A gate control method, device, integrated control machine and storage medium

Abstract

The embodiments of the present application provide a barrier gate control method, device, integrated control machine, and storage medium, relating to the field of video monitoring technology. The method is applied to a monocular camera arranged on the front of the integrated control machine, which also includes a binocular camera arranged on the side. The method includes: obtaining each abnormal event reported by the binocular camera and the occurrence time of each abnormal event; determining the initial control mode for the barrier gate based on the license plate recognition result; if the initial control mode is to open the barrier gate, based on the currently acquired occurrence time of the abnormal event, analyzing whether there is an abnormal event in the lane area indicated by the detection area; if there is, based on the currently existing abnormal event, modifying the initial control mode to obtain a target control mode, and controlling the barrier gate based on the target control mode; if there is no abnormal event, controlling the barrier gate based on the initial control mode. This solution can improve the intelligence level of barrier gate control.

Description

Technical Field

[0001] The present application relates to the field of video monitoring technology, and in particular to a barrier gate control method, device, integrated control machine and storage medium. Background Art

[0002] In a vehicle entrance and exit scenario with a gate, it is necessary to capture the vehicle entering or leaving and identify the vehicle's license plate in order to control the gate at the entrance and exit.

[0003] In the related art, a snapshot camera is usually set up in the entrance and exit scene. The snapshot camera monitors the monitoring area in front of the gate, captures the vehicles in the monitoring area, and recognizes the license plates of the vehicles.

[0004] However, controlling the barrier gate solely based on the license plate recognized by the snapshot camera is not intelligent enough. Summary of the Invention

[0005] The purpose of the embodiments of the present application is to provide a gate control method, device, integrated control machine, and storage medium to improve the intelligence level of gate control. The specific technical solution is as follows:

[0006] In a first aspect, an embodiment of the present application provides a barrier gate control method, which is applied to a monocular camera disposed on the front of an integrated control and management machine, the integrated control and management machine also including a binocular camera disposed on the side, the monocular camera being used to capture images of vehicles that contact a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, the detection area including a portion of the lane area located in front of the barrier gate and a portion of the lane area located behind the barrier gate, the trigger line being located within the detection area and being at least a predetermined distance from a designated edge of the detection area, the designated edge being the edge that the vehicle first contacts when entering; the method comprising:

[0007] Acquiring each abnormal event reported by the binocular camera and the time of occurrence of each abnormal event; the binocular camera is used to monitor abnormal events in the lane area indicated by the detection area and report the monitored abnormal events;

[0008] In response to the license plate recognition result obtained by analysis, an initial control mode for the barrier gate is determined based on the license plate recognition result;

[0009] If the initial control mode is to open the gate, based on the currently acquired occurrence time of the abnormal event, analyzing whether there is currently an abnormal event in the lane area indicated by the detection area;

[0010] If so, based on the currently existing abnormal event, the initial control mode is modified to obtain a target control mode, and the gate is controlled based on the target control mode; and if not, the gate is controlled based on the initial control mode;

[0011] The target control method is a control method for dealing with existing abnormal events.

[0012] Optionally, the analyzing whether an abnormal event currently occurs in the lane area indicated by the detection area based on the currently acquired occurrence time of the abnormal event includes:

[0013] From the abnormal events currently obtained, determine whether there is an abnormal event whose time difference between the occurrence time and the current time is less than a predetermined time threshold; if so, determine that an abnormal event currently exists in the lane area indicated by the detection area; otherwise, determine that no abnormal event currently exists in the lane area indicated by the detection area.

[0014] Optionally, the abnormal event monitoring includes monitoring of one or more of the following events:

[0015] Monitoring of abnormal lane status events, abnormal vehicle status events, and abnormal gate status events;

[0016] The lane state abnormality event includes: a vehicle following too closely event in the lane area before the barrier, and / or a congestion event in the lane area entered after passing through the barrier;

[0017] The abnormal vehicle status event includes a fake license plate event.

[0018] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0019] When the current abnormal event is a congestion event, the initial control mode is changed to a mode for keeping the gate closed and outputting a first alarm message through the integrated management and control machine to obtain a target control mode; wherein, the first alarm message is information for indicating that congestion has occurred and instructing to wait.

[0020] Optionally, the method further includes:

[0021] Obtaining a notification of eliminating the abnormal event detected by the binocular camera;

[0022] In the case where the current abnormal event is a congestion event, after the step of controlling the barrier gate based on the target control method, if a notification of elimination of the current abnormal event is obtained, the barrier gate is controlled to open for the vehicle indicated by the license plate recognition result.

[0023] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0024] When the current abnormal event is a fake license plate event, the initial control mode is changed to a mode for keeping the gate closed and outputting a second alarm message through the integrated management and control machine to obtain a target control mode; wherein, the second alarm message is information for indicating that the current license plate is a fake license plate.

[0025] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0026] In the case where the currently existing abnormal event is a vehicle following too closely event, the initial control mode is changed to a mode for opening the barrier and extending the duration of the barrier being in the open state to obtain a target control mode.

[0027] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0028] In the case where the currently existing abnormal event is a gate state abnormal event, the initial control mode is changed to a mode for performing abnormal recovery processing on the gate and opening the gate after the abnormal recovery processing, so as to obtain a target control mode.

[0029] Optionally, the congestion event identification method includes:

[0030] Monitoring whether a boundary of a congestion monitoring area within the detection area overlaps with the vehicle; wherein the congestion monitoring area includes a portion of the lane area behind the gate;

[0031] If there is overlap, the congestion monitoring area is monitored to see whether it meets the congestion conditions. If the congestion conditions are met, a congestion event is identified. The congestion conditions include: the presence of adjacent vehicles separated by a number of pixels less than a target number of pixels; the target number of pixels is a specified proportion of the pixel outline of the target vehicle, and the target vehicle is a vehicle among the adjacent vehicles that is closer to the barrier.

[0032] Optionally, the method for identifying an abnormal gate status event includes:

[0033] Based on a pre-trained barrier gate state monitoring model, the current image currently captured by the binocular camera containing the barrier gate is recognized to obtain a recognition result of whether the barrier gate is in an open state or a closed state;

[0034] Based on the obtained recognition result of whether the barrier gate is in an open state or a closed state, and the target barrier gate state corresponding to the current image, it is determined whether the barrier gate is in an abnormal state. If so, an abnormal barrier gate state event is identified. The target barrier gate state corresponding to the current image is the state that the barrier gate needs to have when the current image represents the presence or absence of vehicle passage.

[0035] In a second aspect, an embodiment of the present application provides a barrier gate control device, which is applied to a monocular camera arranged on the front of an integrated control and management machine, and the integrated control and management machine also includes a binocular camera arranged on the side, the monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, and the detection area includes a partial lane area located in front of the barrier gate and a partial lane area located behind the barrier gate. The trigger line is located within the detection area and is at least a predetermined distance from a specified edge of the detection area, and the specified edge is the edge that the vehicle first contacts when entering; the device includes:

[0036] an acquisition module, configured to acquire each abnormal event reported by the binocular camera and the time of occurrence of each abnormal event; the binocular camera is configured to monitor the lane area indicated by the detection area for abnormal events and report the monitored abnormal events;

[0037] a determination module, configured to determine an initial control mode for the barrier gate based on the license plate recognition result obtained in response to the analysis;

[0038] an analysis module configured to analyze whether an abnormal event currently occurs in the lane area indicated by the detection area based on the currently acquired occurrence time of the abnormal event if the initial control mode is to open the barrier;

[0039] a control module configured to, if any, modify the initial control mode based on the currently existing abnormal event to obtain a target control mode, and control the barrier gate based on the target control mode; and, if no abnormal event exists, control the barrier gate based on the initial control mode;

[0040] The target control method is a control method for dealing with existing abnormal events.

[0041] In a third aspect, an embodiment of the present application provides an integrated control and management machine, the integrated control and management machine including a monocular camera arranged on the front and a binocular camera arranged on the side, the monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, the detection area includes a partial lane area located in front of the barrier and a partial lane area located behind the barrier, the trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area, the designated edge being the edge that the vehicle first contacts when entering; the monocular camera includes:

[0042] Memory for storing computer programs;

[0043] The processor is used to implement any of the above-mentioned gate control methods when executing the program stored in the memory.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, any of the above-mentioned gate control methods is implemented.

[0045] An embodiment of the present application also provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-described gate control methods.

[0046] Beneficial effects of the embodiments of the present application:

[0047] The barrier gate control method provided in an embodiment of the present application is applied to a monocular camera installed on the front of an integrated control and management machine, and the integrated control and management machine also includes a binocular camera installed on the side. The monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition. A polygonal detection area is pre-marked in the binocular camera's captured image. The detection area includes a portion of the lane area located in front of the barrier gate and a portion of the lane area located behind the barrier gate. The trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area. The designated edge is the edge that the vehicle first contacts when entering. If the monocular camera analyzes and obtains a license plate recognition result, an initial control mode for the barrier gate is determined based on the license plate recognition result. If the initial control mode of the barrier gate determined based on the license plate recognition result of the monocular camera is to open the barrier gate, the present application does not directly open the barrier gate. Instead, based on the occurrence time of the abnormal event reported by the binocular camera, the method analyzes whether an abnormal event currently exists in the lane area indicated by the detection area. If an abnormal event exists, the initial control mode is modified based on the current abnormal event to address the existing abnormal event. If no abnormal event exists, the barrier gate can be directly controlled based on the initial control mode. It can be seen that the present application can improve the intelligence level of gate control. In addition, the binocular camera is used to monitor the lane area indicated by the detection area for abnormal events and report the detected abnormal events. By setting the lane area included in the detection area and the position relationship with the trigger line, the vehicle entry process can be fully monitored, reducing the missed detection of abnormal events and further improving the intelligence level of gate control.

[0048] Of course, it is not necessary to achieve all the advantages described above at the same time when implementing any product or method of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0050] Figure 1 A schematic diagram of setting up a snapshot camera for monitoring entrance and exit scenes in the prior art provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of a captured image of a snapshot camera in the prior art provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of monitoring the entire lane area through an integrated control device provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of an integrated control and management machine provided in an embodiment of the present application;

[0054] Figure 5 A schematic flow chart of a gate control method provided in an embodiment of the present application;

[0055] Figure 6 A schematic diagram of a vehicle following too closely monitoring area provided in an embodiment of the present application;

[0056] Figure 7 A schematic diagram of a monitoring line configured with a gate in a closed state provided in an embodiment of the present application;

[0057] Figure 8 A schematic diagram of a gate control device provided in an embodiment of the present application;

[0058] Figure 9 A block diagram of a monocular camera in an all-in-one control machine provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field based on this application are within the scope of protection of this application.

[0060] In the vehicle entrance and exit scenario with a gate, it is necessary to capture the vehicles entering or leaving; Figure 1 As shown, currently, a snapshot camera 02 is usually set up at the entrance and exit scene. The snapshot camera 02 monitors a monitoring area 01 in front of the gate 03 and performs license plate recognition. The monitoring area 01 is about 2-5 meters in the vertical direction and about 4 meters in the horizontal direction.

[0061] Vehicles may generate abnormal events (such as reversing, turning back, staying, etc.) in the lane area of ​​the entrance and exit scene. The captured image of the snapshot camera is as follows: Figure 2 As shown, it can be seen that the field of view of the snapshot camera only includes part of the lane area before the entrance (or exit) gate and cannot cover the entire lane area; and the monocular camera can only monitor and identify vehicles, and cannot monitor and analyze abnormal events in the entire lane area, nor can it alarm for abnormal events. It is obvious that the control of the gate is not intelligent enough by relying solely on the license plate recognized by the snapshot camera.

[0062] like Figure 3As shown, the present application monitors the entire lane area through the integrated control machine 300. The captured image of the binocular camera includes part of the lane area before the gate in the entrance and exit scene, and part of the lane area after the gate ( Figure 3 The required field of view range of the entrance scene is given only as an example; the required field of view range of the exit scene is similar to that of the entrance scene).

[0063] At present, it is usually necessary to add an additional monitoring camera on the safety island in the entrance and exit scene to cover the lane area of ​​the entrance and exit scene and monitor and analyze abnormal events in the lane area. However, manual assistance is still needed for the monitoring and analysis of abnormal events. It can be seen that according to the existing method, there are many devices installed on the safety island in the entrance and exit scene, and manual assistance is required, the monitoring efficiency is low, and the control of the gate is not intelligent enough.

[0064] Based on this, the embodiments of the present application provide a barrier gate control method, device, integrated management and control machine and storage medium to improve the intelligence level of barrier gate control.

[0065] The following first introduces a gate control method provided by this application.

[0066] Among them, a gate control method provided in an embodiment of the present application can be applied to a monocular camera on the front of an integrated control machine. The integrated control machine is provided with a monocular camera on the front and a binocular camera on the side. That is, the integrated control machine can be an electronic device integrated with a monocular camera and a binocular camera for monitoring entrance and exit scenes. Compared with the situation where the monocular camera and the binocular camera are separated into two devices, it can save wiring or wireless communication configuration, etc. The monocular camera and the binocular camera in the integrated control machine can communicate quickly (the binocular camera can quickly report the detected abnormal events to the monocular camera); Figure 4 As shown, the integrated control and management machine provided in the embodiment of the present application includes a monocular camera A installed on the front and a binocular camera B installed on the side. The monocular camera is used to capture images for license plate recognition (its field of view can include the monitoring area in front of the barrier). The binocular camera's captured image is pre-calibrated with a polygonal detection area. The detection area includes the lane area located in front of the barrier and the lane area located behind the barrier. Abnormal events within the lane area indicated by the entire detection area are monitored and reported. The integrated control and management machine can also display prompts such as "Welcome" and "6000 parking spaces remaining."

[0067] In addition, the entrance and exit scenes involved in this application may be scenes including one-way exits and / or entrances, or scenes including two-way entrance and exit scenes (in the two-way entrance and exit scenes, it is necessary to set up an integrated control machine in the exit direction and the entrance direction respectively; or, the integrated control machine includes two monocular cameras and a binocular camera, and the field of view of the two monocular cameras includes the monitoring area in the exit direction and the monitoring area in the entrance direction respectively). This application does not limit this. The so-called monitoring area in front of the barrier is the area required for vehicle identification in order to pass through the barrier when the vehicle is traveling in the current direction of traffic.

[0068] It should be noted that the binocular camera can monitor various abnormal events in the lane area indicated by the detection area. Abnormal events may include: reversing, turning back, staying, occupying the lane, fake license plate, following too close, congestion, abnormal gate status, etc. The binocular camera can also count the number of vehicles traveling in the lane area indicated by the detection area, etc. This application does not limit this. Among the various abnormal events, there may be some types of abnormal events that affect the control method of the gate by the monocular camera of the integrated management and control machine.

[0069] In addition, the barrier gate control method provided in the embodiment of the present application can be applied to any entrance and exit scene with a barrier gate, such as parking lots, community entrances and exits, etc., and this application does not limit this. In addition, it should be noted that the above-mentioned monocular camera and binocular camera are set on different sides of the body of the control and management all-in-one machine: the monocular camera is located on the front and the binocular camera is located on the side; for the control and management all-in-one machine, the front side of the body is the side that can face the vehicle before the vehicle drives to the barrier gate; Figure 4 As shown, for the integrated management and control machine, the side that displays prompt information such as "Welcome" and "6000 parking spaces remaining" is the front side of the integrated management and control machine.

[0070] The executor of a barrier gate control method provided in an embodiment of the present application may be a barrier gate control device, which may be functional software or a functional module provided in a monocular camera. The monocular camera may control the barrier gate in combination with the monitoring results (abnormal events) of the binocular camera.

[0071] An embodiment of the present application provides a barrier gate control method, which is applied to a monocular camera disposed on the front of an integrated control and management machine, the integrated control and management machine also including a binocular camera disposed on the side, the monocular camera being used to capture images of vehicles that contact a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, the detection area including a portion of the lane area located in front of the barrier gate and a portion of the lane area located behind the barrier gate; the trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area, the designated edge being the edge that the vehicle first contacts when entering; the method comprising:

[0072] Acquiring each abnormal event reported by the binocular camera and the time of occurrence of each abnormal event; the binocular camera is used to monitor abnormal events in the lane area indicated by the detection area and report the monitored abnormal events;

[0073] In response to the license plate recognition result obtained by analysis, an initial control mode for the barrier gate is determined based on the license plate recognition result;

[0074] If the initial control mode is to open the gate, based on the currently acquired occurrence time of the abnormal event, analyzing whether there is currently an abnormal event in the lane area indicated by the detection area;

[0075] If so, based on the currently existing abnormal event, the initial control mode is modified to obtain a target control mode, and the gate is controlled based on the target control mode; and if not, the gate is controlled based on the initial control mode;

[0076] The target control method is a control method for dealing with existing abnormal events.

[0077] The barrier gate control method provided in an embodiment of the present application is applied to a monocular camera installed on the front of an integrated control and management machine, and the integrated control and management machine also includes a binocular camera installed on the side. The monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition. A polygonal detection area is pre-marked in the binocular camera's captured image. The detection area includes a portion of the lane area located in front of the barrier gate and a portion of the lane area located behind the barrier gate. The trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area. The designated edge is the edge that the vehicle first contacts when entering. If the monocular camera analyzes and obtains a license plate recognition result, an initial control mode for the barrier gate is determined based on the license plate recognition result. If the initial control mode of the barrier gate determined based on the license plate recognition result of the monocular camera is to open the barrier gate, the present application does not directly open the barrier gate. Instead, based on the occurrence time of the abnormal event reported by the binocular camera, the method analyzes whether an abnormal event currently exists in the lane area indicated by the detection area. If an abnormal event exists, the initial control mode is modified based on the current abnormal event to address the existing abnormal event. If no abnormal event exists, the barrier gate can be directly controlled based on the initial control mode. It can be seen that the present application can improve the intelligence level of gate control. In addition, the binocular camera is used to monitor the lane area indicated by the detection area for abnormal events and report the detected abnormal events. By setting the lane area included in the detection area and the position relationship with the trigger line, the vehicle entry process can be fully monitored, reducing the missed detection of abnormal events and further improving the intelligence level of gate control.

[0078] The following is an illustrative introduction to a gate control method provided in an embodiment of the present application in conjunction with the accompanying drawings.

[0079] like Figure 5 As shown, an embodiment of the present application provides a barrier gate control method, which is applied to a monocular camera arranged on the front of an integrated control machine, and the integrated control machine also includes a binocular camera arranged on the side. The monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, and the detection area includes a partial lane area located in front of the barrier gate and a partial lane area located behind the barrier gate. The trigger line is located in the detection area and is at least a predetermined distance from a specified edge of the detection area, and the specified edge is the edge that the vehicle first contacts when entering. The method may include the following steps:

[0080] S501: Acquire each abnormal event reported by the binocular camera and the occurrence time of each abnormal event;

[0081] The binocular camera is used to monitor abnormal events in the lane area indicated by the detection area and report the abnormal events detected;

[0082] In this application, a polygonal detection area is pre-marked in the acquisition picture of the binocular camera arranged on the side of the control and management integrated machine. The detection area includes part of the lane area in front of the barrier and part of the lane area behind the barrier. The binocular camera can monitor abnormal events in the lane area indicated by the detection area and report the monitored abnormal events; among them, the binocular camera can monitor abnormal events such as reversing, turning back, detention, occupying the lane, fake license plate, following too close, congestion, abnormal barrier status, etc. The specific monitoring method will be introduced in subsequent embodiments and will not be repeated here.

[0083] It should be noted that the binocular camera can report the abnormal events detected in real time. The monocular camera that can be received by the integrated management and control machine can obtain the various abnormal events reported by the binocular camera and the time when each abnormal event occurred, so that the monocular camera can subsequently control the gate and improve the intelligence level of the gate control.

[0084] In addition, the polygon of the boundary of the detection area in the acquisition picture of the binocular camera is drawn based on the lane area before and after the barrier, and can be a polygon detection area manually calibrated; or, the lane area and barrier in the acquisition picture of the binocular camera are identified, and the lane area before and after the barrier is determined to be included is automatically calibrated. This application does not limit the calibration method and shape of the detection area.

[0085] It should be emphasized that the binocular camera in this application has a pre-marked polygonal detection area in the captured image. The binocular camera can monitor and report abnormal events in the lane area indicated by the detection area. The detection area includes the partial lane area in front of the barrier and the partial lane area behind the barrier. In order to fully monitor the vehicle's entry process, the trigger line can be located within the detection area (the trigger line is located in the partial lane area in front of the barrier so that the vehicle can be identified before passing through the barrier), and the distance between the trigger line and the designated edge that the vehicle first contacts when entering is not less than a predetermined distance (for example, the distance of a parking space), that is, the binocular camera can fully monitor the process of the vehicle moving from the designated edge to the trigger line. Without considering the complete monitoring of the vehicle's entry process, the trigger line can also coincide with the designated edge.

[0086] S502: In response to the license plate recognition result obtained by analysis, determining an initial control mode for the gate based on the license plate recognition result;

[0087] A preset trigger line is marked within the field of view of the monocular camera. When the monocular camera detects that a vehicle has touched the trigger line, it captures an image for license plate recognition. (The so-called contact refers to the vehicle touching the trigger line in the image captured by the monocular camera, not necessarily actual contact with the trigger line). After the monocular camera analyzes the captured image and obtains the license plate recognition result, it can determine the initial control method for the gate based on the license plate recognition result.

[0088] The initial control method for the barrier gate varies in different entrance and exit scenarios. For example, at a parking lot entrance and exit, it is not necessary to determine whether the vehicle represented by the license plate has permission to enter the parking lot; the vehicle can enter by simply identifying the license plate. In other words, in a parking lot, the initial control method for the barrier gate may be to open the barrier gate. At a residential entrance and exit, it is necessary to determine whether the vehicle represented by the license plate has permission to enter the residential area and to identify whether the license plate has permission to enter the residential area. If so, the initial control method for the barrier gate may be to open the barrier gate; otherwise, the initial control method for the barrier gate may be to keep the barrier gate closed.

[0089] It should be noted that this application does not limit the execution order of step S501 and step S502. Step S502 can also be executed first, then step S501, or step S501 and step S502 can be executed at the same time.

[0090] S503: If the initial control mode is to open the gate, based on the currently acquired occurrence time of the abnormal event, analyzing whether there is currently an abnormal event in the lane area indicated by the detection area;

[0091] When the initial control mode is to open the barrier, this application does not open the barrier directly, but analyzes whether there is an abnormal event in the lane area indicated by the detection area based on the occurrence time of the abnormal event currently obtained, so as to correct the control mode of the barrier when an abnormal event occurs, thereby improving the intelligence level of the barrier control.

[0092] Exemplarily, in one implementation, analyzing whether an abnormal event currently occurs in the lane area indicated by the detection area based on the currently acquired occurrence time of the abnormal event includes:

[0093] From the abnormal events currently obtained, determine whether there is an abnormal event whose time difference between the occurrence time and the current time is less than a predetermined time threshold; if so, determine that an abnormal event currently exists in the lane area indicated by the detection area; otherwise, determine that no abnormal event currently exists in the lane area indicated by the detection area.

[0094] The monocular camera can determine from the abnormal events currently obtained whether there is an abnormal event whose time difference between the occurrence time and the current time is less than a predetermined time threshold, thereby determining whether there is an abnormal event in the lane area indicated by the detection area; wherein the predetermined time threshold can be flexibly adjusted based on the actual scenario, for example: 1S; this application does not limit this.

[0095] It can be seen that in this application, the monocular camera can accurately analyze whether there is an abnormal event in the lane area indicated by the detection area based on the occurrence time of the abnormal event reported by the binocular camera and combined with the predetermined time threshold, so as to accurately control the barrier and improve the intelligence level of the barrier control.

[0096] S504: If yes, based on the currently existing abnormal event, modify the initial control mode to obtain a target control mode, and control the gate based on the target control mode; and if no, control the gate based on the initial control mode;

[0097] The target control method is a control method for dealing with existing abnormal events.

[0098] If it is identified that an abnormal event currently exists in the lane area indicated by the detection area, the barrier gate needs to be controlled to deal with the abnormal event; that is, the application can modify the initial control method based on the current abnormal event (different abnormal events require different ways of modifying the initial control method), obtain the target control method for dealing with the existing abnormal event, and control the barrier gate based on the target control method; if there is no abnormal event, the barrier gate can be directly controlled based on the initial control method.

[0099] For example, in one implementation, if an abnormal event occurs, the target control mode can be to keep the gate closed or perform abnormal recovery. That is, if an abnormal event occurs, the gate cannot be opened according to the initial control mode, and the gate can be kept closed or abnormal recovery can be performed. The specific implementation of modifying the initial control mode to obtain the target control mode will be detailed in subsequent embodiments in conjunction with specific abnormal events and is not detailed here.

[0100] It should be noted that the initial control mode can also be to keep the barrier closed. Normally, when an abnormal event is identified, such as a fake license plate, following a vehicle too close, or congestion, the initial control mode is corrected, and the resulting target control mode is also to keep the barrier closed. This application does not elaborate on the correction when the initial control mode is to keep the barrier closed.

[0101] The binocular camera can also identify and report emergency events in the lane area indicated by the detection area and the time of the emergency event. If the initial control method is to keep the gate closed, if an emergency event is detected based on the content reported by the binocular camera, the initial control method can be modified based on the current emergency event to obtain a designated control method, and the gate can be controlled based on the designated control method. For example, the emergency event may be the identification of an emergency rescue vehicle, such as an ambulance, fire truck, or emergency rescue vehicle. In this case, the initial control method of keeping the gate closed can be modified to obtain a designated control method of opening the gate.

[0102] It can be seen that this application can identify abnormal events and emergency events in entrance and exit scenarios, and control the gate based on abnormal events and emergency events to respond to abnormal events and emergency events, thereby improving the intelligence level of gate control.

[0103] In the technical solution of this application, the acquisition, storage, use, processing, transmission, provision and disclosure of various abnormal events, the time of occurrence of abnormal events, license plate recognition results, etc. are all carried out with the user's authorization.

[0104] The barrier gate control method provided in an embodiment of the present application is applied to a monocular camera installed on the front of an integrated control and management machine, and the integrated control and management machine also includes a binocular camera installed on the side. The monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition. A polygonal detection area is pre-marked in the binocular camera's captured image. The detection area includes a portion of the lane area located in front of the barrier gate and a portion of the lane area located behind the barrier gate. The trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area. The designated edge is the edge that the vehicle first contacts when entering. If the monocular camera analyzes and obtains a license plate recognition result, an initial control mode for the barrier gate is determined based on the license plate recognition result. If the initial control mode of the barrier gate determined based on the license plate recognition result of the monocular camera is to open the barrier gate, the present application does not directly open the barrier gate. Instead, based on the occurrence time of the abnormal event reported by the binocular camera, the method analyzes whether an abnormal event currently exists in the lane area indicated by the detection area. If an abnormal event exists, the initial control mode is modified according to the current abnormal event to address the existing abnormal event. If no abnormal event exists, the barrier gate can be directly controlled based on the initial control mode. It can be seen that the present application can improve the intelligence level of gate control. In addition, the binocular camera is used to monitor the lane area indicated by the detection area for abnormal events and report the detected abnormal events. By setting the lane area included in the detection area and the position relationship with the trigger line, the vehicle entry process can be fully monitored, reducing the missed detection of abnormal events, and further improving the intelligence level of gate control.

[0105] Optionally, in another embodiment of the present application, the abnormal event monitoring includes monitoring one or more of the following events:

[0106] Monitoring of abnormal lane status events, abnormal vehicle status events, and abnormal gate status events;

[0107] The lane state abnormality event includes: a vehicle following too closely event in the lane area before the barrier, and / or a congestion event in the lane area entered after passing through the barrier;

[0108] The abnormal vehicle status event includes a fake license plate event.

[0109] In the present application, the binocular camera can monitor and report abnormal events in the lane area indicated by the detection area. The abnormal event monitoring may include one or more of the following: monitoring of abnormal lane status events, monitoring of abnormal vehicle status events, and monitoring of abnormal gate status events; that is, the binocular camera can monitor events such as abnormal lane status, abnormal vehicle status, and abnormal gate status in the lane area indicated by the detection area.

[0110] Lane status abnormalities may include events of following vehicles too closely in the lane area before the barrier, and / or congestion events in the lane area entered after passing through the barrier; vehicle status abnormalities include fake license plate events, which can be understood as events where a license plate exists but no real vehicle exists, such as: license plates photographed by mobile phones, license plates of toy cars, license plates printed on paper or acrylic boards, license plates held by people, etc.

[0111] It should be noted that the abnormal events in this application may include abnormal events that affect the control mode of the barrier gate, as well as abnormal events that do not affect the control mode of the barrier gate; the abnormal events exemplified above are abnormal events that affect the control mode of the barrier gate, and the binocular camera can also identify abnormal events such as turning back, reversing, staying, occupying the road, etc. and report them, and the integrated management and control machine can alarm, etc.; and the binocular camera can also count the vehicles passing through the barrier gate, etc., so that the integrated management and control machine can display the number of vehicles passing through the barrier gate (or display the number of remaining parking spaces, etc.).

[0112] Exemplarily, in one implementation, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0113] When the current abnormal event is a congestion event, the initial control mode is changed to a mode for keeping the gate closed and outputting a first alarm message through the integrated management and control machine to obtain a target control mode; wherein, the first alarm message is information for indicating that congestion has occurred and instructing to wait.

[0114] If the current abnormal event is a congestion event, that is, a congestion event within the lane area entered after passing through the barrier, the number of vehicles entering the barrier should be controlled. The initial control mode can be changed to keep the barrier closed, and the control and management integrated machine outputs a first alarm message indicating that congestion has occurred and instructing to wait, thereby obtaining a target control mode. It can be seen that this application can modify the initial control mode for congestion events, prevent vehicles from continuing to pass through the barrier, and issue an alarm to cope with the congestion event.

[0115] Adaptively, the method further comprises:

[0116] Obtaining a notification of eliminating the abnormal event detected by the binocular camera;

[0117] In the case where the current abnormal event is a congestion event, after the step of controlling the barrier gate based on the target control method, if a notification of elimination of the current abnormal event is obtained, the barrier gate is controlled to open for the vehicle indicated by the license plate recognition result.

[0118] For congestion events, this application can also obtain the elimination notification of the monitored congestion event reported by the binocular camera, that is, after monitoring the congestion event and controlling the barrier gate based on the target control method of the congestion event, the binocular camera can monitor the elimination of the congestion event and report the elimination notification of the congestion event; the monocular camera can target the vehicle indicated by the license plate recognition result, and if the vehicle can pass through the barrier gate (that is, it has the authority to pass through the barrier gate), it can control the barrier gate to open so that the vehicle can pass through the barrier gate normally.

[0119] It can be seen that this application can intelligently control the gate to eliminate the congestion event; and after the congestion event is eliminated, the gate is intelligently controlled to open so that vehicles can pass through the gate normally.

[0120] Exemplarily, in another implementation, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0121] When the current abnormal event is a fake license plate event, the initial control mode is changed to a mode for keeping the gate closed and outputting a second alarm message through the integrated management and control machine to obtain a target control mode; wherein, the second alarm message is information for indicating that the current license plate is a fake license plate.

[0122] If the current abnormal event is a fake license plate event, that is, the binocular camera does not detect the presence of a real vehicle, but the license plate is present, and the vehicle with the license plate cannot enter the gate, the initial control mode can be changed to keep the gate closed, and the control and management integrated machine outputs a second alarm message indicating that the current license plate is a fake license plate, thereby obtaining the target control mode. As can be seen, this application can modify the initial control mode for fake license plate events, prevent vehicles with fake license plates from passing through the gate, and issue an alarm to deal with fake license plate events.

[0123] For example, in another implementation, the initial control mode is modified based on the currently existing abnormal event to obtain the target control mode, including:

[0124] In the case where the currently existing abnormal event is a vehicle following too closely event, the initial control mode is changed to a mode for opening the barrier and extending the duration of the barrier being in the open state to obtain a target control mode.

[0125] In the case where the current abnormal event is a following-too-close event, that is, the vehicle in the lane area in front of the barrier is following too closely, the monocular camera may not be able to recognize the license plate of the rear vehicle in the following-too-close event. The binocular camera can supplement the license plate of the rear vehicle. If the vehicle represented by the license plate of the rear vehicle has the authority to pass through the barrier, the barrier can be kept open; if the vehicle represented by the license plate of the rear vehicle does not have the authority to pass through the barrier, due to the following-too-close phenomenon, the rear vehicle may follow the front vehicle through the barrier. To ensure safety, the barrier can be kept open; that is, the initial control mode can be changed to a mode for opening the barrier, and the duration of the barrier being in the open state is extended to obtain the target control mode; that is, the target control mode is to keep the barrier open.

[0126] If the current abnormal event is a close following incident, the target control method may also include: outputting a third alarm message via the integrated control and management device, the third alarm message being used to indicate the current close following phenomenon, thereby reminding adjacent vehicles to maintain a safe distance. Thus, this application can modify the initial control method for close following incidents, ensuring that the following vehicle can safely pass through the gate, and issuing an alarm to address close following incidents.

[0127] Exemplarily, in another implementation, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0128] In the case where the currently existing abnormal event is a gate state abnormal event, the initial control mode is changed to a mode for performing abnormal recovery processing on the gate and opening the gate after the abnormal recovery processing, so as to obtain a target control mode.

[0129] If the current event is a barrier gate status abnormality event, the barrier gate must first be restored to its normal state before it can be opened. The initial control mode can be changed to restore the barrier gate to its normal state (for example, restarting the barrier gate) and then opening the barrier gate after the abnormality recovery process, thereby obtaining the target control mode. This application addresses barrier gate status abnormality events by modifying the initial control mode, performing abnormality recovery on the barrier gate, and then opening the barrier gate after the abnormality recovery process, ensuring that vehicles can pass through the barrier gate normally, in order to cope with barrier gate status abnormality events.

[0130] It can be seen that this application can flexibly change the initial control method for incidents of following vehicles too closely, congestion incidents, fake license plate incidents and abnormal gate status incidents to cope with existing abnormal events and improve the intelligence level of gate control.

[0131] Optionally, in another embodiment of the present application, the congestion event identification method includes:

[0132] Monitoring whether a boundary of a congestion monitoring area within the detection area overlaps with the vehicle; wherein the congestion monitoring area includes a portion of the lane area behind the gate;

[0133] If there is overlap, the congestion monitoring area is monitored to see whether it meets the congestion conditions. If the congestion conditions are met, a congestion event is identified. The congestion conditions include: the presence of adjacent vehicles separated by a number of pixels less than a target number of pixels; the target number of pixels is a specified proportion of the pixel outline of the target vehicle, and the target vehicle is a vehicle among the adjacent vehicles that is closer to the barrier.

[0134] When identifying congestion events, the binocular camera first monitors whether the boundary of the congestion monitoring area within the detection area overlaps with the vehicle. If there is overlap, it indicates that congestion may exist in the congestion monitoring area. The congestion monitoring area is further monitored to see whether the congestion condition of adjacent vehicles with the number of pixels between them being less than the target number of pixels is met. If so, a congestion event is identified.

[0135] Among them, the congestion monitoring area in this application includes the part of the lane area that needs to be entered after passing through the barrier; this application can pre-configure the congestion monitoring area of ​​the binocular camera, for example: manually drawing the boundary line of the congestion monitoring area, or, through the area recognition algorithm, identifying the part of the lane area located behind the barrier of the binocular camera, and using the identified calibration frame as the boundary line of the congestion monitoring area; the congestion monitoring area can be flexibly configured according to different entrance and exit scenarios, and this application does not limit this.

[0136] Moreover, the target pixel number in the present application is the number of pixels of a specified proportion of the pixel outline of the target vehicle, and the specified proportion can be 30%. The target vehicle is the vehicle among the adjacent vehicles that is closer to the barrier. Thus, for any pair of adjacent vehicles, the number of pixels of the specified proportion of the pixel outline of the vehicle among the adjacent vehicles that is closer to the barrier is used as the criterion for judging whether there is congestion. Accurate congestion identification can be performed on adjacent vehicles at different distances from the barrier in the congestion monitoring area, that is, congestion judgment is made for nearby adjacent vehicles according to the nearby pixel distance, and congestion judgment is made for distant adjacent vehicles according to the distant pixel distance. This enables accurate identification of congestion events in the congestion monitoring area within the detection area.

[0137] Optionally, in another embodiment of the present application, the method for identifying an abnormal gate status event includes:

[0138] Based on a pre-trained barrier gate state monitoring model, the current image currently captured by the binocular camera containing the barrier gate is recognized to obtain a recognition result of whether the barrier gate is in an open state or a closed state;

[0139] Based on the obtained recognition result of whether the barrier gate is in an open state or a closed state, and the target barrier gate state corresponding to the current image, it is determined whether the barrier gate is in an abnormal state. If so, an abnormal barrier gate state event is identified. The target barrier gate state corresponding to the current image is the state that the barrier gate needs to have when the current image represents the presence or absence of vehicle passage.

[0140] When the binocular camera identifies an abnormal barrier state event, it first identifies the current image containing the barrier captured by the binocular camera based on the pre-trained barrier state recognition model to obtain a recognition result of whether the barrier is in an open or closed state; then, based on the obtained recognition result and the state of the barrier corresponding to the current image, which represents the presence or absence of vehicles passing, it is determined whether the barrier is in an abnormal state. If so, that is, the barrier state is abnormal, then an abnormal barrier state event is recognized.

[0141] The present application can pre-train a barrier gate status monitoring model. For example, by using images captured by a binocular camera when there are vehicles passing and when there are no vehicles passing, a monitoring line is configured when the barrier gate is in a closed state (i.e., a monitoring line that represents the position of the barrier gate when the barrier gate is in a closed state). The barrier gate status monitoring model is trained by using images captured by the binocular camera when there are vehicles passing and when there are no vehicles passing with the monitoring line configured, and the trained barrier gate status monitoring model is stored locally in the binocular camera.

[0142] When identifying an abnormal barrier state event, the binocular camera uses a pre-trained barrier state monitoring model to identify the barrier state in the current image and determine whether the barrier is open or closed. Based on this recognition result and the target barrier state corresponding to the current image, the camera determines whether the barrier is in an abnormal state. For example, if the current image shows no vehicles passing through, and the pre-trained barrier state monitoring model indicates that the barrier is open, while the target barrier state corresponding to the current image is closed, the barrier is determined to be in an abnormal state (i.e., the barrier is open when no vehicles are passing through), and an abnormal barrier state event is identified. Another example: the current image shows a vehicle passing through, and the initial control method determined by the monocular camera based on the license plate recognition result of the current image is to open the barrier (that is, the vehicle has the authority to pass through the barrier), and the result obtained based on the barrier state monitoring model is that the barrier is in the closed state (the results obtained from images within a continuous period of time (such as 5 seconds, etc.) are all that the barrier is in the closed state, that is, the barrier is continuously closed for a period of time); the target barrier state corresponding to the current image is open, then it is determined that the barrier is in an abnormal state (that is, when there is a vehicle that can pass through the barrier, the barrier is continuously closed), and an abnormal barrier state event is identified.

[0143] The present application can identify the status of the barrier gate in the current image based on a pre-trained barrier gate status monitoring model. According to the identification results and in combination with the target barrier gate status corresponding to the current image, it can accurately identify whether there is an abnormal barrier gate status event, so as to accurately and intelligently control the barrier gate in the event of an abnormal barrier gate status event.

[0144] The gate control method provided in this application is introduced below in conjunction with another embodiment.

[0145] This application provides an entrance and exit panoramic stitching capture device (i.e., a control and management all-in-one machine), which can realize the capture and recognition of vehicles in the entrance and exit scenes, monitor various abnormal events in the lane area, and report them to the police; the control and management all-in-one machine is as follows: Figure 4 As shown in the figure, the device consists of three image sensors (a monocular camera and a binocular camera), including a monocular camera A installed on the front of the device, which is used to capture passing vehicles, recognize license plates, and control gates at entrances and exits; a binocular camera B installed on the side of the device is used to identify and alarm abnormal events in the lane area of ​​the entrance and exit scenes. Events that binocular camera B can identify include: following vehicles too close, congestion, occupying the lane, turning back, abnormal gate status, channel counting, fake license plates, etc.

[0146] Among them, for the incident of following the vehicle too closely, such as Figure 6 As shown, a polygonal area is demarcated as the vehicle following too closely monitoring area 610. Based on the object segmentation algorithm and the object monitoring algorithm (the specific algorithm can be similar to the existing technology and will not be described in detail here), the vehicles passing through the entrance and exit scenes are segmented and monitored. If there are multiple vehicle objects in the vehicle following too closely monitoring area at the same time (for example, the vehicle following too closely monitoring area includes the front of the front vehicle and the rear of the rear vehicle), it is determined that there is a vehicle following too closely event and reported. Among them, the integrated control machine 640 monitors the entire scene; the polygonal detection area 600 in the acquisition picture of the binocular camera in this application is as shown Figure 6 The dotted area shown in the figure, the detection area 600 includes the partial lane area located in front of the gate and the partial lane area located behind the gate. The too close following monitoring area 610 for the too close following event belongs to the partial lane area located in front of the gate. The too close following monitoring area 610 is a polygonal area and can be configured according to actual needs. In the case where the too close following monitoring area 610 is the partial lane area located in front of the gate, this application does not limit the position of the too close following monitoring area 610. In addition, Figure 6 As shown, the trigger line 630 may be located within the detection area 600 , and the distance between the trigger line 630 and the designated edge 620 that the vehicle first contacts when entering the detection area is not less than a predetermined distance.

[0147] For congestion events, a polygonal monitoring area is delineated as the congestion monitoring area. Based on the object segmentation algorithm, the vehicles passing through the entrance and exit scenes are segmented and monitored. If the left and right boundaries of the congestion monitoring area overlap with any vehicle, and the number of pixels between adjacent vehicles in the congestion monitoring area is less than the target number of pixels (30% of the number of pixels of the vehicle outline of the adjacent vehicle closer to the gate), then a congestion event is determined to exist in the entrance and exit scene.

[0148] For turnaround events, a polygonal monitoring area is delineated as the turnaround monitoring area, and the passing vehicles in the entrance and exit scenes are segmented and monitored based on the object segmentation algorithm. If a vehicle enters 50% of the turnaround monitoring area (this ratio can be set according to actual needs and is not limited) and then leaves the turnaround monitoring area in the opposite direction, a turnaround event is determined to have occurred.

[0149] For road-occupying incidents, a polygonal monitoring area is delineated as the road-occupying monitoring area. Based on the object segmentation algorithm and the object classification algorithm, various objects are segmented and monitored. If the same object is in the road-occupying monitoring area for a long time (continuous period of time, for example: 10s, 1min, etc.), it is determined that the object has a road-occupying incident; and based on the object classification algorithm, the object is classified into types such as motor vehicles, non-motor vehicles, pedestrians, etc., and a road-occupying alarm is output.

[0150] In case of abnormal gate status, the binocular camera trains the gate status monitoring model locally and generates the corresponding model file. Figure 7 As shown, for the scenario where the integrated control machine 700 detects the entire lane area, the present application can use the images collected by the binocular camera when there are vehicles passing and when there are no vehicles passing to configure the monitoring line ( Figure 7 ), the barrier gate status monitoring model is trained using the images captured by the binocular camera with and without the presence of a vehicle passing through it, and the trained barrier gate status monitoring model is stored locally in the binocular camera. When identifying an abnormal barrier gate status event, the pre-trained barrier gate status monitoring model is used to identify the barrier gate status of the current image to obtain an identification result of whether the barrier gate is in an open state or a closed state; then, based on the identification result and the target barrier gate status corresponding to the current image, it is determined whether the barrier gate is in an abnormal state. For example, when there is a vehicle passing through (the vehicle has the authority to pass through the barrier gate), the barrier gate continues to be in a non-lifting state (i.e., closed state) for a continuous period of time; or, when there is no vehicle passing through, the barrier gate continues to be in a lifting state (i.e., open state) for a continuous period of time, then it is determined that an abnormal barrier gate status event exists.

[0151] For channel counting, a polygonal monitoring area is delineated as the vehicle counting area. Vehicles are monitored and segmented based on the object segmentation algorithm, and vehicle targets are continuously monitored. When a vehicle crosses the center line of the vehicle counting area, it is judged as a vehicle entering or leaving (the vehicle can be judged to enter or leave based on the vehicle's direction of travel and the direction of travel of the current lane).

[0152] For fake license plate incidents, a polygonal monitoring area is delineated as the fake license plate monitoring area, and vehicles are monitored and segmented based on the object segmentation algorithm. When a vehicle is currently monitored to enter, the monocular camera recognizes the license plate, and the binocular camera performs auxiliary monitoring of fake license plates (or the binocular camera can monitor fake license plate incidents alone) to confirm whether there is a real vehicle. When the binocular camera detects that there is no real vehicle, it indicates that the current capture of the monocular camera is caused by a fake license plate, and it is determined that a fake license plate incident has occurred. The monocular camera of the integrated control machine does not open the gate for processing, that is, the gate is kept in the closed state.

[0153] Among them, the above-mentioned various monitoring areas can be adjusted according to actual conditions. The close following monitoring area belongs to the partial lane area before the barrier, the congestion monitoring area belongs to the partial lane area after the barrier, the turnaround monitoring area belongs to the partial lane area before the barrier or the partial lane area after the barrier, the lane occupation monitoring area belongs to the partial lane area before the barrier or the partial lane area after the barrier, the vehicle counting area belongs to the partial lane area in front of the barrier, and the fake license plate monitoring area belongs to the partial lane area before the barrier. This application does not limit this.

[0154] The barrier gate control method provided in the embodiments of the present application is applied to a monocular camera on the front of an integrated control and management machine, which also includes a binocular camera on the side. In addition to its snapshot function, the integrated control and management machine can also monitor and report abnormal events within the lane area of ​​the entrance and exit scenes. The integrated control and management machine can immediately intervene based on abnormal events, improving the intelligence of barrier gate control and lane traffic efficiency. Furthermore, the integrated control and management machine integrates multiple functions such as vehicle snapshot and event monitoring, reducing the need for redundant equipment on the safety islands of entrance and exit scenes.

[0155] Based on the above method embodiment, the embodiment of the present application also provides a barrier gate control device, which is applied to a monocular camera arranged on the front of the control and management integrated machine, and the control and management integrated machine also includes a binocular camera arranged on the side, and the monocular camera is used to capture images of vehicles that touch a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the capture image of the binocular camera, and the detection area includes a partial lane area located in front of the barrier gate and a partial lane area located behind the barrier gate. The trigger line is located in the detection area and is not less than a predetermined distance from a specified edge of the detection area. The specified edge is the edge that the vehicle first contacts when entering; Figure 8 As shown, the device includes:

[0156] An acquisition module 810 is configured to acquire each abnormal event reported by the binocular camera and the time of occurrence of each abnormal event; the binocular camera is configured to monitor the lane area indicated by the detection area for abnormal events and report the monitored abnormal events;

[0157] a determination module 820 for determining an initial control mode for the barrier gate based on the license plate recognition result obtained in response to the analysis;

[0158] An analysis module 830 is configured to analyze whether an abnormal event currently occurs in the lane area indicated by the detection area based on the currently acquired occurrence time of the abnormal event if the initial control mode is to open the barrier;

[0159] The control module 840 is configured to modify the initial control mode based on the currently existing abnormal event to obtain a target control mode, if any, and control the gate based on the target control mode; and, if no abnormal event exists, control the gate based on the initial control mode;

[0160] The target control method is a control method for dealing with existing abnormal events.

[0161] The barrier gate control device provided in an embodiment of the present application is applied to a monocular camera installed on the front of an integrated control and management machine, and the integrated control and management machine also includes a binocular camera installed on the side. The monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition. The binocular camera's captured image is pre-marked with a polygonal detection area. The detection area includes a portion of the lane area located in front of the barrier gate and a portion of the lane area located behind the barrier gate. The trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area. The designated edge is the edge that the vehicle first contacts when entering. If the monocular camera analyzes and obtains a license plate recognition result, an initial control mode for the barrier gate is determined based on the license plate recognition result. If the initial control mode of the barrier gate determined based on the license plate recognition result of the monocular camera is to open the barrier gate, the present application does not directly open the barrier gate. Instead, based on the occurrence time of the abnormal event reported by the binocular camera, it analyzes whether there is an abnormal event in the lane area indicated by the detection area. If an abnormal event exists, the initial control mode is modified according to the current abnormal event to address the existing abnormal event. If no abnormal event exists, the barrier gate can be directly controlled based on the initial control mode. It can be seen that the present application can improve the intelligence level of gate control. In addition, the binocular camera is used to monitor the lane area indicated by the detection area for abnormal events and report the detected abnormal events. By setting the lane area included in the detection area and the position relationship with the trigger line, the vehicle entry process can be fully monitored, reducing the missed detection of abnormal events, and further improving the intelligence level of gate control.

[0162] Optionally, the analysis module is specifically configured to:

[0163] From the abnormal events currently obtained, determine whether there is an abnormal event whose time difference between the occurrence time and the current time is less than a predetermined time threshold; if so, determine that an abnormal event currently exists in the lane area indicated by the detection area; otherwise, determine that no abnormal event currently exists in the lane area indicated by the detection area.

[0164] Optionally, the abnormal event monitoring includes monitoring of one or more of the following events:

[0165] Monitoring of abnormal lane status events, abnormal vehicle status events, and abnormal gate status events;

[0166] The lane state abnormality event includes: a vehicle following too closely event in the lane area before the barrier, and / or a congestion event in the lane area entered after passing through the barrier;

[0167] The abnormal vehicle status event includes a fake license plate event.

[0168] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0169] When the current abnormal event is a congestion event, the initial control mode is changed to a mode for keeping the gate closed and outputting a first alarm message through the integrated management and control machine to obtain a target control mode; wherein, the first alarm message is information for indicating that congestion has occurred and instructing to wait.

[0170] Optionally, the device further includes a congestion event elimination module, configured to:

[0171] Obtaining a notification of eliminating the abnormal event detected by the binocular camera;

[0172] In the case where the current abnormal event is a congestion event, after the step of controlling the barrier gate based on the target control method, if a notification of elimination of the current abnormal event is obtained, the barrier gate is controlled to open for the vehicle indicated by the license plate recognition result.

[0173] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0174] When the current abnormal event is a fake license plate event, the initial control mode is changed to a mode for keeping the gate closed and outputting a second alarm message through the integrated management and control machine to obtain a target control mode; wherein, the second alarm message is information for indicating that the current license plate is a fake license plate.

[0175] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0176] In the case where the currently existing abnormal event is a vehicle following too closely event, the initial control mode is changed to a mode for opening the barrier and extending the duration of the barrier being in the open state to obtain a target control mode.

[0177] Optionally, the modifying of the initial control mode based on the currently existing abnormal event to obtain the target control mode includes:

[0178] In the case where the currently existing abnormal event is a gate state abnormal event, the initial control mode is changed to a mode for performing abnormal recovery processing on the gate and opening the gate after the abnormal recovery processing, so as to obtain a target control mode.

[0179] Optionally, the congestion event identification method includes:

[0180] Monitoring whether a boundary of a congestion monitoring area within the detection area overlaps with the vehicle; wherein the congestion monitoring area includes a portion of the lane area behind the gate;

[0181] If there is overlap, the congestion monitoring area is monitored to see whether it meets the congestion conditions. If the congestion conditions are met, a congestion event is identified. The congestion conditions include: the presence of adjacent vehicles separated by a number of pixels less than a target number of pixels; the target number of pixels is a specified proportion of the pixel outline of the target vehicle, and the target vehicle is a vehicle among the adjacent vehicles that is closer to the barrier.

[0182] Optionally, the method for identifying an abnormal gate status event includes:

[0183] Based on a pre-trained barrier gate state monitoring model, the current image currently captured by the binocular camera containing the barrier gate is recognized to obtain a recognition result of whether the barrier gate is in an open state or a closed state;

[0184] Based on the obtained recognition result of whether the barrier gate is in an open state or a closed state, and the target barrier gate state corresponding to the current image, it is determined whether the barrier gate is in an abnormal state. If so, an abnormal barrier gate state event is identified. The target barrier gate state corresponding to the current image is the state that the barrier gate needs to have when the current image represents the presence or absence of vehicle passage.

[0185] The embodiment of the present application also provides an integrated management and control machine, which includes a monocular camera arranged on the front and a binocular camera arranged on the side, the monocular camera is used to capture images of vehicles that touch a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, and the detection area includes a partial lane area located in front of the barrier and a partial lane area located behind the barrier, the trigger line is located in the detection area and is not less than a predetermined distance from a specified edge of the detection area, and the specified edge is the edge that the vehicle first touches when entering; Figure 9 As shown, the monocular camera includes:

[0186] Memory 901, used for storing computer programs;

[0187] The processor 902 is used to implement any of the gate control methods when executing the program stored in the memory 901.

[0188] In addition, the above-mentioned integrated management and control machine may further include a communication bus and / or a communication interface, and the processor 902, the communication interface, and the memory 901 communicate with each other via the communication bus.

[0189] The communication bus mentioned in the electronic devices mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into address buses, data buses, control buses, etc. For ease of illustration, only a single thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0190] The communication interface is used for communication between the above electronic device and other devices.

[0191] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0192] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0193] In another embodiment provided in the present application, a computer-readable storage medium is further provided, in which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned gate control methods are implemented.

[0194] In another embodiment provided in the present application, a computer program product comprising instructions is also provided, which, when executed on a computer, enables the computer to execute any of the barrier gate control methods in the above embodiments.

[0195] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be magnetic media (e.g., floppy disk, hard disk, tape), optical media (e.g., DVD), or solid-state drive (SSD).

[0196] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0197] Each embodiment in this specification is described in a related manner. Similar portions between the various embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. In particular, the device and integrated control machine embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0198] The above description is only a preferred embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application are included in the scope of protection of the present application.

Claims

1. A gate control method, characterized in that: The method is applied to a monocular camera arranged on the front of the integrated control machine, the integrated control machine also including a binocular camera arranged on the side, the monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition; a polygonal detection area is pre-marked in the captured image of the binocular camera, the detection area includes a partial lane area located in front of the barrier and a partial lane area located behind the barrier, the trigger line is located within the detection area and is at least a predetermined distance from a specified edge of the detection area, the specified edge being the edge that the vehicle first contacts when entering; the method includes: Acquiring each abnormal event reported by the binocular camera and the time of occurrence of each abnormal event; the binocular camera is used to monitor abnormal events in the lane area indicated by the detection area and report the monitored abnormal events; In response to the license plate recognition result obtained by analysis, an initial control mode for the barrier gate is determined based on the license plate recognition result; If the initial control mode is to open the gate, based on the currently acquired occurrence time of the abnormal event, analyzing whether there is currently an abnormal event in the lane area indicated by the detection area; If so, based on the currently existing abnormal event, the initial control mode is modified to obtain a target control mode, and the gate is controlled based on the target control mode; and if not, the gate is controlled based on the initial control mode; The target control method is a control method for dealing with existing abnormal events.

2. The method according to claim 1, characterized in that The analyzing whether an abnormal event currently occurs in the lane area indicated by the detection area based on the currently acquired occurrence time of the abnormal event includes: From the abnormal events currently obtained, determine whether there is an abnormal event whose time difference between the occurrence time and the current time is less than a predetermined time threshold; if so, determine that an abnormal event currently exists in the lane area indicated by the detection area; otherwise, determine that no abnormal event currently exists in the lane area indicated by the detection area.

3. The method according to claim 1, characterized in that The abnormal event monitoring includes monitoring of one or more of the following events: Monitoring of abnormal lane status events, abnormal vehicle status events, and abnormal gate status events; The lane state abnormality event includes: a vehicle following too closely event in the lane area before the barrier, and / or a congestion event in the lane area entered after passing through the barrier; The abnormal vehicle status event includes a fake license plate event.

4. The method according to claim 3, characterized in that The initial control mode is modified based on the currently existing abnormal event to obtain the target control mode, including: When the current abnormal event is a congestion event, the initial control mode is changed to a mode for keeping the gate closed and outputting a first alarm message through the integrated management and control machine to obtain a target control mode; wherein, the first alarm message is information for indicating that congestion has occurred and instructing to wait.

5. The method according to claim 4, characterized in that The method further comprises: Obtaining a notification of eliminating the abnormal event detected by the binocular camera; In the case where the current abnormal event is a congestion event, after the step of controlling the barrier gate based on the target control method, if a notification of elimination of the current abnormal event is obtained, the barrier gate is controlled to open for the vehicle indicated by the license plate recognition result.

6. The method according to claim 3, characterized in that The initial control mode is modified based on the currently existing abnormal event to obtain the target control mode, including: When the current abnormal event is a fake license plate event, the initial control mode is changed to a mode for keeping the gate closed and outputting a second alarm message through the integrated management and control machine to obtain a target control mode; wherein, the second alarm message is information for indicating that the current license plate is a fake license plate.

7. The method according to claim 3, characterized in that The initial control mode is modified based on the currently existing abnormal event to obtain the target control mode, including: In the case where the currently existing abnormal event is a vehicle following too closely event, the initial control mode is changed to a mode for opening the barrier and extending the duration of the barrier being in the open state to obtain a target control mode.

8. The method according to claim 3, characterized in that The initial control mode is modified based on the currently existing abnormal event to obtain the target control mode, including: In the case where the currently existing abnormal event is a gate state abnormal event, the initial control mode is changed to a mode for performing abnormal recovery processing on the gate and opening the gate after the abnormal recovery processing, so as to obtain a target control mode.

9. The method according to claim 3, characterized in that The congestion event identification method includes: Monitoring whether a boundary of a congestion monitoring area within the detection area overlaps with the vehicle; wherein the congestion monitoring area includes a portion of the lane area behind the gate; If there is overlap, the congestion monitoring area is monitored to see whether it meets the congestion conditions. If the congestion conditions are met, a congestion event is identified. The congestion conditions include: the presence of adjacent vehicles separated by a number of pixels less than a target number of pixels; the target number of pixels is a specified proportion of the pixel outline of the target vehicle, and the target vehicle is a vehicle among the adjacent vehicles that is closer to the barrier.

10. The method according to claim 3, characterized in that The method for identifying abnormal gate status events includes: Based on a pre-trained barrier gate state monitoring model, the current image currently captured by the binocular camera containing the barrier gate is recognized to obtain a recognition result of whether the barrier gate is in an open state or a closed state; Based on the obtained recognition result of whether the barrier gate is in an open state or a closed state, and the target barrier gate state corresponding to the current image, it is determined whether the barrier gate is in an abnormal state. If so, an abnormal barrier gate state event is identified. The target barrier gate state corresponding to the current image is the state that the barrier gate needs to have when the current image represents the presence or absence of vehicle passage.

11. A gate control device, characterized in that: The monocular camera is used to be arranged on the front of the integrated control machine, and the integrated control machine also includes a binocular camera arranged on the side. The monocular camera is used to capture images of vehicles that contact a preset trigger line for license plate recognition. A polygonal detection area is pre-marked in the captured image of the binocular camera. The detection area includes a partial lane area located in front of the barrier and a partial lane area located behind the barrier. The trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area. The designated edge is the edge that the vehicle first contacts when entering. The device includes: an acquisition module, configured to acquire each abnormal event reported by the binocular camera and the time of occurrence of each abnormal event; the binocular camera is configured to monitor the lane area indicated by the detection area for abnormal events and report the monitored abnormal events; a determination module, configured to determine an initial control mode for the barrier gate based on the license plate recognition result obtained in response to the analysis; an analysis module configured to analyze whether an abnormal event currently occurs in the lane area indicated by the detection area based on the currently acquired occurrence time of the abnormal event if the initial control mode is to open the barrier; a control module configured to, if any, modify the initial control mode based on the currently existing abnormal event to obtain a target control mode, and control the barrier gate based on the target control mode; and, if no abnormal event exists, control the barrier gate based on the initial control mode; The target control method is a control method for dealing with existing abnormal events.

12. A management and control all-in-one machine, characterized in that: The integrated control machine includes a monocular camera arranged on the front and a binocular camera arranged on the side. The monocular camera is used to capture images of vehicles that touch a preset trigger line for license plate recognition. A polygonal detection area is pre-marked in the captured image of the binocular camera. The detection area includes a partial lane area located in front of the barrier and a partial lane area located behind the barrier. The trigger line is located within the detection area and is at least a predetermined distance from a designated edge of the detection area. The designated edge is the edge that the vehicle first touches when entering. The monocular camera includes: Memory for storing computer programs; A processor, configured to implement the method according to any one of claims 1 to 10 when executing a program stored in a memory.

13. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images