Vehicle parking behavior determination method, electronic device and storage medium

Abstract

The present application discloses a method for determining a vehicle parking behavior, an electronic device, and a computer-readable storage medium. The method comprises: determining whether there is a reference vehicle in a stationary state in the target parking area during a delay period after determining that the target vehicle has entered the target parking area; if there is a reference vehicle in the target parking area, determining whether there is a target vehicle among the reference vehicles to determine whether the target vehicle has parking behavior. By means of the above method, the accuracy of the parking behavior determination result of the target vehicle can be improved.

Description

Technical Field

[0001] The present application relates to the field of video surveillance, and in particular to a method for determining vehicle parking behavior, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the field of traffic monitoring, the determination of vehicle parking behavior is required in many application scenarios. For example, in the process of calculating the number of parking spaces, it is necessary to determine whether there is a vehicle in the parking space, so it is necessary to determine whether there is parking behavior in the parking space. For another example, in the process of calculating parking fees, it is necessary to determine when the vehicle starts to park in the parking space, so it is necessary to determine whether there is parking behavior in the parking space. For another example, in the process of determining illegal parking behavior, it is necessary to determine whether the vehicle has parked in a prohibited parking area.

[0003] However, the current method for determining the parking behavior of a vehicle does not provide a high accuracy in determining the parking behavior. Summary of the invention

[0004] The present application provides a vehicle parking behavior determination method, an electronic device, and a computer-readable storage medium, which can solve the problem that the current vehicle parking behavior determination method has a low accuracy in the parking behavior determination result.

[0005] In order to solve the above technical problems, a technical solution adopted by the present application is to provide a method for determining vehicle parking behavior. The method comprises: in a delay period after determining that a target vehicle enters a target parking area, determining whether there is a reference vehicle in a stationary state in the target parking area; if there is a reference vehicle, determining whether there is a target vehicle among the reference vehicles to determine whether the target vehicle has parking behavior.

[0006] To solve the above technical problems, another technical solution adopted in the present application is: to provide an electronic device, which includes a processor and a memory connected to the processor, wherein the memory stores program instructions; the processor is used to execute the program instructions stored in the memory to implement the above method.

[0007] In order to solve the above technical problems, another technical solution adopted by the present application is: providing a computer-readable storage medium storing program instructions, which can implement the above method when executed.

[0008] Through the above-mentioned method, the present application determines whether there is a reference vehicle in a stationary state in the target parking area (determines whether there is a possibility that the target vehicle has stopped steadily) during the delay period after the target vehicle enters the target parking area; if there is a reference vehicle (there is a possibility that the target vehicle has stopped steadily), it determines whether there is a target vehicle among the reference vehicles (determines whether the target vehicle has really stopped steadily) to determine whether the target vehicle has stopped. Therefore, when the target vehicle enters the target parking area, the present application does not directly determine whether the target vehicle has stopped steadily, but only considers that the target vehicle may have stopped steadily, and further determines whether the target vehicle has stopped steadily on this basis, and then determines whether the target vehicle has stopped steadily based on whether the target vehicle has stopped steadily, thereby reducing the possibility of the target vehicle's parking behavior being misjudged and improving the accuracy of the target vehicle's parking behavior determination result. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 It is a flow chart of an embodiment of a method for determining a vehicle parking behavior of the present application;

[0010] Figure 2 It is a flowchart of another embodiment of the method for determining vehicle parking behavior of the present application;

[0011] Figure 3 yes Figure 2 The specific process diagram of S21 in FIG.

[0012] Figure 4 It is a flowchart of another embodiment of the method for determining vehicle parking behavior of the present application;

[0013] Figure 5 It is a flowchart of another embodiment of the method for determining the parking behavior of a vehicle of the present application;

[0014] Figure 6 yes Figure 5 The specific process diagram of S43;

[0015] Figure 7 It is a schematic diagram of the relationship between the reference point and the target parking area at each moment in the image coordinate system XOY;

[0016] Figure 8 It is a structural diagram of an embodiment of a behavior determination device of the present application;

[0017] Fig. 9 It is a structural schematic diagram of an embodiment of the electronic device of the present application;

[0018] Fig.10 It is a structural schematic diagram of an embodiment of a computer-readable storage medium of the present application; DETAILED DESCRIPTION

[0019] 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.

[0020] The terms "first", "second", and "third" in this application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first", "second", and "third" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "multiple" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0021] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments without conflict.

[0022] The following is a detailed description of the application scenarios of the present application method in the form of several examples:

[0023] Application scenario 1: parking fee calculation. Determine whether the vehicle has parked in the parking area; if it is determined that the vehicle has parked in the parking area, record the vehicle's entry information (time of entering the parking area, the vehicle's license plate number, and the parking area ID); and when it is subsequently determined that the vehicle has exited the parking area, record the vehicle's exit information (time of exiting the parking area, the vehicle's license plate number, and the parking area ID); determine the vehicle's entry time and exit time based on the vehicle's license plate number; calculate the time the vehicle occupies the parking area based on the vehicle's entry time and exit time; calculate the vehicle's parking fee based on the time of occupying the parking area and the charging standard.

[0024] Application scenario 2: Calculation of remaining parking spaces. Determine whether the vehicle has parked in the parking area; if it is determined that the vehicle has parked in the parking area, record the vehicle's entry information (time of entering the parking area, the vehicle's license plate number, and changes in the parking area); and reduce the number of parking spaces in the parking area by one.

[0025] Application scenario 3: Identification of illegal parking behavior. Determine whether the vehicle has parked in a prohibited parking area; if so, record the vehicle's license plate number and report the illegal parking incident.

[0026] The following is an explanation of the vehicle parking behavior determination method and its defects in the related art:

[0027] In the related art, the target vehicle is tracked to obtain the trajectory information of the target vehicle, and it is determined whether the relationship between the position of the target vehicle at the latest moment in the trajectory information of the target vehicle and the target parking area meets the requirements; if the requirements are met, it is determined that the target vehicle has entered the parking area; if it is determined that the target vehicle has entered the parking area, it is determined that the target vehicle has parked.

[0028] The inventor of the present application has found through long-term research that the position of the target vehicle may be inaccurate, resulting in an erroneous result in the judgment of the vehicle parking behavior. The reasons for the inaccurate position of the target vehicle include at least the following two:

[0029] Reason 1: The target vehicle is a passing vehicle, that is, the target vehicle only passes through the target parking area, and does not stay in the target parking area. However, because it passes through the target parking area, the relationship between the position of the target vehicle and the target parking area meets the requirements, so it is determined that the target vehicle enters the parking area, and then it is determined that the target vehicle has parked in the target parking area. In this case, the target vehicle actually does not have a parking behavior, but it is determined to have a parking behavior.

[0030] Reason 2: The target vehicle is blocked, causing the target vehicle ID to be confused, that is, the blocking vehicle ID of the target vehicle is mistaken for the target vehicle ID, so the target vehicle is judged to have entered the target parking area because the blocking vehicle has entered the target parking area, and then it is judged that the target vehicle has parked in the target parking area. In this case, the target vehicle actually did not park, but was judged to have parked.

[0031] Based on this, the vehicle parking behavior determination method provided by the present application can be divided into two parts, one part is to determine whether the target vehicle has entered the target parking area, and the other part is to determine whether the target vehicle has parking behavior during the delay period after determining that the target vehicle has entered the target parking area. The specific method can be as follows:

[0032] Figure 1 FIG. 1 is a flow chart of an embodiment of the method for determining the parking behavior of a vehicle of the present application. It should be noted that if there are substantially the same results, this embodiment does not use Figure 1 The process sequence shown is limited. Figure 1 As shown, this embodiment may include:

[0033] S11: Acquire first video data of a target area.

[0034] The target area includes the target parking area and its surrounding area.

[0035] A camera is arranged in the target area, and the field of view of the camera is the target area. The target parking area can be a parking area that allows parking, such as a parking space in a parking lot, a parking space on the roadside, etc., or a parking area that prohibits parking, such as a zebra crossing on a road, a highway, etc. The first video data includes a plurality of video frames, each of which corresponds to a moment.

[0036] S12: Perform vehicle tracking based on the first video data to obtain track information of several vehicles in the first video data.

[0037] The trajectory information of a vehicle may include the relevant position information of the vehicle at several moments. The relevant position information of the vehicle at a single moment may include the vehicle ID, the vehicle position, the vehicle type, the vehicle license plate information, the video frame number, etc. The vehicle license plate information may include the license plate number, the license plate position, the license plate color, the license plate appearance, etc. The trajectory information of a vehicle may include multiple sub-trajectory information, such as the license plate sub-trajectory information composed of the license plate information (hereinafter referred to as the first license plate sub-trajectory information), the vehicle sub-trajectory information composed of the vehicle position, and so on.

[0038] The vehicle tracking involved in this application may include three parts: vehicle position detection, vehicle position association, and vehicle license plate information acquisition. For each video frame in the first video data, the vehicle position detection is performed on the video frame to obtain the position of each vehicle to be associated in the video frame; the position of each vehicle to be associated is matched with the trajectory information of each existing vehicle; if matched, the position of the vehicle to be associated is used to update the trajectory information of the existing vehicle that matches it; if not matched, the trajectory information of a new vehicle is established based on the position of the vehicle to be associated. The license plate detection can be performed on the area corresponding to the position of the license plate in each video frame to obtain the vehicle's license plate information.

[0039] S13: Taking at least one vehicle in the first video data as a target vehicle, and judging whether the target vehicle enters the target parking area based on the relationship between the position of the target vehicle at the latest moment in the trajectory information of the target vehicle and the target parking area.

[0040] The overlap between the position of the target vehicle at the latest moment and the target parking area can be calculated, and whether the target vehicle has entered the target parking area can be determined based on the overlap. That is, a overlap threshold is set, and if the overlap is greater than the overlap threshold, it is determined that the target vehicle has entered the target parking area; otherwise, it is determined that the target vehicle has not entered the target parking area.

[0041] If the target vehicle enters the target parking area, it means that the target vehicle may have parking behavior; if the target vehicle does not enter the target parking area, it means that the target vehicle does not have parking behavior.

[0042] Furthermore, after determining that the target vehicle has entered the target parking area, that is, based on determining that the target vehicle may have parking behavior, it can be determined whether the target vehicle actually has parking behavior. Specifically, it can be as follows:

[0043] Figure 2 FIG. 1 is a flow chart of another embodiment of the method for determining the parking behavior of a vehicle of the present application. It should be noted that if there is substantially the same result, this embodiment does not necessarily use Figure 2 The process sequence shown is limited. Figure 2 As shown, this embodiment may include:

[0044] S21: During a delay period after determining that the target vehicle enters the target parking area, determining whether there is a reference vehicle in a stationary state in the target parking area.

[0045] In this application, the time period when the target vehicle enters the target parking area is referred to as the original time period, and the continuous time period of a preset duration after the original time period is referred to as the delayed time period. The time period when the target vehicle enters the target parking area may include the time period before the target vehicle enters the target parking area and the time period during the process of entering the target parking area, that is, the time period starting from the moment when the target vehicle enters the field of view of the camera (the moment corresponding to the first video frame included in the first video data) and ending at the moment when the relationship between the position of the target vehicle and the target parking area meets the requirements.

[0046] The delay time period after the target vehicle enters the target parking area in S21 may be achieved, but is not limited to, through S11 to S13.

[0047] Combined with reference Figure 3 In some embodiments, S21 may include sub-steps:

[0048] S211: Acquire second video data of the target area during a delay period after determining that the target vehicle enters the target parking area.

[0049] S212: Tracking the license plate based on the second video data to obtain a plurality of second license plate sub-track information in the second video data.

[0050] The composition structure and acquisition method of the second license plate sub-track information are similar to those of the first license plate sub-track information, and are not described here.

[0051] S213: Determine whether there is a reference vehicle in the target parking area based on the relationship between the license plate positions at different times in each second license plate sub-trajectory information.

[0052] For each second license plate sub-trajectory information, it can be determined whether the vehicle to which it belongs is a reference vehicle based on the relationship between the license plate positions at different times; when at least one vehicle to which the second license plate sub-trajectory information belongs is a reference vehicle, it is determined that there is a reference vehicle among the vehicles. Among them, if there is no change or the change amplitude is not large between the license plate positions at different times in the second license plate sub-trajectory information, it is determined that the vehicle to which the second license plate sub-trajectory information belongs is in a stationary state and is a reference vehicle. No change between the license plate positions at different times means that the displacement between the license plate positions at different times is 0; the change amplitude between the license plate positions at different times is not large, which means that the displacement between the license plate positions at different times is less than the displacement threshold. The displacement between the license plate positions at different times can be calculated by any reference point of the license plate position, such as the center point or the vertex.

[0053] If there is a reference vehicle in the target parking area, execute S22; otherwise, execute S23.

[0054] S22: Determine whether there is a target vehicle among the reference vehicles to determine whether the target vehicle has parking behavior.

[0055] In some embodiments, it can be determined whether there is a target vehicle in each reference vehicle based on the second license plate sub-track information. S22 can include the following sub-steps: the second license plate sub-track information includes a license plate number, based on which it can be determined whether there is second license plate sub-track information that meets the requirements, and the license plate number included in the second license plate sub-track information that meets the requirements is consistent with the target license plate number of the target vehicle; if there is, it is determined that there is a target vehicle in each reference vehicle, that is, the reference vehicle to which the second license plate sub-track information that meets the requirements belongs is the target vehicle; if not, it is determined that there is no target vehicle in each reference vehicle.

[0056] The license plate number of the target vehicle can be determined from the first license plate sub-track information of the target vehicle. It is understandable that the license plate information at at least one moment in the first license plate sub-track information of the target vehicle includes the license plate number. Since the license plate of the target vehicle may be blocked in some video frames, the license plate information at the corresponding moment in the license plate information of the target vehicle is empty. Therefore, the license plate number of the target license plate can be the license plate number in the license plate information at any moment.

[0057] For example, if there is a reference vehicle PP in the target parking area during the delay period after it is determined that the target vehicle has entered the target parking area, that is, the number of PPs is not 0, then the license plate numbers of each PP and the target vehicle P are compared. If the license plate number of the PP is consistent with the license plate number of the P, it is determined that P exists in the PP; otherwise, it is determined that P does not exist in the PP.

[0058] Furthermore, based on the judgment result of whether the target vehicle exists among the reference vehicles, it can be determined whether the target vehicle has parking behavior.

[0059] It is understandable that if the target vehicle has the behavior of the target parking area, the target vehicle will stop or approach the target parking area. The reference vehicles are stationary during the delay period, and the target vehicle exists in each reference vehicle, which means that the target vehicle stops or approaches the target parking area. Therefore, if the judgment result is that the target vehicle exists in each reference vehicle, it is determined that the target vehicle has the behavior of parking; if the judgment result is that the target vehicle does not exist in each reference vehicle, it is determined that the target vehicle does not have the behavior of parking.

[0060] S23: Determine whether the target vehicle has any parking behavior, or determine whether the target vehicle has any parking behavior based on the license plate trajectory information of the target vehicle.

[0061] It is understandable that, during the delay period, there is no reference vehicle in a stationary state in the target parking area, which means that the target vehicle has not stopped steadily in the target parking area, so it can be directly determined that the target vehicle has no parking behavior.

[0062] Furthermore, if there is no reference vehicle in the target parking area, if it is directly determined that the target vehicle has no parking behavior, there may be a misjudgment. To this end, it is possible to further determine whether the target vehicle has parking behavior through the license plate trajectory information of the target vehicle. The license plate trajectory information of the target vehicle includes the license plate positions of the target vehicle at multiple times in the original time period and the delayed time period. The original time period is the time period before and during the target vehicle enters the target parking area.

[0063] Through the implementation of this embodiment, the present application determines whether there is a reference vehicle in a stationary state in the target parking area (determines whether there is a possibility that the target vehicle has stopped steadily) during the delay period after the target vehicle enters the target parking area; if there is a reference vehicle (there is a possibility that the target vehicle has stopped steadily), then it is determined whether there is a target vehicle among the reference vehicles (determines whether the target vehicle has really stopped steadily) to determine whether the target vehicle has stopped. Therefore, when the target vehicle enters the target parking area, the present application does not directly determine whether the target vehicle has stopped, but only considers that the target vehicle may have stopped, and further determines whether the target vehicle has stopped steadily on this basis, and then determines whether the target vehicle has stopped steadily based on whether the target vehicle has stopped steadily, thereby reducing the possibility of the target vehicle's parking behavior being misjudged and improving the accuracy of the target vehicle's parking behavior determination result.

[0064] Figure 4 FIG. 1 is a flow chart of another embodiment of the method for determining the parking behavior of a vehicle of the present application. It should be noted that if there are substantially the same results, this embodiment does not necessarily use Figure 4 The process sequence shown is limited. Figure 4 As shown, this embodiment may include:

[0065] S31: Acquire second video data of the target area during a delay period after determining that the target vehicle enters the target parking area.

[0066] S32: Tracking the license plate based on the second video data to obtain second license plate sub-track information of the target vehicle.

[0067] The license plate tracking can obtain a plurality of second license plate sub-track information in the second video data, and the second license plate sub-track information including the license plate number consistent with the target license plate number of the target vehicle is used as the second license plate sub-track information of the target vehicle.

[0068] S33: Merge the first license plate sub-track information of the target vehicle and the second license plate sub-track information of the target vehicle to obtain the license plate track information of the target vehicle.

[0069] S31 to S33 and S211 to S213 may be performed in parallel, or S31 to S33 may be performed after S211 to S213 , that is, when it is determined by S211 to S213 that there is no reference vehicle, S31 to S33 are executed.

[0070] The following is an example to illustrate the parallel operation of S31-S33 and S211-S213:

[0071] 1) During a delay period after determining that the target vehicle enters the target parking area, second video data of the target area is acquired.

[0072] 2) Tracking the license plate based on the second video data to obtain a plurality of second license plate sub-track information in the second video data; determining the second license plate sub-track information of the target vehicle from each second license plate sub-track information; merging the first license plate sub-track information of the target vehicle and the second license plate sub-track information of the target vehicle to obtain the license plate track information of the target vehicle.

[0073] 3) Based on the relationship between the license plate positions at different times in each second license plate sub-trajectory information, determine whether there is a reference vehicle in the target parking area.

[0074] Furthermore, in the case of determining whether the target vehicle has parking behavior based on the license plate trajectory information of the target vehicle in the above S23, the false positive filter coefficient of the parking behavior can be obtained based on the reference points (center point, vertex, etc.) of the license plate position at multiple times in the license plate trajectory information; determine whether the false positive filter coefficient meets the coefficient condition; if the coefficient condition is met, determine that the target vehicle has parking behavior; otherwise, determine that the target vehicle does not have parking behavior.

[0075] The misjudgment filtering coefficient can be obtained in at least the following ways:

[0076] Method 1: Determine whether the reference point meets the false positive filtering condition, the false positive filtering condition includes that the number of reference points is greater than the number threshold, and the reference point at a specific time among multiple time points is outside the target parking area, and the specific time point at least includes the start time and the end time; if the false positive filtering condition is not met, the false positive filtering coefficient is determined to be a preset coefficient value, and the preset coefficient value meets the coefficient condition; if the false positive filtering condition is met, the false positive filtering coefficient is determined to be other coefficient values, and the other coefficient values ​​do not meet the coefficient condition. Accordingly, the coefficient condition is that the false positive filtering coefficient is the preset coefficient value.

[0077] Method 2: Obtain the misjudgment filtering coefficient based on the distance between reference points at different times.

[0078] In some embodiments, a distance interval can be set in advance based on the parking behavior of the target parking area. The distance interval is the fluctuation range of the sum S of the distances of the reference points of each two adjacent moments in multiple moments when the vehicle has the parking behavior of the target parking area. A distance interval is suitable for all vehicle types, or a distance interval is only suitable for one vehicle type, that is, a distance interval is set for each vehicle type. The misjudgment filtering coefficient can be the sum of the distances of the reference points of each two adjacent moments in multiple moments, relative to the deviation degree of the distance interval. Accordingly, the coefficient condition is that the misjudgment filtering coefficient is less than the deviation degree threshold.

[0079] In some embodiments, the misjudgment filter coefficient can be C / S, where C is the arc length of the target arc, and S is the sum of the distances of the reference points at each two adjacent moments. The target arc is an arc with the reference point at the start moment and the reference point at the end moment as endpoints, respectively. Alternatively, the misjudgment filter coefficient can be ln(C / S). The specific acquisition method of C / S can refer to the following embodiment description. Accordingly, the coefficient condition can be that the misjudgment filter coefficient is less than or equal to the coefficient threshold. When the misjudgment filter coefficient is C / S, the coefficient threshold can be 1, or it can be a floating value around 1 (with a certain degree of fault tolerance). When the misjudgment filter coefficient is ln(C / S), the coefficient threshold can be 0, or it can be a floating value around 0 (with a certain degree of fault tolerance).

[0080] Method 3: The false positive filtering coefficient can be obtained by combining method 1 and method 2. That is, it is determined whether the reference point meets the false positive filtering condition; if the false positive filtering condition is not met, the false positive filtering coefficient is determined to be a preset coefficient value; if the false positive filtering condition is met, the false positive filtering coefficient is obtained based on the distance between the reference points at different times in multiple times.

[0081] The following is a detailed introduction to method three:

[0082] Figure 5 FIG. 1 is a flow chart of another embodiment of the method for determining the parking behavior of a vehicle of the present application. It should be noted that if there are substantially the same results, this embodiment does not necessarily refer to the method of determining the parking behavior of a vehicle of the present application. Figure 5 The process sequence shown is limited. This embodiment is a further extension of S23. Figure 5 As shown, this embodiment may include:

[0083] S41: Determine whether the reference point meets the misjudgment filtering condition.

[0084] The false positive filtering condition includes that the number of reference points is greater than a number threshold, and the reference point at a specific time among multiple time points is outside the target parking area, and the specific time point at least includes a start time and an end time.

[0085] The so-called false positive filtering condition refers to the condition that can effectively judge whether the target vehicle has parked through the false positive filtering coefficient. The number of reference points is greater than the number threshold, which means that the amount of data is sufficient; the reference point at a specific moment is outside the target parking area, which means that if there is no reference vehicle in the target parking area, it is directly judged that the target vehicle has not parked, and there is a possibility of false positive.

[0086] In some embodiments, the quantity threshold may be 3, 4, etc. The specific moment may also include the moment before the end moment, the two moments before the end moment, etc. Thus, the accuracy of the judgment result of whether the false judgment filtering condition is met can be improved.

[0087] If the false positive filtering condition is not met, S42 and S44 are executed; if the false positive filtering condition is met, S43 to S44 are executed.

[0088] S42: Determine the misjudgment filtering coefficient as a preset coefficient value.

[0089] The preset coefficient value satisfies the coefficient condition.

[0090] S43: Obtaining a misjudgment filtering coefficient based on the distances between reference points at different times.

[0091] Combined with reference Figure 6 In the case where the filter coefficient is misjudged as C / S or ln(C / S), S43 may include the following sub-steps:

[0092] S431: Obtain the sum of distances between reference points of every two adjacent moments in a plurality of moments.

[0093] S432: Obtain the arc length of the target arc.

[0094] The target arc is an arc having a reference point at the start time and a reference point at the end time as endpoints.

[0095] In some embodiments, the translation distance between the reference point at the start time and the reference point at the end time, as well as the straight-line distance (also called chord length) between the reference point at the start time and the reference point at the end time can be obtained; it is determined whether the translation distance meets the distance condition; if the distance condition is not met, the chord height of the target arc is obtained based on the horizontal distance; if the distance condition is met, the chord height of the target arc is obtained based on the straight-line distance; based on the straight-line distance and the chord height, the arc length of the target arc is determined.

[0096] In the image coordinate system, the reference point has a horizontal coordinate in the horizontal direction and a vertical coordinate in the vertical direction, and the translation distance between the reference point at the start time and the reference point at the end time can be the distance between the coordinates in the horizontal direction or the vertical direction.

[0097] The distance condition can be that the translation distance is 0, or a fluctuation value near 0 (allowing a certain tolerance), etc. If the distance condition is not met, the chord height can be equal to the translation distance. Alternatively, the chord height can be a preset multiple of the translation distance. If the distance condition is not met, the chord height can be one-half, two-thirds, etc. of the straight-line distance.

[0098] S433: Obtain a misjudgment filtering coefficient based on the ratio of the arc length to the sum.

[0099] S44: Determine whether the misjudgment filtering coefficient meets the coefficient condition.

[0100] If the coefficient condition is met, execute S45; if the coefficient condition is not met, execute S46.

[0101] S45: Determine whether the target vehicle has stopped.

[0102] S46: Determine whether the target vehicle has stopped.

[0103] Different from the situation in the previous embodiment where it is directly determined that the target vehicle has not parked when there is no reference license plate, this embodiment can determine whether the target vehicle has parked by using the reference point of the license plate position of the target vehicle when there is no reference vehicle in the target parking area, thereby further reducing the possibility of misjudgment of the parking behavior of the target vehicle (i.e., there is actually parking behavior but it is determined that there is no parking behavior), and improving the accuracy of the parking behavior determination result of the target vehicle.

[0104] Combine as follows Figure 7 , S41 to S46 are explained as an example:

[0105] The target vehicle’s track information contains the license plate track information {p1, p2, p3…, p n}, p i (x i ,y i), i = 1, ..., n. x i and i Respectively represent the horizontal and vertical coordinates of the reference point of the license plate position at the i-th moment in the image coordinate system. The target parking area is a parking space on one side of the lane and is parallel to the lane.

[0106] 1) Determine whether the false positive filtering condition is met. The false positive filtering condition is n ≥ 3 and p1, p n-1 、p n Outside the parking space; if the false positive filtering condition is met, proceed to 2) to 4); otherwise, set the false positive filtering coefficient α to 0 and proceed to 5).

[0107] 2) The sum of the distances between the reference points at each two adjacent moments is S:

[0108]

[0109] 3) Calculate the arc length C of the target arc between P1 and Pn:

[0110] ① Calculate p1 and p n The distance between P1 and Pn is taken as the chord length l of the target arc between P1 and Pn:

[0111]

[0112] ② Calculate the chord height h of the target arc between P1 and Pn:

[0113]

[0114] ③ Calculate the arc length C of the target arc between P1 and Pn based on h and l:

[0115]

[0116] 4) Calculate the misjudgment filtering coefficient α based on S and C:

[0117]

[0118] 5) Determine whether α≤0 or α>0; if α≤0, execute 6); if α>0, execute 7).

[0119] 6) Determine the parking behavior of the target vehicle in the parking space.

[0120] 7) Determine the parking behavior of the target vehicle in a parking space that does not exist.

[0121] Combined with reference Figure 7 , Figure 7 It is a schematic diagram of the relationship between the reference point and the target parking area at each moment in the image coordinate system XOY. Figure 7(a) is a schematic diagram of the relationship between parking spaces and lanes; (b) is a schematic diagram of calculating the misjudgment filtering coefficient; (c) is a schematic diagram of the relationship between the reference point and the target parking area at each moment when there is no parking behavior in a parking space; (d) is a schematic diagram of the relationship between the reference point and the target parking area at each moment when there is parking behavior in a parking space.

[0122] Figure 8 Schematic diagram of the structure of an embodiment of the behavior determination device of the present application. Figure 8 As shown, the behavior determination device may include a first judgment module 11 and a second judgment module 12 .

[0123] The first determination module 11 may be used to determine whether there is a reference vehicle in a stationary state in the target parking area during a delay period after determining that the target vehicle has entered the target parking area.

[0124] The second judgment module 12 can be used to judge whether there is a target vehicle among the reference vehicles when there are reference vehicles in the target parking area, so as to determine whether the target vehicle has parking behavior.

[0125] For other detailed descriptions of this embodiment, please refer to the previous method embodiments, which will not be repeated here.

[0126] Through the implementation of this embodiment, the present application uses the first judgment module to judge whether there is a reference vehicle in a stationary state in the target parking area (to judge whether there is a possibility that the target vehicle has stopped steadily) during the delay period after the target vehicle enters the target parking area; and uses the second judgment module to judge whether there is a target vehicle among the reference vehicles (to judge whether the target vehicle has really stopped steadily) when there is a reference vehicle (there is a possibility that the target vehicle has stopped steadily) to determine whether the target vehicle has stopped. Therefore, when the target vehicle enters the target parking area, the present application does not directly determine whether the target vehicle has stopped, but only considers that the target vehicle may have stopped, and further judges whether the target vehicle has stopped steadily on this basis, and then determines whether the target vehicle has stopped steadily based on whether the target vehicle has stopped steadily, thereby reducing the possibility of the target vehicle's parking behavior being misjudged and improving the accuracy of the target vehicle's parking behavior determination result.

[0127] Fig. 9 Schematic diagram of the structure of an embodiment of the electronic device of the present application. Fig. 9 As shown, the electronic device includes a processor 21 and a memory 22 coupled to the processor 21 .

[0128] The memory 22 stores program instructions for implementing the method of any of the above embodiments; the processor 21 is used to execute the program instructions stored in the memory 22 to implement the steps of the above method embodiments. The processor 21 may also be referred to as a CPU (Central Processing Unit). The processor 21 may be an integrated circuit chip with signal processing capabilities. The processor 21 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0129] The electronic device may be a camera, a server that establishes a communication connection with the camera, or a behavior determination terminal that establishes a communication connection with the camera. The camera may be used to obtain video data of a target area, and the camera / server / behavior determination terminal may be used to analyze the video data to determine the parking behavior of the target vehicle in the video data. For the specific parking behavior determination method, please refer to the previous method embodiment, which will not be described here.

[0130] Fig.10 Schematic diagram of the structure of an embodiment of a computer-readable storage medium of the present application. Fig.10 As shown, the computer-readable storage medium 30 of the embodiment of the present application stores program instructions 31, and the program instructions 31 are executed to implement the method provided in the above embodiment of the present application. Among them, the program instructions 31 can form a program file and be stored in the above computer-readable storage medium 30 in the form of a software product, so that a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) executes all or part of the steps of each implementation method of the present application. The aforementioned computer-readable storage medium 30 includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a disk or an optical disk, or a terminal device such as a computer, a server, a mobile phone, and a tablet.

[0131] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0132] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. The above is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the description and drawings of this application, or directly or indirectly used in other related technical fields, is also included in the patent protection scope of the present application.

Claims

1. A method for determining vehicle parking behavior, characterized in that: include: During a delay period after determining that the target vehicle has entered the target parking area, determining whether there is a reference vehicle in a stationary state in the target parking area; If the reference vehicle exists in the target parking area, determining whether the target vehicle exists in each of the reference vehicles to determine whether the target vehicle has parking behavior; If the reference vehicle in a stationary state does not exist in the target parking area, judging whether the target vehicle has parking behavior based on the license plate trajectory information of the target vehicle; Wherein, judging whether the target vehicle has parking behavior based on the license plate trajectory information of the target vehicle includes: Based on the reference points of the license plate position at multiple moments in the license plate trajectory information, the sum of the distances between each two adjacent reference points in the multiple moments is obtained; the arc length of the target arc is obtained, and the target arc is an arc with the reference point at the start moment and the reference point at the end moment as endpoints respectively; based on the ratio of the arc length to the sum, a misjudgment filtering coefficient is obtained, and the misjudgment filtering coefficient is less than or equal to the coefficient threshold to satisfy the coefficient condition; If the misjudgment filtering coefficient satisfies the coefficient condition, it is determined that the target vehicle has parking behavior; If the misjudgment filtering coefficient does not satisfy the coefficient condition, it is determined that the target vehicle does not have a parking behavior.

2. The method according to claim 1, characterized in that in, The license plate trajectory information of the target vehicle includes the license plate positions of the target vehicle at multiple moments in an original time period and a delayed time period, wherein the original time period is a time period before and during the target vehicle enters the target parking area.

3. The method according to claim 1 or 2, characterized in that: The determining, based on the license plate trajectory information of the target vehicle, whether the target vehicle has parking behavior includes: Determining whether the reference point satisfies a false positive filtering condition, wherein the false positive filtering condition includes that the number of the reference points is greater than a number threshold, and the reference point at a specific time among the multiple time points is outside the target parking area, and the specific time point includes at least a start time and an end time; If the false positive filtering condition is not satisfied, determining the false positive filtering coefficient to be a preset coefficient value, the preset coefficient value satisfies the coefficient condition; If the false positive filtering condition is met, the reference point based on the license plate position at the multiple moments is executed to obtain the sum of the distances between each two adjacent reference points at the multiple moments; the arc length of the target arc is obtained, and the target arc is an arc with the reference point at the start moment and the reference point at the end moment as endpoints respectively; based on the ratio of the arc length to the sum, the false positive filtering coefficient is obtained, and the false positive filtering coefficient is less than or equal to the coefficient threshold to meet the coefficient condition.

4. The method according to claim 3, characterized in that The step of obtaining the arc length of the target arc comprises: Acquire the translation distance between the reference point at the start time and the reference point at the end time, and the straight-line distance between the reference point at the start time and the reference point at the end time; Determining whether the translation distance satisfies a distance condition; If the distance condition is not met, the chord height of the target arc is obtained based on the translation distance; if the distance condition is met, the chord height of the target arc is obtained based on the straight-line distance; The arc length of the target arc is determined based on the straight-line distance and the chord height.

5. The method according to claim 1, characterized in that The step of determining that the target vehicle enters the target parking area comprises: Acquire first video data of a target area, wherein the target area includes the target parking area and its surrounding area; Performing vehicle tracking based on the first video data to obtain trajectory information of a plurality of vehicles in the first video data; At least one of the vehicles in the first video data is used as the target vehicle, and based on the relationship between the position of the target vehicle at the latest moment in the trajectory information of the target vehicle and the target parking area, it is determined whether the target vehicle enters the target parking area.

6. The method according to claim 5, characterized in that The target vehicle's trajectory information includes the target vehicle's first license plate sub-trajectory information, and the method further includes: acquiring second video data of the target area during a delay period after determining that the target vehicle enters the target parking area; Perform license plate tracking based on the second video data to obtain second license plate sub-track information of the target vehicle; The first license plate sub-track information of the target vehicle and the second license plate sub-track information of the target vehicle are combined to obtain the license plate track information of the target vehicle.

7. The method according to claim 1, characterized in that The determining whether there is a reference vehicle in a stationary state in the target parking area includes: acquiring second video data of a target area during a delay period after determining that the target vehicle enters the target parking area, the target area including the target parking area and its surrounding area; Perform license plate tracking based on the second video data to obtain a plurality of second license plate sub-track information in the second video data; Based on the relationship between the license plate positions at different times in each of the second license plate sub-trajectory information, it is determined whether the reference vehicle exists in the target parking area.

8. The method according to claim 7, characterized in that The second license plate sub-track information includes a license plate number, and the determining whether the target vehicle exists in each of the reference vehicles includes: Determine whether there is second license plate sub-track information that meets the requirements, the license plate number included in the second license plate sub-track information that meets the requirements is consistent with the target license plate number of the target vehicle; If so, it is determined that the target vehicle exists in each of the reference vehicles.

9. An electronic device, characterized in that: The method comprises a processor and a memory connected to the processor, wherein: The memory stores program instructions; The processor is configured to execute the program instructions stored in the memory to implement the method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores program instructions, which can be executed by a processor and implement the method according to any one of claims 1 to 8 when executed.

Images