Camera access method and device of aircraft support node, medium and equipment

Abstract

The application provides a camera access method and device of an aircraft support node, a medium and equipment, relates to the field of aircraft safety, and comprises the following steps: acquiring a key video stream corresponding to a current support node in a target time period to obtain a key video stream list G; performing feature extraction on each key video stream in G to obtain a feature vector list T; inputting each feature vector in T into a preset single-node decision tree model corresponding to the current support node to determine a target access camera; determining completion information corresponding to the current support node according to the target access camera corresponding to the current support node and uploading the completion information; and the completion information comprises a node completion time. The application is provided with a single-node decision tree model corresponding to each support node, is targeted for the corresponding support node, and can select a precise target camera that can be accessed for each support node.

Description

Technical Field

[0001] This application relates to the field of aircraft safety, and in particular to camera acquisition methods, devices, media, and equipment for aircraft support nodes. Background Technology

[0002] Aircraft support nodes refer to a series of operational steps or procedures set up and recorded during the flight's journey from takeoff to landing to ensure smooth operation. These nodes play a crucial role in flight operations, not only ensuring safety and normal operation but also optimizing support workflows and improving ground support efficiency. Currently, most aircraft support node identification technologies rely on single cameras. When the aircraft, equipment, or other obstacles obstruct the camera's view, single-camera-based identification systems may fail to accurately capture critical information about the support node. Furthermore, the limited field of view of a single camera may prevent coverage of all important support nodes. However, when using multiple cameras for node identification, cameras positioned at different locations exhibit varying accuracy in identifying different nodes. Therefore, the issue of camera reliability for each support node urgently needs to be addressed. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides a camera data acquisition method, apparatus, medium, and equipment for aircraft support nodes, which at least partially solves the problems existing in the prior art.

[0004] In a first aspect of this application, a method for camera data acquisition in an aircraft support node is provided, the method comprising the following steps:

[0005] S100, Obtain the key video streams corresponding to the current protection node within the target time period to obtain the key video stream list G = (G1, G2, ..., G...). j , ..., G m ); j = 1, 2, ..., m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th video stream in the target time period in which the node information corresponding to the current support node is detected. The target video stream is obtained by collecting video information of the target parking position from each target camera set at different locations for collecting the support node information of the target parking position. The start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream. The node information is used to indicate that the corresponding support node has been completed. Each support node has corresponding node information.

[0006] S200, extract features from each key video stream in G to obtain a feature vector list T = (T1, T2, ..., T...). j,…,T m ); where T j For G j The corresponding feature vector; T j =(TJ j TF j1 TF j2 , ..., TF jx , ..., TF jf(j) );x=1,2,…,f(j);TJ j According to G j Feature information obtained from the detected node information; TF jx According to G j Feature information obtained from the auxiliary information of the x-th node detected in G; f(j) is the feature information obtained from the auxiliary information of the x-th node detected in G. j The number of node auxiliary information detected in TJ; j With corresponding confidence level TJZ j ;TF jx With corresponding confidence level TFZ jx Node auxiliary information is used to help determine whether a support node has completed its task; each target camera has a corresponding weight relative to each support node.

[0007] S300, each feature vector in T is input into the preset single-node decision tree model corresponding to the current protection node to determine the target acquisition camera; wherein, the internal nodes of the preset single-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's node attribute and each node auxiliary attribute have corresponding attribute values; T j The corresponding node attribute value TJA j＝ TJY j *TJZ j *TQ j The attribute value corresponding to the auxiliary attribute of the x-th node is TFA. jx =TFY jx *TFZ jx *TQ j TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process;

[0008] S400: Based on the target acquisition camera corresponding to the current protection node, determine the completion information corresponding to the current protection node and upload it; the completion information includes the node completion time.

[0009] In a second aspect of this application, a camera data acquisition device for an aircraft support node is provided, the device comprising:

[0010] The acquisition unit is used to acquire the key video streams corresponding to the current protection node within the target time period, so as to obtain the key video stream list G = (G1, G2, ..., G...). j , ..., G m ); j = 1, 2, ..., m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th video stream in the target time period in which the node information corresponding to the current support node is detected. The target video stream is obtained by collecting video information of the target parking position from each target camera set at different locations for collecting the support node information of the target parking position. The start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream. The node information is used to indicate that the corresponding support node has been completed. Each support node has corresponding node information.

[0011] The extraction unit is used to extract features from each key video stream in G to obtain a feature vector list T = (T1, T2, ..., T...). j ,…,T m ); where T j For G j The corresponding feature vector; T j =(TJ j TF j1 TF j2 , ..., TF jx , ..., TF jf(j) );x=1,2,…,f(j);TJ j According to G j Feature information obtained from the detected node information; TF jx According to G j Feature information obtained from the auxiliary information of the x-th node detected in G; f(j) is the feature information obtained from the auxiliary information of the x-th node detected in G. j The number of node auxiliary information detected in TJ; j With corresponding confidence level TJZ j ;TF jx With corresponding confidence level TFZ jx Node auxiliary information is used to help determine whether a support node has completed its task; each target camera has a corresponding weight relative to each support node.

[0012] The input unit is used to input each feature vector in T into the preset single-node decision tree model corresponding to the current protection node to determine the target acquisition camera; wherein, the internal nodes of the preset single-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's node attribute and each node auxiliary attribute have corresponding attribute values; T j The corresponding node attribute value TJA j＝ TJY j *TJZ j *TQ j The attribute value corresponding to the auxiliary attribute of the x-th node is TFA. jx =TFY jx *TFZ jx *TQ j TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process;

[0013] The uploading unit is used to determine the completion information corresponding to the current protection node based on the target acquisition camera corresponding to the current protection node, and upload it; the completion information includes the node completion time.

[0014] In a third aspect of this application, a non-transitory computer-readable storage medium is provided, wherein at least one instruction or at least one program is stored in the storage medium, and the at least one instruction or at least one program is loaded and executed by a processor to implement the aforementioned camera data acquisition method for the aircraft support node.

[0015] In a fourth aspect of this application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0016] This application has at least the following beneficial effects:

[0017] The camera acquisition method for aircraft support nodes provided in this application first acquires video information of the target parking position using multiple target cameras positioned near the target parking position. These target cameras can be positioned at different locations within the target parking position to obtain video information from different angles. Furthermore, when identifying the current support node based on the target video stream, due to factors such as camera position or angle, some target cameras may fail to acquire or fully acquire the node information of the current support node. Therefore, this application selects several key video streams from the aforementioned target video streams. These key video streams are the target video streams containing the node information corresponding to the current support node. This node information is used to indicate that the corresponding support node has been completed. However, due to the different positions and angles of the different target cameras, the acquisition time and accuracy of the node information by each target camera vary. It is possible that a target camera, due to a slightly off-center angle, acquires the node information of the current support node at that angle (detecting that the support node is completed), but the current support node may not actually be completed. Therefore, the confidence level of the node information of the current support node identified by each target camera may also differ due to the different position and angle relationships relative to the current support node. Then, feature extraction is performed on each key video stream to obtain a feature vector corresponding to each key video stream. Each feature vector includes the feature information of the corresponding node and the number of corresponding node auxiliary information. The node auxiliary information is information used to help determine whether the support node has been completed. For example, if the support node is closing the hatch, the node information is the hatch position, and the node auxiliary information is the luggage cart position, etc. Each target camera has a corresponding weight relative to the current support node. That is, because the positions of each target camera are different, the preset position corresponding to the node information of each support node (e.g., the actual position of the hatch) is different from the relative position of each camera, and the angle from which they obtain the node information of each support node is different. Therefore, each target camera has a corresponding weight relative to the current support node. Here, the higher the weight for the current support node, the clearer and better the node information obtained by the target camera for that support node, and the greater the probability of obtaining accurate node information.The attribute value of each attribute (node ​​attribute, node auxiliary attribute) is obtained by comprehensively considering the initial attribute value of each node information or node auxiliary information (the initial attribute value is the attribute value assigned to the image of the node information or node auxiliary information acquired by the target camera after decision tree analysis; the higher the attribute value, the more accurately the corresponding feature information reflects the node information), the weight of the target camera itself (which can be obtained based on historical data or experience), and the corresponding confidence level (both node information and node auxiliary information have corresponding confidence levels; the confidence level of node information is higher than that of node auxiliary information, and the confidence levels of node auxiliary information may also differ; the higher the confidence level, the more accurately the image corresponding to the node information or node auxiliary information represents the progress of the support node). This process takes into account the weight of the target camera in relation to the location of the node information marker (e.g., the location of the hatch in a node closing a hatch) for the current support node, as well as the different confidence levels of node information and node auxiliary information in determining whether the support node has been completed. By combining multiple factors, the obtained attribute values ​​are more accurate, meaning the resulting decision tree can select more accurate and reliable target cameras.

[0018] In addition, each support node is equipped with a separate single-node decision tree model, and the single-node decision tree model corresponding to each support node is trained based on the relevant information of each support node. It is targeted to the corresponding support node and can select accurate and reliable target cameras for each support node. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating the camera data acquisition method for an aircraft support node provided in this application embodiment;

[0021] Figure 2 This is a structural block diagram of the camera data acquisition device for an aircraft support node provided in an embodiment of this application. Detailed Implementation

[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0024] It should be noted that the following description covers various aspects of embodiments within the scope of the appended claims. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this application, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0025] Please refer to Figure 1 As shown, an embodiment of this application provides a camera data acquisition method for an aircraft support node, the method comprising:

[0026] S100, Obtain the key video streams corresponding to the current protection node within the target time period to obtain the key video stream list G = (G1, G2, ..., G...). j , ..., G m ); j = 1, 2, ..., m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G jThe target video stream is the j-th video stream in the target time period in which the node information corresponding to the current support node is detected. The target video stream is obtained by collecting video information of the target parking position from each target camera set at different locations for collecting the support node information of the target parking position. The start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream. The node information is used to indicate that the corresponding support node has been completed. Each support node has corresponding node information.

[0027] Specifically, step S100 includes:

[0028] S110, acquire the video information of the target parking position collected by each target camera set at different locations for collecting target parking position guarantee node information, so as to obtain the target video stream list S = (S1, S2, ..., S...). i S n ); i = 1, 2, ..., n; where n is the number of target cameras corresponding to the target parking position; S i The target video stream is acquired by the i-th target camera corresponding to the target parking position.

[0029] Step S110 includes:

[0030] S110, Obtain the identifier of each target camera set at different locations for collecting target parking position support node information, to obtain a target camera identifier list B = (B1, B2, ..., B...). i B n );B i The identifier is the i-th target camera corresponding to the target parking position; each target camera has a corresponding field of view angle range; the field of view angle ranges corresponding to any two target cameras are different.

[0031] Here, since the equipment or components corresponding to each support node may be located at different positions on the aircraft, target cameras can be set at different positions on the target parking position to collect video information from different angles. First, the identifier of each target camera is obtained, resulting in a list of target camera identifiers. Each target camera has a corresponding field of view range, used to collect video information within that range. In this application, the field of view ranges of any two target cameras are not the same; that is, the video information collected by any two target cameras may have some similarities, but will not be completely identical. This ensures that all target cameras can acquire video information from the target parking position as comprehensively as possible.

[0032] S120, in response to receiving the start signal for information acquisition from the protection node, controls each target camera to acquire video information from the target stopping position to obtain a target video stream list S = (S1, S2, ..., S...). i S n );S i The target video stream is acquired by the i-th target camera corresponding to the target parking position.

[0033] Here, in response to receiving the signal to start collecting information from the protection node, that is, starting from the first protection node, each target camera is controlled to start collecting video messages.

[0034] S120, Based on S, obtain the key video streams corresponding to the current protection node within the target time period to obtain the key video stream list G = (G1, G2, ..., G...). j , ..., G m ); j = 1, 2, ..., m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th one in the target time period that detects the node information corresponding to the current support node; the start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream; the node information is used to indicate that the corresponding support node has been completed; each support node has corresponding node information.

[0035] Specifically, when identifying the current support node based on the target video stream, due to factors such as setting position or angle, some target cameras may not be able to acquire or fully acquire the node information of the current support node. Therefore, this embodiment selects several key video streams from the aforementioned target video streams. The key video streams are the target video streams containing the node information corresponding to the current support node. The node information here is used to indicate that the corresponding support node has been completed. However, due to the different positions and angles of different target cameras, the acquisition time and accuracy of node information by each target camera are different. It is possible that due to the slightly off-center angle of a certain target camera, a judgment deviation may occur. That is, the node information of the current support node is acquired at that angle (the support node is detected to be completed), but the current support node may not actually be completed. Therefore, due to the different position and angle relationship of each target camera relative to the current support node, the confidence level of the node information of the current support node may also be different. As an example: the current support node is closing the hatch, but because the relative positions of each target camera and the hatch are different, if a certain camera is set directly opposite the nose of the aircraft, the detected completion time of the hatch closing node may be inaccurate due to the deviation in the field of view angle. If a camera is positioned directly in front of the cabin door, it can clearly capture the actual position of the door and more accurately determine the closing time. Therefore, the confidence level of a camera positioned directly in front of the cabin door is higher than that of a camera positioned directly opposite the nose of the aircraft.

[0036] Furthermore, the start time of the target time period is the first time that node information corresponding to the current support node is detected in any target video stream. That is, from the moment node information corresponding to the current support node is detected in any target video stream, it is considered that the support node may have completed. Acquisition continues within the target time period to obtain several key video streams whose node information can be detected and whose support node is considered to have completed. For example, the duration of the target time period is 30 seconds. Here, since the time interval between some nodes may be short, the duration of the target time period should not be set too long; if it is too long, the next support node may not be identified. Also, in order to acquire multiple key video streams, the duration of the target time period should not be set too short.

[0037] It should be noted that the entire support process for the aircraft involves several support nodes. Each support node has corresponding node information. If the corresponding target camera detects the node information of the support node, then the target camera considers that the support node has been completed from that perspective.

[0038] S200, extract features from each key video stream in G to obtain a feature vector list T = (T1, T2, ..., T...). j ,…,T m); where T j For G j The corresponding eigenvector; T j =(TJ j TF j1 TF j2 , ..., TF jx , ..., TF jf(j) );x=1,2,…,f(j);TJ j According to G j Feature information obtained from the detected node information; TF jx According to G j Feature information obtained from the auxiliary information of the x-th node detected in G; f(j) is the feature information obtained from the auxiliary information of the x-th node detected in G. j The number of node auxiliary information detected in TJ; j With corresponding confidence level TJZ j ;TF jx With corresponding confidence level TFZ jx Node auxiliary information is information used to help determine whether a support node has completed its task; each target camera has a corresponding weight relative to each support node.

[0039] Specifically, feature extraction is performed on each key video stream to obtain a corresponding feature vector. Each feature vector includes feature information of the corresponding node and the number of corresponding node auxiliary information. Node auxiliary information is used to help determine whether the support node has been completed. For example, if the support node is closing the hatch, the node information is the hatch position, and the node auxiliary information is the luggage cart position, etc. Each target camera has a corresponding weight relative to the current support node. That is, because the positions of each target camera are different, the preset position corresponding to the node information of each support node (e.g., the actual position of the hatch) is different from the relative position of each camera, and the angle from which they obtain the node information of each support node is different. Therefore, each target camera has a corresponding weight relative to the current support node. Here, the higher the weight for the current support node, the clearer and better the node information obtained by the target camera, and the greater the probability of the obtained node information being accurate.

[0040] S300, each feature vector in T is input into the preset single-node decision tree model corresponding to the current protection node to determine the target acquisition camera; wherein, the internal nodes of the preset single-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's node attribute and each node auxiliary attribute have corresponding attribute values; T j The corresponding node attribute value TJA j＝ TJYj *TJZ j *TQ j The attribute value corresponding to the auxiliary attribute of the x-th node is TFA. jx =TFY jx *TFZ jx *TQ j TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process.

[0041] Specifically, the attribute value of each node attribute and node auxiliary attribute is obtained by combining the initial attribute value of each node information or node auxiliary information (the initial attribute value is the attribute value assigned to the image of the node information or node auxiliary information acquired by the target camera after analysis by the decision tree; the higher the attribute value, the more accurately the corresponding feature information reflects the node information), the weight of the target camera itself (which can be obtained based on historical data or experience), and the corresponding confidence level (both node information and node auxiliary information have corresponding confidence levels; the confidence level of node information is higher than that of node auxiliary information, and the confidence levels of node auxiliary information may also differ; the higher the confidence level, the more accurately the image corresponding to the node information or node auxiliary information represents the progress of the support node). This process considers the weight of the target camera in relation to the location of the node information marker (e.g., the location of the hatch in a node closing a hatch) for the current support node, as well as the different confidence levels of node information and node auxiliary information in determining whether the support node has been completed. By combining multiple factors, the obtained attribute values ​​are more accurate, meaning the resulting decision tree can select more accurate and reliable target cameras.

[0042] In addition, in this embodiment, a separate single-node decision tree model is set up for each protection node, and the single-node decision tree model corresponding to each protection node is trained based on the relevant information of each protection node. It is targeted to the corresponding protection node and can select accurate and credible target cameras for each protection node.

[0043] S400: Based on the target acquisition camera corresponding to the current protection node, determine the completion information corresponding to the current protection node and upload it; the completion information includes the node completion time.

[0044] Specifically, based on the target acquisition camera corresponding to the current support node, the completion information corresponding to the current support node is determined and uploaded. This completion information can include the node's completion time, thus accurately recording the actual completion time of each support node. This provides a real-time view of the aircraft support process. The completion information in this application can also record other content that needs to be recorded by support nodes in this field, which will not be elaborated here.

[0045] In one exemplary embodiment of this application, after step S200, the method further includes:

[0046] The first step is to input T and the flag bit corresponding to the current protection node into the preset full-node decision tree model to determine the target acquisition camera; wherein, each protection node has a corresponding flag bit; the flag bit is used to identify the corresponding protection node to start recognition.

[0047] Among them, the internal nodes of the preset full-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's corresponding node attribute and each node auxiliary attribute have corresponding attribute values; T j The corresponding node attribute value TJA j＝ TJY j *TJZ j *TQ j The attribute value corresponding to the auxiliary attribute of the x-th node is TFA. jx =TFY jx *TFZ jx *TQ j TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process.

[0048] In this embodiment, for several support nodes, the same decision tree is used. Each support node has a pre-set corresponding flag. The full-node decision tree model in this embodiment can identify the current support node based on the input flag. Then, based on the initial attribute value of each node information or node auxiliary information (the initial attribute value is the attribute value assigned to the image of the node information or node auxiliary information acquired by the target camera after decision tree analysis; the higher the attribute value, the more accurately the corresponding feature information reflects the node information), the weight of the target camera itself (which can be obtained based on historical data or experience), and the corresponding confidence level, the model further refines the model. The confidence level (both node information and node auxiliary information have corresponding confidence levels, with node information having a higher confidence level than node auxiliary information, and the confidence levels of node auxiliary information may also differ; a higher confidence level indicates that the image corresponding to the node information or node auxiliary information is more representative of the progress of the support node) is used to comprehensively obtain the attribute value of each attribute (node ​​attribute, node auxiliary attribute). This considers the weight of the position of the corresponding target camera relative to the node information marker (e.g., the position of the hatch of a node closing the hatch) for the current support node, and also considers the different confidence levels of node information and node auxiliary information when judging whether the support node has been completed. By combining multiple factors, the obtained attribute values ​​are more accurate, and only a single decision tree model is used, saving time and increasing efficiency. The resulting full-node decision tree model can determine the current support progress based on the corresponding flag positions pre-set for each support node. After identifying the corresponding support node, it can also select accurate and trustworthy target cameras for the support node based on the input feature vector.

[0049] In one exemplary embodiment of this application, after step S100, the method further includes:

[0050] The first step is to obtain the docking deviation angle J of the target aircraft corresponding to the target parking position and the deviation direction F relative to the deviation direction of each target camera; wherein, the docking deviation angle J is the angle between the straight line containing the central axis of the target aircraft fuselage and the side of the target parking position that is preset to be parallel to the fuselage.

[0051] Specifically, in real-world scenarios, when an aircraft docks at a target parking position, there may be an angular deviation from the preset standard position. In this embodiment, the docking deviation angle J is the angle between the straight line containing the central axis of the target aircraft fuselage and the preset side of the target parking position that is parallel to the fuselage. The deviation direction F includes either an obstructed direction or an unobstructed direction.

[0052] The second step is to obtain the target camera weight list QZ = (QZ1, QZ2, ..., QZG) based on J, F, and G. j QZ m ); where QZj Let be the target camera weight corresponding to the j-th key video stream.

[0053] Specifically, firstly, if, based on the node information corresponding to the current protection node, F is an obstruction direction relative to the target camera corresponding to the j-th key video stream, then QZ j =TQ j -JQ j Among them, TQ j For G j The initial weights of the corresponding target cameras; JQ j This is the weighted deviation value obtained based on the angular range of J.

[0054] Here, the occlusion direction refers to the situation relative to the preset docking position. For the corresponding target camera, the area obstructed when identifying the location of the marker corresponding to the current support node (e.g., the location of the hatch of a node with a closed hatch) becomes larger, making it more difficult to identify. The opposite is true for the non-occluded direction. Furthermore, if it is an occluded direction, the accuracy of the judgment will be lower than that of the preset position, so its weight value should be reduced. The reduction value of the weight is determined based on the range of the deviation angle.

[0055] Furthermore, JQ j Determined in the following manner:

[0056] If 0 < J < JYZ1, then JQ j =JQ j1 ;

[0057] If JYZ1≤J≤JYZ2, then JQ j =JQ j2 ;

[0058] If JYZ2 < J < JYZ3, then JQ j =JQ j3 ;

[0059] Among them, JQ j1 <JQ j2 <JQ j3 JYZ1 is the preset first angle threshold; JYZ2 is the preset second angle threshold; JYZ3 is the preset third angle threshold; JQ j1 This is the first weighted deviation value; JQ j2 This is the second weighted deviation value; JQ j3 This is the third weighted deviation value.

[0060] That is, the larger the angle of deviation, the greater the reduction in its weight.

[0061] Conversely, if, based on the node information corresponding to the current guaranteed node, F is in a non-occluded direction relative to the target camera corresponding to the j-th key video stream, then QZ j =TQ j +JQ j .

[0062] Here, the occlusion direction refers to the situation relative to the preset docking position. For the corresponding target camera, the area obstructed when identifying the location of the marker corresponding to the current support node (e.g., the location of the hatch of a node with a closed hatch) becomes larger, making identification more difficult. The opposite is true for the unobstructed direction. Therefore, if it is an unobstructed direction, the accuracy of the judgment will be higher than the preset position, so its weight value should be increased. The increase in weight is determined based on the range of the deviation angle. That is, the larger the deviation angle, the greater the increase in weight.

[0063] The third step is to determine the target acquisition camera corresponding to the current protection node from each target camera corresponding to G based on QZ and the preset decision tree algorithm.

[0064] Specifically, after determining the weight value of each target camera, it provides a certain reference for the decision tree algorithm results. Furthermore, this embodiment considers the impact of the deviation direction between the actual parking position of the aircraft at the target parking position and the preset parking position on whether each target camera identifies the current support node as positive (non-obstructed direction) or negative (obstructed direction), and adjusts the original weight value of each target camera accordingly. This allows for a more accurate identification of the target cameras based on the decision tree.

[0065] In one exemplary embodiment of this application, after step S100, the method further includes:

[0066] The first step is to determine the target camera corresponding to the current protection node from each target camera corresponding to G, according to an exemplary embodiment of this application, if the current protection node does not have a corresponding preset acceptance camera. The preset acceptance camera is the target camera with the largest weight relative to the current protection node and whose corresponding weight is greater than a preset weight threshold.

[0067] Specifically, each support node may have a corresponding preset data acquisition camera. Here, the preset data acquisition camera is the target camera with the highest weight relative to the current support node, and its weight is greater than a preset weight threshold. That is, it obtains the most accurate node information relative to the current support node. The preset data acquisition camera can be determined based on historical data, that is, by acquiring the target camera that the current support node has acquired the most data from within the historical target time window. A corresponding weight is assigned to it based on its acquisition probability. That is, the higher the acquisition probability, the higher the weight. This acquisition can be implemented based on decision tree algorithms or other technical solutions that can be determined by those skilled in the art.

[0068] If the current support node does not have a corresponding preset data acquisition camera, then the target data acquisition camera corresponding to the current support node is determined from each target camera corresponding to G according to the preset decision tree algorithm. Here, the target data acquisition camera is the target camera with the highest confidence obtained through the preset decision tree algorithm.

[0069] In one exemplary embodiment of this application, after step S100, the method further includes:

[0070] The first step is to determine the target video stream collected by the current protection node as the target protection camera if the current protection node has a corresponding preset acquisition camera and G includes the target video stream collected by the preset acquisition camera.

[0071] Specifically, if the current protection node has a corresponding preset acceptance camera, and the target video stream collected by the preset acceptance camera is included in G, then the preset acceptance camera can be directly accepted.

[0072] In one exemplary embodiment of this application, after step S100, the method further includes:

[0073] The first step is to determine the target acquisition camera corresponding to the current protection node from each target camera in G according to the preset decision tree algorithm if the current protection node has a corresponding preset acquisition camera and G does not include the target video stream collected by the preset acquisition camera.

[0074] Specifically, if the current support node has a corresponding preset acquisition camera, and G does not include the target video stream acquired by that preset acquisition camera, meaning that due to some special circumstances, the corresponding preset acquisition camera may not have been able to acquire the corresponding target video stream, then that preset acquisition camera is discarded. The target acquisition camera corresponding to the current support node is then determined from each target camera in G according to a preset decision tree algorithm.

[0075] Please refer to Figure 2As shown, an embodiment of this application provides a camera data acquisition device 100 for an aircraft support node, the device comprising:

[0076] Acquisition unit 110 is used to acquire the key video streams corresponding to the current protection node within the target time period, so as to obtain a key video stream list G = (G1, G2, ..., G...). j , ..., G m ); j = 1, 2, ..., m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th video stream in the target time period in which the node information corresponding to the current support node is detected. The target video stream is obtained by collecting video information of the target parking position from each target camera set at different locations for collecting the support node information of the target parking position. The start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream. The node information is used to indicate that the corresponding support node has been completed. Each support node has corresponding node information.

[0077] Extraction unit 120 is used to extract features from each key video stream in G to obtain a feature vector list T = (T1, T2, ..., T...). j ,…,T m ); where T j For G j The corresponding feature vector; T j =(TJ j TF j1 TF j2 , ..., TF jx , ..., TF jf(j) );x=1,2,…,f(j);TJ j According to G j Feature information obtained from the detected node information; TF jx According to G j Feature information obtained from the auxiliary information of the x-th node detected in G; f(j) is the feature information obtained from the auxiliary information of the x-th node detected in G. j The number of node auxiliary information detected in TJ; j With corresponding confidence level TJZ j ;TF jx With corresponding confidence level TFZ jx Node auxiliary information is used to help determine whether a support node has completed its task; each target camera has a corresponding weight relative to each support node.

[0078] Input unit 130 is used to input each feature vector in T into a preset single-node decision tree model corresponding to the current protection node to determine the target acquisition camera; wherein, the internal nodes of the preset single-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's node attribute and each node auxiliary attribute have corresponding attribute values; T j The corresponding node attribute value TJA j＝ TJY j *TJZ j *TQ j The attribute value corresponding to the auxiliary attribute of the x-th node is TFA. jx =TFY jx *TFZ jx *TQ j TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process;

[0079] The uploading unit 140 is used to determine the completion information corresponding to the current protection node based on the target acquisition camera corresponding to the current protection node, and upload it; the completion information includes the node completion time.

[0080] Embodiments of this application also provide a computer program product including program code that, when the program product is run on an electronic device, causes the electronic device to perform the steps of the methods described above according to various exemplary embodiments of this application.

[0081] Furthermore, although the steps of the method in this application are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0082] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the method according to the embodiments of this application.

[0083] In an exemplary embodiment of this application, an electronic device capable of implementing the above-described method is also provided.

[0084] Those skilled in the art will understand that various aspects of this application can be implemented as a system, method, or program product. Therefore, various aspects of this application can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, collectively referred to herein as a "circuit," "module," or "system."

[0085] An electronic device according to this embodiment of the present application. The electronic device is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of this application.

[0086] Electronic devices are manifested in the form of general-purpose computing devices. Components of an electronic device may include, but are not limited to: at least one processor, at least one memory, and buses connecting different system components (including memory and processor).

[0087] The memory stores program code that can be executed by a processor, causing the processor to perform the steps described in the "Exemplary Methods" section above, according to various exemplary embodiments of this application.

[0088] The storage may include readable media in the form of volatile storage, such as random access memory (RAM) and / or cache memory, and may further include read-only memory (ROM).

[0089] The storage may also include programs / utilities having a set (at least one) of program modules, including but not limited to: an operating system, one or more applications, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0090] A bus can represent one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus that uses any of the various bus architectures.

[0091] The electronic device can also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). This communication can be achieved through input / output (I / O) interfaces. Furthermore, the electronic device can communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter. As shown in the figure, the network adapter communicates with other modules of the electronic device via a bus. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with the electronic device, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0092] Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the method according to the embodiments of this application.

[0093] In exemplary embodiments of this application, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this application may also be implemented as a program product including program code, which, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this application described in the "Exemplary Methods" section above.

[0094] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0095] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0096] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0097] Program code for performing the operations of this application can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0098] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this application, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0099] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0100] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for camera data acquisition at an aircraft support node, characterized in that, The method includes: S100, Obtain the key video streams corresponding to the current protection node within the target time period to obtain the key video stream list G=(G1, G2, ..., G... j , ..., G m ); j=1,2,…,m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th video stream in the target time period in which the node information corresponding to the current support node is detected. The target video stream is obtained by collecting video information of the target parking position from each target camera set at different locations for collecting the support node information of the target parking position. The start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream. The node information is used to indicate that the corresponding support node has been completed. Each support node has corresponding node information. S200, extract features from each key video stream in G to obtain a feature vector list T = (T1, T2, ..., T...). j ,…,T m ); where T j For G j The corresponding feature vector; T j =(TJ j TF j1 TF j2 , ..., TF jx , ..., TF jf(j) ); x = 1, 2, ..., f(j); TJ j According to G j Feature information obtained from the detected node information; TF jx According to G j Feature information obtained from the auxiliary information of the x-th node detected in G; f(j) is the feature information obtained from the auxiliary information of the x-th node detected in G. j The number of node auxiliary information detected in TJ; j With corresponding confidence level TJZ j ;TF jx With corresponding confidence level TFZ jx Node auxiliary information is used to help determine whether a support node has completed its task; each target camera has a corresponding weight relative to each support node. S300, each feature vector in T is input into the preset single-node decision tree model corresponding to the current protection node to determine the target acquisition camera; wherein, the internal nodes of the preset single-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's node attribute and each node auxiliary attribute have corresponding attribute values; T j The attribute value of the corresponding node attribute The attribute value corresponding to the auxiliary attribute of the x-th node is TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process; S400: Based on the target acquisition camera corresponding to the current protection node, determine the completion information corresponding to the current protection node and upload it; the completion information includes the node completion time.

2. The camera data acquisition method for aircraft support nodes according to claim 1, characterized in that, Step S100 includes: S110, acquire the video information of the target parking position collected by each target camera set at different locations for collecting target parking position support node information, so as to obtain the target video stream list S=(S1, S2, ..., S... i S n ); i = 1, 2, ..., n; where n is the number of target cameras corresponding to the target parking position; S i The target video stream acquired by the i-th target camera corresponding to the target parking position; S120, Based on the target video stream list S, obtain the key video streams corresponding to the current protection node within the target time period, to obtain the key video stream list G=(G1, G2, ..., G...). j , ..., G m ); j=1,2,…,m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th one in the target time period that detects the node information corresponding to the current support node; the start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream; the node information is used to indicate that the corresponding support node has been completed; each support node has corresponding node information.

3. The camera data acquisition method for aircraft support nodes according to claim 2, characterized in that, Step S110 includes: S111, Obtain the identifier of each target camera set at different locations for collecting target parking position support node information, to obtain a target camera identifier list B=(B1, B2, ..., B i B n ); B i This is the identifier of the i-th target camera corresponding to the target parking position; each target camera has a corresponding field of view angle range; the field of view angle ranges corresponding to any two target cameras are different; S112, in response to receiving the start signal for information acquisition from the protection node, controls each target camera to acquire video information from the target stopping position to obtain a target video stream list S=(S1, S2, ..., S... i S n );S i The target video stream is acquired by the i-th target camera corresponding to the target parking position.

4. The camera data acquisition method for aircraft support nodes according to claim 1, characterized in that, The target time period is 30 seconds long.

5. A camera data acquisition device for an aircraft support node, characterized in that, The device includes: The acquisition unit is used to acquire the key video streams corresponding to the current protection node within the target time period, so as to obtain the key video stream list G=(G1, G2, ..., G...). j , ..., G m ); j=1,2,…,m; where m is the number of target video streams whose node information corresponding to the current protection node is detected within the target time period; G j The target video stream is the j-th video stream in the target time period in which the node information corresponding to the current support node is detected. The target video stream is obtained by collecting video information of the target parking position from each target camera set at different locations for collecting the support node information of the target parking position. The start time of the target time period is the time when the node information corresponding to the current support node is first detected in any target video stream. The node information is used to indicate that the corresponding support node has been completed. Each support node has corresponding node information. The extraction unit is used to extract features from each key video stream in G to obtain a feature vector list T = (T1, T2, ..., T...). j ,…,T m ); where T j For G j The corresponding feature vector; T j =(TJ j TF j1 TF j2 , ..., TF jx , ..., TF jf(j) ); x = 1, 2, ..., f(j); TJ j According to G j Feature information obtained from the detected node information; TF jx According to G j Feature information obtained from the auxiliary information of the x-th node detected in G; f(j) is the feature information obtained from the auxiliary information of the x-th node detected in G. j The number of node auxiliary information detected in TJ; j With corresponding confidence level TJZ j ;TF jx With corresponding confidence level TFZ jx Node auxiliary information is used to help determine whether a support node has completed its task; each target camera has a corresponding weight relative to each support node. The input unit is used to input each feature vector in T into the preset single-node decision tree model corresponding to the current protection node to determine the target acquisition camera; wherein, the internal nodes of the preset single-node decision tree model corresponding to the current protection node include node attributes corresponding to node information and node auxiliary attributes corresponding to each node auxiliary information; each feature vector's node attribute and each node auxiliary attribute have corresponding attribute values; T j The attribute value of the corresponding node attribute The attribute value corresponding to the auxiliary attribute of the x-th node is TJY j For T j The initial attribute value of the corresponding node attribute; TQ j For T j The corresponding target camera weights; TFY jx According to G j The initial attribute value corresponding to the auxiliary attribute of the xth node detected in the process; The uploading unit is used to determine the completion information corresponding to the current protection node based on the target acquisition camera corresponding to the current protection node, and upload it; the completion information includes the node completion time.

6. A non-transitory computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor to implement the method as described in any one of claims 1-4.

7. An electronic device, characterized in that, Includes a processor and the non-transitory computer-readable storage medium as described in claim 6.

Images