Vehicle behavior monitoring method and device and storage medium

Abstract

The invention discloses a vehicle behavior monitoring method and device and a storage medium. The method comprises the steps that a first monitoring video collected by a multi-view camera is acquired; if a first recognition result of the first vehicle is recognized in the first monitoring video, a second monitoring video corresponding to the first vehicle and collected by a multi-view camera is obtained, and the second monitoring video comprises videos of a gate rod front area and a gate rod rear area of the channel; performing authentication release on the first vehicle based on the first identification result; and based on the second monitoring video, behavior analysis is carried out on the first vehicle, and a corresponding behavior processing flow is executed. According to the invention, the multi-view camera is installed on the channel of the entrance and exit, and the multi-view camera can monitor the monitoring videos of the area in front of the gate rod and the area behind the gate rod of the channel, so that the first vehicle is identified and the behavior of the first vehicle is analyzed according to the monitoring videos, and the corresponding behavior processing flow is executed. Manual analysis processing is not needed, and the management efficiency of the parking lot is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle management, and in particular to a vehicle behavior monitoring method, device and storage medium. Background Art

[0002] A control machine is usually provided in the management system used in current parking lots, and the vehicle recognition camera installed on the current control machine is a single recognition camera, which is usually set in the direction facing the oncoming vehicle. Due to the limited field of view of a single camera, the control machine with a single camera can only complete the function of vehicle recognition, resulting in the existing control machine having a relatively simple function, and being unable to recognize many abnormal behaviors in the parking lot, which can only be handled manually. This situation seriously affects the management efficiency of the parking lot. Summary of the invention

[0003] Based on this, it is necessary to provide a vehicle behavior monitoring method, device and storage medium for the above technical problems to solve at least one of the above technical problems.

[0004] The present invention provides a vehicle behavior monitoring method, comprising:

[0005] Obtaining a first surveillance video collected by a multi-camera;

[0006] If a first recognition result of a first vehicle is recognized in the first monitoring video, a second monitoring video corresponding to the first vehicle collected by the multi-view camera is obtained, wherein the second monitoring video includes a video of an area in front of a gate bar and an area behind a gate bar of the passage;

[0007] Authenticating and releasing the first vehicle based on the first recognition result;

[0008] Based on the second monitoring video, a behavior analysis is performed on the first vehicle, and a corresponding behavior processing flow is executed.

[0009] Optionally, according to a vehicle behavior monitoring method provided by the present invention, the second monitoring video is also used to analyze the gate lever state;

[0010] The gate bar state analysis includes: identifying a gate bar position and / or a gate bar area in the second monitoring video;

[0011] Determine whether the gate lever has fallen to a preset position according to the gate lever position, and generate an alarm notification if it has not fallen to a preset position;

[0012] Determine whether the gate rod is intact according to the gate rod area, and generate an alarm notification if it is not intact.

[0013] Optionally, according to a vehicle behavior monitoring method provided by the present invention, the executing corresponding behavior processing flow further includes:

[0014] identifying an area where the first vehicle is currently located;

[0015] When the current area overlaps with the gate rod drop area, the gate rod is controlled to be prohibited from dropping;

[0016] When the current area does not overlap with the gate rod lowering area, the gate rod is controlled to lower.

[0017] Optionally, according to a vehicle behavior monitoring method provided by the present invention, the executing corresponding behavior processing flow further includes:

[0018] Identifying the driving trajectory of the first vehicle and determining whether the direction of the first vehicle is consistent with that of the lane;

[0019] If they are consistent, it means driving in the forward direction and the forward traffic processing flow is started;

[0020] If there is inconsistency, it means driving in the reverse direction and the reverse traffic processing flow will be initiated.

[0021] Optionally, according to a vehicle behavior monitoring method provided by the present invention, the forward traffic processing process includes: at least one of a vehicle gate-passing detection process, a vehicle following detection process, a congestion detection process and a traffic abnormality detection process;

[0022] The reverse traffic processing process includes: at least one of a reversing detection process and a reverse traffic detection process.

[0023] Optionally, according to a vehicle behavior monitoring method provided by the present invention, when the traffic control device associated with the multi-camera is an entrance control device;

[0024] The authenticating and releasing the first vehicle based on the first recognition result includes:

[0025] Saving the first recognition result and recording the entry time of the first vehicle;

[0026] The performing behavior analysis on the first vehicle based on the second monitoring video and executing a corresponding behavior processing flow includes:

[0027] A first rear end recognition result of the first vehicle is identified, and the first rear end recognition result is matched with the first recognition result, and when they are inconsistent, the first recognition result is replaced with the first rear end recognition result.

[0028] Optionally, according to a vehicle behavior monitoring method provided by the present invention, before identifying the first rear end recognition result of the first vehicle, the method further includes:

[0029] Start the vehicle gate detection process;

[0030] If the vehicle fails to pass the gate, the first recognition result and the entry time of the first vehicle are deleted;

[0031] When passing through the gate, a first rear end recognition result of the first vehicle is recognized.

[0032] Optionally, according to a vehicle behavior monitoring method provided by the present invention, when the traffic control device associated with the multi-camera is an exit control device;

[0033] The authenticating and releasing the first vehicle based on the first recognition result includes:

[0034] Performing exit authentication on the first vehicle according to the first recognition result;

[0035] If the authentication fails, the first vehicle is re-identified based on the second monitoring video, and the first vehicle is authenticated for exit based on the secondary identification result.

[0036] The present invention also provides a vehicle behavior monitoring device, comprising:

[0037] An acquisition module is used to acquire a first surveillance video collected by a multi-eye camera;

[0038] an identification module, configured to obtain a second monitoring video corresponding to the first vehicle captured by the multi-view camera if a first identification result of the first vehicle is identified in the first monitoring video, wherein the second monitoring video includes a video of an area in front of a gate bar and an area behind a gate bar of the passage;

[0039] an authentication module, configured to authenticate and release the first vehicle based on the first recognition result;

[0040] An analysis module is used to perform behavior analysis on the first vehicle based on the second monitoring video and execute a corresponding behavior processing flow.

[0041] The present invention also provides a computer device, comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-mentioned vehicle behavior monitoring method when executing the computer-readable instructions.

[0042] The present invention also provides one or more readable storage media storing computer-readable instructions, and the computer-readable instructions implement the above-mentioned vehicle behavior monitoring method when executed by a processor.

[0043] The above-mentioned vehicle behavior monitoring method, device and storage medium include: obtaining a first monitoring video collected by a multi-eye camera; if a first recognition result of a first vehicle is recognized in the first monitoring video, then obtaining a second monitoring video corresponding to the first vehicle collected by the multi-eye camera, wherein the second monitoring video includes videos of the area before the gate bar and the area after the gate bar of the passage; authenticating and releasing the first vehicle based on the first recognition result; and analyzing the behavior of the first vehicle based on the second monitoring video, and executing a corresponding behavior processing flow. The present invention installs a multi-eye camera on the passage at the entrance and exit, and the multi-eye camera can monitor and obtain monitoring videos of the first vehicle in the area before the gate bar and the area after the gate bar of the passage, and can identify the first vehicle and analyze the passing behavior of the first vehicle based on the monitoring video, thereby executing a corresponding behavior processing flow without the need for manual analysis and processing, and effectively improving the management efficiency of the parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0045] Figure 1 It is one of the flow charts of the vehicle behavior monitoring method in one embodiment of the present invention;

[0046] Figure 2 This is a second flow chart of a vehicle behavior monitoring method according to an embodiment of the present invention;

[0047] Figure 3 This is a third flow chart of a vehicle behavior monitoring method according to an embodiment of the present invention;

[0048] Figure 4 is a structural schematic diagram of a vehicle behavior monitoring device in one embodiment of the present invention;

[0049] Figure 5 is a schematic diagram of a computer device in one embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] The terms used in one or more embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of the present invention. The singular forms of "a", "said" and "the" used in one or more embodiments of the present invention are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of the present invention refers to and includes any or all possible combinations of one or more associated listed items.

[0052] It should be noted that multi-eye cameras include but are not limited to binocular cameras and trinocular cameras, which are imaging devices that have multiple cameras at the same time and the multiple cameras are independent of each other and can work together. For the sake of convenience, the embodiments of this application are all explained by taking binocular cameras as an example. It can be understood that the same solution can still be applied to trinocular cameras or even devices with more cameras.

[0053] In one embodiment, if Figure 1 As shown, Figure 1 FIG. 1 is a flow chart of a vehicle behavior monitoring method in an embodiment of the present invention. The present invention provides a vehicle behavior monitoring method, comprising the following steps:

[0054] Step S11, obtaining a first monitoring video captured by a binocular camera;

[0055] It should be noted that the binocular camera includes two independent cameras. In one embodiment, the binocular camera can be integrated into the control machine of the barrier gate. In other embodiments, the binocular camera can be separately set on the passage of the parking lot exit or entrance and communicated with the control machine.

[0056] In one embodiment, the recognition range of the binocular black light camera can be adjusted according to the lane of the parking lot entrance to obtain the best recognition effect, wherein the monitoring field of the binocular camera includes the area in front of the gate bar and the area behind the gate bar of the passage, that is, the binocular camera can continuously collect monitoring videos of the entire process from the entrance to the gate, thereby realizing full-scene monitoring of the passage. In one embodiment, the binocular camera is set as a binocular black light camera. Even under extremely low light conditions, the black light camera can still clearly capture the image on the lane, ensuring that the binocular camera can clearly obtain relevant information about the vehicle at night or in an environment with insufficient light, without the need for night supplementary lighting debugging of the control machine.

[0057] It can be understood that the vehicle behavior monitoring method provided by the embodiment of the present invention can be applied to the exit of a parking lot, and can also be applied to the entrance of a parking lot.

[0058] Step S12, if a first recognition result of the first vehicle is recognized in the first monitoring video, a second monitoring video corresponding to the first vehicle captured by the binocular camera is obtained;

[0059] In one embodiment, after obtaining the first monitoring video collected by the binocular camera, the first monitoring video is subjected to vehicle identification; if the vehicle is not identified, the first monitoring video is deleted. If the first identification result of the first vehicle is identified, it proves that the first vehicle is driving into the monitoring area of ​​the binocular camera, wherein the first identification result includes identification results such as license plate information, vehicle type, vehicle color and vehicle driving direction, and then the second monitoring video corresponding to the first vehicle collected by the binocular camera is obtained, and the second monitoring video includes the video of the area before the gate bar and the area after the gate bar of the passage, so that the whole process from driving into the monitoring area of ​​the binocular camera to driving out of the monitoring area can be monitored. It can be understood that the binocular camera reports the first monitoring video to the control machine, and if the first identification result of the first vehicle is identified in the first monitoring video, the long recording function is activated to obtain the second monitoring video of the first vehicle in the area before the gate bar and the area after the gate bar, and optionally, the first monitoring video is merged with the monitoring video collected later. In addition, in one embodiment, a maximum recording time is set. If the first vehicle is still identified as being in the monitoring area of ​​the binocular camera after the maximum recording time, it proves that the first vehicle is in a stranded state. The reason for the stranded state may be vehicle failure, channel congestion, gate lever abnormality, etc., and then an alarm is issued for the management personnel to check the channel condition or equipment condition. It can be understood that the first vehicle in this application can be any car, and the first vehicle does not represent only one car. In some cases of queuing and following cars, the first vehicle can also include multiple cars. When the first vehicle includes multiple cars, each car is authenticated, released, and analyzed for behavior.

[0060] Step S13, authenticating and releasing the first vehicle based on the first recognition result;

[0061] In one embodiment, after the first recognition result is identified, authentication can be performed on whether the first vehicle has the right to pass based on the first recognition result. If the authentication is passed, the vehicle can be released, and if the authentication fails, the vehicle will not be released. Therefore, the authentication and release in this application includes two situations: release if the authentication is passed, and refusal to release if the authentication fails.

[0062] In one embodiment, when the access control device associated with the binocular camera is an entrance control device, after identifying the first recognition result of the first vehicle, the first recognition result is saved, the entry time of the first vehicle is recorded, and then the first vehicle is allowed to enter.

[0063] In one embodiment, when the access control device associated with the binocular camera is an exit control device; based on the first recognition result, the first vehicle is authenticated for exit; if the authentication passes, the first vehicle is directly allowed to exit; if the authentication fails, the first vehicle is secondary identified based on the second monitoring video, and the first vehicle is authenticated for exit based on the secondary recognition result, thereby improving the accuracy of vehicle authentication.

[0064] Step S14: Based on the second monitoring video, a behavior analysis is performed on the first vehicle, and a corresponding behavior processing flow is executed.

[0065] In one embodiment, based on the second monitoring video, the behavior of the first vehicle is analyzed to obtain the driving trajectory of the first vehicle; according to the driving trajectory, it is determined whether the direction of the first vehicle is consistent with that of the lane; if they are consistent, it is proved that the first vehicle is traveling in the forward direction, and then the forward passage processing flow is started; if they are inconsistent, it is proved that the first vehicle is traveling in the reverse direction, and then the reverse passage processing flow is started. Among them, each behavior processing flow is specifically described in the following embodiments and will not be repeated here.

[0066] In another embodiment, based on the second monitoring video, the first vehicle is analyzed to determine the current area of ​​the first vehicle; if the area where the vehicle is located overlaps with the gate bar lowering area of ​​the gate bar, that is, the first vehicle is in a position where the gate bar is about to be lowered, the gate bar is prohibited from being lowered to prevent the vehicle from being blocked by the gate bar or colliding. If the area where the vehicle is located does not overlap with the gate bar lowering area, that is, the first vehicle is not in the area where the gate bar is about to be lowered, the gate bar is allowed to be lowered so that the gate bar is lowered normally. It can be understood that after the first identification result of the first vehicle is authenticated, the gate bar will be controlled to lift and release it. After the authentication is passed, it will not start to detect whether the current area of ​​the vehicle overlaps with the gate bar lowering area until a period of time has passed or the movement of the car is detected, thereby reserving preparation time for the car to start passing; when the first vehicle leaves the gate bar lowering area, that is, the current area of ​​the first vehicle does not overlap with the gate bar lowering area, it is necessary to control the gate bar to drop in time, wherein the situation where the first vehicle and the current area do not overlap with the gate bar lowering area includes but is not limited to, the vehicle passes normally and leaves the gate bar lowering area and the vehicle reverses and leaves the gate bar lowering area; when the first vehicle includes multiple vehicles and the following vehicle has a following vehicle passing behavior, when the area where the first vehicle is located overlaps with the gate bar lowering area, it is still necessary to control the gate bar to prohibit dropping until the area where the first vehicle is located does not overlap with the gate bar lowering area, then control the gate bar to drop, and then start the following vehicle passing processing flow.

[0067] In another embodiment, since the binocular camera can identify the entire process of the first vehicle in the area in front of the gate bar and the area behind the gate bar in the channel, in order to improve the accuracy of vehicle identification, the first rear identification result of the first vehicle is identified based on the second monitoring video, wherein the first rear identification result includes the rear license plate information, vehicle type and vehicle color of the first vehicle, and then the first rear identification result is matched with the first identification result. If there is inconsistency, the first identification result is directly replaced with the first rear identification result. It should be noted that the matching of the rear identification result with the first identification result is only applicable to cars that simultaneously identify the front identification result and the rear identification result. When the first vehicle includes multiple cars and there is a following car that makes it impossible to identify the rear result of the front car, the process is not started, or when the front identification result of the rear car cannot be identified, the rear identification result of the rear car can be used as the identification result of the rear car.

[0068] The embodiment of the present invention, through the above scheme, includes: obtaining a first monitoring video collected by a binocular camera; if a first recognition result of the first vehicle is recognized in the first monitoring video, then obtaining a second monitoring video corresponding to the first vehicle collected by the binocular camera, wherein the second monitoring video includes videos of the area before the gate bar and the area after the gate bar of the passage; authenticating and releasing the first vehicle based on the first recognition result; and analyzing the behavior of the first vehicle based on the second monitoring video, and executing a corresponding behavior processing flow. The embodiment of the present invention installs a binocular camera on the passage at the entrance and exit, and the binocular camera can monitor and obtain monitoring videos of the first vehicle in the area before the gate bar and the area after the gate bar of the passage. The first vehicle can be identified and the passing behavior of the first vehicle can be analyzed based on the monitoring video, thereby executing a corresponding behavior processing flow without the need for manual analysis and processing, and effectively improving the management efficiency of the parking lot.

[0069] In one embodiment of the present invention, the second monitoring video is also used to perform gate rod status analysis; the gate rod status analysis includes: identifying the gate rod position and / or gate rod area in the second monitoring video; determining whether the gate rod has fallen to a preset position based on the gate rod position, and generating an alarm notification if not; determining whether the gate rod is intact based on the gate rod area, and generating an alarm notification if not.

[0070] In one embodiment, the gate rod position of the gate rod is obtained based on the second monitoring video recognition, and whether the gate rod has fallen to a preset position is determined based on the gate rod position of the gate rod. The preset position refers to the position when the gate rod is fully closed. If it has not fallen to the preset position, it proves that an abnormal event such as a gate rod failure has occurred, and an alarm notification is generated.

[0071] In one embodiment, a gate rod area of ​​the gate rod in the second monitoring video is identified, where the gate rod area refers to an area including the entire gate rod shape. Further, the integrity of the gate rod is detected in the gate rod area, and if part of the gate rod is missing in the gate rod area, an alarm notification is generated.

[0072] The embodiment of the present invention, through the above-mentioned scheme, realizes identifying the gate position and / or gate area of ​​the gate rod according to the second monitoring video, and analyzing the gate state according to the gate position and / or gate area of ​​the gate rod, which can monitor and promptly discover the abnormal situation of the gate rod in real time, thereby reducing the situation of channel congestion caused by gate rod failure.

[0073] Figure 2 FIG. 2 is a flow chart of a vehicle behavior monitoring method according to an embodiment of the present invention. Figure 2 As shown, in one embodiment of the present invention, executing the corresponding behavior processing flow also includes:

[0074] Step S21, identifying the driving track of the first vehicle and determining whether the direction of the first vehicle is consistent with the lane;

[0075] Step S22: if the two are consistent, it is forward travel, and the forward travel processing flow is started;

[0076] Step S23: if there is inconsistency, it is reverse driving, and the reverse traffic processing flow is started.

[0077] In one embodiment, the driving trajectory of the first vehicle is identified based on the second monitoring video, and whether the driving direction of the first vehicle is consistent with the direction of the lane is determined based on the driving trajectory. If they are consistent, it proves that the first vehicle is traveling in the forward direction, and then the forward traffic processing flow is started; if they are inconsistent, it proves that the first vehicle is traveling in the reverse direction, and then the reverse traffic processing flow is started.

[0078] It should be noted that the forward traffic processing flow includes vehicle gate-passing detection flow, vehicle following detection flow, congestion detection flow and traffic abnormality detection flow; the reverse traffic processing flow includes reversing detection flow and reverse detection flow. Among them, the vehicle gate-passing detection process refers to the detection process for detecting whether the first vehicle drives through the gate area; the vehicle following detection process refers to the detection process for detecting whether the first vehicle follows the front vehicle in and out of the gate; the congestion detection process refers to the detection process for detecting whether there is vehicle congestion on the channel, for example, judging whether the channel is congested according to the number of vehicles on the lane or the length of time the first vehicle is detained; the abnormal traffic detection process refers to the detection process for detecting whether the first vehicle has abnormal traffic behavior, wherein the abnormal traffic behavior includes abnormal behaviors such as the first vehicle being detained due to a fault, a vehicle collision, and the presence of foreign objects in the channel causing the first vehicle to be detained; the reversing detection process refers to the processing process for detecting whether the first vehicle has a reversing behavior, for example, determining whether the first vehicle has a reversing behavior based on the position change of the first vehicle in continuous frames; the reverse detection process refers to the processing process for detecting whether the first vehicle has a reverse behavior; for example, determining whether the first vehicle has a reverse behavior based on the driving direction or the front direction of the first vehicle.

[0079] Through the above scheme, the embodiment of the present invention realizes identifying the driving trajectory of the first vehicle according to the second monitoring video, executing the corresponding behavior processing flow according to the driving trajectory, and effectively improving the management level of the parking lot.

[0080] Figure 3 FIG. 3 is a flow chart of a vehicle behavior monitoring method according to an embodiment of the present invention. Figure 3 As shown, in one embodiment of the present invention, executing the corresponding behavior processing flow also includes:

[0081] Step S31, identifying the area where the first vehicle is currently located;

[0082] Step S32, when the current area overlaps with the gate bar falling area, controlling the gate bar to prohibit the gate bar from falling;

[0083] Step S33, when the current area does not overlap with the gate rod lowering area, control the gate rod to lower.

[0084] In one embodiment, based on the second monitoring video, the current area of ​​the first vehicle is identified, and it is determined whether the current area overlaps with the gate bar dropping area of ​​the gate bar. When the current area overlaps with the gate bar dropping area, it proves that the first vehicle is at risk of being hit by the gate bar, and then the gate bar is controlled to prohibit dropping; when the current area does not overlap with the gate bar dropping area, the gate bar is directly controlled to drop.

[0085] The embodiment of the present invention uses the above scheme to determine whether the current area of ​​the first vehicle overlaps with the gate bar falling area of ​​the gate bar, and controls whether the gate bar falls according to the judgment result, which can effectively prevent the gate bar from falling above the vehicle and avoid damage to the vehicle and personnel.

[0086] In one embodiment of the present invention, when the access control device associated with the binocular camera is an entrance control device; authenticating and releasing the first vehicle based on the first recognition result includes:

[0087] Saving the first recognition result and recording the entry time of the first vehicle;

[0088] Based on the second monitoring video, the first vehicle is subjected to behavior analysis, and a corresponding behavior processing flow is executed, including:

[0089] A first rear end recognition result of the first vehicle is identified, and the first rear end recognition result is matched with the first recognition result, and when they are inconsistent, the first recognition result is replaced with the first rear end recognition result.

[0090] In one embodiment, when the access control device associated with the binocular camera is an entrance control device: after identifying the first recognition result of the first vehicle, the first vehicle is allowed to enter. In addition, the first recognition result of the first vehicle is saved, and the entry time of the first vehicle is recorded.

[0091] In order to improve the accuracy of vehicle identification, in other embodiments, a first rear end identification result of the first vehicle is identified based on the second monitoring video, wherein the first rear end identification result includes characteristic information such as the rear license plate information, vehicle color and vehicle type of the first vehicle, and then the first rear end identification result is matched with the first identification result. If they are inconsistent, the first identification result is directly replaced by the first rear end identification result.

[0092] It should be noted that before identifying the first rear end recognition result of the first vehicle, the vehicle gate detection process needs to be started; when it is detected that the first vehicle has not passed the gate, it proves that the first vehicle has not driven into the venue, and the first recognition result and entry time of the first vehicle are deleted. When it is detected that the first vehicle has driven into the venue, the first rear end recognition result of the first vehicle is identified.

[0093] Through the above solution, the embodiment of the present invention realizes that when the first tail recognition result does not match the first recognition result, the first recognition result of the first vehicle is corrected based on the first tail recognition result, thereby effectively improving the accuracy of vehicle license plate recognition.

[0094] In one embodiment of the present invention, authenticating and releasing the first vehicle based on the first recognition result includes:

[0095] Performing exit authentication on the first vehicle according to the first recognition result;

[0096] If the authentication fails, a second identification is performed on the first vehicle according to the second monitoring video, and an exit authentication is performed on the first vehicle according to the result of the second identification.

[0097] In one embodiment, when the access control device associated with the binocular camera is an exit control device: according to the first recognition result, the first vehicle is authenticated for exit. For example, according to the entry time in the first recognition result, the parking fee is determined and pushed to the owner of the first vehicle for payment. If the payment success notification is not received, it is determined that the first vehicle authentication has not passed, and then the first vehicle is re-identified according to the second monitoring video, and then the first vehicle is authenticated for exit again according to the secondary recognition result. In addition, if the exit authentication fails, the first vehicle is prohibited from exiting the lot.

[0098] The embodiment of the present invention realizes exit authentication of the first vehicle based on the first recognition result through the above scheme. When the initial exit authentication fails, the first vehicle can be authenticated again based on the secondary recognition result identified by the second monitoring video, thereby improving the accuracy of authentication, reducing the waiting time of the vehicle at the entrance and exit, and improving the user experience.

[0099] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0100] In one embodiment, a vehicle behavior monitoring device is provided, which corresponds one-to-one to the vehicle behavior monitoring method in the above embodiment. Figure 4 As shown, Figure 4 : is a schematic diagram of a structure of a vehicle behavior monitoring device in one embodiment of the present invention, the vehicle behavior monitoring device comprises:

[0101] An acquisition module 41 is used to acquire a first surveillance video captured by a binocular camera;

[0102] The recognition module 42 is used to obtain a second monitoring video corresponding to the first vehicle captured by the binocular camera if a first recognition result of the first vehicle is recognized in the first monitoring video, wherein the second monitoring video includes a video of the area in front of the gate bar and the area behind the gate bar of the passage;

[0103] An authentication module 43, configured to authenticate and release the first vehicle based on the first recognition result;

[0104] The analysis module 44 is used to perform behavior analysis on the first vehicle based on the second monitoring video and execute a corresponding behavior processing flow.

[0105] The vehicle behavior monitoring device also includes:

[0106] The second monitoring video is also used for gate lever status analysis;

[0107] The gate bar state analysis includes: identifying the gate bar position and / or gate bar area in the second monitoring video;

[0108] A first determination module is used to determine whether the gate rod has fallen to a preset position according to the gate rod position, and generate an alarm notification if it is not;

[0109] The second determination module is used to determine whether the gate rod is intact according to the gate rod area, and generate an alarm notification if it is not.

[0110] The analysis module 44 is also used to:

[0111] identifying an area where the first vehicle is currently located;

[0112] When the current area overlaps with the gate bar drop area, the gate bar is controlled to be prohibited from dropping;

[0113] When the current area does not overlap with the gate rod lowering area, the gate rod is controlled to drop.

[0114] The analysis module 44 is also used to:

[0115] Identify the driving track of the first vehicle and determine whether the direction of the first vehicle is consistent with the lane;

[0116] If they are consistent, it means driving in the forward direction and the forward traffic processing flow is started;

[0117] If there is inconsistency, it means driving in the reverse direction and the reverse traffic processing flow will be initiated.

[0118] The forward traffic processing process includes at least one of the following: vehicle gate detection process, vehicle following detection process, congestion detection process and traffic abnormality detection process;

[0119] The reverse traffic processing flow includes: at least one of a reversing detection flow and a reverse traffic detection flow.

[0120] The authentication module 43 is also used for:

[0121] When the access control device associated with the binocular camera is an entrance control device:

[0122] The first recognition result is saved, and the entry time of the first vehicle is recorded.

[0123] The analysis module 44 is also used to:

[0124] A first rear end recognition result of the first vehicle is identified, and the first rear end recognition result is matched with the first recognition result, and when they are inconsistent, the first recognition result is replaced with the first rear end recognition result.

[0125] The vehicle behavior monitoring device also includes:

[0126] A start module is used to start the vehicle gate detection process;

[0127] A deletion module, used to delete the first recognition result and the entry time of the first vehicle when the vehicle has not passed the gate;

[0128] The rear end recognition result recognition module is used to recognize a first rear end recognition result of a first vehicle when passing through a gate.

[0129] The authentication module 43 is also used for:

[0130] When the access control device associated with the binocular camera is an exit control device:

[0131] Performing exit authentication on the first vehicle according to the first recognition result;

[0132] If the authentication fails, a second identification is performed on the first vehicle according to the second monitoring video, and an exit authentication is performed on the first vehicle according to the result of the second identification.

[0133] For the specific definition of the vehicle behavior monitoring device, please refer to the definition of the vehicle behavior monitoring method above, which will not be repeated here. Each module in the above-mentioned vehicle behavior monitoring device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0134] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, Figure 5 : is a schematic diagram of a computer device in one embodiment of the present invention. The computer device includes a processor, a memory, a network interface and a database connected by a device bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium and an internal memory. The readable storage medium stores operating computer-readable instructions and a database. The internal memory provides an environment for the operation of the operating device and computer-readable instructions in the readable storage medium. The database of the computer device is used to store data involved in the vehicle behavior monitoring method. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a vehicle behavior monitoring method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0135] In one embodiment, a computer device is provided. The computer device may be a terminal device, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory, and a network interface connected through a device bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a readable storage medium. The readable storage medium stores computer-readable instructions. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer-readable instructions are executed by the processor, a vehicle behavior monitoring method is implemented. The readable storage medium provided in this embodiment includes a non-volatile readable storage medium and a volatile readable storage medium.

[0136] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and the processor implements the steps of the vehicle behavior monitoring method described above when executing the computer-readable instructions.

[0137] In one embodiment, a readable storage medium is provided, the readable storage medium stores computer-readable instructions, and the computer-readable instructions are executed by the processor to implement the steps of the vehicle behavior monitoring method as described above. A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through computer-readable instructions, and the computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When the computer-readable instructions are executed, they may include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0138] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0139] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A vehicle behavior monitoring method, characterized in that: include: Obtaining a first surveillance video collected by a multi-camera; If a first recognition result of a first vehicle is recognized in the first monitoring video, a second monitoring video corresponding to the first vehicle collected by the multi-view camera is obtained, wherein the second monitoring video includes a video of an area in front of a gate bar and an area behind a gate bar of the passage; Authenticating and releasing the first vehicle based on the first recognition result; Based on the second monitoring video, a behavior analysis is performed on the first vehicle, and a corresponding behavior processing flow is executed.

2. The vehicle behavior monitoring method according to claim 1, characterized in that: The second monitoring video is also used to analyze the gate lever status; The gate bar state analysis includes: identifying a gate bar position and / or a gate bar area in the second monitoring video; Determine whether the gate lever has fallen to a preset position according to the gate lever position, and generate an alarm notification if it has not fallen to a preset position; Determine whether the gate rod is intact according to the gate rod area, and generate an alarm notification if it is not intact.

3. The vehicle behavior monitoring method according to claim 1, characterized in that: The execution of the corresponding behavior processing flow also includes: identifying an area where the first vehicle is currently located; When the current area overlaps with the gate rod drop area, the gate rod is controlled to be prohibited from dropping; When the current area does not overlap with the gate rod lowering area, the gate rod is controlled to lower.

4. The vehicle behavior monitoring method according to claim 1, characterized in that: The execution of the corresponding behavior processing flow also includes: Identifying the driving trajectory of the first vehicle and determining whether the direction of the first vehicle is consistent with that of the lane; If they are consistent, it means driving in the forward direction and the forward traffic processing flow is started; If there is inconsistency, it means driving in the reverse direction and the reverse traffic processing flow will be initiated.

5. The vehicle behavior monitoring method according to claim 4, characterized in that: The forward traffic processing process includes: at least one of a vehicle gate detection process, a vehicle following detection process, a congestion detection process and a traffic abnormality detection process; The reverse traffic processing process includes: at least one of a reversing detection process and a reverse traffic detection process.

6. The vehicle behavior monitoring method according to any one of claims 1 to 5, characterized in that: When the access control device associated with the multi-camera is an entrance control device; The authenticating and releasing the first vehicle based on the first recognition result includes: Saving the first recognition result and recording the entry time of the first vehicle; The performing behavior analysis on the first vehicle based on the second monitoring video and executing a corresponding behavior processing flow includes: A first rear end recognition result of the first vehicle is identified, and the first rear end recognition result is matched with the first recognition result, and when they are inconsistent, the first recognition result is replaced with the first rear end recognition result.

7. The vehicle behavior monitoring method according to claim 6, characterized in that: Before identifying the first rear end recognition result of the first vehicle, the method further includes: Start the vehicle gate detection process; If the vehicle fails to pass the gate, the first recognition result and the entry time of the first vehicle are deleted; When passing through the gate, a first rear end recognition result of the first vehicle is recognized.

8. The vehicle behavior monitoring method according to any one of claims 1 to 5, characterized in that: When the access control device associated with the multi-camera is an exit control device; The authenticating and releasing the first vehicle based on the first recognition result includes: Performing exit authentication on the first vehicle according to the first recognition result; If the authentication fails, the first vehicle is re-identified based on the second monitoring video, and the first vehicle is authenticated for exit based on the secondary identification result.

9. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executed on the processor, characterized in that: When the processor executes the computer-readable instructions, the vehicle behavior monitoring method according to any one of claims 1 to 8 is implemented.

10. A readable storage medium having computer readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, the vehicle behavior monitoring method according to any one of claims 1 to 8 is implemented.

Images