. Therefore, the maximum value among all the IoUs corresponding to the current image information or historical image information is determined as the target IoU of the current image information or historical image information. Example: There are aircraft regions A and B in the current image information. The IoU between A and the aircraft region in the aircraft parking-in image is 0.4; the IoUs between B and the aircraft region in the aircraft parking-in image are 0.7 respectively; 0.7 is greater than 0.4, and 0.7 is taken as the target IoU of the current image information.

[0089] Further, calculate the IoU between the aircraft region in the current image information or historical image information and the aircraft region in the aircraft parking-in image through the following formula.

[0090]

[0091] Where, IOU is the intersection over union, S1 is the area of the aircraft region in the aircraft parking-in image, and S2 is the area of the aircraft region in the current image information or historical image information.

[0092] III. Input the current image information and historical image information into the aircraft detection model respectively to obtain the probability of the presence of an aircraft at the parking position; the aircraft detection model is trained through sample image information and the corresponding probability of the presence of an aircraft.

[0093] In the embodiment of the present application, the aircraft detection model adopts the EfficientDet network model. The aircraft presence probability refers to the probability that an aircraft exists at the parking position.

[0094] IV. Determine the detection result according to all the target intersection over union ratios and the aircraft presence probabilities of all the parking positions.

[0095] Specifically, calculate the average values of all the target intersection over union ratios and all the aircraft presence probabilities respectively to obtain the first average value and the second average value; if the first average value is greater than or equal to the first preset threshold and the second average value is greater than or equal to the second preset threshold, the detection result is that there is an aircraft; otherwise, the detection result is that there is no aircraft.

[0096] S102. If the detection result is that there is no aircraft, then judge whether the first flight guarantee node of the parking position is an aircraft departure according to the historical flight guarantee node information of the parking position.

[0097] In the embodiment of the present application, since all the flight guarantee nodes except aircraft arrival and aircraft departure are carried out when there is an aircraft, when there is no aircraft at the parking position, it is only necessary to judge whether the first flight guarantee node of the parking position is an aircraft departure.

[0098] Specifically, if there is a target aircraft arrival without aircraft departure in the historical flight guarantee nodes, the first flight guarantee node is the aircraft departure corresponding to the target aircraft arrival.

[0099] In the embodiment of the present application, aircraft arrival and aircraft departure exist in pairs, and each flight guarantee node of aircraft arrival corresponds to a flight guarantee node of aircraft departure. There is no corresponding flight guarantee node of aircraft departure for this target aircraft arrival. The historical flight guarantee nodes include the flight guarantee node of the target aircraft arrival, that is to say, there is no corresponding flight guarantee node of aircraft departure for this target aircraft arrival, then the first flight guarantee node is the aircraft departure corresponding to the target aircraft arrival. The first flight guarantee node includes the aircraft departure and the monitoring time of the current image information.

[0100] S103. If the first flight guarantee node of the parking position is an aircraft departure, then determine the first flight guarantee node as the current flight guarantee node of the parking position.

[0101] In the embodiment of the present application, if the first flight guarantee node of the parking position is an aircraft departure, then there is no aircraft at this parking position, and it is not necessary to detect other flight guarantee nodes. Directly determine the first flight guarantee node as the current flight guarantee node of the parking position.

[0102] S104. If the detection result is that there is an aircraft, compare the current image information with the template image of the flight guarantee node to obtain the second flight guarantee node; and determine whether the first flight guarantee node of the parking position is the aircraft parking in according to the historical flight guarantee node information of the parking position.

[0103] In the embodiment of the present application, the flight guarantee node can also be understood as the ground service provided for an aircraft during the process from the aircraft arriving at the parking position to the aircraft flying away from the parking position. If there is an aircraft in the parking position, it is also necessary to continue to determine whether the current parking position is other flight guarantee nodes except for the aircraft leaving the position and the aircraft parking in, and it is also necessary to determine whether the parking position is the first flight guarantee node of the aircraft parking in when the current image information is monitored. The template image of the flight guarantee node refers to the images when each flight guarantee node occurs and the images when no flight guarantee node occurs. The second flight guarantee node is the flight guarantee node of the template image of the flight guarantee node that is successfully compared with the current image information.

[0104] In addition, since the opening and closing of the cabin door will occur after the corridor bridge is docked, the template image of the flight guarantee node does not include the template image of the flight guarantee node of the opening and closing of the cabin door.

[0105] Compare the current image information with the template image of the flight guarantee node through the following steps:

[0106] I. Calculate the first similarity between the current image information and the first template image; the template image of the flight guarantee node includes at least one first template image with flight guarantee equipment and a second template image without flight guarantee equipment.

[0107] In the embodiment of the present application, the higher the first similarity between the current image information and the first template image, the higher the possibility that the current flight guarantee node of the parking position is the flight guarantee node corresponding to the first template image. The first template image with flight guarantee equipment refers to the images when each flight guarantee node occurs. The flight guarantee equipment refers to the equipment required for the occurrence of the flight guarantee node, such as a guiding vehicle, a refueling vehicle, a corridor bridge, etc. The second template image without flight guarantee equipment refers to the image of the parking position when no flight guarantee node occurs.

[0108] II. Calculate the second similarity between the current image information and the second template image.

[0109] In the embodiment of the present application, the higher the second similarity, the greater the possibility that there is no flight guarantee node at the current parking position. The second similarity is the cosine similarity between the previous image information and the second template image.

[0110] Determine the cosine similarity between the current image information and the second template image through the following method.

[0111]

[0112] where ρ X,U is the cosine similarity between the current image information and the second template image, cov(X, Y) represents the covariance between the current image information and the second template image, X is the current image information, Y is the second template image, E is the mathematical expectation, and σ X is the standard deviation of the current image information, and σ Y is the standard deviation of the second template image.

[0113] III. Compare the maximum value among all the first similarities with the second similarity to obtain the second flight guarantee node.

[0114] In the embodiment of the present application, the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value in the first similarity is most likely to be the current flight guarantee node of the parking position.

[0115] Specifically, if the maximum value is greater than the second similarity, it is determined whether the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value is included in the historical flight guarantee node information.

[0116] Specifically, if the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value is included in the historical flight guarantee node information, the second flight guarantee node is empty.

[0117] In the embodiment of the present application, if the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value is included in the historical flight guarantee node information, it means that the flight guarantee node has been recorded, and the second flight guarantee node is empty.

[0118] However, if the duration between the occurrence time of the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value included in the historical flight guarantee node information and the monitoring time of the current image information is greater than the preset occurrence duration, the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value is determined as the second flight guarantee node.

[0119] Here, the preset occurrence duration is because there is a situation where airplanes stay overnight at the airport, and it is possible for the same flight guarantee node to occur twice.

[0120] Specifically, if the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value is not included in the historical flight guarantee node information, the flight guarantee node corresponding to the template image of the flight guarantee node with the maximum value is determined as the second flight guarantee node.

[0121] In the embodiment of the present application, if the flight guarantee node in the historical flight guarantee node information does not include the flight guarantee node of the flight guarantee node template image corresponding to the maximum value, it indicates that the flight guarantee node has not been recorded, and the flight guarantee node of the flight guarantee node template image corresponding to the maximum value is determined as the second flight guarantee node.

[0122] Specifically, if the maximum value is less than the second similarity, all flight guarantee nodes without end nodes in the historical flight guarantee node information are used as target flight guarantee nodes; and the second flight guarantee node is determined as the end node of the target flight guarantee node.

[0123] In the embodiment of the present application, each flight guarantee node corresponds to an end node. If the maximum value is less than the second similarity, it means that there is no flight guarantee node occurrence at this parking position. Therefore, for the flight guarantee nodes that did not have an end node before, when the current image information is monitored, they should be the end nodes of the target flight guarantee node.

[0124] Furthermore, according to the historical flight guarantee node information of the parking position, it is judged whether the first flight guarantee node of the parking position is an aircraft entering the position, including: if all aircraft entering positions in the historical flight guarantee node information correspond to aircraft leaving positions, then the first flight guarantee node is an aircraft entering the position.

[0125] In the embodiment of the present application, each flight guarantee node of an aircraft entering the position corresponds to an aircraft leaving position. If all aircraft entering positions in the historical flight guarantee node information correspond to aircraft leaving positions, then when the first flight guarantee node is an aircraft entering the position, the first flight guarantee node should be an aircraft entering the position.

[0126] In addition, if the target aircraft entering position without a corresponding aircraft leaving position is included in the historical flight guarantee node information, and the time duration between the occurrence time of the target aircraft entering position and the monitoring time of the current image information is greater than the preset occurrence duration, then it is judged whether the first flight guarantee node is an aircraft entering the position.

[0127] S105. If the first flight guarantee node is an aircraft entering the position, then the first flight guarantee node and the second flight guarantee node are determined as the current flight guarantee nodes of the parking position; otherwise, the second flight guarantee node is determined as the current flight guarantee node of the parking position.

[0128] In the real-time mode of the present application, when the detection result is that there is an aircraft, there will only be a first flight guarantee node when the first flight guarantee node is an aircraft entering the position. Therefore, if the first flight guarantee node is an aircraft entering the position, then the first flight guarantee node and the second flight guarantee node are determined as the current flight guarantee nodes of the parking position; otherwise, the second flight guarantee node is determined as the current flight guarantee node of the parking position.

[0129] Refer toFigure 2 As shown in the figure, it is a schematic flowchart of another method for determining a flight guarantee node provided by an embodiment of the present application. The specific execution process of this method for determining a flight guarantee node is as follows:

[0130] S201. If the historical flight guarantee node information contains a jet bridge docking node and does not contain an end node of the jet bridge docking node, extract the moving area image from the current image information.

[0131] In the embodiment of the present application, only after the jet bridge docking node occurs will the cabin door opening node or the cabin door closing node occur. When the historical flight guarantee node information contains a jet bridge docking node and does not contain an end node of the jet bridge docking node, it means that the jet bridge has been docked and has not been disconnected. The moving area image refers to the area that is moving in the image.

[0132] Here, the moving area image in the current image information is extracted by using a Gaussian mixture model. Since the cabin door moves when it is opened and closed, it is only necessary to extract the moving area image in the current image information.

[0133] S202. Calculate the similarity between the moving area image and the cabin door template image.

[0134] In the embodiment of the present application, the cabin door template image is a picture of the cabin door in a half-open state. This similarity is a pre-set similarity. The higher the similarity, the greater the possibility that the current flight guarantee node at the parking position is the cabin door opening node or the cabin door closing node.

[0135] Here, since the cabin door is in a half-open state only when it is opened and closed, the cabin door opening node or the cabin door closing node is determined by calculating the similarity between the moving area image and the cabin door template image.

[0136] S203. If the similarity is greater than the third preset threshold and the historical flight guarantee node information contains a cabin door opening node without a corresponding cabin door closing node, determine the cabin door closing node as the current flight guarantee node at the parking position.

[0137] In the embodiment of the present application, one cabin door opening node corresponds to one cabin door closing node. The similarity being greater than the third preset threshold indicates that the current flight guarantee node is the cabin door opening node or the cabin door closing node. The historical flight guarantee node information contains a cabin door opening node without a corresponding cabin door closing node, that is to say, the opening node does not have a corresponding cabin door closing node, indicating that the current flight guarantee node at the parking position is the cabin door closing node.

[0138] S204. If the similarity is greater than the third preset threshold and all cabin door opening nodes in the historical flight guarantee node information have corresponding cabin door closing nodes, determine the cabin door opening node as the current flight guarantee node at the parking position.

[0139] In the embodiment of the present application, when the similarity is greater than the third preset threshold, it indicates that the current flight guarantee section is the cabin door opening node or the cabin door closing node. If all the cabin door opening nodes in the historical flight guarantee node information correspond to the cabin door closing nodes, it indicates that the current flight guarantee node of the parking position is the cabin door opening node.

[0140] The embodiment of the present application provides another method for determining the flight guarantee node, which can determine whether the current flight guarantee node is the cabin door opening node or the cabin door closing node after the bridge docking node occurs.

[0141] Refer to Figure 3 Shown is a schematic diagram of a device for determining a flight guarantee node provided by an embodiment of the present application. The device for determining the flight guarantee node includes:

[0142] A detection module 301, configured to detect whether an aircraft exists in the current image information monitored at the parking position, and obtain a detection result;

[0143] A judgment module 302, configured to, if the detection result is that no aircraft exists, judge whether the first flight guarantee node of the parking position is the aircraft leaving the position according to the historical flight guarantee node information of the parking position;

[0144] A determination module 303, configured to, if the first flight guarantee node of the parking position is the aircraft leaving the position, determine the first flight guarantee node as the current flight guarantee node of the parking position;

[0145] A comparison module 304, configured to, if the detection result is that an aircraft exists, compare the current image information with the template image of the flight guarantee node to obtain the second flight guarantee node; and judge whether the first flight guarantee node of the parking position is the aircraft entering the position according to the historical flight guarantee node information of the parking position;

[0146] The determination module 303 is further configured to, if the first flight guarantee node is the aircraft entering the position, determine the first flight guarantee node and the second flight guarantee node as the current flight guarantee node of the parking position; otherwise, determine the second flight guarantee node as the current flight guarantee node of the parking position.

[0147] In a possible implementation, the detection module 301 is specifically configured to: identify the aircraft area where the aircraft is located in the current image information and the historical image information within a preset duration from the current time; determine the intersection-over-union ratio between each aircraft area in the current image information or the historical image information and the aircraft area of the aircraft docking image corresponding to the parking position, and determine the maximum value among all the intersection-over-union ratios as the target intersection-over-union ratio of the current image information or the historical image information; input the current image information and the historical image information into the aircraft detection model respectively to obtain the aircraft presence probability of the parking position; the aircraft detection model is trained by sample image information and the corresponding aircraft presence probability; determine the detection result according to all the target intersection-over-union ratios and the aircraft presence probabilities of all the parking positions.

[0148] In a possible implementation, the detection module 301 is further configured to:

[0149] Calculate the average values of all the target intersection-over-union ratios and all the aircraft presence probabilities respectively to obtain a first average value and a second average value;

[0150] If the first average value is greater than or equal to a first preset threshold and the second average value is greater than or equal to a second preset threshold, the detection result is that there is an aircraft;

[0151] Otherwise, the detection result is that there is no aircraft.

[0152] In a possible implementation, the comparison module 304 is specifically configured to: calculate the first similarity between the current image information and the first template image; the flight support node template image includes at least one first template image with flight support equipment and a second template image without flight support equipment; calculate the second similarity between the current image information and the second template image; compare the maximum value among all the first similarities with the second similarity to obtain the second flight support node.

[0153] In a possible implementation, the comparison module 304 is further configured to:

[0154] If the maximum value is greater than the second similarity, determine whether the flight support node corresponding to the maximum value in the historical flight support node information contains the flight support node of the flight support node template image corresponding to the maximum value;

[0155] If the historical flight support node information contains the flight support node of the flight support node template image corresponding to the maximum value, the second flight support node is empty;

[0156] If the historical flight support node information does not contain the flight support node of the flight support node template image corresponding to the maximum value, determine the flight support node of the flight support node template image corresponding to the maximum value as the second flight support node;

[0157] If the maximum value is less than the second similarity, all flight guarantee nodes without end nodes in the historical flight guarantee node information are used as target flight guarantee nodes; and the second flight guarantee node is determined as the end node of the target flight guarantee node.

[0158] In a possible implementation manner, the apparatus further includes: an extraction module 305 and a calculation module 306;

[0159] The extraction module 305 is configured to extract a moving area image in the current image information if the historical flight guarantee node information includes a jet bridge docking node and does not include an end node of the jet bridge docking node;

[0160] The calculation module 306 is configured to calculate the similarity between the moving area image and the cabin door template image;

[0161] The determination module 303 is further configured to determine the cabin door closing node as the current flight guarantee node of the parking position if the similarity is greater than a third preset threshold and the historical flight guarantee node information includes a cabin door opening node without a cabin door closing node;

[0162] The determination module 303 is further configured to determine the cabin door opening node as the current flight guarantee node of the parking position if the similarity is greater than a third preset threshold and all cabin door opening nodes in the historical flight guarantee node information correspond to cabin door closing nodes.

[0163] In a possible implementation manner, the judgment module 302 is specifically configured to use the first flight guarantee node as the aircraft parking position if the detection result is that an aircraft exists and all aircraft parking positions in the historical flight guarantee node information correspond to aircraft leaving positions; and use the first flight guarantee node as the aircraft leaving position corresponding to the target aircraft parking position if the detection result is that no aircraft exists and the historical flight guarantee node includes a target aircraft parking position without an aircraft leaving position.

[0164] As Figure 4 shown, an electronic device 400 provided by an embodiment of the present application includes: a processor 401, a memory 402, and a bus. The memory 402 stores machine-readable instructions executable by the processor 401. When the electronic device runs, the processor 401 communicates with the memory 402 through the bus, and the processor 401 executes the machine-readable instructions to perform the steps of the method for determining a flight guarantee node as described above.

[0165] Specifically, the above-mentioned memory 402 and processor 401 can be general memories and processors, which are not specifically limited here. When the processor 401 runs the computer program stored in the memory 402, it can execute the method for determining a flight guarantee node as described above.

[0166] Corresponding to the above method for determining flight guarantee nodes, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, it executes the steps for determining the above flight guarantee nodes.

[0167] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems and devices can refer to the corresponding processes in the method embodiments, which will not be elaborated herein. In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For another example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some communication interfaces. The indirect coupling or communication connection of the devices or modules can be in an electrical, mechanical, or other form.

[0168] The modules described as separate components may or may not be physically separated. The components displayed as modules may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0169] In addition, in each embodiment of the present application, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0170] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or this part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the information processing method described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0171] The above are only the specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for determining flight guarantee nodes, characterized in that, The method for determining the flight guarantee node includes: Detect whether there is an aircraft in the current image information monitored at the parking position to obtain a detection result; If the detection result is that there is no aircraft, then according to the historical flight guarantee node information of the parking position, determine whether the first flight guarantee node of the parking position is the departure of the aircraft; If the first flight guarantee node of the parking position is the departure of the aircraft, then determine the first flight guarantee node as the current flight guarantee node of the parking position; If the detection result is that there is an aircraft, then compare the current image information with the flight guarantee node template image to obtain a second flight guarantee node; and according to the historical flight guarantee node information of the parking position, determine whether the first flight guarantee node of the parking position is the arrival of the aircraft; If the first flight guarantee node is the arrival of the aircraft, then determine the first flight guarantee node and the second flight guarantee node as the current flight guarantee node of the parking position; otherwise, determine the second flight guarantee node as the current flight guarantee node of the parking position.

2. The method for determining flight guarantee nodes according to claim 1, characterized in that, The detection of whether there is an aircraft in the current image information monitored at the parking position includes: Identify the aircraft areas where the aircraft is located in the current image information and the historical image information within a current preset time period; Determine the intersection-over-union ratio between each aircraft area in the current image information or the historical image information and the aircraft area of the aircraft arrival image corresponding to the parking position, and determine the maximum value among all the intersection-over-union ratios as the target intersection-over-union ratio of the current image information or the historical image information; Input the current image information and the historical image information into an aircraft detection model respectively to obtain the aircraft existence probability of the parking position; the aircraft detection model is trained by sample image information and the corresponding aircraft existence probability; Determine the detection result according to all the target intersection-over-union ratios and all the aircraft existence probabilities of the parking positions.

3. The method for determining flight guarantee nodes according to claim 2, characterized in that, The determination of the detection result includes: Calculate the average values of all the target intersection-over-union ratios and all the aircraft existence probabilities respectively to obtain a first average value and a second average value; If the first average value is greater than or equal to a first preset threshold and the second average value is greater than or equal to a second preset threshold, then the detection result is that there is an aircraft; Otherwise, the detection result is that there is no aircraft.

4. The method for determining flight guarantee nodes according to claim 1, characterized in that, The comparison of the current image information with the flight guarantee node template image includes: Calculate the first similarity between the current image information and the first template image; the flight guarantee node template image includes at least one first template image with flight guarantee equipment and a second template image without flight guarantee equipment; Calculate the second similarity between the current image information and the second template image; Compare the maximum value among all the first similarities with the second similarity to obtain a second flight guarantee node.

5. The method for determining flight guarantee nodes according to claim 4, characterized in that, The comparison of the maximum value among all the first similarities with the second similarity to obtain a second flight guarantee node includes: If the maximum value is greater than the second similarity, it is determined whether the flight guarantee node corresponding to the maximum value in the historical flight guarantee node information is included in the historical flight guarantee node information; If the flight guarantee node corresponding to the maximum value in the historical flight guarantee node information is included in the historical flight guarantee node information, the second flight guarantee node is empty; If the flight guarantee node corresponding to the maximum value in the historical flight guarantee node information is not included in the historical flight guarantee node information, the flight guarantee node corresponding to the maximum value is determined as the second flight guarantee node; If the maximum value is less than the second similarity, all flight guarantee nodes without end nodes in the historical flight guarantee node information are used as target flight guarantee nodes; and the second flight guarantee node is determined as the end node of the target flight guarantee node.

6. The method for determining flight guarantee nodes according to claim 1, characterized in that, The method further includes: If the historical flight guarantee node information includes a jet bridge docking node and does not include an end node of the jet bridge docking node, the moving area image in the current image information is extracted; Calculate the similarity between the moving area image and the cabin door template image; If the similarity is greater than a third preset threshold and the historical flight guarantee node information includes a cabin door opening node without a cabin door closing node, the cabin door closing node is determined as the current flight guarantee node of the parking position; If the similarity is greater than a third preset threshold and all cabin door opening nodes in the historical flight guarantee node information correspond to cabin door closing nodes, the cabin door opening node is determined as the current flight guarantee node of the parking position.

7. The method for determining flight guarantee nodes according to claim 1, characterized in that, Determining whether the first flight guarantee node of the parking position is an aircraft departure or an aircraft arrival includes: If the detection result is that an aircraft exists and all aircraft arrivals in the historical flight guarantee node information correspond to aircraft departures, the first flight guarantee node is an aircraft arrival; If the detection result is that no aircraft exists and the historical flight guarantee includes a target aircraft arrival without an aircraft departure, the first flight guarantee node is the aircraft departure corresponding to the target aircraft arrival.

8. A determining device for flight guarantee nodes, characterized in that, The device for determining the flight guarantee node includes: A detection module for detecting whether an aircraft exists in the current image information monitored at the parking position to obtain a detection result; A judgment module for, if the detection result is that no aircraft exists, judging whether the first flight guarantee node of the parking position is an aircraft departure according to the historical flight guarantee node information of the parking position; A determination module for, if the first flight guarantee node of the parking position is an aircraft departure, determining the first flight guarantee node as the current flight guarantee node of the parking position; A comparison module for, if the detection result is that an aircraft exists, comparing the current image information with the flight guarantee node template image to obtain a second flight guarantee node; and judging whether the first flight guarantee node of the parking position is an aircraft arrival according to the historical flight guarantee node information of the parking position; The determining module is further configured to, if the first flight guarantee node is the aircraft parking position, determine the first flight guarantee node and the second flight guarantee node as the current flight guarantee nodes of the parking position; otherwise, determine the second flight guarantee node as the current flight guarantee node of the parking position.

9. An electronic device, characterized in that, including: a processor, a storage medium, and a bus. The storage medium stores machine-readable instructions executable by the processor. When the electronic device runs, the processor communicates with the storage medium through the bus. The processor executes the machine-readable instructions to perform the steps of the method for determining a flight guarantee node according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium. When the computer program is run by the processor, it performs the steps of the method for determining a flight guarantee node according to any one of claims 1 to 7.

Images