Attitude specification recognition method and device under refueling scene of aviation fuel vehicle

By using cameras to identify face and skeletons in the refueling scenario of air fuel vehicles, the security risks caused by relying on manual monitoring in the refueling process in the existing technology are solved, and automated identification and dual identity authentication of the refueling process are realized, and security is improved sex.

CN119091469APending Publication Date: 2024-12-06CHINA AVIATION OIL CO LTD ZHEJIANG BRANCH
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411291029.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-14
Publication Date
2024-12-06

AI Technical Summary

Technical Problem

The prior art cannot automatically identify the attitude specifications during refueling of air fuel vehicles, and relies on manual monitoring, which poses safety risks.

Method used

Videos are collected through the camera, facial recognition and skeleton authentication are performed, and posture specification recognition results are generated to realize automatic identification and dual identity authentication of the refueling process.

Benefits of technology

The safety risks of the refueling process are avoided and the accuracy and safety of the automated identification of the refueling process are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119091469A_ABST
    Figure CN119091469A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a posture specification identification method and device under an aviation fuel vehicle refueling scene. The method comprises the following steps: determining a current working target aviation fuel vehicle, determining a current working target person according to each collected monitoring video, and performing face recognition authentication on the target person; after the face recognition authentication is passed, determining a current working node of the target person, and obtaining a current task posture; skeleton information is obtained, skeleton data and posture behavior data of a target person are recognized, and skeleton authentication is carried out; and after the skeleton authentication is passed, generating a posture specification recognition result. According to the embodiment of the invention, not only can the posture standard of the target personnel in the refueling work of the aviation fuel vehicle be identified, but also the identity of the target personnel can be subjected to dual authentication, unmanned automatic identification on the refueling process from two aspects of the personnel identity and the personnel operation standard is realized, and the safety risk in the refueling process is avoided.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] One or more embodiments of the present specification relate to data processing technology, and more particularly to a method and device for recognizing posture specifications in a fuel truck refueling scenario. Background Art

[0002] The fuel truck will refuel the aircraft during the docking process. In order to ensure the safety of the refueling process, the refueling process of the staff is generally recorded dynamically through video monitoring technology, and the video is transmitted to the remote background for real-time monitoring by the management personnel. However, this method cannot automatically identify and must rely on manual real-time background monitoring. This dependence may cause omissions by the management personnel during the monitoring process, which still causes safety risks. Summary of the invention

[0003] In order to solve the above problems, one or more embodiments of this specification describe a method and device for posture specification recognition in a fuel truck refueling scenario.

[0004] According to a first aspect, a method for recognizing posture norms in a fuel truck refueling scenario is provided, the method comprising: When receiving the refueling work information of the aviation fuel truck, determining the target aviation fuel truck currently working, and determining the target personnel currently working based on the monitoring videos collected by the target aviation fuel truck, and performing face recognition authentication on the target personnel according to the face information currently assigned to the target aviation fuel truck, wherein the target aviation fuel truck is provided with at least one camera at each refueling work node; After the face recognition authentication is passed, the current working node of the target person is determined based on the target monitoring video, and the current task posture of the current working node is obtained, and the target monitoring video is the monitoring video in which the target person is identified; Obtaining the skeleton information currently assigned to the target fuel truck, identifying the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target surveillance video, and performing skeleton authentication based on the skeleton information and skeleton data; After the skeleton authentication is passed, a posture specification recognition result is generated according to the matching result of the posture behavior data and the current task posture.

[0005] Preferably, after performing face recognition authentication on the target person according to the identity information currently assigned to the target fuel truck, the method further includes: When the face recognition authentication fails, a first warning message is generated; After skeleton authentication is performed according to the skeleton information and skeleton data, the method further includes: When the skeleton authentication fails, a second warning message is generated, wherein the first warning message and the second warning message are both used to characterize operator errors, and the warning level of the second warning message is higher than the warning level of the first warning message.

[0006] Preferably, performing skeleton authentication according to the skeleton information and skeleton data includes: Determine first data of the operator based on the skeleton information, the first data including a first arm length, a first leg length, and a first spine length; Determine second data of the target person based on the skeleton data, the second data including a second arm length, a second leg length, and a second spine length; The similarity between the first data and the second data is calculated, and a skeleton authentication result is generated according to the similarity, wherein the skeleton authentication result is characterized as authentication passed when the similarity is greater than a preset value, and is characterized as authentication failed when the similarity is not greater than the preset value.

[0007] Preferably, the identifying the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target surveillance video includes: Acquire current frame data of the target surveillance video, and set an identification frame range based on the current frame data; Determine each heat map corresponding to each frame data within the recognition frame range, and determine the skeleton data in the heat map; The skeleton data are smoothed in time order to obtain the posture behavior data of the target person.

[0008] Preferably, determining skeleton data in the heat map includes: Determine key nodes based on the heat distribution of the heat map; After performing component affinity field analysis on each of the key nodes, each of the key nodes is connected to obtain skeleton data.

[0009] Preferably, the method further comprises: Determine a target workflow based on the fueling work information of the aviation fuel truck, and generate an actual workflow according to each target fueling work node in chronological order, wherein the target fueling work node is the fueling work node characterized by the posture specification recognition result as being in compliance with the specification; A process specification identification result is generated according to the matching result between the target process and the actual process.

[0010] Preferably, the method further comprises: Determine the proficiency of the target person at the current work node, where the proficiency is determined based on the number of historical irregularities of the target person at the current work node, and the proficiency is inversely proportional to the number of historical irregularities; The number of posture standard recognitions of the current working node is set based on the proficiency interval corresponding to the proficiency, and the recognition waiting interval is calculated based on the average working time of the current working node; After each recognition waiting interval, the standard posture recognition is repeated until the accumulated recognition times meet the standard posture recognition times.

[0011] According to a second aspect, a posture specification recognition device in a fuel tanker refueling scenario is provided, the device comprising: The first determination module is used to determine the target aviation fuel truck currently working when receiving the fuel truck refueling work information, and determine the target personnel currently working based on the monitoring videos collected by the target aviation fuel truck, and perform face recognition authentication on the target personnel according to the face information currently assigned to the target aviation fuel truck, wherein the target aviation fuel truck is provided with at least one camera at each refueling work node; A second determination module is used to determine the current working node of the target person based on the target monitoring video after the face recognition authentication is passed, and obtain the current task posture of the current working node, wherein the target monitoring video is the monitoring video in which the target person is identified; An identification module, used to obtain the skeleton information currently assigned to the target fuel truck, identify the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target monitoring video, and perform skeleton authentication based on the skeleton information and skeleton data; The generation module is used to generate a posture specification recognition result according to the matching result of the posture behavior data and the current task posture after the skeleton authentication is passed.

[0012] According to a third aspect, there is provided an electronic device, comprising a processor and a memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to execute the steps of the method provided in the first aspect or any possible implementation manner of the first aspect.

[0013] According to a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and the computer-readable storage medium stores instructions, which, when the instructions are executed on a computer or a processor, cause the computer or the processor to execute the method provided in the first aspect or any possible implementation of the first aspect.

[0014] The method and device provided in the embodiments of this specification can collect video from cameras set at the refueling work nodes of the aviation fuel truck to identify the posture and behavior data of the target person, and in this process perform face recognition authentication and skeleton authentication on the target person according to the face information and skeleton information respectively. In this way, not only can the posture specifications of the target person working in the aviation fuel truck be identified, but also the identity of the target person can be doubly authenticated, thereby realizing unmanned automatic recognition of the refueling process from the two perspectives of personnel identity and personnel operation specifications, thereby avoiding safety risks in the refueling process. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flowchart of a posture specification recognition method in a fuel truck refueling scenario in one embodiment of the present specification.

[0017] Figure 2 It is a structural schematic diagram of a posture standard recognition device in a fuel truck refueling scenario in one embodiment of this specification.

[0018] Figure 3 It is a structural diagram of an electronic device in one embodiment of this specification. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0020] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present application, and different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, although the embodiment may not be clearly recorded in the following text.

[0021] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0022] See also Figure 1 , Figure 1 : is a flow chart of a method for recognizing posture norms in a fuel tanker refueling scenario provided in an embodiment of the present application. In the embodiment of the present application, the method includes: S101. When receiving the refueling work information of the aviation fuel truck, determine the target aviation fuel truck currently working, and determine the target person currently working based on the monitoring videos collected by the target aviation fuel truck, and perform face recognition authentication on the target person according to the face information currently assigned to the target aviation fuel truck.

[0023] Wherein, the target aviation fuel truck is provided with at least one camera at each refueling work node.

[0024] The execution entity of this application can be a cloud server.

[0025] In the embodiment of the present specification, when the refueling device on the aviation fuel truck is unlocked, the control system of the aviation fuel truck will send the aviation fuel truck refueling work information to the cloud server to inform the cloud server that the vehicle is about to start refueling. The cloud server will determine the aviation fuel truck ID according to the aviation fuel truck refueling work information, thereby determining the target aviation fuel truck currently working, and communicate with the target aviation fuel truck through a local area network, the Internet, etc., to obtain the monitoring video collected by the camera of each refueling work node of the target aviation fuel truck, and find and determine the target personnel currently performing the work operation by recognizing the portrait of the monitoring video. Among them, different equipment will be set at different positions of the aviation fuel truck, such as fuel tanks, cantilevers, platform joints, warning lights, etc., and according to different refueling work, some or all of the equipment may need to be operated accordingly. Each equipment position that may be operated during the refueling work is a refueling work node. In addition, after the target aviation fuel truck is determined, the face information of the staff currently assigned to operate the target aviation fuel truck can be queried according to the work arrangement table. The cloud server will perform face recognition authentication on the face image of the target personnel identified in the monitoring video according to the face information to determine whether the target personnel currently performing the refueling work is the designated staff.

[0026] S102: After the face recognition authentication is passed, the current working node of the target person is determined based on the target monitoring video, and the current task posture of the current working node is obtained.

[0027] The target surveillance video is a surveillance video in which the target person is identified.

[0028] In the embodiment of this specification, only after the face recognition authentication is passed, the cloud server will consider the target person to be a compliant person and will proceed with the subsequent processing. The cloud server will first determine the target surveillance video, that is, determine which surveillance video has identified the target person, and determine the refueling work node where the target person is currently located based on the camera that collects the surveillance video, that is, the current work node. The operation actions required at each refueling work node are different. A database can be pre-set in the cloud server, which stores the mapping relationship between the refueling work node and the task posture that needs to be met. By querying the database, the current task posture corresponding to the current work node can be determined.

[0029] S103, obtaining the skeleton information currently assigned to the target fuel truck, identifying the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target monitoring video, and performing skeleton authentication based on the skeleton information and skeleton data.

[0030] In the embodiment of the present specification, the work arrangement table can also query the skeleton information of the staff currently assigned to operate the target fuel truck. The cloud server can determine the skeleton data and posture behavior data of the target person by identifying and analyzing the heat map of the target monitoring video. Before determining whether the posture of the target person meets the specification, the cloud server will also compare the skeleton data and skeleton information to perform skeleton authentication on the target person and realize secondary identification of the identity of the target person. The reason why secondary identification is needed is to avoid illegal personnel passing the face recognition through the photo of the target person. Therefore, after identifying the skeleton data of the target person, the body shape of the target person will be re-authenticated according to the skeleton data. Only when both face recognition and skeleton recognition are passed, the cloud server can truly confirm that the target person is the corresponding staff member to ensure the safety of the aircraft refueling process. In addition, this method also eliminates the possibility that some staff members will throw their work to other staff members for processing after the face recognition is passed.

[0031] In one possible implementation, after performing face recognition authentication on the target person according to the identity information currently assigned to the target fuel truck, the method further includes: When the face recognition authentication fails, a first warning message is generated; After skeleton authentication is performed according to the skeleton information and skeleton data, the method further includes: When the skeleton authentication fails, a second warning message is generated, wherein the first warning message and the second warning message are both used to characterize operator errors, and the warning level of the second warning message is higher than the warning level of the first warning message.

[0032] In the embodiment of this specification, whether the face recognition or skeleton recognition fails, the cloud server will generate a warning message to the terminal used by the management and security personnel to warn the corresponding personnel to go to the location of the target fuel truck to verify the actual situation and avoid safety problems. If the second warning message is generated, it means that the face recognition passes but the skeleton authentication fails. This means that the target person is already trying to refuel, and there is a higher safety risk, so the warning level set for the second warning message will also be higher.

[0033] In one possible implementation, performing skeleton authentication according to the skeleton information and skeleton data includes: Determine first data of the operator based on the skeleton information, the first data including a first arm length, a first leg length, and a first spine length; Determine second data of the target person based on the skeleton data, the second data including a second arm length, a second leg length, and a second spine length; The similarity between the first data and the second data is calculated, and a skeleton authentication result is generated according to the similarity, wherein the skeleton authentication result is characterized as authentication passed when the similarity is greater than a preset value, and is characterized as authentication failed when the similarity is not greater than the preset value.

[0034] In the embodiments of this specification, since the skeleton postures of the skeleton data and skeleton information may be different, if the matching degree of the two is simply identified, it is necessary to train a data processing model such as a neural network model to adjust the posture of the skeleton data, which is too cumbersome and has low processing efficiency. Therefore, after the cloud server identifies the skeleton information and skeleton data, it will distinguish the type of each skeleton segment according to the key points corresponding to the joints, and then determine the arm length, leg length and spine length according to the sum of the lengths of the same type of skeleton segments, and calculate the similarity based on these three data. As long as the similarity between the first data and the second data is higher than the preset value, the skeleton authentication is considered to have passed.

[0035] In one possible implementation, the identifying the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target surveillance video includes: Acquire current frame data of the target surveillance video, and set an identification frame range based on the current frame data; Determine each heat map corresponding to each frame data within the recognition frame range, and determine the skeleton data in the heat map; The skeleton data are smoothed in time order to obtain the posture behavior data of the target person.

[0036] In the embodiments of the present specification, the identification frame range is based on the current frame data, and the data range formed by selecting the data of the N frames before and after the current frame data. The heat map represents the transient hot spot distribution of a certain frame in the surveillance video. In order to identify the action behavior of the target person, it is necessary to determine it through multiple continuous heat maps. Specifically, the cloud server will obtain the current frame data in the surveillance video and set the identification frame range based on the current frame data. Then determine the heat map corresponding to each frame data within the identification frame range. According to the heat distribution in the heat map, the skeleton data of the target person in the heat map can be determined, and the skeleton data can represent the action posture of the target person in this frame data. By smoothing each skeleton data in chronological order, it is ensured that the changes in the skeleton data of the current frame in the previous and next frames are taken into account, so that the posture behavior data finally generated can more accurately represent the action posture of the target person in the surveillance video, that is, reflect the movement trajectory of the target person.

[0037] In one possible implementation, determining skeleton data in the heat map includes: Determine key nodes based on the heat distribution of the heat map; After performing component affinity field analysis on each of the key nodes, each of the key nodes is connected to obtain skeleton data.

[0038] In the embodiments of this specification, the heat map can characterize the heat distribution in the whole picture. Through the heat distribution, the coordinates of the local maximum value of the heat map can be used as the coordinates of the key nodes of the target person, so as to determine the key nodes in the heat map. Then, by performing component affinity field analysis on each key node, the relationship between each key node can be determined, and the key nodes can be connected to obtain skeleton data. Specifically, the above process can use openpose to realize recognition and calculation. Among them, the key nodes are the main joints of the human body that can form human postures, such as head, shoulders, torso, etc.

[0039] S104: after the skeleton authentication is passed, a posture specification recognition result is generated according to the matching result of the posture behavior data and the current task posture.

[0040] In the embodiment of this specification, after the skeleton authentication is passed, the cloud server will finally confirm that the target person is the assigned staff member, match the posture behavior data with the current task posture, and generate a posture standard recognition result based on the matching degree of the two. The posture standard recognition result will be characterized as qualified when the matching degree is higher than the preset matching degree, otherwise it will be characterized as unqualified.

[0041] In one embodiment, the method further comprises: Determine a target workflow based on the fueling work information of the aviation fuel truck, and generate an actual workflow according to each target fueling work node in chronological order, wherein the target fueling work node is the fueling work node characterized by the posture specification recognition result as being in compliance with the specification; A process specification identification result is generated according to the matching result between the target process and the actual process.

[0042] In the embodiments of this specification, the refueling process of the aviation fuel truck should be a fixed process, that is, the order of going to each refueling work node should be fixed. Therefore, in addition to identifying the posture and action specifications at a single refueling work node, the cloud server will also record each target refueling node, and integrate each target refueling node in chronological order to generate an actual workflow. Next, the cloud server will also obtain the target workflow, that is, the workflow that should be executed for normal refueling work, match it with the actual workflow, and generate a process specification recognition result based on the matching result. If there is a problem with the process specification recognition result, an early warning prompt will also be issued.

[0043] In one embodiment, the method further comprises: Determine the proficiency of the target person at the current work node, where the proficiency is determined based on the number of historical irregularities of the target person at the current work node, and the proficiency is inversely proportional to the number of historical irregularities; The number of posture standard recognitions of the current working node is set based on the proficiency interval corresponding to the proficiency, and the recognition waiting interval is calculated based on the average working time of the current working node; After each recognition waiting interval, the standard posture recognition is repeated until the accumulated recognition times meet the standard posture recognition times.

[0044] In the embodiment of the present specification, according to the historical non-standard times of the target personnel at each refueling work node, the cloud server will record the proficiency of the target personnel at each refueling work node, and the proficiency can be specifically determined according to the mapping relationship between the preset proficiency and the historical non-standard times. Under normal circumstances, the cloud server will only perform one recognition authentication on the posture of the target personnel at a refueling work node, and for unskilled nodes, multiple recognition authentications should be performed to ensure the effectiveness of the target personnel's operation. Specifically, the cloud server will also determine the number of posture standard recognitions corresponding to the current work node through the mapping relationship between the preset proficiency interval and the number of posture standard recognitions. At the same time, considering that it is better to perform multiple recognitions evenly during the operation of the target personnel than continuous recognition, the cloud server will also calculate the recognition waiting interval according to the average working time of the current work node, and the recognition waiting interval can be the ratio of the average working time to the number of posture standard recognitions. Then, the cloud server will repeat the process of posture standard recognition every time after the recognition waiting interval, until the specified number of recognitions is completed, as long as one of the recognition results is characterized as non-standard posture, the cloud server will issue an early warning.

[0045] The following will be combined with the attached Figure 2 , the posture standard recognition device in the fuel tanker refueling scenario provided by the embodiment of the present application is introduced in detail. Figure 2 The posture standard recognition device in the aviation fuel truck refueling scene shown is used to execute the application Figure 1 For the convenience of explanation, only the part related to the embodiment of the present application is shown. For the specific technical details not disclosed, please refer to the present application. Figure 1 The embodiment shown.

[0046] See also Figure 2 , Figure 2 Schematic diagram of a posture standard recognition device for a fuel truck refueling scenario provided by an embodiment of the present application. Figure 2 As shown, the device comprises: The first determination module 201 is used to determine the target aviation fuel truck currently working when receiving the fuel truck refueling work information, and determine the target personnel currently working based on the monitoring videos collected by the target aviation fuel truck, and perform face recognition authentication on the target personnel according to the face information currently assigned to the target aviation fuel truck, and the target aviation fuel truck is provided with at least one camera at each refueling work node; The second determination module 202 is used to determine the current working node of the target person based on the target monitoring video after the face recognition authentication is passed, and obtain the current task posture of the current working node, wherein the target monitoring video is the monitoring video in which the target person is identified; The identification module 203 is used to obtain the skeleton information currently assigned to the target fuel truck, identify the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target monitoring video, and perform skeleton authentication based on the skeleton information and skeleton data; The generation module 204 is used to generate a posture specification recognition result according to the matching result of the posture behavior data and the current task posture after the skeleton authentication is passed.

[0047] In one possible implementation, the first determining module 201 is further configured to: When the face recognition authentication fails, a first warning message is generated; The identification module 203 is further specifically used for: When the skeleton authentication fails, a second warning message is generated, wherein the first warning message and the second warning message are both used to characterize operator errors, and the warning level of the second warning message is higher than the warning level of the first warning message.

[0048] In one possible implementation, the identification module 203 is specifically used for: Determine first data of the operator based on the skeleton information, the first data including a first arm length, a first leg length, and a first spine length; Determine second data of the target person based on the skeleton data, the second data including a second arm length, a second leg length, and a second spine length; The similarity between the first data and the second data is calculated, and a skeleton authentication result is generated according to the similarity, wherein the skeleton authentication result is characterized as authentication passed when the similarity is greater than a preset value, and is characterized as authentication failed when the similarity is not greater than the preset value.

[0049] In one possible implementation, the identification module 203 is further configured to: Acquire current frame data of the target surveillance video, and set an identification frame range based on the current frame data; Determine each heat map corresponding to each frame data within the recognition frame range, and determine the skeleton data in the heat map; The skeleton data are smoothed in time order to obtain the posture behavior data of the target person.

[0050] In one possible implementation, the identification module 203 is further configured to: Determine key nodes based on the heat distribution of the heat map; After performing component affinity field analysis on each of the key nodes, each of the key nodes is connected to obtain skeleton data.

[0051] In one embodiment, the device further comprises: A third determination module is used to determine a target workflow based on the fueling work information of the aviation fuel truck, and generate an actual workflow according to each target fueling work node in chronological order, wherein the target fueling work node is the fueling work node characterized by the posture specification recognition result as being in compliance with the specification; The matching module is used to generate a process specification identification result according to the matching result between the target process and the actual process.

[0052] In one embodiment, the device further comprises: A fourth determination module is used to determine the proficiency of the target person at the current work node, wherein the proficiency is determined based on the number of historical irregularities of the target person at the current work node, and the proficiency is inversely proportional to the number of historical irregularities; A setting module, used to set the number of posture standard recognition times of the current working node based on the proficiency interval corresponding to the proficiency, and calculate the recognition waiting interval based on the average working time of the current working node; The repetition module is used to repeat the standard posture recognition every time the recognition waiting interval passes until the accumulated recognition times meet the standard posture recognition times.

[0053] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be implemented with the help of software and / or hardware. The "unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array (Field-Programmable Gate Array, FPGA), an integrated circuit (Integrated Circuit, IC), etc.

[0054] Each processing unit and / or module of the embodiments of the present application may be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or may be implemented by software that executes the functions described in the embodiments of the present application.

[0055] See also Figure 3 , which shows a schematic diagram of the structure of an electronic device involved in an embodiment of the present application, the electronic device can be used to implement Figure 1 The method in the embodiment shown. Figure 3 As shown, the electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0056] The communication bus 302 is used to realize the connection and communication between these components.

[0057] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0058] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0059] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts of the entire electronic device 300, and executes various functions and processes data of the electronic device 300 by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics central processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0060] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned processor 301. As Figure 3 As shown, the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module, and program instructions.

[0061] exist Figure 3 In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the posture specification recognition application in the aviation fuel truck refueling scene stored in the memory 305, and specifically perform the following operations: When receiving the refueling work information of the aviation fuel truck, determining the target aviation fuel truck currently working, and determining the target personnel currently working based on the monitoring videos collected by the target aviation fuel truck, and performing face recognition authentication on the target personnel according to the face information currently assigned to the target aviation fuel truck, wherein the target aviation fuel truck is provided with at least one camera at each refueling work node; After the face recognition authentication is passed, the current working node of the target person is determined based on the target monitoring video, and the current task posture of the current working node is obtained, and the target monitoring video is the monitoring video in which the target person is identified; Obtaining the skeleton information currently assigned to the target fuel truck, identifying the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target surveillance video, and performing skeleton authentication based on the skeleton information and skeleton data; After the skeleton authentication is passed, a posture specification recognition result is generated according to the matching result of the posture behavior data and the current task posture.

[0062] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0063] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0064] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0065] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0066] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0067] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0068] 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 memory. Based on this understanding, the technical solution of the present application 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 memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM), random access memory (RAM), mobile hard disk, disk or optical disk and other media that can store program codes.

[0069] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by entering a program to instruct related hardware, and the program may be stored in a computer-readable memory, which may include a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0070] The above is only an exemplary embodiment of the present disclosure, and the scope of the present disclosure cannot be limited thereto. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure here, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the technical field not recorded in the present disclosure. The description and examples are regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for recognizing posture norms in a fuel tanker refueling scenario, characterized in that: The method comprises: When receiving the refueling work information of the aviation fuel truck, determining the target aviation fuel truck currently working, and determining the target personnel currently working based on the monitoring videos collected by the target aviation fuel truck, and performing face recognition authentication on the target personnel according to the face information currently assigned to the target aviation fuel truck, wherein the target aviation fuel truck is provided with at least one camera at each refueling work node; After the face recognition authentication is passed, the current working node of the target person is determined based on the target monitoring video, and the current task posture of the current working node is obtained, and the target monitoring video is the monitoring video in which the target person is identified; Obtaining the skeleton information currently assigned to the target fuel truck, identifying the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target surveillance video, and performing skeleton authentication based on the skeleton information and skeleton data; After the skeleton authentication is passed, a posture specification recognition result is generated according to the matching result of the posture behavior data and the current task posture.

2. The method according to claim 1, characterized in that After performing face recognition authentication on the target person according to the identity information currently assigned to the target fuel truck, the method further includes: When the face recognition authentication fails, a first warning message is generated; After skeleton authentication is performed according to the skeleton information and skeleton data, the method further includes: When the skeleton authentication fails, a second warning message is generated, wherein the first warning message and the second warning message are both used to characterize operator errors, and the warning level of the second warning message is higher than the warning level of the first warning message.

3. The method according to claim 1, characterized in that: The performing skeleton authentication according to the skeleton information and the skeleton data includes: Determine first data of the operator based on the skeleton information, the first data including a first arm length, a first leg length, and a first spine length; Determine second data of the target person based on the skeleton data, the second data including a second arm length, a second leg length, and a second spine length; The similarity between the first data and the second data is calculated, and a skeleton authentication result is generated according to the similarity, wherein the skeleton authentication result is characterized as authentication passed when the similarity is greater than a preset value, and is characterized as authentication failed when the similarity is not greater than the preset value.

4. The method according to claim 1, characterized in that: The identifying of the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target surveillance video includes: Acquire current frame data of the target surveillance video, and set an identification frame range based on the current frame data; Determine each heat map corresponding to each frame data within the recognition frame range, and determine the skeleton data in the heat map; The skeleton data are smoothed in time order to obtain the posture behavior data of the target person.

5. The method according to claim 4, characterized in that Determining skeleton data in the heat map includes: Determine key nodes based on the heat distribution of the heat map; After performing component affinity field analysis on each of the key nodes, each of the key nodes is connected to obtain skeleton data.

6. The method according to claim 1, characterized in that The method further comprises: Determine a target workflow based on the fueling work information of the aviation fuel truck, and generate an actual workflow according to each target fueling work node in chronological order, wherein the target fueling work node is the fueling work node characterized by the posture specification recognition result as being in compliance with the specification; A process specification identification result is generated according to the matching result between the target process and the actual process.

7. The method according to claim 1, characterized in that The method further comprises: Determine the proficiency of the target person at the current work node, where the proficiency is determined based on the number of historical irregularities of the target person at the current work node, and the proficiency is inversely proportional to the number of historical irregularities; The number of posture standard recognitions of the current working node is set based on the proficiency interval corresponding to the proficiency, and the recognition waiting interval is calculated based on the average working time of the current working node; After each recognition waiting interval, the standard posture recognition is repeated until the accumulated recognition times meet the standard posture recognition times.

8. A posture standard recognition device in the fuel tanker refueling scene, characterized in that: The device comprises: The first determination module is used to determine the target aviation fuel truck currently working when receiving the fuel truck refueling work information, and determine the target personnel currently working based on the monitoring videos collected by the target aviation fuel truck, and perform face recognition authentication on the target personnel according to the face information currently assigned to the target aviation fuel truck, wherein the target aviation fuel truck is provided with at least one camera at each refueling work node; A second determination module is used to determine the current working node of the target person based on the target monitoring video after the face recognition authentication is passed, and obtain the current task posture of the current working node, wherein the target monitoring video is the monitoring video in which the target person is identified; An identification module, used to obtain the skeleton information currently assigned to the target fuel truck, identify the skeleton data and posture behavior data of the target person based on the heat map corresponding to the target monitoring video, and perform skeleton authentication based on the skeleton information and skeleton data; The generation module is used to generate a posture specification recognition result according to the matching result of the posture behavior data and the current task posture after the skeleton authentication is passed.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium has instructions stored therein, and when the instructions are executed on a computer or a processor, the computer or the processor executes the steps of the method according to any one of claims 1 to 7.

Citation Information

Cited By

  • Track correction method and device for cluster flying target, and medium

    CN119493094A