CN-118869947-B - Camera signal acquisition method, device, medium and equipment of aircraft guarantee node

CN118869947BCN 118869947 BCN118869947 BCN 118869947BCN-118869947-B

Abstract

The application provides a camera signal acquisition method, a camera signal acquisition device, a camera signal acquisition medium and camera signal acquisition equipment for an aircraft security node, which relate to the field of aircraft security and comprise the steps of acquiring a key video stream corresponding to a current security node in a target time period to obtain a key video stream list G; the method comprises the steps of carrying out feature extraction on each key video stream in the G to obtain a feature vector list T, inputting each feature vector in the T into a preset single-node decision tree model corresponding to a current guarantee node to determine a target signal acquisition camera, determining and uploading completion information corresponding to the current guarantee node according to the target signal acquisition camera corresponding to the current guarantee node, wherein the completion information comprises node completion time. According to the application, each protection node is provided with a single-node decision tree model which corresponds to each protection node, and the corresponding protection node is targeted, so that an accurate trusted target camera can be selected for each protection node.

Inventors

ZHANG FANSHOU
LIU HAO
ZHANG PENGCHENG
Luan yue
ZHANG QI

Assignees

中航信移动科技有限公司

Dates

Publication Date: 20260508
Application Date: 20240820

Claims (7)

1. The camera signal acquisition method of the aircraft security node is characterized by comprising the following steps of: S100, acquiring a key video stream corresponding to a current guarantee node in a target time period to obtain a key video stream list G= (G 1 ,G 2 ,…,G j ,…,G m ), j=1, 2, and m, wherein m is the number of target video streams of node information corresponding to the current guarantee node in the target time period, G j is the target video stream of the node information corresponding to the current guarantee node in the j-th detection in the target time period, the target video streams are obtained through video information of target stand acquired by each target camera arranged at different positions and used for acquiring target stand guarantee node information, the starting time of the target time period is the time when the node information corresponding to the current guarantee node is detected in any target video stream for the first time, the node information is used for representing that the corresponding guarantee node is completed, and each guarantee node has the corresponding node information; S200, respectively extracting features of each key video stream in G to obtain a feature vector list T= (T 1 ,T 2 ,…,T j ,…,T m ), wherein T j is feature vector ;T j =(TJ j ,TF j1 ,TF j2 ,…,TF jx ,…,TF jf(j) );x=1,2,…,f(j);TJ j corresponding to G j and is feature information obtained according to node information detected in G j , TF jx is feature information obtained according to the x-th node auxiliary information detected in G j , f (j) is the number of node auxiliary information detected in G j , TJ j has corresponding confidence degree TJZ j ;TF jx and has corresponding confidence degree TFZ jx , node auxiliary information is information for assisting in judging whether a guarantee node is completed or not, and each target camera has corresponding weight relative to each protection node; S300, inputting each feature vector in the T into a preset single-node decision tree model corresponding to the current guarantee node to determine a target acquisition camera, wherein the inner node of the preset single-node decision tree model corresponding to the current guarantee node comprises a node attribute corresponding to node information and a node auxiliary attribute corresponding to auxiliary information of each node, the node attribute corresponding to each feature vector and the auxiliary attribute of each node have corresponding attribute values, and the attribute value of the node attribute corresponding to the T j The attribute value corresponding to the auxiliary attribute of the xth node is TJY j is the initial attribute value of the node attribute corresponding to T j , TQ j is the weight of the target camera corresponding to T j , and TFY jx is the initial attribute value corresponding to the x-th node auxiliary attribute detected in G j ; S400, determining and uploading completion information corresponding to the current guarantee node according to the target signal acquisition camera corresponding to the current guarantee node, wherein the completion information comprises node completion time.
2. The method for camera acquisition of an aircraft security node of claim 1, wherein step S100 comprises: S110, acquiring video information of target stand acquired by each target camera which is arranged at different positions and used for acquiring information of a target stand guarantee node, so as to obtain a target video stream list S= (S 1 ,S 2 ,…,S i ,…,S n ), wherein i=1, 2, n is the number of target cameras corresponding to the target stand, S i is the target video stream acquired by the ith target camera corresponding to the target stand; S120, acquiring a key video stream corresponding to the current guarantee node in a target time period according to the target video stream list S to obtain a key video stream list G= (G 1 ,G 2 ,…,G j ,…,G m ); j=1, 2, and m, wherein m is the number of target video streams in which node information corresponding to a current guarantee node is detected in a target time period, G j is a target video stream in which node information corresponding to the current guarantee node is detected in a j-th detected target time period, starting time of the target time period is time when node information corresponding to the current guarantee node is contained in any one target video stream detected for the first time, the node information is used for representing that the corresponding guarantee node is completed, and each guarantee node has the corresponding node information.
3. The method of camera acquisition of an aircraft security node of claim 2, wherein step S110 comprises: S111, obtaining the identification of each target camera arranged at different positions and used for collecting the information of the support node of the target stand so as to obtain a target camera identification list B= (B 1 ,B 2 ,…,B i ,…,B n );B i is the identification of the ith target camera corresponding to the target stand; And S112, responding to the received information acquisition start signal of the guarantee node, and controlling each target camera to acquire video information of the target stand so as to obtain a target video stream list S= (S 1 ,S 2 ,…,S i ,…,S n );S i is a target video stream acquired by the ith target camera corresponding to the target stand.
4. The method of camera acquisition of an aircraft security node of claim 1, wherein the target time period is 30 seconds in length.
5. A camera letter picking device for an aircraft security node, the device comprising: The acquisition unit is used for acquiring a key video stream corresponding to a current guarantee node in a target time period to obtain a key video stream list G= (G 1 ,G 2 ,…,G j ,…,G m ), j=1, 2,..m, wherein m is the number of target video streams of node information corresponding to the current guarantee node in the target time period, G j is the target video stream of the node information corresponding to the current guarantee node in the j-th detection in the target time period, the target video streams are obtained through video information of target stand acquired by each target camera which is arranged at different positions and is used for acquiring target stand guarantee node information, the starting time of the target time period is the time when the node information corresponding to the current guarantee node is detected in any target video stream for the first time, the node information is used for representing that the corresponding guarantee node is completed, and each guarantee node has the corresponding node information; The extraction unit is used for respectively carrying out feature extraction on each key video stream in G to obtain a feature vector list T= (T 1 ,T 2 ,…,T j ,…,T m ), wherein T j is feature vector ;T j =(TJ j ,TF j1 ,TF j2 ,…,TF jx ,…,TF jf(j) );x=1,2,…,f(j);TJ j corresponding to G j and is feature information obtained according to node information detected in G j , TF jx is feature information obtained according to the x-th node auxiliary information detected in G j , f (j) is the number of the node auxiliary information detected in G j , TJ j has corresponding confidence degree TJZ j ;TF jx and has corresponding confidence degree TFZ jx , the node auxiliary information is information for assisting in judging whether a guarantee node is completed or not, and each target camera has corresponding weight relative to each protection node; The input unit is used for inputting each feature vector in the T into a preset single-node decision tree model corresponding to the current guarantee node to determine the target acquisition camera, wherein the internal node of the preset single-node decision tree model corresponding to the current guarantee node comprises a node attribute corresponding to node information and a node auxiliary attribute corresponding to auxiliary information of each node, the node attribute corresponding to each feature vector and the auxiliary attribute of each node have corresponding attribute values, and the attribute value of the node attribute corresponding to the T j The attribute value corresponding to the auxiliary attribute of the xth node is TJY j is the initial attribute value of the node attribute corresponding to T j , TQ j is the weight of the target camera corresponding to T j , and TFY jx is the initial attribute value corresponding to the x-th node auxiliary attribute detected in G j ; And the uploading unit is used for determining the completion information corresponding to the current guarantee node according to the target acquisition camera corresponding to the current guarantee node and uploading the completion information, wherein the completion information comprises the node completion time.
6. A non-transitory computer readable storage medium having stored therein at least one instruction or at least one program loaded and executed by a processor to implement the method of any one of claims 1-4.
7. An electronic device comprising a processor and the non-transitory computer-readable storage medium of claim 6.

Description

Camera signal acquisition method, device, medium and equipment of aircraft guarantee node Technical Field The application relates to the field of aircraft safety, in particular to a camera letter picking method, device, medium and equipment of an aircraft security node. Background The guarantee node of the aircraft refers to a series of working links or steps which are set and recorded for guaranteeing the smooth progress of the flight in the process of taking off to landing of the flight. The guarantee nodes of the aircraft play a vital role in the flight operation, so that the safety and normal operation of the flight are guaranteed, the flight guarantee operation flow is optimized, and the flight ground operation guarantee efficiency is improved. In the related art, the identification of the aircraft security node is mostly based on a single camera, and when the camera sight is blocked by an aircraft, equipment or other obstacles, the key information of the security node may not be accurately captured by an identification system based on the single camera. And the view angle of a single camera is limited, and all important guarantee nodes may not be covered. However, when multiple cameras are used for node identification, the cameras arranged at different positions have different identification accuracies for different nodes, so that the problem of picking up the information by the cameras for each protection node is needed to be solved. Disclosure of Invention Aiming at the technical problems, the application provides a camera letter picking method, device, medium and equipment for an aircraft security node, which at least partially solve the problems existing in the prior art. In a first aspect of the present application, there is provided a camera letter picking method for an aircraft security node, the method comprising the steps of: S100, acquiring a key video stream corresponding to a current guarantee node in a target time period to obtain a key video stream list G= (G 1,G2,…,Gj,…,Gm), j=1, 2, and m, wherein m is the number of target video streams of node information corresponding to the current guarantee node in the target time period, G j is the target video stream of the node information corresponding to the current guarantee node in the j-th detection in the target time period, the target video streams are obtained through video information of target stand acquired by each target camera arranged at different positions and used for acquiring target stand guarantee node information, the starting time of the target time period is the time when the node information corresponding to the current guarantee node is detected in any target video stream for the first time, the node information is used for representing that the corresponding guarantee node is completed, and each guarantee node has the corresponding node information; S200, respectively extracting features of each key video stream in G to obtain a feature vector list T= (T 1,T2,…,Tj,…,Tm), wherein T j is feature vector ;Tj＝(TJj,TFj1,TFj2,…,TFjx,…,TFjf(j));x＝1,2,…,f(j);TJj corresponding to G j and is feature information obtained according to node information detected in G j, TF jx is feature information obtained according to the x-th node auxiliary information detected in G j, f (j) is the number of node auxiliary information detected in G j, TJ j has corresponding confidence degree TJZ j;TFjx and has corresponding confidence degree TFZ jx, node auxiliary information is information for assisting in judging whether a guarantee node is completed or not, and each target camera has corresponding weight relative to each protection node; S300, inputting each feature vector in T into a preset single-node decision tree model corresponding to a current guarantee node to determine a target acquisition camera, wherein the inner node of the preset single-node decision tree model corresponding to the current guarantee node comprises node attributes corresponding to node information and node auxiliary attributes corresponding to auxiliary information of each node, each node attribute corresponding to each feature vector and each node auxiliary attribute has a corresponding attribute value, an attribute value TJA j＝TJYj*TJZj*TQj of the node attribute corresponding to T j, an attribute value corresponding to the xth node auxiliary attribute is TFA jx＝TFYjx*TFZjx*TQj;TJYj which is an initial attribute value of the node attribute corresponding to T j, TQ j is a weight of the target camera corresponding to T j, and TFY jx is an initial attribute value corresponding to the xth node auxiliary attribute detected in G j; S400, determining and uploading completion information corresponding to the current guarantee node according to the target signal acquisition camera corresponding to the current guarantee node, wherein the completion information comprises node completion time. In a second aspect of the present application, there is provided a camera letter picking