Airport isolation area auxiliary verification system and method based on face recognition

Abstract

The invention is suitable for the technical field of temporary airport isolation area management, and provides an airport isolation area auxiliary verification system and method based on face recognition, and the method comprises the steps: obtaining the motion track video data of a preset number of target persons authorized to enter a target airport isolation area; and analyzing the obtained motion trail video data of all the target persons, and judging whether an abnormal roundabout area exists in the target airport isolation area or not. After the temporary isolation area of the airport is established, the traffic and walking efficiency in the area can be scientifically analyzed by using the motion trail video data of people entering the area, and whether a roundabout area causing abnormal traffic or slow walking exists or not can be identified through the data. Once the existence of the roundabout area is confirmed, the reason of the roundabout area can be intelligently analyzed, especially whether the indication marks are unreasonably arranged or not is checked.

Description

Technical Field

[0001] The present invention belongs to the technical field of temporary airport isolation zone management technology, and in particular relates to an airport isolation zone auxiliary verification system and method based on face recognition. Background Art

[0002] With the increasing frequency of global travel and air transportation, airport security management has become one of the important issues. In order to cope with emergencies or peak passenger processing needs, airports often set up temporary isolation areas to effectively manage passenger flow and improve security inspection efficiency. These areas are usually equipped with temporary fences and movable partitions to facilitate rapid adjustment of space to meet different security needs. However, this setting often needs to be completed in a short period of time and often lacks long-term planning, which poses a challenge to the functionality and efficiency of the isolation area.

[0003] Currently, temporary quarantine areas at airports rely on basic manual management and simple sign systems to guide passengers. These signposts are often improperly arranged and lack sufficient visual guidance or information transmission efficiency, resulting in inefficient movement of passengers in the quarantine area. Passengers may walk in circles in the quarantine area due to difficulty in quickly identifying their destination or unclear instructions, which not only increases the inconvenience of passengers, but also reduces the operating efficiency of the entire quarantine area. In addition, this situation may cause confusion and safety risks, especially during peak hours or in emergency situations. Summary of the invention

[0004] The purpose of the present invention is to provide an airport isolation zone auxiliary verification system and method based on face recognition, aiming to solve the problems raised in the background technology.

[0005] The present invention is implemented as follows: an airport isolation zone auxiliary verification system based on face recognition, the system comprising:

[0006] A video data acquisition module, used to acquire the motion trajectory video data of a preset number of target persons who are authorized to enter the isolation area of ​​the target airport;

[0007] The abnormal detour area judgment module is used to analyze the obtained motion trajectory video data of all target personnel and determine whether there is an abnormal detour area in the isolation area of ​​the target airport;

[0008] An abnormal indication mark judgment module is used to analyze whether there is an abnormal indication mark in the abnormal detour area if it is determined that there is an abnormal detour area in the isolation area of ​​the target airport;

[0009] The abnormality indicator mark adjustment module is used to analyze the environment of the abnormality indicator mark after determining that there is an abnormality indicator mark, and make optimization adjustments to the abnormality indicator mark based on the environment.

[0010] As a further limitation of the technical solution of the embodiment of the present invention, the video data acquisition module specifically includes:

[0011] A target person verification unit, used to verify that the person entering the isolation area of ​​the target airport is an authorized target person based on face recognition technology;

[0012] A real-time face information acquisition unit, used to acquire the real-time face information of the target person during the verification process based on face recognition technology;

[0013] The motion trajectory video data acquisition unit is used to acquire the motion trajectory video data of a preset number of target persons according to the real-time face information of the preset number of target persons.

[0014] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal detour area judgment module specifically includes:

[0015] A motion trajectory line graph drawing unit is used to analyze the obtained motion trajectory video data of all target persons one by one, and draw a motion trajectory line graph for the motion trajectory video data of each target person;

[0016] A behavior recognition unit is used to analyze the movement trajectory line graphs of a preset number of target persons in sequence and identify whether there is frequent back-and-forth behavior in a specific area;

[0017] The abnormal detour area determination unit is used to identify the specific area as an abnormal detour area if, among the movement trajectories of a preset number of target persons, more than a first preset proportion of target persons show frequent back-and-forth behavior in the same specific area, and set the target persons who show frequent back-and-forth behavior in the same specific area as abnormal target persons.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal indication mark judgment module specifically includes:

[0019] A local video data acquisition unit is used to retrieve the motion trajectory video data of abnormal target personnel if it is determined that there is an abnormal detour area in the isolation area of ​​the target airport, and intercept the local video data of these abnormal target personnel in the abnormal detour area;

[0020] A distribution position acquisition unit, used to acquire the distribution position of the indicator mark of the abnormal circuitous area;

[0021] The abnormal indication mark determination unit is used to intelligently analyze the local video data of each abnormal target person, and analyze whether the facial orientation of each abnormal target person has ever corresponded to the distribution position of the indication mark of the abnormal detour area. If the facial orientation of the abnormal target persons exceeding a second preset proportion has never corresponded to the distribution position of the indication mark of the abnormal detour area, the indication mark of the abnormal detour area is determined to be the abnormal indication mark.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the abnormal indication mark adjustment module specifically includes:

[0023] A bystander angle video data acquisition unit, used to acquire the environment where the abnormal indicator mark is located and the bystander angle video data of the abnormal detour area after determining that there is an abnormal indicator mark in the abnormal detour area;

[0024] The obstacle judgment unit is used to intelligently analyze the video data of the environment where the abnormal indicator mark is located and the bystander angle of the abnormal detour area, and analyze whether there is an obstacle between the abnormal detour area and the abnormal indicator mark;

[0025] A first adjustment optimization instruction generating unit is used to generate a deployment position adjustment optimization instruction if there is an obstacle, and send it to the target airport isolator manager terminal;

[0026] The second adjustment optimization instruction generating unit is used to analyze the display conditions of the abnormal indication mark based on the video data from the bystander angle of the environment where the abnormal indication mark is located if there is no obstacle. If the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

[0027] An airport isolation zone auxiliary verification method based on face recognition, the method comprising:

[0028] Obtaining motion trajectory video data of a preset number of target persons who are authorized to enter the isolation area of ​​the target airport;

[0029] Analyze the obtained motion trajectory video data of all target personnel and determine whether there are abnormal detour areas in the isolation area of ​​the target airport;

[0030] If it is determined that there is an abnormal detour area within the isolation zone of the target airport, analyze whether there is an abnormal indicator mark within the abnormal detour area;

[0031] After determining that there is an abnormality indicator mark, the environment in which the abnormality indicator mark is located is analyzed, and optimization adjustments are made to the abnormality indicator mark based on the environment.

[0032] As a further limitation of the technical solution of the embodiment of the present invention, the step of obtaining the motion trajectory video data of a preset number of target persons who are authorized to enter the isolation zone of the target airport includes:

[0033] Verify that the person entering the isolation area of ​​the target airport is an authorized target person based on facial recognition technology;

[0034] In the verification process based on face recognition technology, real-time face information of the target person is obtained;

[0035] According to the real-time facial information of a preset number of target persons, the motion trajectory video data of a preset number of target persons are obtained.

[0036] As a further limitation of the technical solution of the embodiment of the present invention, the step of parsing the obtained motion trajectory video data of all target personnel and determining whether there is an abnormal detour area in the isolation zone of the target airport includes:

[0037] Analyze the obtained motion trajectory video data of all target persons one by one, and draw a motion trajectory line graph for the motion trajectory video data of each target person;

[0038] Analyze the movement trajectory line graphs of a preset number of target persons in sequence and identify whether there is frequent back and forth behavior in the designated area;

[0039] If, among the movement trajectories of a preset number of target persons, target persons exceeding a first preset proportion show frequent back-and-forth behavior in the same specific area, the specific area will be identified as an abnormal detour area, and the target persons who show frequent back-and-forth behavior in the same specific area will be set as abnormal target persons.

[0040] As a further limitation of the technical solution of the embodiment of the present invention, if it is determined that there is an abnormal detour area in the isolation zone of the target airport, the step of analyzing whether there is an abnormal indication mark in the abnormal detour area includes:

[0041] If it is determined that there is an abnormal detour area in the isolation zone of the target airport, the motion trajectory video data of the abnormal target personnel is retrieved, and the local video data of these abnormal target personnel in the abnormal detour area is intercepted;

[0042] Obtaining the distribution locations of indicator marks of abnormal detour areas;

[0043] Intelligently analyze the local video data of each abnormal target person, and analyze whether the facial orientation of each abnormal target person has ever corresponded to the distribution position of the indicator mark of the abnormal detour area. If the facial orientation of more than a second preset proportion of the abnormal target persons has never corresponded to the distribution position of the indicator mark of the abnormal detour area, the indicator mark of the abnormal detour area is determined to be an abnormal indication mark.

[0044] As a further limitation of the technical solution of the embodiment of the present invention, after determining that there is an abnormality indicator mark, the step of analyzing the environment in which the abnormality indicator mark is located, and optimizing and adjusting the abnormality indicator mark based on the environment includes:

[0045] After determining that there is an abnormal indicator mark in the abnormal detour area, obtaining video data of the environment where the abnormal indicator mark is located and the viewing angle of the abnormal detour area;

[0046] Intelligently analyze the video data of the environment where the abnormal indicator mark is located and the abnormal detour area from the perspective of the observer, and analyze whether there are obstacles between the abnormal detour area and the abnormal indicator mark;

[0047] If there are obstacles, an optimization instruction for adjusting the deployment position is generated and sent to the terminal of the isolator manager at the target airport;

[0048] If there is no obstacle, the display condition of the abnormal indicator mark is analyzed based on the video data from the bystander angle of the environment in which the abnormal indicator mark is located. If the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

[0049] Compared with the prior art, the present invention obtains the motion trajectory video data of a preset number of target personnel authorized to enter the isolation zone of the target airport; analyzes the motion trajectory video data of all target personnel obtained, and determines whether there is an abnormal detour area in the isolation zone of the target airport; if it is determined that there is an abnormal detour area in the isolation zone of the target airport, analyzes whether there is an abnormal indicator mark in the abnormal detour area; after determining that there is an abnormal indicator mark, analyzes the environment of the abnormal indicator mark, and optimizes and adjusts the abnormal indicator mark based on the environment. After the establishment of the temporary isolation zone of the airport, the motion trajectory video data of the personnel entering the area can be used to scientifically analyze the flow and walking efficiency in the area, and through these data, it can be identified whether there is a detour area that causes abnormal flow or slow walking. Once the existence of the detour area is confirmed, the cause of its generation can also be intelligently analyzed, especially to check whether it is due to unreasonable arrangement of the indicator mark. If so, an optimization plan will be proposed to adjust the indicator mark to improve the efficiency of personnel flow and overall operation efficiency, thereby optimizing the internal management of the isolation zone of the airport. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 An application architecture diagram of a system provided by an embodiment of the present invention;

[0051] Figure 2 A structural block diagram of a video data acquisition module in a system provided by an embodiment of the present invention;

[0052] Figure 3A structural block diagram of an abnormal detour area determination module in a system provided by an embodiment of the present invention;

[0053] Figure 4 A structural block diagram of an abnormal indication mark judgment module in a system provided by an embodiment of the present invention;

[0054] Figure 5 A structural block diagram of an abnormal indication mark adjustment module in a system provided by an embodiment of the present invention;

[0055] Figure 6 A flowchart of a method provided by an embodiment of the present invention;

[0056] Figure 7 A flowchart of obtaining motion trajectory video data of a preset number of target persons in the method provided in an embodiment of the present invention;

[0057] Figure 8 A flow chart of determining whether there is an abnormal detour area in the isolation zone of a target airport in the method provided in an embodiment of the present invention;

[0058] Fig. 9 A flow chart of analyzing whether there is an abnormal indication mark in an abnormal detour area in the method provided in an embodiment of the present invention;

[0059] Fig.10 A flow chart of optimizing and adjusting an abnormality indication mark in a method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0062] Figure 1 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0063] Among them, in another preferred embodiment provided by the present invention, an airport isolation area auxiliary verification system based on face recognition includes:

[0064] The video data acquisition module 100 is used to acquire the motion trajectory video data of a preset number of target persons who are authorized to enter the isolation zone of the target airport.

[0065] Specifically, Figure 2 It shows a structural block diagram of the video data acquisition module 100 in the system provided by the embodiment of the present invention.

[0066] Among them, in the preferred implementation manner provided by the present invention, the video data acquisition module 100 specifically includes:

[0067] A target person verification unit 101 is used to verify that the person entering the isolation area of ​​the target airport is an authorized target person based on face recognition technology;

[0068] A real-time face information acquisition unit 102 is used to acquire the real-time face information of the target person during the verification process based on face recognition technology;

[0069] The motion trajectory video data acquisition unit 103 is used to acquire the motion trajectory video data of a preset number of target persons according to the real-time face information of the preset number of target persons.

[0070] In an embodiment of the present invention, an intelligent high-definition camera is installed at the entrance of the isolation zone of the target airport, and whenever a person inside the airport wants to enter the isolation zone of the target airport, the intelligent high-definition camera will record the facial image of the person and verify whether the person entering is the target person who has been authorized in advance based on face recognition technology, thereby ensuring that the people entering the isolation zone of the target airport are all authorized target persons.

[0071] Intelligent high-definition cameras are installed in different areas of the isolation zone of the target airport. When any target person enters the isolation zone of the target airport, the target person's movement trajectory video data is obtained through the real-time facial information of the target person and the intelligent high-definition cameras installed in different areas.

[0072] The preset number is pre-set by the target airport isolation zone management personnel, preferably between 20-50.

[0073] Furthermore, the airport isolation area auxiliary verification system based on face recognition also includes:

[0074] The abnormal detour area judgment module 200 is used to analyze the obtained motion trajectory video data of all target personnel and determine whether there is an abnormal detour area in the isolation area of ​​the target airport.

[0075] Specifically, Figure 3 The structure block diagram of the abnormal detour area determination module 200 in the system provided by the embodiment of the present invention is shown.

[0076] Among them, in the preferred embodiment provided by the present invention, the abnormal detour area judgment module 200 specifically includes:

[0077] A motion trajectory line graph drawing unit 201 is used to analyze the obtained motion trajectory video data of all target persons one by one, and draw a motion trajectory line graph for the motion trajectory video data of each target person;

[0078] The behavior recognition unit 202 is used to analyze the movement trajectory line graphs of a preset number of target persons in sequence and recognize whether there is a behavior of frequent back and forth movement in a specific area;

[0079] The abnormal detour area determination unit 203 is used to identify the specific area as an abnormal detour area if, among the movement trajectories of a preset number of target persons, more than a first preset proportion of target persons show frequent back-and-forth behavior in the same specific area, and set the target persons who show frequent back-and-forth behavior in the same specific area as abnormal target persons.

[0080] In the embodiment of the present invention, drawing a motion trajectory line graph from the motion trajectory video data of the target person can be obtained by recording the motion trajectory of the target person.

[0081] The target person's frequent back-and-forth behavior in a specific area can be regarded as the target person's repeated back-and-forth behavior in the specific area for at least three times. The first preset ratio is pre-set by the staff of the isolation area of ​​the target airport, and is preferably set at 1 / 3-1 / 2. When the target persons exceeding the first preset ratio in the movement trajectories of a preset number of target persons show frequent back-and-forth behavior in the same specific area, it means that when the target person enters the specific area, there is a greater probability of frequent back-and-forth walking behavior, which indirectly reflects that the target person failed to obtain clear walking instructions after entering this specific area.

[0082] Furthermore, the airport isolation area auxiliary verification system based on face recognition also includes:

[0083] The abnormal indication mark judging module 300 is used to analyze whether there is an abnormal indication mark in the abnormal detour area if it is determined that there is an abnormal detour area in the isolation zone of the target airport.

[0084] Specifically, Figure 4 It shows a structural block diagram of the abnormal indication mark judgment module 300 in the system provided by an embodiment of the present invention.

[0085] Among them, in the preferred embodiment provided by the present invention, the abnormal indication mark judgment module 300 specifically includes:

[0086] The local video data acquisition unit 301 is used to retrieve the motion trajectory video data of the abnormal target personnel if it is determined that there is an abnormal detour area in the isolation zone of the target airport, and intercept the local video data of these abnormal target personnel in the abnormal detour area;

[0087] A distribution position acquisition unit 302 is used to acquire the distribution position of the indicator mark of the abnormal circuitous area;

[0088] The abnormal indication mark determination unit 303 is used to intelligently analyze the local video data of each abnormal target person, and analyze whether the facial orientation of each abnormal target person has ever corresponded to the distribution position of the indicator mark of the abnormal detour area. If the facial orientation of the abnormal target persons exceeding a second preset proportion has never corresponded to the distribution position of the indicator mark of the abnormal detour area, the indicator mark of the abnormal detour area is determined to be the abnormal indication mark.

[0089] In an embodiment of the present invention, the distribution positions of the indicator marks of the abnormal detour area are pre-set. When analyzing the local video data of the abnormal target person in the abnormal detour area, the focus should be set to the face of the target person and the facial orientation of the target person should be monitored. Then, a deep learning algorithm (such as a convolutional neural network (CNN)) is used to analyze whether the facial orientation of each abnormal target person corresponds to the distribution positions of the indicator marks of the abnormal detour area.

[0090] The second preset ratio is pre-set by the staff of the isolation area of ​​the target airport, and is preferably between 1 / 2 and 4 / 5. When the facial orientation of the abnormal target persons exceeding the second preset ratio has never corresponded to the distribution position of the indication mark of the abnormal detour area, it can indirectly indicate that there is a high probability that a large number of abnormal target persons have not been able to understand or observe the indication mark of the abnormal detour area. Therefore, there is an abnormality in the guidance function of the indication mark in the abnormal detour area, and it is set as an abnormal indication mark.

[0091] Furthermore, the airport isolation area auxiliary verification system based on face recognition also includes:

[0092] The abnormality indicator mark adjustment module 400 is used to analyze the environment of the abnormality indicator mark after determining that there is an abnormality indicator mark, and optimize and adjust the abnormality indicator mark based on the environment.

[0093] Specifically, Figure 5 It shows a structural block diagram of the abnormal indication mark adjustment module 400 in the system provided by an embodiment of the present invention.

[0094] Among them, in the preferred embodiment provided by the present invention, the abnormal indication mark adjustment module 400 specifically includes:

[0095] A bystander angle video data acquisition unit 401 is used to acquire the video data of the environment where the abnormal indicator mark is located and the bystander angle of the abnormal detour area after determining that there is an abnormal indicator mark in the abnormal detour area;

[0096] The obstacle judgment unit 402 is used to intelligently analyze the video data of the environment where the abnormal indication mark is located and the bystander angle of the abnormal detour area, and analyze whether there is an obstacle between the abnormal detour area and the abnormal indication mark;

[0097] The first adjustment optimization instruction generating unit 403 is used to generate a deployment position adjustment optimization instruction if there is an obstacle, and send it to the target airport isolator manager terminal;

[0098] The second adjustment optimization instruction generating unit 404 is used to analyze the display conditions of the abnormal indication mark according to the video data from the bystander angle of the environment where the abnormal indication mark is located if there is no obstacle. If the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

[0099] In an embodiment of the present invention, video data from a bystander's perspective of the environment in which the abnormal indication mark is located and the abnormal detour area can be obtained by an intelligent high-definition camera that is arranged at a distance from the abnormal detour area and the environment in which the abnormal indication mark is located. It should be noted that the intelligent high-definition camera must be able to comprehensively and clearly obtain video data of the environment in which the abnormal indication mark is located and the abnormal detour area.

[0100] Analyze the video data of the environment in which the abnormal indication mark is located and the abnormal detour area from the perspective of a bystander, and analyze whether there is an obstacle between the abnormal detour area and the abnormal indication mark. It can be understood that any point in the abnormal detour area and the abnormal indication mark can be set as an observation straight line, and when there is an obstacle in any observation straight line, it is determined that there is an obstacle between the abnormal detour area and the abnormal indication mark, and generate a layout position adjustment optimization instruction containing obstacle information and send it to the target airport isolator management personnel terminal.

[0101] If there is no obstacle between the abnormal detour area and the abnormal indicator mark, it means that the reason why the abnormal target person fails to have a direct facial orientation correspondence with the abnormal indicator mark is most likely that the actual conditions of the abnormal indicator mark are insufficient (insufficient lighting). At this time, the display conditions of the abnormal indicator mark are analyzed based on the video data from the bystander angle of the environment in which the abnormal indicator mark is located. If it is determined that the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

[0102] Through the above technical solution, after the temporary isolation zone of the airport is established, the video data of the movement trajectory of people entering the area can be used to scientifically analyze the flow and walking efficiency in the area, and through these data, it can be identified whether there are detours that cause abnormal flow or slow walking. Once the existence of a detour is confirmed, the cause of its occurrence can be intelligently analyzed, especially to check whether it is due to unreasonable layout of the indicator marks. If so, an optimization plan will be proposed to adjust the indicator marks to improve the efficiency of personnel flow and overall operation efficiency, thereby optimizing the internal management of the airport isolation zone.

[0103] Furthermore, Figure 6 A flow chart of a method provided by an embodiment of the present invention is shown.

[0104] Specifically, an airport isolation zone auxiliary verification method based on face recognition includes the following steps:

[0105] Step S100, obtaining motion trajectory video data of a preset number of target persons who are authorized to enter the isolation area of ​​the target airport.

[0106] Specifically, Figure 7 A flow chart for obtaining motion trajectory video data of a preset number of target persons is shown.

[0107] The process of obtaining the motion trajectory video data of a preset number of target persons who are authorized to enter the isolation area of ​​the target airport specifically includes the following steps:

[0108] Step S101, verifying that the person entering the isolation area of ​​the target airport is an authorized target person based on face recognition technology;

[0109] Step S102, obtaining real-time facial information of the target person during the verification process based on facial recognition technology;

[0110] Step S103, acquiring motion trajectory video data of a preset number of target persons according to the real-time face information of the preset number of target persons.

[0111] In an embodiment of the present invention, an intelligent high-definition camera is installed at the entrance of the isolation zone of the target airport, and whenever a person inside the airport wants to enter the isolation zone of the target airport, the intelligent high-definition camera will record the facial image of the person and verify whether the person entering is the target person who has been authorized in advance based on face recognition technology, thereby ensuring that the people entering the isolation zone of the target airport are all authorized target persons.

[0112] Intelligent high-definition cameras are installed in different areas of the isolation zone of the target airport. When any target person enters the isolation zone of the target airport, the target person's movement trajectory video data is obtained through the real-time facial information of the target person and the intelligent high-definition cameras installed in different areas.

[0113] The preset number is pre-set by the target airport isolation zone management personnel, preferably between 20-50.

[0114] Furthermore, the airport isolation zone auxiliary verification method based on face recognition also includes the following steps:

[0115] Step S200, analyzing the obtained motion trajectory video data of all target personnel, and determining whether there is an abnormal detour area in the isolation zone of the target airport.

[0116] Specifically, Figure 8 A flow chart is shown for determining whether there is an abnormal detour area within the isolation zone of a target airport.

[0117] The following steps are specifically included in analyzing the obtained motion trajectory video data of all target personnel and determining whether there is an abnormal detour area in the isolation area of ​​the target airport:

[0118] Step S201, analyzing the obtained motion trajectory video data of all target persons one by one, and drawing a motion trajectory line graph for the motion trajectory video data of each target person;

[0119] Step S202, analyzing the movement trajectory line graphs of a preset number of target persons in turn, and identifying whether there is frequent back-and-forth behavior in a designated area;

[0120] Step S203, if among the movement trajectories of a preset number of target persons, target persons exceeding a first preset proportion show frequent back-and-forth behavior in the same specific area, the specific area is identified as an abnormal detour area, and the target persons showing frequent back-and-forth behavior in the same specific area are set as abnormal target persons.

[0121] In the embodiment of the present invention, drawing a motion trajectory line graph from the motion trajectory video data of the target person can be obtained by recording the motion trajectory of the target person.

[0122] The target person's frequent back-and-forth behavior in a specific area can be regarded as the target person's repeated back-and-forth behavior in the specific area for at least three times. The first preset ratio is pre-set by the staff of the isolation area of ​​the target airport, and is preferably set at 1 / 3-1 / 2. When the target persons exceeding the first preset ratio in the movement trajectories of a preset number of target persons show frequent back-and-forth behavior in the same specific area, it means that when the target person enters the specific area, there is a greater probability of frequent back-and-forth walking behavior, which indirectly reflects that the target person failed to obtain clear walking instructions after entering this specific area.

[0123] Furthermore, the airport isolation zone auxiliary verification method based on face recognition also includes the following steps:

[0124] Step S300: If it is determined that there is an abnormal detour area in the isolation zone of the target airport, analyze whether there is an abnormal indication mark in the abnormal detour area.

[0125] Specifically, Fig. 9 A flow chart is shown for analyzing whether there is an abnormal indication mark in an abnormal detour area.

[0126] If it is determined that there is an abnormal detour area in the isolation zone of the target airport, analyzing whether there is an abnormal indicator mark in the abnormal detour area specifically includes the following steps:

[0127] Step S301, if it is determined that there is an abnormal detour area in the isolation zone of the target airport, the motion trajectory video data of the abnormal target personnel is retrieved, and the local video data of these abnormal target personnel in the abnormal detour area is intercepted;

[0128] Step S302, obtaining the distribution position of the indicator mark of the abnormal circuitous area;

[0129] Step S303, intelligently analyze the local video data of each abnormal target person, and analyze whether the facial orientation of each abnormal target person has ever corresponded to the distribution position of the indicator mark of the abnormal detour area. If the facial orientation of more than a second preset proportion of the abnormal target persons has never corresponded to the distribution position of the indicator mark of the abnormal detour area, then the indicator mark of the abnormal detour area is determined to be an abnormal indication mark.

[0130] In an embodiment of the present invention, the distribution positions of the indicator marks of the abnormal detour area are pre-set. When analyzing the local video data of the abnormal target person in the abnormal detour area, the focus should be set to the face of the target person and the facial orientation of the target person should be monitored. Then, a deep learning algorithm (such as a convolutional neural network (CNN)) is used to analyze whether the facial orientation of each abnormal target person corresponds to the distribution positions of the indicator marks of the abnormal detour area.

[0131] The second preset ratio is pre-set by the staff of the isolation area of ​​the target airport, and is preferably between 1 / 2 and 4 / 5. When the facial orientation of the abnormal target persons exceeding the second preset ratio has never corresponded to the distribution position of the indication mark of the abnormal detour area, it can indirectly indicate that there is a high probability that a large number of abnormal target persons have not been able to understand or observe the indication mark of the abnormal detour area. Therefore, there is an abnormality in the guidance function of the indication mark in the abnormal detour area, and it is set as an abnormal indication mark.

[0132] Furthermore, the airport isolation zone auxiliary verification method based on face recognition also includes the following steps:

[0133] Step S400, after determining that there is an abnormality indicator mark, analyzing the environment in which the abnormality indicator mark is located, and optimizing and adjusting the abnormality indicator mark based on the environment.

[0134] Specifically, Fig.10 A flow chart for optimizing the adjustment of abnormality indication marks is shown.

[0135] The airport isolation area auxiliary verification method based on face recognition specifically includes the following steps:

[0136] Step S401, after determining that there is an abnormal indication mark in the abnormal detour area, obtaining video data of the environment where the abnormal indication mark is located and the viewing angle of the abnormal detour area;

[0137] Step S402, intelligently analyzing the video data of the environment where the abnormal indication mark is located and the abnormal detour area from a bystander's perspective, and analyzing whether there is an obstacle between the abnormal detour area and the abnormal indication mark;

[0138] Step S403, if there is an obstacle, generate a layout position adjustment optimization instruction and send it to the target airport isolator manager terminal;

[0139] Step S404, if there is no obstacle, the display condition of the abnormal indicator mark is analyzed according to the video data from the bystander angle of the environment where the abnormal indicator mark is located. If the display condition is insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator manager terminal.

[0140] In an embodiment of the present invention, video data from a bystander's perspective of the environment in which the abnormal indication mark is located and the abnormal detour area can be obtained by an intelligent high-definition camera that is arranged at a distance from the abnormal detour area and the environment in which the abnormal indication mark is located. It should be noted that the intelligent high-definition camera must be able to comprehensively and clearly obtain video data of the environment in which the abnormal indication mark is located and the abnormal detour area.

[0141] Analyze the video data of the environment in which the abnormal indication mark is located and the abnormal detour area from the perspective of a bystander, and analyze whether there is an obstacle between the abnormal detour area and the abnormal indication mark. It can be understood that any point in the abnormal detour area and the abnormal indication mark can be set as an observation straight line, and when there is an obstacle in any observation straight line, it is determined that there is an obstacle between the abnormal detour area and the abnormal indication mark, and generate a layout position adjustment optimization instruction containing obstacle information and send it to the target airport isolator management personnel terminal.

[0142] If there is no obstacle between the abnormal detour area and the abnormal indicator mark, it means that the reason why the abnormal target person fails to have a direct facial orientation correspondence with the abnormal indicator mark is most likely that the actual conditions of the abnormal indicator mark are insufficient (insufficient lighting). At this time, the display conditions of the abnormal indicator mark are analyzed based on the video data from the bystander angle of the environment in which the abnormal indicator mark is located. If it is determined that the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

[0143] Through the above technical solution, after the temporary isolation zone of the airport is established, the video data of the movement trajectory of people entering the area can be used to scientifically analyze the flow and walking efficiency in the area, and through these data, it can be identified whether there are detours that cause abnormal flow or slow walking. Once the existence of a detour is confirmed, the cause of its occurrence can be intelligently analyzed, especially to check whether it is due to unreasonable layout of the indicator marks. If so, an optimization plan will be proposed to adjust the indicator marks to improve the efficiency of personnel flow and overall operation efficiency, thereby optimizing the internal management of the airport isolation zone.

[0144] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0145] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0146] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0147] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0148] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An airport isolation zone auxiliary verification system based on face recognition, characterized in that: The system comprises: A video data acquisition module, used to acquire the motion trajectory video data of a preset number of target persons who are authorized to enter the isolation area of ​​the target airport; The abnormal detour area judgment module is used to analyze the obtained motion trajectory video data of all target personnel and determine whether there is an abnormal detour area in the isolation area of ​​the target airport; An abnormal indication mark judgment module is used to analyze whether there is an abnormal indication mark in the abnormal detour area if it is determined that there is an abnormal detour area in the isolation area of ​​the target airport; The abnormality indicator mark adjustment module is used to analyze the environment of the abnormality indicator mark after determining that there is an abnormality indicator mark, and make optimization adjustments to the abnormality indicator mark based on the environment.

2. The airport isolation area auxiliary verification system based on face recognition according to claim 1 is characterized in that: The video data acquisition module specifically includes: A target person verification unit, used to verify that the person entering the isolation area of ​​the target airport is an authorized target person based on face recognition technology; A real-time face information acquisition unit, used to acquire the real-time face information of the target person during the verification process based on face recognition technology; The motion trajectory video data acquisition unit is used to acquire the motion trajectory video data of a preset number of target persons according to the real-time face information of the preset number of target persons.

3. The airport isolation area auxiliary verification system based on face recognition according to claim 1 is characterized in that: The abnormal detour area judgment module specifically includes: A motion trajectory line graph drawing unit is used to analyze the obtained motion trajectory video data of all target persons one by one, and draw a motion trajectory line graph for the motion trajectory video data of each target person; A behavior recognition unit is used to analyze the movement trajectory line graphs of a preset number of target persons in sequence and identify whether there is frequent back-and-forth behavior in a specific area; The abnormal detour area determination unit is used to identify the specific area as an abnormal detour area if, among the movement trajectories of a preset number of target persons, more than a first preset proportion of target persons show frequent back-and-forth behavior in the same specific area, and set the target persons who show frequent back-and-forth behavior in the same specific area as abnormal target persons.

4. The airport isolation area auxiliary verification system based on face recognition according to claim 3 is characterized in that: The abnormal indication mark judgment module specifically includes: A local video data acquisition unit is used to retrieve the motion trajectory video data of abnormal target personnel if it is determined that there is an abnormal detour area in the isolation area of ​​the target airport, and intercept the local video data of these abnormal target personnel in the abnormal detour area; A distribution position acquisition unit, used to acquire the distribution position of the indicator mark of the abnormal circuitous area; The abnormal indication mark determination unit is used to intelligently analyze the local video data of each abnormal target person, and analyze whether the facial orientation of each abnormal target person has ever corresponded to the distribution position of the indication mark of the abnormal detour area. If the facial orientation of the abnormal target persons exceeding a second preset proportion has never corresponded to the distribution position of the indication mark of the abnormal detour area, the indication mark of the abnormal detour area is determined to be the abnormal indication mark.

5. The airport isolation area auxiliary verification system based on face recognition according to claim 4 is characterized in that: The abnormal indication mark adjustment module specifically includes: A bystander angle video data acquisition unit, used to acquire the environment where the abnormal indicator mark is located and the bystander angle video data of the abnormal detour area after determining that there is an abnormal indicator mark in the abnormal detour area; The obstacle judgment unit is used to intelligently analyze the video data of the environment where the abnormal indicator mark is located and the bystander angle of the abnormal detour area, and analyze whether there is an obstacle between the abnormal detour area and the abnormal indicator mark; A first adjustment optimization instruction generating unit is used to generate a deployment position adjustment optimization instruction if there is an obstacle, and send it to the target airport isolator manager terminal; The second adjustment optimization instruction generating unit is used to analyze the display conditions of the abnormal indication mark based on the video data from the bystander angle of the environment where the abnormal indication mark is located if there is no obstacle. If the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

6. An airport isolation zone auxiliary verification method based on face recognition, characterized in that: The method comprises: Obtaining motion trajectory video data of a preset number of target persons who are authorized to enter the isolation area of ​​the target airport; Analyze the motion trajectory video data of all target personnel and determine whether there are abnormal detour areas in the isolation area of ​​the target airport; If it is determined that there is an abnormal detour area within the isolation zone of the target airport, analyze whether there is an abnormal indicator mark within the abnormal detour area; After determining that there is an abnormality indicator mark, the environment in which the abnormality indicator mark is located is analyzed, and optimization adjustments are made to the abnormality indicator mark based on the environment.

7. The airport isolation zone auxiliary verification method based on face recognition according to claim 6 is characterized in that: The step of obtaining the motion trajectory video data of a preset number of target persons who are authorized to enter the isolation zone of the target airport comprises: Verify that the person entering the isolation area of ​​the target airport is an authorized target person based on facial recognition technology; In the verification process based on face recognition technology, real-time face information of the target person is obtained; According to the real-time facial information of a preset number of target persons, the motion trajectory video data of a preset number of target persons are obtained.

8. The airport isolation zone auxiliary verification method based on face recognition according to claim 7 is characterized in that: The steps of analyzing the obtained motion trajectory video data of all target personnel and determining whether there is an abnormal detour area in the isolation area of ​​the target airport include: Analyze the obtained motion trajectory video data of all target persons one by one, and draw a motion trajectory line graph for the motion trajectory video data of each target person; Analyze the movement trajectory line graphs of a preset number of target persons in sequence and identify whether there is frequent back and forth behavior in the designated area; If, among the movement trajectories of a preset number of target persons, target persons exceeding a first preset proportion show frequent back-and-forth behavior in the same specific area, the specific area will be identified as an abnormal detour area, and the target persons who show frequent back-and-forth behavior in the same specific area will be set as abnormal target persons.

9. The airport isolation zone auxiliary verification method based on face recognition according to claim 8 is characterized in that: If it is determined that there is an abnormal detour area in the isolation zone of the target airport, the step of analyzing whether there is an abnormal indication mark in the abnormal detour area includes: If it is determined that there is an abnormal detour area in the isolation zone of the target airport, the motion trajectory video data of the abnormal target personnel is retrieved, and the local video data of these abnormal target personnel in the abnormal detour area is intercepted; Obtaining the distribution locations of indicator marks of abnormal detour areas; Intelligently analyze the local video data of each abnormal target person, and analyze whether the facial orientation of each abnormal target person has ever corresponded to the distribution position of the indicator mark of the abnormal detour area. If the facial orientation of more than a second preset proportion of the abnormal target persons has never corresponded to the distribution position of the indicator mark of the abnormal detour area, the indicator mark of the abnormal detour area is determined to be an abnormal indication mark.

10. The airport isolation zone auxiliary verification method based on face recognition according to claim 9 is characterized in that: After determining that there is an abnormality indicator mark, the step of analyzing the environment in which the abnormality indicator mark is located and optimizing and adjusting the abnormality indicator mark based on the environment includes: After determining that there is an abnormal indicator mark in the abnormal detour area, obtaining video data of the environment where the abnormal indicator mark is located and the viewing angle of the abnormal detour area; Intelligently analyze the video data of the environment where the abnormal indicator mark is located and the abnormal detour area from the perspective of the observer, and analyze whether there are obstacles between the abnormal detour area and the abnormal indicator mark; If there are obstacles, an optimization instruction for adjusting the deployment position is generated and sent to the terminal of the isolator manager at the target airport; If there is no obstacle, the display condition of the abnormal indicator mark is analyzed based on the video data from the bystander angle of the environment in which the abnormal indicator mark is located. If the display conditions are insufficient, a display enhancement adjustment instruction is generated and sent to the target airport isolator management personnel terminal.

Images