Parking lot entrance and exit recommendation method and device, medium, product and equipment

Abstract

The invention discloses a parking lot entrance and exit recommendation method and device, a medium, a product and equipment, and the method comprises the steps: obtaining the video data of a parking lot, and recognizing the state of each entrance and exit in the parking lot; determining a to-be-monitored vehicle corresponding to the non-unblocked entrance and exit based on the video data when determining that the non-unblocked entrance and exit exists in each entrance and exit according to the state of each entrance and exit, and determining the predicted passing time of the to-be-monitored vehicle leaving the parking lot through the non-unblocked entrance and exit; generating entrance and exit recommendation information of the parking lot based on the predicted passing time corresponding to each non-unblocked entrance and exit and the state of each entrance and exit; and the entrance and exit recommendation information is pushed to the target terminal, so that the entrance and exit recommendation information of the parking lot can be displayed in real time for a user to check and select, and the congestion rate of the entrance and exit of the parking lot is reduced.

Description

Technical Field

[0001] The present application relates to the field of data analysis technology, and in particular to a method, device, medium, product and equipment for recommending parking lot entrances and exits. Background Art

[0002] In the prior art, general parking lot management systems are usually designed with user parking management functions and user parking fee collection management functions. The general process is as follows: vehicle entry, when a vehicle enters the parking lot entrance, the camera or license plate recognition device will automatically identify the license plate number and record the vehicle entry time; vehicle exit, when the vehicle is about to leave the parking lot, the camera or license plate recognition device will automatically identify the license plate number again and record the vehicle exit time; vehicle payment, according to the parking lot's billing rules and rates, the system will automatically calculate the parking fee, and the user can choose to pay the toll collector in cash, or settle the payment through the electronic payment method supported by the system. Once the payment is completed, the system will record the relevant information and open the exit gate to allow the vehicle to leave the parking lot.

[0003] However, in the prior art, when a user exits the parking lot, they will randomly select an exit or select an exit within the parking lot according to their own habits. At this time, if the traffic volume at the exit is too large or an emergency causes the exit to be blocked, the user will not be able to perceive it in the first time, resulting in a long exit time and possibly aggravating the blockage of the exit, thereby causing a poor user experience and parking lot operation and guidance problems. Summary of the invention

[0004] In order to solve the above technical problems, the embodiments of the present application propose a parking lot entrance and exit recommendation method, device, medium, product and equipment, which can display the parking lot entrance and exit recommendation information in real time for users to view and select, thereby reducing the congestion rate of the parking lot entrance and exit.

[0005] In a first aspect, an embodiment of the present application provides a method for recommending a parking lot entrance and exit, comprising:

[0006] Acquire video data of a parking lot and identify the status of each entrance and exit of the parking lot;

[0007] When it is determined according to the states of the various entrances and exits that there is a non-smooth entrance and exit among the various entrances and exits, for the non-smooth entrance and exit, based on the video data, a vehicle to be monitored corresponding to the non-smooth entrance and exit is determined, and a predicted passage time for the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit is determined;

[0008] Generate entrance and exit recommendation information of the parking lot based on the predicted travel time corresponding to each of the non-unblocked entrances and exits and the status of each entrance and exit;

[0009] The entrance and exit recommendation information is pushed to the target terminal.

[0010] Further, the determining, based on the video data, the vehicle to be monitored corresponding to the non-unblocked entrance and exit includes:

[0011] Using a target detection algorithm, converting the appearance pictures of the objects to be identified corresponding to the non-unblocked entrances and exits in the video data into matching target vectors, and determining the prediction confidence of each of the target vectors;

[0012] For each of the target vectors, if the prediction confidence of the target vector is higher than a confidence threshold, the object to be identified that matches the target vector is determined as the vehicle to be monitored.

[0013] Further, based on the video data, determining the predicted travel time of the monitored vehicle to leave the parking lot via the non-unblocked entrance and exit includes:

[0014] Determine the passing position of the last vehicle based on the video data, wherein the last vehicle is a vehicle without a following vehicle among the vehicles to be monitored;

[0015] Based on the video data, calculating the time average speed of the vehicle to be monitored at the passing position;

[0016] Based on the time average speed and the travel section between the travel position and the non-smooth entrance and exit, the travel time of the last vehicle leaving the parking lot via the non-smooth entrance and exit is determined as the predicted travel time.

[0017] Furthermore, the determining of the travel time of the last vehicle to leave the parking lot via the non-smooth entrance and exit based on the time average speed and the travel section between the travel position and the non-smooth entrance and exit includes:

[0018] Constructing a Kalman state estimation model using the time average speed as a measurement variable and the road section density corresponding to the passable road section as a state variable;

[0019] The Kalman state estimation model is used to perform estimation to determine the travel time of the last vehicle.

[0020] Furthermore, the method further comprises:

[0021] Determine a time factor at a vehicle gate corresponding to the parking lot, wherein the time factor at the vehicle gate is used to indicate a single vehicle charging time corresponding to the parking lot;

[0022] The using the Kalman state estimation model to perform estimation to determine the passing time of the last vehicle includes:

[0023] According to the time factor at the vehicle gate, the travel time estimated by the Kalman state estimation model is corrected to obtain the travel time of the last vehicle.

[0024] Furthermore, the Kalman state estimation model is a model that does not consider at least one of the following: ramp vehicle merging and unmerging factors, traffic light cycle interval time in the road, and lane number model factor.

[0025] In a second aspect, an embodiment of the present application provides a parking lot entrance and exit recommendation device, comprising:

[0026] A state recognition module, used to obtain video data of the parking lot and identify the state of each entrance and exit in the parking lot;

[0027] A predicted passage time determination module is used for, when it is determined according to the status of each entrance and exit that there is a non-smooth entrance and exit among the various entrances and exits, determining, for the non-smooth entrance and exit, based on the video data, a vehicle to be monitored corresponding to the non-smooth entrance and exit, and determining a predicted passage time for the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit;

[0028] A recommendation information generation module, configured to generate the entrance and exit recommendation information of the parking lot based on the predicted travel time corresponding to each of the non-unblocked entrances and exits and the status of each entrance and exit;

[0029] The display module is used to push the entrance and exit recommendation information to the target terminal.

[0030] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods for recommending parking lot entrances and exits are implemented.

[0031] In a fourth aspect, an embodiment of the present application provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of any of the above-mentioned parking lot entrance and exit recommendation methods.

[0032] In a fifth aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the steps of any of the above-mentioned parking lot entrance and exit recommendation methods when executing the computer program.

[0033] In summary, the embodiments of the present application have at least the following beneficial effects:

[0034] According to the embodiment of the present application, the status of each entrance and exit in the parking lot is identified by acquiring video data of the parking lot; when it is determined that a non-smooth entrance and exit exists among the entrances and exits according to the status of the entrances and exits, the vehicle to be monitored corresponding to the non-smooth entrance and exit is determined based on the video data, and the predicted passage time of the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit is determined; based on the predicted passage time corresponding to each of the non-smooth entrances and exits and the status of the entrances and exits, entrance and exit recommendation information of the parking lot is generated; the entrance and exit recommendation information is pushed to the target terminal, so that the entrance and exit recommendation information of the parking lot can be displayed in real time for users to view and select, thereby reducing the congestion rate of the entrances and exits of the parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a flowchart of a parking lot entrance and exit recommendation method provided in an embodiment of the present application;

[0036] Figure 2 is a schematic diagram of a parking lot provided in an embodiment of the present application;

[0037] Figure 3 It is a schematic diagram of a parking lot entrance and exit recommendation provided in an embodiment of the present application;

[0038] Figure 4 It is a structural schematic diagram of a parking lot entrance and exit recommendation device provided in an embodiment of the present application;

[0039] Figure 5 It is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0041] In the description of the present application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, features defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more. In the description of the present application, the term "including" and its variations are open inclusions, i.e., "including but not limited to". The term "based on" means "at least partially based on". The term "according to" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments".

[0042] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0043] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in this application have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.

[0044] First, see Figure 1 , shows a schematic flow chart of a parking lot entrance and exit recommendation method provided in an embodiment of the present application, the method comprising steps S101-S104, which are as follows:

[0045] S101, acquiring video data of a parking lot and identifying the status of each entrance and exit of the parking lot;

[0046] It should be noted that the status of each entrance and exit can be divided into a smooth state and a blocked state. For example, the status of different entrances and exits can be judged based on the number of vehicles waiting to leave at different entrances and exits captured in the video corresponding to the video data.

[0047] S102, when it is determined according to the status of each entrance and exit that there is a non-smooth entrance and exit among the entrances and exits, for the non-smooth entrance and exit, based on the video data, the vehicle to be monitored corresponding to the non-smooth entrance and exit is determined, and the predicted passage time of the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit is determined; it can be understood that, among the entrances and exits, except for the non-smooth entrance and exit, all other entrances and exits are smooth entrances and exits.

[0048] It should be noted that the video data in this embodiment may include video data collected by video collection cameras located near each entrance and exit of the parking lot, wherein, see Figure 2 , the entrances and exits of the parking lot may refer to exit A and / or exit B, and the video acquisition camera may be correspondingly arranged at the camera installation position S around exit A and / or exit B. In this way, in some examples, whether the corresponding entrance and exit is a non-smooth entrance and exit can be determined by detecting whether there is a vehicle with a driving speed lower than a preset speed threshold in the video data collected by the video acquisition camera arranged near the entrances and exits of the parking lot, wherein the driving speed can be represented by the average speed of the vehicle in a preset time period, and here, the vehicle with a driving speed lower than the preset speed threshold can also be regarded as the vehicle to be monitored corresponding to the corresponding entrance and exit.

[0049] In one example, the time it takes for the monitored vehicle to travel from its current position to the corresponding non-unobstructed entrance or exit at its own driving speed can be used as the corresponding predicted travel time.

[0050] S103, generating entrance and exit recommendation information of the parking lot based on the predicted travel time corresponding to each of the non-unblocked entrances and exits and the status of each entrance and exit;

[0051] In one example, the entrance and exit recommendation information may only include: the predicted travel time corresponding to the non-smooth entrances and exits and the status of each entrance and exit, so that the status of each entrance and exit and the predicted travel time required for each non-smooth entrance and exit can be intuitively displayed to the user, thereby facilitating user decision-making.

[0052] In one example, generating the entrance and exit recommendation information of the parking lot may include:

[0053] Generate a recommendation list according to the status of each entrance and exit, wherein all unobstructed entrances and exits are displayed in a first color (e.g., green) in the recommendation list;

[0054] Arrange the non-smooth entrances and exits in ascending order of predicted travel time;

[0055] For each non-smooth entrance and exit after arrangement, the first 1 / m entrances and exits are configured with a first color (for example, green), the entrances and exits between 1 / m and 1 / M are configured with a second color (for example, yellow), and the entrances and exits after 1 / M are configured with a third color (for example, green). Then, each non-smooth entrance and exit is displayed in the recommendation list according to its configured color, where 1 / m is less than 1 / M.

[0056] Here are some examples:

[0057] All the smooth entrances and exits and the first 1 / 3 of the non-smooth entrances and exits can be configured as green, for example, represented by the set {AD E...};

[0058] 1 / 3 to 2 / 3 of the non-smooth entrances and exits are configured in yellow, for example, the set {B FG...} represents 1 / 3 to 2 / 3 of the entrances and exits;

[0059] The entrances and exits after 2 / 3 of the non-unblocked entrances and exits are configured in red, for example, the set {CG H...} represents the entrances and exits after 2 / 3.

[0060] In this embodiment, the unblocked entrances and exits can be assigned a color different from the blocked entrances and exits, so that users can distinguish and quickly find the unblocked entrances and exits. The unblocked entrances and exits can also be assigned a color that is the same as the first 1 / m of the blocked entrances and exits (arranged in ascending order of predicted travel time). In this case, since the predicted travel time of the first 1 / m of the entrances and exits is small enough, it can be considered that the entrance and exit has become unblocked after the user's vehicle arrives at the entrance and exit.

[0061] Optionally, the entrance and exit recommendation information is updated in real time. In this embodiment, if any of the entrances and exits recommended in the top 1 / m, such as Exit A, is updated from the top 1 / m to fall out of the top 1 / m, the user can be instructed to change other exits that are still in the top 1 / m.

[0062] S104: Push the entrance and exit recommendation information to the target terminal.

[0063] It should be noted that the entrance and exit recommendation information can be output to an indication screen provided in the parking lot, for example Figure 2 Indicator screen X shown. In addition, the entrance and exit recommendation information can also be displayed to a vehicle terminal located in the parking lot and having a need to leave the parking lot. The above-mentioned indicator screen and vehicle terminal are target terminals.

[0064] In combination with the above example, the entrance and exit recommendation information may be displayed by displaying each entrance and exit and its configured color.

[0065] In an optional implementation, determining the to-be-monitored vehicle corresponding to the non-unblocked entrance and exit based on the video data includes:

[0066] Using a target detection algorithm, converting the appearance pictures of the objects to be identified corresponding to the non-unblocked entrances and exits in the video data into matching target vectors, and determining the prediction confidence of each of the target vectors;

[0067] For each of the target vectors, if the prediction confidence of the target vector is higher than a confidence threshold, the object to be identified that matches the target vector is determined as the vehicle to be monitored.

[0068] In one example, the target detection algorithm may include the YOLO target monitoring algorithm; the appearance picture of the object to be identified may include the appearance of different types of vehicles, such as sedans, SUVs (Sport Utility Vehicle), minivans, etc.; the size of the target vector may be 7*7*30; the prediction confidence in YOLO may be obtained based on a pre-trained parking lot vehicle recognition model to eliminate other interference factors such as people and objects.

[0069] In an optional implementation, determining, based on the video data, a predicted travel time of the monitored vehicle to leave the parking lot via the non-unblocked entrance and exit includes:

[0070] Based on the video data, the passing position of the last vehicle is determined, wherein the last vehicle is a vehicle without a rear vehicle among the vehicles to be monitored; it should be understood that, see Figure 3 The last vehicle may refer to the last vehicle in any vehicle queue (ie, target chain), and the last vehicle will be added to the target chain for tracking.

[0071] Based on the video data, calculating the time average speed of the vehicle to be monitored at the passing position;

[0072] Based on the time average speed and the travel section between the travel position and the non-smooth entrance and exit, the travel time of the last vehicle leaving the parking lot via the non-smooth entrance and exit is determined as the predicted travel time.

[0073] In one example, the calculation of the time average speed may include: determining the speed of the vehicle to be monitored at the location of the passage based on the video data; calculating the time average speed based on the speed and the number of vehicles to be monitored, for example, the time average speed The calculation formula can be expressed as:

[0074]

[0075] in, is the speed of the i-th vehicle to be monitored at the passage position determined by the video data, and n is the number of vehicles to be monitored.

[0076] In one example, since the interval average speed is generally difficult to obtain, the interval average speed and the time average speed can be calculated in the following manner. At this time, the calculation of the time average speed can also include: calculating the interval average speed of the vehicle to be monitored at the passing position based on the video data; calculating the time average speed based on the interval average speed;

[0077] The average speed of the interval The calculation is expressed as:

[0078]

[0079] Where n is the number of vehicles to be monitored, u i is the speed of the i-th vehicle to be monitored determined by the video data, and L is the distance between the passing position of the last vehicle determined by the video data and the corresponding non-unblocked entrance and exit;

[0080] The time average speed is calculated based on the interval average speed, which may include the following calculation formula:

[0081]

[0082] in, is the time average speed, is the average speed of the interval, is the variance of the measurement error.

[0083] In one example, the travel time of the last vehicle can be represented by the average travel time of the road section where the last vehicle is located, for example, the average travel time of the road section It is expressed as:

[0084]

[0085] Where L is the distance between the last vehicle's passing position and the corresponding non-smooth entrance and exit. is the time average speed.

[0086] In an optional implementation, determining the travel time of the last vehicle to leave the parking lot via the non-smooth entrance / exit based on the time average speed and the travel section between the travel position and the non-smooth entrance / exit comprises:

[0087] Constructing a Kalman state estimation model using the time average speed as a measurement variable and the road section density corresponding to the passable road section as a state variable;

[0088] The Kalman state estimation model is used to estimate to determine the travel time of the last vehicle. In one example, the Kalman state estimation model is in discrete form and can be expressed as:

[0089] k(t)=Φ(t)k(t-1)+u(t)+w(t)

[0090] T(t)=H(t)k(t)+v(t)

[0091] Among them, Φ(t) is the state transfer matrix, H(t) is the measurement matrix, u(t) is the input control variable, k(t) is the road section density, t represents the tth estimation, w(t) is the state noise, v(t) is the measurement noise, T(t) represents the measurement variable of the road section travel time required to be estimated by the Kalman state estimation model, and the time average speed is T(t).

[0092] Because traffic demand in different environments and at different times is highly random, and there are also measurement errors during detection, there are state noise and measurement noise. At this time, assuming that the state noise and measurement noise are independent Gaussian white noise, the recursive calculation formula of the Kalman filter algorithm can be expressed as:

[0093] k(t|t-1)=Φ(t-1|t-1)k(t-1|t-1)

[0094] P(t|t-1)=Φ(t-1|t-1)P(t-1|t-1)Φ T (t-1|t-1)+Q

[0095] Wherein, Q is the system noise covariance, (t|t-1) represents the period from the t-1th time to the tth time, (t-1|t-1) represents the period from the t-1th time, and P is the prediction error covariance.

[0096] The filter coefficient K of the Kalman state estimation model can be expressed as:

[0097] K(t)=P(t|t-1)H T (t)[H(t)P(t|t-1)H T (t)+R] -1

[0098] Where R is the measurement noise covariance.

[0099] The state update equation of the Kalman state estimation model can be expressed as:

[0100]

[0101] P(t|t)=[1-K(t)H(t)]P(t|t-1)

[0102] in, Indicates the updated status.

[0103] Accordingly, in this embodiment, it is only necessary to give the initial k(0), the initial value of the error covariance P(0) and the real-time observed T(t) to obtain the optimal state estimate of the next k(t+1) and the estimated travel time T(t+1), which will not be repeated here.

[0104] In an optional embodiment, the method further includes:

[0105] Determine a time factor at a vehicle gate corresponding to the parking lot, wherein the time factor at the vehicle gate is used to indicate a single vehicle charging time corresponding to the parking lot;

[0106] The using the Kalman state estimation model to perform estimation to determine the passing time of the last vehicle includes:

[0107] According to the time factor at the vehicle gate, the travel time estimated by the Kalman state estimation model is corrected to obtain the travel time of the last vehicle.

[0108] In one example, the travel time estimated by the Kalman state estimation model may be corrected by the following formula:

[0109]

[0110] in, is the corrected travel time of the last vehicle, H(t) is the measurement matrix, represents the state of the Kalman state estimation model after the tth update, n is the number of vehicles to be monitored, t γ is the time factor at the vehicle gate.

[0111] It should be noted that the time factor at the vehicle gate in this embodiment can be determined by the average of the scanning time intervals of each vehicle in the parking lot, and the scanning time interval is the time interval from the start of scanning at the gate to the start of rising of the gate railing.

[0112] In this embodiment, parameters such as the time factor at the vehicle gate are specially set for the parking lot scenario, so that more accurate prediction and judgment can be made, making the corrected passage time more accurate.

[0113] In an optional implementation, the Kalman state estimation model is a model that does not consider at least one of the following: ramp vehicle merging and unmerging factors, traffic light cycle interval time in the road, and lane number model factor.

[0114] Generally speaking, compared with conventional lanes, the number of one-way lanes is usually greater than or equal to 2. Therefore, it is necessary to consider the lane change situation, which will affect the establishment of the speed and time model of the vehicle during driving. In the embodiment of the present application, the application scenario is a parking lot, and the number of one-way lanes is usually preset to 1. Therefore, the lane number parameter factor in the usual model and the lane change situation affected by it are no longer applicable. Therefore, there is no need to introduce / consider the lane number model factor in the low-speed and small-channel parking lot.

[0115] It should be noted that the ramp vehicle inflow and outflow factor in this embodiment is used to indicate the intersection of vehicles in the ramp, but when this embodiment is applied to a parking lot, ramp intersection is generally not required near the parking lot entrance and exit, so the impact of the ramp vehicle inflow and outflow factor on the Kalman state estimation model can be ignored. In addition, when this embodiment is applied to a parking lot, there is no need to consider the cycle gap time of the traffic light in the road, so the impact of the cycle gap time of the traffic light in the road on the Kalman state estimation model can be ignored.

[0116] Compared with the general Kalman filtering and travel time prediction technology for expressways with multiple lanes and large traffic volumes, this embodiment can ignore the factors of ramp vehicle entry and exit, the cycle interval time of traffic lights on the road, and / or the model factors of the number of lanes, so as to be more adaptable to the scenario of low traffic volume in a single-lane channel of a parking lot, improve prediction accuracy, and reduce the amount of calculation.

[0117] In the second aspect, accordingly, the embodiments of the present application also provide a parking lot entrance and exit recommendation device, which can implement all the processes of the parking lot entrance and exit recommendation method provided in the above embodiments.

[0118] See also Figure 4 , showing a schematic diagram of the structure of a parking lot entrance and exit recommendation device provided in an embodiment of the present application, including:

[0119] A state recognition module 401 is used to obtain video data of a parking lot and recognize the state of each entrance and exit in the parking lot;

[0120] The predicted passage time determination module 402 is used for, when it is determined according to the status of each entrance and exit that there is a non-smooth entrance and exit among the various entrances and exits, determining, for the non-smooth entrance and exit, based on the video data, a vehicle to be monitored corresponding to the non-smooth entrance and exit, and determining a predicted passage time for the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit;

[0121] A recommendation information generating module 403, configured to generate the entrance and exit recommendation information of the parking lot based on the predicted travel time corresponding to each of the non-unblocked entrances and exits and the status of each entrance and exit;

[0122] The display module 404 is used to push the entrance and exit recommendation information to the target terminal.

[0123] In an optional implementation, determining the to-be-monitored vehicle corresponding to the non-unblocked entrance and exit based on the video data includes:

[0124] Using a target detection algorithm, converting the appearance pictures of the objects to be identified corresponding to the non-unblocked entrances and exits in the video data into matching target vectors, and determining the prediction confidence of each of the target vectors;

[0125] For each of the target vectors, if the prediction confidence of the target vector is higher than a confidence threshold, the object to be identified that matches the target vector is determined as the vehicle to be monitored.

[0126] In an optional implementation, determining, based on the video data, a predicted travel time of the monitored vehicle to leave the parking lot via the non-unblocked entrance and exit includes:

[0127] Determine the passing position of the last vehicle based on the video data, wherein the last vehicle is a vehicle without a following vehicle among the vehicles to be monitored;

[0128] Based on the video data, calculating the time average speed of the vehicle to be monitored at the passing position;

[0129] Based on the time average speed and the travel section between the travel position and the non-smooth entrance and exit, the travel time of the last vehicle leaving the parking lot via the non-smooth entrance and exit is determined as the predicted travel time.

[0130] In an optional implementation, determining the travel time of the last vehicle to leave the parking lot via the non-smooth entrance / exit based on the time average speed and the travel section between the travel position and the non-smooth entrance / exit comprises:

[0131] Constructing a Kalman state estimation model using the time average speed as a measurement variable and the road section density corresponding to the passable road section as a state variable;

[0132] The Kalman state estimation model is used to perform estimation to determine the travel time of the last vehicle.

[0133] In an optional embodiment, the device further comprises:

[0134] A vehicle gate time factor determination module, used to determine the vehicle gate time factor corresponding to the parking lot, wherein the vehicle gate time factor is used to indicate a single vehicle charging time corresponding to the parking lot;

[0135] The using the Kalman state estimation model to perform estimation to determine the passing time of the last vehicle includes:

[0136] According to the time factor at the vehicle gate, the travel time estimated by the Kalman state estimation model is corrected to obtain the travel time of the last vehicle.

[0137] In an optional implementation, the Kalman state estimation model is a model that does not consider at least one of the following: ramp vehicle merging and unmerging factors, traffic light cycle interval time in the road, and lane number model factor.

[0138] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods for recommending parking lot entrances and exits are implemented.

[0139] In a fourth aspect, an embodiment of the present application provides a computer program product, including computer instructions, which, when executed by a processor, implement the steps of any of the above-mentioned parking lot entrance and exit recommendation methods.

[0140] In a fifth aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the steps of any of the above-mentioned parking lot entrance and exit recommendation methods when executing the computer program.

[0141] See also Figure 5 The computer device of this embodiment includes: a processor 501, a memory 502, and a computer program stored in the memory 502 and executable on the processor 501, such as a parking lot entrance and exit recommendation program. When the processor 501 executes the computer program, the steps in the above-mentioned parking lot entrance and exit recommendation method embodiments are implemented, such as Figure 1 Steps S101-S104 are shown.

[0142] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory 502 and executed by the processor 501 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the computer device.

[0143] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may include, but not limited to, a processor 501 and a memory 502. Those skilled in the art will appreciate that the schematic diagram is merely an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the diagram, or may combine certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0144] The processor 501 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor 501 may also be any conventional processor, etc. The processor 501 is the control center of the computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0145] The memory 502 can be used to store the computer program and / or module. The processor 501 implements various functions of the computer device by running or executing the computer program and / or module stored in the memory 502 and calling the data stored in the memory 502. The memory 502 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 502 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0146] Wherein, if the module / unit integrated in the computer device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor 501. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0147] In summary, the embodiments of the present application have at least the following beneficial effects:

[0148] According to the embodiment of the present application, the status of each entrance and exit in the parking lot is identified by acquiring video data of the parking lot; when it is determined that a non-smooth entrance and exit exists among the entrances and exits according to the status of the entrances and exits, the vehicle to be monitored corresponding to the non-smooth entrance and exit is determined based on the video data, and the predicted passage time of the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit is determined; based on the predicted passage time corresponding to each of the non-smooth entrances and exits and the status of the entrances and exits, entrance and exit recommendation information of the parking lot is generated; the entrance and exit recommendation information is pushed to the target terminal, so that the entrance and exit recommendation information of the parking lot can be displayed in real time for users to view and select, thereby reducing the congestion rate of the entrances and exits of the parking lot.

[0149] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus the necessary hardware platform, and of course, it can also be implemented entirely by hardware. Based on such an understanding, all or part of the contribution of the technical solution of the present application to the background technology can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application or some parts of the embodiments.

[0150] The above is a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications are also considered to be within the scope of protection of the present application.

Claims

1. A parking lot entrance and exit recommendation method, characterized in that: include: Acquire video data of a parking lot and identify the status of each entrance and exit of the parking lot; When it is determined according to the states of the various entrances and exits that there is a non-smooth entrance and exit among the various entrances and exits, for the non-smooth entrance and exit, based on the video data, a vehicle to be monitored corresponding to the non-smooth entrance and exit is determined, and a predicted passage time for the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit is determined; Generate entrance and exit recommendation information of the parking lot based on the predicted travel time corresponding to each of the non-unblocked entrances and exits and the status of each entrance and exit; The entrance and exit recommendation information is pushed to the target terminal.

2. The parking lot entrance and exit recommendation method according to claim 1, characterized in that: The determining, based on the video data, the vehicle to be monitored corresponding to the non-unblocked entrance and exit includes: Using a target detection algorithm, converting the appearance pictures of the objects to be identified corresponding to the non-unblocked entrances and exits in the video data into matching target vectors, and determining the prediction confidence of each of the target vectors; For each of the target vectors, if the prediction confidence of the target vector is higher than a confidence threshold, the object to be identified that matches the target vector is determined as the vehicle to be monitored.

3. The parking lot entrance and exit recommendation method according to claim 1, characterized in that: Determining, based on the video data, a predicted travel time of the vehicle to be monitored to leave the parking lot via the non-unblocked entrance and exit, comprising: Determine the passing position of the last vehicle based on the video data, wherein the last vehicle is a vehicle without a following vehicle among the vehicles to be monitored; Based on the video data, calculating the time average speed of the vehicle to be monitored at the passing position; Based on the time average speed and the travel section between the travel position and the non-smooth entrance and exit, the travel time of the last vehicle leaving the parking lot via the non-smooth entrance and exit is determined as the predicted travel time.

4. The parking lot entrance and exit recommendation method according to claim 3, characterized in that: The determining, based on the time average speed and the passage section between the passage position and the non-smooth entrance and exit, the passage time of the last vehicle leaving the parking lot via the non-smooth entrance and exit comprises: Constructing a Kalman state estimation model using the time average speed as a measurement variable and the road section density corresponding to the passable road section as a state variable; The Kalman state estimation model is used to perform estimation to determine the travel time of the last vehicle.

5. The parking lot entrance and exit recommendation method according to claim 4, characterized in that: The method further comprises: Determine a time factor at a vehicle gate corresponding to the parking lot, wherein the time factor at the vehicle gate is used to indicate a single vehicle charging time corresponding to the parking lot; The using the Kalman state estimation model to perform estimation to determine the passing time of the last vehicle includes: According to the time factor at the vehicle gate, the travel time estimated by the Kalman state estimation model is corrected to obtain the travel time of the last vehicle.

6. The parking lot entrance and exit recommendation method according to claim 4, characterized in that: The Kalman state estimation model is a model that does not consider at least one of the following: ramp vehicle merging and unmerging factors, traffic signal light cycle interval time in the road, and lane number model factor.

7. A parking lot entrance and exit recommendation device, characterized in that: include: A state recognition module, used to obtain video data of the parking lot and identify the state of each entrance and exit in the parking lot; A predicted passage time determination module is used for, when it is determined according to the status of each entrance and exit that there is a non-smooth entrance and exit among the various entrances and exits, determining, for the non-smooth entrance and exit, based on the video data, a vehicle to be monitored corresponding to the non-smooth entrance and exit, and determining a predicted passage time for the vehicle to be monitored to leave the parking lot via the non-smooth entrance and exit; A recommendation information generation module, configured to generate the entrance and exit recommendation information of the parking lot based on the predicted travel time corresponding to each of the non-unblocked entrances and exits and the status of each entrance and exit; The display module is used to push the entrance and exit recommendation information to the target terminal.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the parking lot entrance and exit recommendation method according to any one of claims 1 to 6 is implemented.

9. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by the processor, the parking lot entrance and exit recommendation method according to any one of claims 1 to 6 is implemented.

10. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the method for recommending parking lot entrances and exits according to any one of claims 1 to 6 is implemented when the processor executes the computer program.

Images