Flight on / off block time identification method, device, equipment and storage medium

Abstract

The present invention relates to the field of image recognition technology, and discloses a method, device, equipment and storage medium for identifying the on- and off-block times of flights. The method for identifying the on- and off-block times of flights comprises: collecting video images fixedly shot at the aircraft parking position at preset time intervals; inputting the video images into a pre-trained aircraft recognition model for recognition, and outputting the circumscribed rectangular coordinate frame of the recognized target aircraft; calculating the first overlap value and the second overlap value of the circumscribed rectangular coordinate frame of the target aircraft and the preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula; recording the first time node when the first overlap value is valid and the second time node when the second overlap value is valid; based on the first time node and the second time node, determining the on-block time or off-block time of the target aircraft. The present invention realizes the automatic recognition of the on- and off-block times of aircraft, reduces the recognition cost, and improves the efficiency and accuracy of recording.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a method, device, equipment and storage medium for identifying on / off block times of a flight. Background Art

[0002] With the rapid development of the aviation industry, airports need to collect data on multiple time nodes for each flight to ensure flight safety and flight order. However, flight delays often occur due to various subjective and objective factors, so it is necessary to accurately obtain the take-off and landing times of the aircraft for the convenience of management.

[0003] In the existing technology, after arriving at the airport and parking at the parking position, the aircraft needs to put on the chocks to prevent the aircraft from sliding; before taking off, the chocks need to be removed first, and then the gliding takeoff is performed. Therefore, the time when the aircraft puts on or off the chocks is usually used to determine the time of the aircraft landing or taking off. The time when the aircraft puts on or off the chocks is generally determined and recorded by manual reporting, which is uncertain and has low accuracy and efficiency. Summary of the invention

[0004] The main purpose of the present invention is to provide a flight on-and-off block time identification method, device, equipment and storage medium, aiming to solve the technical problems of inaccurate and low efficiency of flight on-and-off block time recording methods in the prior art.

[0005] A first aspect of the present invention provides a method for identifying on- and off-block times of a flight, comprising:

[0006] Collect video images taken at fixed positions of aircraft parking positions at preset time intervals;

[0007] Inputting the video image into a pre-trained aircraft recognition model for recognition, and outputting a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0008] Based on a preset overlap value calculation formula, a first overlap value and a second overlap value between a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame are calculated;

[0009] Recording a first time point when the first overlap value is valid and a second time point when the second overlap value is valid;

[0010] Based on the first time node and the second time node, an on-block time or an off-block time of the target aircraft is determined.

[0011] Optionally, in a first implementation of the first aspect of the present invention, the calculating, based on a preset overlap value calculation formula, a first overlap value and a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame comprises:

[0012] Calculating a first overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset first overlap value calculation formula;

[0013] Calculating a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset second overlap value calculation formula;

[0014] The first overlap value calculation formula and the second overlap value calculation formula are as follows:

[0015]

[0016] Where IOU1 represents the first overlap value, IOU2 represents the second overlap value, and B p Represents the external rectangular coordinate frame of the target aircraft, B a Represents the base bounding rectangle coordinate frame.

[0017] Optionally, in a second implementation of the first aspect of the present invention, the recording of a first time node when the first overlap value is valid and a second time node when the second overlap value is valid includes:

[0018] Determine whether the first overlap value is within a preset maximum overlap threshold and a minimum overlap threshold; if so, confirm that the first overlap value is valid, and record the shooting time of the video image as the first time node;

[0019] Determine whether the second overlap value is greater than the maximum overlap threshold; if so, confirm that the second overlap value is valid, and record the shooting time of the video image as the second time node.

[0020] Optionally, in a third implementation manner of the first aspect of the present invention, determining the on-block time or the off-block time of the target aircraft based on the first time node and the second time node includes:

[0021] Comparing the first time node with the second time node;

[0022] If the first time node is greater than the second time node, determining the next block time of the target aircraft to be the second time node;

[0023] If the first time node is less than the second time node, the on-block time of the target aircraft is determined to be the second time node.

[0024] Optionally, in a fourth implementation of the first aspect of the present invention, the flight block time identification method further includes:

[0025] If it is determined that the next block time of the target aircraft is the second time node, determining whether the difference between the first time node and the second time node is within a first preset time range;

[0026] If the difference between the first time node and the second time node is within the first preset time range, determining whether the difference between the off-block time of the target aircraft and the current flight take-off time of the aircraft parking position is within the second preset time range, and if so, determining that the off-block time of the target aircraft is correct;

[0027] If it is determined that the block time of the target aircraft is the second time node, determining whether the difference between the first time node and the second time node is within the first preset time range;

[0028] If the difference between the first time node and the second time node is within the first preset time range, it is determined whether the difference between the on-block time of the target aircraft and the arrival time of the current flight at the aircraft parking position is within the second preset time range; if so, it is determined that the on-block time of the target aircraft is correct.

[0029] Optionally, in a fifth implementation of the first aspect of the present invention, before acquiring the video images fixedly shot at the aircraft parking stand at preset time intervals, the method further includes:

[0030] Obtain sample video images of the upper and lower wheels of a sample aircraft shot at the same aircraft parking position;

[0031] sequentially inputting the sample video images into the aircraft recognition model for recognition, and outputting the circumscribed rectangular coordinate frame of each recognized sample aircraft;

[0032] Using a preset clustering algorithm to cluster the circumscribed rectangular coordinate frames of each of the sample aircraft to obtain a plurality of clusters;

[0033] The average bounding rectangular coordinate frame, the minimum bounding rectangular coordinate frame and the maximum bounding rectangular coordinate frame of the cluster with the largest number of bounding rectangular coordinate frames are counted, and the average bounding rectangular coordinate frame is used as the reference bounding rectangular coordinate frame.

[0034] Optionally, in a sixth implementation of the first aspect of the present invention, the calculation formula of the minimum overlap threshold is as follows:

[0035]

[0036] Among them, Th(min) is the minimum overlap threshold, B min is the minimum bounding rectangle coordinate frame, B a is the reference circumscribed rectangular coordinate frame;

[0037] The calculation formula of the maximum overlap threshold is as follows:

[0038]

[0039] Among them, Th(max) is the maximum overlap threshold, B max is the maximum circumscribed rectangular coordinate frame, B a is the reference circumscribed rectangular coordinate frame.

[0040] A second aspect of the present invention provides a flight block time identification device, comprising:

[0041] An acquisition module is used to acquire video images taken at fixed positions of aircraft parking positions at preset time intervals;

[0042] A recognition module, used for inputting the video image into a pre-trained aircraft recognition model for recognition, and outputting a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0043] A calculation module, used for calculating a first overlap value and a second overlap value between a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula;

[0044] A recording module, used for recording a first time node when the first overlap value is valid and a second time node when the second overlap value is valid;

[0045] A determination module is used to determine the on-block time or the off-block time of the target aircraft based on the first time node and the second time node.

[0046] Optionally, in a first implementation manner of the second aspect of the present invention, the calculation module is specifically used to:

[0047] Calculating a first overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset first overlap value calculation formula;

[0048] Calculating a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset second overlap value calculation formula;

[0049] The first overlap value calculation formula and the second overlap value calculation formula are as follows:

[0050]

[0051] Where IOU1 represents the first overlap value, IOU2 represents the second overlap value, and B p Represents the external rectangular coordinate frame of the target aircraft, B aRepresents the base bounding rectangle coordinate frame.

[0052] Optionally, in a second implementation of the second aspect of the present invention, the recording module is specifically used to:

[0053] Determine whether the first overlap value is within a preset maximum overlap threshold and a minimum overlap threshold; if so, confirm that the first overlap value is valid, and record the shooting time of the video image as the first time node;

[0054] Determine whether the second overlap value is greater than the maximum overlap threshold; if so, confirm that the second overlap value is valid, and record the shooting time of the video image as the second time node.

[0055] Optionally, in a third implementation manner of the second aspect of the present invention, the determining module is specifically configured to:

[0056] Comparing the first time node with the second time node;

[0057] If the first time node is greater than the second time node, determining the next block time of the target aircraft to be the second time node;

[0058] If the first time node is less than the second time node, the on-block time of the target aircraft is determined to be the second time node.

[0059] Optionally, in a fourth implementation of the second aspect of the present invention, the flight block time identification device further includes:

[0060] A first verification module, configured to determine whether a difference between the first time node and the second time node is within a first preset time range if it is determined that the next block time of the target aircraft is the second time node;

[0061] A second verification module is used to determine whether the difference between the next block time of the target aircraft and the current flight take-off time of the aircraft parking position is within a second preset time range if the difference between the first time node and the second time node is within the first preset time range, and if so, determine that the next block time of the target aircraft is correct;

[0062] a third verification module, configured to determine whether a difference between the first time node and the second time node is within the first preset time range if it is determined that the block time of the target aircraft is the second time node;

[0063] The fourth verification module is used to determine whether the difference between the on-block time of the target aircraft and the arrival time of the current flight at the aircraft parking position is within the second preset time range if the difference between the first time node and the second time node is within the first preset time range; if so, determine that the on-block time of the target aircraft is correct.

[0064] Optionally, in a fifth implementation of the second aspect of the present invention, the flight block time identification device further includes:

[0065] A sample acquisition module is used to acquire sample video images of upper and lower wheel blocks of a sample aircraft shot at the same aircraft parking position;

[0066] A sample recognition module, used to sequentially input the sample video images into the aircraft recognition model for recognition, and output the circumscribed rectangular coordinate frame of each recognized sample aircraft;

[0067] A sample clustering module, used for clustering the circumscribed rectangular coordinate frame of each sample aircraft using a preset clustering algorithm to obtain multiple clusters;

[0068] The sample statistics module is used to count the average bounding rectangular coordinate frame, the minimum bounding rectangular coordinate frame and the maximum bounding rectangular coordinate frame of the cluster with the largest number of bounding rectangular coordinate frames, and use the average bounding rectangular coordinate frame as the reference bounding rectangular coordinate frame.

[0069] Optionally, in a sixth implementation of the second aspect of the present invention, the calculation formula of the minimum overlap threshold is as follows:

[0070]

[0071] Among them, Th(min) is the minimum overlap threshold, B min is the minimum bounding rectangle coordinate frame, B a is the reference circumscribed rectangular coordinate frame;

[0072] The calculation formula of the maximum overlap threshold is as follows:

[0073]

[0074] Among them, Th(max) is the maximum overlap threshold, B max is the maximum circumscribed rectangular coordinate frame, B a is the reference circumscribed rectangular coordinate frame.

[0075] A third aspect of the present invention provides an electronic device, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the electronic device executes the above-mentioned flight up and down block time identification method.

[0076] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned flight on / off block time identification method.

[0077] In the technical solution provided by the present invention, image acquisition is performed at preset time intervals, and the acquired images are recognized by a preset aircraft recognition model to obtain the circumscribed rectangular coordinate frame of the aircraft, and the overlap between the circumscribed rectangular coordinate frame of the aircraft and the reference circumscribed rectangular coordinate frame is calculated by an overlap calculation formula, and valid time nodes are recorded, and the aircraft's on-block time or off-block time is identified based on the time nodes. The present invention automatically acquires and recognizes images taken at fixed aircraft parking positions in real time, and determines whether the aircraft appears at the target position by a preset overlap value calculation formula, thereby realizing automatic identification of the aircraft's on-block and off-block times, greatly improving the efficiency and accuracy of time recording, and reducing the identification cost of the aircraft's on-block and off-block times. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] Figure 1 It is a schematic diagram of a first embodiment of a method for identifying block times of flights in an embodiment of the present invention;

[0079] Figure 2 It is a schematic diagram of a second embodiment of a method for identifying block times of flights in an embodiment of the present invention;

[0080] Figure 3 It is a schematic diagram of a third embodiment of a method for identifying block times of flights in an embodiment of the present invention;

[0081] Figure 4 It is a schematic diagram of a first embodiment of a device for identifying block times for flights in an embodiment of the present invention;

[0082] Figure 5 It is a schematic diagram of a second embodiment of the device for identifying block times of flights in an embodiment of the present invention;

[0083] Figure 6 It is a schematic diagram of a third embodiment of the device for identifying the block time of an aircraft in an embodiment of the present invention;

[0084] Figure 7 FIG. 1 is a schematic diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] The embodiment of the present invention provides a flight on-and-off block time identification method, device, equipment and storage medium, which automatically identifies the aircraft through a preset aircraft identification model, calculates the overlap between the aircraft and the preset reference circumscribed rectangular coordinate frame, and thus determines the aircraft on-and-off block time. Automatically identifying the aircraft on-and-off block time greatly improves the efficiency and accuracy of time recording and reduces labor costs.

[0086] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0087] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 The first embodiment of the method for identifying the on- and off-block times of a flight in the embodiment of the present invention includes:

[0088] 101. Collect video images taken at fixed positions of aircraft parking positions at preset time intervals;

[0089] It is understandable that the execution subject of the present invention may be a flight block time identification device, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.

[0090] In this embodiment, a fixed shooting camera is installed in the airport for shooting fixed parking spaces.

[0091] In this embodiment, the captured surveillance video is obtained, and screenshots are taken of the acquired surveillance video at preset time intervals to obtain an image to be detected that can be used for aircraft identification, that is, a video image.

[0092] In this embodiment, the video image may be acquired at a preset time interval, or may be acquired at a preset number of frames.

[0093] 102. Input the video image into a pre-trained aircraft recognition model for recognition, and output a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0094] In this embodiment, the aircraft recognition model uses image recognition technology to identify whether there is an aircraft in the image. If so, the circumscribed rectangular coordinate frame of the recognized aircraft is marked.

[0095] In this embodiment, the aircraft recognition model is trained using pictures of various parts such as the whole aircraft, the nose, the tail, and other parts and pictures in different directions.

[0096] In this embodiment, the target aircraft is the aircraft in the video image identified by the aircraft recognition model.

[0097] In this embodiment, the circumscribed rectangular coordinate frame is a circumscribed rectangular frame that includes the target object, marks the position of the target object, and is represented by coordinates.

[0098] In this embodiment, the method for representing the circumscribed rectangular coordinate frame is not limited. Optionally, in one embodiment, the circumscribed rectangular coordinate frame is represented by the coordinates of the upper left corner vertex and the lower right corner vertex of the circumscribed rectangular coordinate frame, or the circumscribed rectangular coordinate frame is represented by a certain fixed vertex coordinate and the width and height of the circumscribed rectangular coordinate frame.

[0099] In this embodiment, the training method of the aircraft recognition model is not limited, including but not limited to MASK-RCNN, YOLO, and Faster-RCNN.

[0100] Optionally, in one embodiment, a MASK R-CNN model is used to train an aircraft recognition model, wherein the MASK R-CNN model includes, in sequence: a feature extraction network, an RPN (Region Proposal Network) network, a ROI Align (Region Ofinterest Align) layer and an FCN (Fully Convolutional Networks) network; the feature extraction network is used to extract a feature map of a sample image; the RPN network is used to obtain preset anchor box information in the feature map, and determine whether the anchor box contains an identification target, if so, retain the anchor box, and adjust the position of the anchor box in the feature map to obtain a pre-selected box of the sample image; the ROI Align layer is used to identify the position of the pre-selected box on the feature map, and fuse the pre-selected box with the target feature map, and segment and endpoint pool the pre-selected box to obtain a labeled feature map; the FCN network is used to predict each pixel point of the labeled feature map to obtain a prediction result corresponding to the sample image.

[0101] Based on the above MASK R-CNN model, the aircraft recognition model training includes the following steps:

[0102] (1) Inputting the sample aircraft image and the label information corresponding to the sample aircraft image into the preset MASK R-CNN model;

[0103] (2) extracting a target feature map of the aircraft sample image through the feature extraction network;

[0104] (3) inputting the target feature map into the RPN network so that the RPN network generates a pre-selected box corresponding to the target feature map according to preset anchor box information;

[0105] (4) inputting the pre-selected box and the target feature map into the ROI Align layer, so that the pre-selected box and the target feature map are fused through the ROI Align layer, and the pre-selected box is segmented and the endpoints are pooled to obtain a labeled feature map;

[0106] (5) inputting the annotated feature map into the FCN network so that the FCN network can predict each pixel point of the annotated feature map, obtain a prediction result corresponding to the sample image and output it;

[0107] (6) Optimizing the parameters of the MASK R-CNN model according to the prediction results and the label information until the MASK R-CNN model converges to obtain an aircraft recognition model.

[0108] 103. Calculate a first overlap value and a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula;

[0109] In this embodiment, the overlap value is used to indicate the overlap degree of two circumscribed rectangular coordinate frames.

[0110] In this embodiment, the overlap value calculation formula is used to calculate the overlap value, and is usually calculated using the intersection-and-union ratio of two circumscribed rectangular coordinate frames.

[0111] In this embodiment, the preset reference circumscribed rectangular coordinate frame, that is, the circumscribed rectangular coordinate frame of the aircraft when it is parked at the aircraft parking position, is a reference coordinate frame.

[0112] In this embodiment, the first overlap value is used to determine whether the target aircraft is within a specified range, which is an area range at a certain distance from the aircraft parking position; the second overlap value is used to determine whether the target aircraft is at the aircraft parking position.

[0113] 104. Record a first time point when the first overlap value is valid and a second time point when the second overlap value is valid;

[0114] In this embodiment, the first overlap value is valid, that is, the first overlap value satisfies a preset condition, and the preset condition is used to determine whether the target aircraft is at the specified position, that is, the first overlap value is valid, indicating that the target aircraft is at the specified position. In this embodiment, the specified position is an area range at a certain distance from the aircraft parking position.

[0115] In this embodiment, the second overlap value is valid, that is, the second overlap value satisfies another preset condition, and the preset condition is used to determine whether the target aircraft is at the specified position, that is, the second overlap value is valid, indicating that the target aircraft is at the specified position. In this embodiment, the specified position is an aircraft parking position.

[0116] In this embodiment, the time node is the shooting time of the video image with a valid overlap value.

[0117] 105. Determine an on-block time or an off-block time of the target aircraft based on the first time node and the second time node.

[0118] In this embodiment, the first time node is a time node when the target aircraft is at a certain distance from the aircraft parking position, and the second time node is a time node when the target aircraft is at the aircraft parking position.

[0119] In this embodiment, according to the sequence of the first time node and the second time node, it is determined whether the target aircraft is taking off or landing, thereby determining whether the target aircraft needs to be in gear or out of gear.

[0120] In this embodiment, the second time node is the time node when the target aircraft is at the aircraft parking position, so the second time node is the on-block time or the off-block time of the target aircraft.

[0121] In an embodiment of the present invention, image acquisition is performed at preset time intervals, and the acquired images are recognized by a preset aircraft recognition model to obtain the circumscribed rectangular coordinate frame of the aircraft, and the overlap between the circumscribed rectangular coordinate frame of the aircraft and the reference circumscribed rectangular coordinate frame is calculated by an overlap calculation formula, and valid time nodes are recorded, and the aircraft's on-block time or off-block time is identified based on the time nodes. The present invention automatically acquires and recognizes images taken at fixed aircraft parking positions in real time, and determines whether the aircraft appears at the target position by a preset overlap value calculation formula, thereby realizing automatic identification of the aircraft's on-block and off-block times, greatly improving the efficiency and accuracy of time recording, and reducing the identification cost of the aircraft's on-block and off-block times.

[0122] See also Figure 2 The second embodiment of the method for identifying the on- and off-block times of a flight in the embodiment of the present invention includes:

[0123] 201. Collect video images taken at fixed positions of aircraft parking positions at preset time intervals;

[0124] 202. Input the video image into a pre-trained aircraft recognition model for recognition, and output a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0125] 203. Calculate a first overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset first overlap value calculation formula;

[0126] Optionally, in one embodiment, the first overlap value calculation formula is as follows:

[0127]

[0128] Among them, IOU1 represents the first overlap value, B p Represents the external rectangular coordinate frame of the target aircraft, B a Represents the base bounding rectangle coordinate frame.

[0129] In this embodiment, B p ∩B a represents the intersection of the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame, that is, the area of ​​the intersection of the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame; B p ∪B a The union of the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame, that is, the area of ​​the union of the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame; the overlap between the target aircraft and the reference aircraft parking position is represented by the intersection-union ratio, so as to determine whether the aircraft appears at the target position. In this embodiment, it is used to determine whether the target aircraft appears within a certain distance from the aircraft parking position.

[0130] 204. Calculate a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset second overlap value calculation formula;

[0131] Optionally, in one embodiment, the second overlap value calculation formula is as follows:

[0132]

[0133] Where IOU2 represents the second overlap value, B p Represents the external rectangular coordinate frame of the target aircraft, B a Represents the base bounding rectangle coordinate frame.

[0134] In this embodiment, B p ∩B a It represents the intersection of the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame, that is, the area of ​​the intersection of the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame.

[0135] In this embodiment, the denominator B a Indicates the area of ​​the base bounding rectangle coordinate box.

[0136] In this embodiment, the overlap between the target aircraft and the reference aircraft parking position is represented by the ratio of the intersection area of ​​the target aircraft's circumscribed rectangular coordinate frame and the reference circumscribed rectangular coordinate frame to the area of ​​the reference circumscribed rectangular coordinate frame, so as to determine whether the aircraft appears at the aircraft parking position. The position of the aircraft after it stops is relatively stable, so it is more accurate to use the calculation formula of IOU2 to determine whether the aircraft has arrived at the aircraft parking position.

[0137] 205. Determine whether the first overlap value is within a range between a preset maximum overlap threshold and a minimum overlap threshold; if so, confirm that the first overlap value is valid, and record the shooting time of the video image as a first time node;

[0138] In this embodiment, the maximum overlap threshold and the minimum overlap threshold are used to determine whether the target aircraft is at a specified location. When the first overlap value is between the maximum overlap threshold and the minimum overlap threshold, the target aircraft is within an area at a certain distance from the aircraft parking point.

[0139] In this embodiment, when it is determined that the target aircraft is within a certain distance from the aircraft parking point, the shooting time of the current video image is recorded as the first time node.

[0140] Optionally, in one embodiment, the calculation formula of the minimum overlap threshold is as follows:

[0141]

[0142] Among them, Th(min) is the minimum overlap threshold, B min is the minimum bounding rectangle coordinate frame, B a is the reference circumscribed rectangular coordinate frame;

[0143] The calculation formula of the maximum overlap threshold is as follows:

[0144]

[0145] Among them, Th(max) is the maximum overlap threshold, B max is the maximum circumscribed rectangular coordinate frame, B a is the reference circumscribed rectangular coordinate frame.

[0146] In this embodiment, the minimum circumscribed rectangular coordinate frame is the rectangular coordinate frame of the aircraft with the smallest area that can circumscribe the aircraft parking point; the maximum circumscribed rectangular coordinate frame is the rectangular coordinate frame of the aircraft with the largest area that can circumscribe the aircraft parking point.

[0147] 206. Determine whether the second overlap value is greater than the maximum overlap threshold; if so, confirm that the second overlap value is valid, and record the shooting time of the video image as a second time node;

[0148] In this embodiment, when the second overlap value is greater than the maximum overlap threshold, it is determined that the target aircraft is at the aircraft parking point. When it is determined that the target aircraft is at the aircraft parking point, the shooting time of the current video image is recorded as the second time node.

[0149] 207. Determine an on-block time or an off-block time of the target aircraft based on the first time node and the second time node;

[0150] Optionally, in one embodiment, determining the on-block time or off-block time of the target aircraft based on the first time node and the second time node includes:

[0151] Comparing the first time node with the second time node;

[0152] If the first time node is greater than the second time node, determining the next block time of the target aircraft to be the second time node;

[0153] If the first time node is less than the second time node, the on-block time of the target aircraft is determined to be the second time node.

[0154] In this embodiment, the first time node is a time node when the target aircraft is at a certain distance from the aircraft parking position, and the second time node is a time node when the target aircraft is at the aircraft parking position.

[0155] In this embodiment, according to the sequence of the first time node and the second time node, it is determined whether the target aircraft is taking off or landing, thereby determining whether the target aircraft needs to be in gear or out of gear; when the first time node is greater than the second time node, the target aircraft moves from the aircraft parking position to a position at a certain distance from the aircraft parking position, the aircraft takes off, and the recorded time is the out of gear time; when the first time node is less than the second time node, the target aircraft moves from a position at a certain distance from the aircraft parking position to the aircraft parking position, the aircraft lands and arrives, and the recorded time is the in gear time.

[0156] In this embodiment, the second time node is the time node when the target aircraft is at the aircraft parking position, so the second time node is the on-block time or the off-block time of the target aircraft.

[0157] 208. If it is determined that the down block time of the target aircraft is the second time node, determining whether the difference between the first time node and the second time node is within a first preset time range;

[0158] In this embodiment, the first preset time range is an empirical value that can be set based on experience. For example, if the time it takes for the target aircraft to glide out of the reference circumscribed rectangular coordinate frame from the aircraft parking point is within one minute, the first preset time range can be set to one minute.

[0159] 209. If the difference between the first time node and the second time node is within the first preset time range, determining whether the difference between the off-block time of the target aircraft and the current flight take-off time of the aircraft parking position is within the second preset time range, and if so, determining that the off-block time of the target aircraft is correct;

[0160] In this embodiment, since the aircraft does not lower the gear until before take-off, the aircraft take-off time can be used to verify whether the identified aircraft lowering gear time is correct.

[0161] In this embodiment, the second preset time range is an empirical value that can be set based on experience, such as 30 minutes.

[0162] 210. If it is determined that the block time of the target aircraft is the second time node, determining whether the difference between the first time node and the second time node is within the first preset time range;

[0163] 211. If the difference between the first time node and the second time node is within the first preset time range, determine whether the difference between the on-block time of the target aircraft and the arrival time of the current flight at the aircraft parking position is within the second preset time range; if so, determine that the on-block time of the target aircraft is correct.

[0164] In the embodiment of the present invention, image acquisition is performed at preset time intervals, and the acquired images are recognized by a preset aircraft recognition model to obtain a circumscribed rectangular coordinate frame of the target aircraft. The overlap between the circumscribed rectangular coordinate frame of the target aircraft and the reference circumscribed rectangular coordinate frame is calculated by the IOU1 and IOU2 overlap calculation formula, and the time node of the target aircraft at the specified position is recorded, and the aircraft's up-block time or down-block time is identified based on the time node. The embodiment of the present invention automatically acquires and recognizes images taken at a fixed aircraft parking position in real time, and determines whether the aircraft appears at the target position by a preset overlap value calculation formula, thereby realizing automatic identification of the aircraft's up-block and down-block time, greatly improving the efficiency and accuracy of time recording, and reducing labor costs. The IOU2 overlap calculation formula is used to determine whether the target aircraft is at the aircraft parking position, which has higher accuracy, and the identified up-block and down-block time is verified based on the flight time, reducing the error rate.

[0165] See also Figure 3 A third embodiment of the method for identifying the block time of a flight in the embodiment of the present invention includes:

[0166] 301. Obtain sample video images of upper and lower wheel blocks of a sample aircraft shot at the same aircraft parking position;

[0167] In this embodiment, the video images shot historically may be obtained, or the video images of the aircraft at the aircraft parking point may be obtained by testing the aircraft and shooting the aircraft.

[0168] 302. Input the sample video images into the aircraft recognition model in sequence for recognition, and output the circumscribed rectangular coordinate frame of each recognized sample aircraft;

[0169] In this embodiment, the circumscribed rectangular coordinate frame is represented by the coordinates of its upper left corner vertex and lower right corner vertex.

[0170] 303. Clustering the circumscribed rectangular coordinate frames of each of the sample aircraft using a preset clustering algorithm to obtain a plurality of clusters;

[0171] In this embodiment, the clustering method used is not limited, including but not limited to k-means and EM algorithm.

[0172] 304. Count the average bounding rectangular coordinate frame, the minimum bounding rectangular coordinate frame, and the maximum bounding rectangular coordinate frame of the cluster with the largest number of bounding rectangular coordinate frames, and use the average bounding rectangular coordinate frame as the reference bounding rectangular coordinate frame.

[0173] In this embodiment, the average bounding rectangular coordinate frame is to find the average value of the upper left corner vertex and the lower right corner vertex of all the bounding rectangular coordinate frames of the cluster, and the bounding rectangular coordinate frame represented by the obtained coordinate value is the average bounding rectangular coordinate frame; the minimum bounding rectangular coordinate frame is the bounding rectangular coordinate frame with the smallest area; the maximum bounding rectangular coordinate frame is the bounding rectangular coordinate frame with the largest area.

[0174] 305. Collect video images taken at fixed positions of aircraft parking positions at preset time intervals;

[0175] 306. Input the video image into a pre-trained aircraft recognition model for recognition, and output a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0176] 307. Calculate a first overlap value and a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula;

[0177] 308. Record a first time point when the first overlap value is valid and a second time point when the second overlap value is valid;

[0178] 309. Determine an on-block time or an off-block time of the target aircraft based on the first time node and the second time node.

[0179] In an embodiment of the present invention, a sample video image is obtained, the sample video image is identified and each circumscribed rectangular coordinate frame is obtained, a clustering algorithm is used to cluster each circumscribed rectangular coordinate frame to obtain a circumscribed rectangular coordinate frame used as a judgment reference, image acquisition is performed at preset time intervals, the acquired image is identified by a preset aircraft recognition model to obtain the circumscribed rectangular coordinate frame of the aircraft, the overlap between the circumscribed rectangular coordinate frame of the aircraft and the reference circumscribed rectangular coordinate frame is calculated by an overlap calculation formula, and valid time nodes are recorded, and the aircraft's on-block time or off-block time is identified based on the time nodes. The embodiment of the present invention classifies the circumscribed rectangular coordinate frames in the sample video image by a clustering method, and selects the cluster with the most samples for calculation, thereby reducing noise and improving the accuracy of the reference circumscribed rectangular coordinate frame.

[0180] The above describes the flight block time identification method in the embodiment of the present invention. The following describes the flight block time identification device in the embodiment of the present invention. Figure 4 The first embodiment of the flight block time identification device in the embodiment of the present invention includes:

[0181] The acquisition module 401 is used to acquire video images taken at a fixed position of the aircraft parking position at preset time intervals;

[0182] The recognition module 402 is used to input the video image into a pre-trained aircraft recognition model for recognition, and output a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0183] A calculation module 403, configured to calculate a first overlap value and a second overlap value between a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula;

[0184] A recording module 404, configured to record a first time point when the first overlap value is valid and a second time point when the second overlap value is valid;

[0185] The determination module 405 is used to determine the on-block time or the off-block time of the target aircraft based on the first time node and the second time node.

[0186] Optionally, in one embodiment, the calculation module 403 is specifically used for:

[0187] Calculating a first overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset first overlap value calculation formula;

[0188] Calculating a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset second overlap value calculation formula;

[0189] The first overlap value calculation formula and the second overlap value calculation formula are as follows:

[0190]

[0191] Where IOU1 represents the first overlap value, IOU2 represents the second overlap value, and B p Represents the external rectangular coordinate frame of the target aircraft, B a Represents the base bounding rectangle coordinate frame.

[0192] Optionally, in one embodiment, the recording module 404 is specifically used for:

[0193] Determine whether the first overlap value is within a preset maximum overlap threshold and a minimum overlap threshold; if so, confirm that the first overlap value is valid, and record the shooting time of the video image as the first time node;

[0194] Determine whether the second overlap value is greater than the maximum overlap threshold; if so, confirm that the second overlap value is valid, and record the shooting time of the video image as the second time node.

[0195] Optionally, in one embodiment, the determining module 405 is specifically configured to:

[0196] Comparing the first time node with the second time node;

[0197] If the first time node is greater than the second time node, determining the next block time of the target aircraft to be the second time node;

[0198] If the first time node is less than the second time node, the on-block time of the target aircraft is determined to be the second time node.

[0199] In an embodiment of the present invention, image acquisition is performed at preset time intervals, and the acquired images are recognized by a preset aircraft recognition model to obtain the circumscribed rectangular coordinate frame of the aircraft. The overlap between the circumscribed rectangular coordinate frame of the aircraft and the reference circumscribed rectangular coordinate frame is calculated by an overlap calculation formula, and valid time nodes are recorded, and the aircraft's on-block time or off-block time is identified based on the time nodes. In an embodiment of the present invention, images taken at fixed positions of aircraft parking positions are automatically acquired and recognized in real time, and whether the aircraft appears at the target position is determined by a preset overlap value calculation formula, thereby realizing automatic recognition of the aircraft's on-block and off-block time, greatly improving the efficiency and accuracy of time recording and reducing labor costs.

[0200] See also Figure 5 The second embodiment of the flight block time identification device in the embodiment of the present invention includes:

[0201] The acquisition module 401 is used to acquire video images taken at a fixed position of the aircraft parking position at preset time intervals;

[0202] The recognition module 402 is used to input the video image into a pre-trained aircraft recognition model for recognition, and output a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0203] A calculation module 403, configured to calculate a first overlap value and a second overlap value between a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula;

[0204] A recording module 404, configured to record a first time point when the first overlap value is valid and a second time point when the second overlap value is valid;

[0205] A determination module 405, configured to determine an on-block time or an off-block time of the target aircraft based on the first time node and the second time node;

[0206] A first verification module 406, for determining whether a difference between the first time node and the second time node is within a first preset time range if it is determined that the next block time of the target aircraft is the second time node;

[0207] A second verification module 407 is used to determine whether the difference between the next block time of the target aircraft and the current flight take-off time of the aircraft parking position is within the second preset time range if the difference between the first time node and the second time node is within the first preset time range, and if so, determine that the next block time of the target aircraft is correct;

[0208] A third verification module 408, for determining whether a difference between the first time node and the second time node is within the first preset time range if it is determined that the on-block time of the target aircraft is the second time node;

[0209] The fourth verification module 409 is used to determine whether the difference between the on-block time of the target aircraft and the arrival time of the current flight at the aircraft parking position is within the second preset time range if the difference between the first time node and the second time node is within the first preset time range; if so, determine that the on-block time of the target aircraft is correct.

[0210] In the embodiment of the present invention, image acquisition is performed at preset time intervals, and the acquired images are recognized by a preset aircraft recognition model to obtain a circumscribed rectangular coordinate frame of the target aircraft. The overlap between the circumscribed rectangular coordinate frame of the target aircraft and the reference circumscribed rectangular coordinate frame is calculated by the IOU1 and IOU2 overlap calculation formula, and the time node of the target aircraft at the specified position is recorded, and the aircraft's on-block time or off-block time is identified based on the time node. The embodiment of the present invention automatically acquires and recognizes images taken at a fixed aircraft parking position in real time, and determines whether the aircraft appears at the target position by a preset overlap value calculation formula, thereby realizing automatic identification of the aircraft's on-block and off-block time, greatly improving the efficiency and accuracy of time recording, reducing labor costs, and verifying the identified on-block and off-block time based on flight time, reducing the error rate, and having higher accuracy.

[0211] See also Figure 6 The third embodiment of the flight block time identification device in the embodiment of the present invention includes:

[0212] The acquisition module 401 is used to acquire video images taken at a fixed position of the aircraft parking position at preset time intervals;

[0213] The recognition module 402 is used to input the video image into a pre-trained aircraft recognition model for recognition, and output a circumscribed rectangular coordinate frame of the recognized target aircraft;

[0214] A calculation module 403, configured to calculate a first overlap value and a second overlap value between a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula;

[0215] A recording module 404, configured to record a first time point when the first overlap value is valid and a second time point when the second overlap value is valid;

[0216] A determination module 405, configured to determine an on-block time or an off-block time of the target aircraft based on the first time node and the second time node;

[0217] The sample acquisition module 410 is used to acquire sample video images of upper and lower wheel blocks of a sample aircraft shot at the same aircraft parking position;

[0218] The sample recognition module 411 is used to sequentially input the sample video images into the aircraft recognition model for recognition, and output the circumscribed rectangular coordinate frame of each recognized sample aircraft;

[0219] The sample clustering module 412 is used to cluster the circumscribed rectangular coordinate frames of each sample aircraft using a preset clustering algorithm to obtain multiple clusters;

[0220] The sample statistics module 413 is used to count the average bounding rectangle coordinate frame, the minimum bounding rectangle coordinate frame and the maximum bounding rectangle coordinate frame of the cluster with the largest number of bounding rectangle coordinate frames, and use the average bounding rectangle coordinate frame as the reference bounding rectangle coordinate frame.

[0221] In an embodiment of the present invention, a sample video image is obtained, the sample video image is identified and each circumscribed rectangular coordinate frame is obtained, a clustering algorithm is used to cluster each circumscribed rectangular coordinate frame to obtain a circumscribed rectangular coordinate frame used as a judgment reference, image acquisition is performed at preset time intervals, the acquired image is identified by a preset aircraft recognition model to obtain the circumscribed rectangular coordinate frame of the aircraft, the overlap between the circumscribed rectangular coordinate frame of the aircraft and the reference circumscribed rectangular coordinate frame is calculated by an overlap calculation formula, and valid time nodes are recorded, and the aircraft's on-block time or off-block time is identified based on the time nodes. The embodiment of the present invention classifies the circumscribed rectangular coordinate frames in the sample video image by a clustering method, and selects the cluster with the most samples for calculation, thereby reducing noise and improving the accuracy of the reference circumscribed rectangular coordinate frame.

[0222] above Figure 4 , Figure 5 and Figure 6 The flight block time identification device in the embodiment of the present invention is described in detail from the perspective of modular functional entities, and the electronic device in the embodiment of the present invention is described in detail from the perspective of hardware processing.

[0223] Figure 7is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. The electronic device 500 may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) 510 (for example, one or more processors) and a memory 520, and one or more storage media 530 (for example, one or more mass storage devices) storing application programs 533 or data 532. Among them, the memory 520 and the storage medium 530 can be short-term storage or permanent storage. The program stored in the storage medium 530 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the electronic device 500. Furthermore, the processor 510 can be configured to communicate with the storage medium 530 to execute a series of instruction operations in the storage medium 530 on the electronic device 500.

[0224] The electronic device 500 may also include one or more power supplies 540, one or more wired or wireless network interfaces 550, one or more input and output interfaces 560, and / or one or more operating systems 531, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc. It will be appreciated by those skilled in the art that Figure 5 The structure of the electronic device shown does not constitute a limitation of the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0225] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the flight up and down block time identification method in the above-mentioned embodiments.

[0226] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the flight on / off block time identification method.

[0227] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0228] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0229] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying the on- and off-block times of a flight, characterized in that: The flight block time identification method comprises: Collect video images taken at fixed positions of aircraft parking positions at preset time intervals; Inputting the video image into a pre-trained aircraft recognition model for recognition, and outputting a circumscribed rectangular coordinate frame of the recognized target aircraft; Based on a preset overlap value calculation formula, a first overlap value and a second overlap value of a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame are calculated, wherein the preset reference circumscribed rectangular coordinate frame is a circumscribed rectangular coordinate frame when the aircraft is parked at an aircraft parking position; Recording a first time node when the first overlap value is valid and a second time node when the second overlap value is valid, wherein the first time node is a time node when the target aircraft is at a preset distance from the aircraft parking position, and the second time node is a time node when the target aircraft is at the aircraft parking position; Determining an on-block time or an off-block time of the target aircraft based on the first time node and the second time node; Wherein, the calculating of the first overlap value and the second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and the preset reference circumscribed rectangular coordinate frame based on the preset overlap value calculation formula includes: Calculating a first overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset first overlap value calculation formula; Calculating a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset second overlap value calculation formula; The first overlap value calculation formula and the second overlap value calculation formula are as follows: ， ； Where IOU1 represents the first overlap value, IOU2 represents the second overlap value, and B p Represents the external rectangular coordinate frame of the target aircraft, B a Represents the reference circumscribed rectangular coordinate frame; The recording of the first time node when the first overlap value is valid and the second time node when the second overlap value is valid includes: Determine whether the first overlap value is within a preset maximum overlap threshold and a minimum overlap threshold; if so, confirm that the first overlap value is valid, and record the shooting time of the video image as the first time node; Determine whether the second overlap value is greater than the maximum overlap threshold; if so, confirm that the second overlap value is valid, and record the shooting time of the video image as the second time node; Wherein, determining the on-block time or off-block time of the target aircraft based on the first time node and the second time node includes: Comparing the first time node with the second time node; If the first time node is greater than the second time node, determining the next block time of the target aircraft to be the second time node; If the first time node is less than the second time node, the on-block time of the target aircraft is determined to be the second time node.

2. The flight block time identification method according to claim 1, characterized in that: The flight block time identification method further includes: If it is determined that the next block time of the target aircraft is the second time node, determining whether the difference between the first time node and the second time node is within a first preset time range; If the difference between the first time node and the second time node is within the first preset time range, determining whether the difference between the off-block time of the target aircraft and the current flight take-off time of the aircraft parking position is within the second preset time range, and if so, determining that the off-block time of the target aircraft is correct; If it is determined that the block time of the target aircraft is the second time node, determining whether the difference between the first time node and the second time node is within the first preset time range; If the difference between the first time node and the second time node is within the first preset time range, it is determined whether the difference between the on-block time of the target aircraft and the arrival time of the current flight at the aircraft parking position is within the second preset time range; if so, it is determined that the on-block time of the target aircraft is correct.

3. The flight block time identification method according to claim 1, characterized in that: Before collecting the video images taken at the aircraft parking position at preset time intervals, the method further includes: Obtain sample video images of the upper and lower wheels of a sample aircraft shot at the same aircraft parking position; sequentially inputting the sample video images into the aircraft recognition model for recognition, and outputting the circumscribed rectangular coordinate frame of each recognized sample aircraft; Using a preset clustering algorithm to cluster the circumscribed rectangular coordinate frames of each of the sample aircraft to obtain a plurality of clusters; The average bounding rectangular coordinate frame, the minimum bounding rectangular coordinate frame and the maximum bounding rectangular coordinate frame of the cluster with the largest number of bounding rectangular coordinate frames are counted, and the average bounding rectangular coordinate frame is used as the reference bounding rectangular coordinate frame.

4. The flight block time identification method according to claim 3, characterized in that: The calculation formula of the minimum overlap threshold is as follows: Among them, Th(min) is the minimum overlap threshold, B min is the minimum bounding rectangle coordinate frame, B a is the reference circumscribed rectangular coordinate frame; The calculation formula of the maximum overlap threshold is as follows: Among them, Th(max) is the maximum overlap threshold, B max is the maximum circumscribed rectangular coordinate frame, B a is the reference circumscribed rectangular coordinate frame.

5. A flight block time identification device, characterized in that: The flight up and down block time identification device comprises: An acquisition module is used to acquire video images taken at fixed positions of aircraft parking positions at preset time intervals; A recognition module, used for inputting the video image into a pre-trained aircraft recognition model for recognition, and outputting a circumscribed rectangular coordinate frame of the recognized target aircraft; a calculation module, configured to calculate a first overlap value and a second overlap value between a circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset overlap value calculation formula, wherein the preset reference circumscribed rectangular coordinate frame is a circumscribed rectangular coordinate frame when the aircraft is parked at an aircraft parking position; a recording module, configured to record a first time node when the first overlap value is valid and a second time node when the second overlap value is valid, wherein the first time node is a time node when the target aircraft is at a preset distance from an aircraft parking position, and the second time node is a time node when the target aircraft is at the aircraft parking position; A determination module, configured to determine an on-block time or an off-block time of the target aircraft based on the first time node and the second time node; Wherein, the calculation module is specifically used for: Calculating a first overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset first overlap value calculation formula; Calculating a second overlap value between the circumscribed rectangular coordinate frame of the target aircraft and a preset reference circumscribed rectangular coordinate frame based on a preset second overlap value calculation formula; The first overlap value calculation formula and the second overlap value calculation formula are as follows: ， ； Where IOU1 represents the first overlap value, IOU2 represents the second overlap value, and B p Represents the external rectangular coordinate frame of the target aircraft, B a Represents the reference circumscribed rectangular coordinate frame; Wherein, the recording module is specifically used for: Determine whether the first overlap value is within a preset maximum overlap threshold and a minimum overlap threshold; if so, confirm that the first overlap value is valid, and record the shooting time of the video image as the first time node; Determine whether the second overlap value is greater than the maximum overlap threshold; if so, confirm that the second overlap value is valid, and record the shooting time of the video image as the second time node; Wherein, the determination module is specifically used for: Comparing the first time node with the second time node; If the first time node is greater than the second time node, determining the next block time of the target aircraft to be the second time node; If the first time node is less than the second time node, the on-block time of the target aircraft is determined to be the second time node.

6. An electronic device, characterized in that: The electronic device comprises: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the electronic device to execute the flight on / off block time identification method according to any one of claims 1-4.

7. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the flight on / off block time identification method according to any one of claims 1 to 4 is implemented.

Images