Parking monitoring method and device, electronic equipment, storage medium and program product

Abstract

The invention relates to a parking monitoring method and device, electronic equipment, a storage medium and a program product. The method comprises the following steps: in response to monitoring that a target vehicle enters a parking area according to a received current monitoring video frame, determining parking starting time of the target vehicle; based on a current monitoring video frame shot from the parking starting time, monitoring various first vehicle information of the target vehicle in the parking area, and determining the first vehicle information credibility of the current monitoring video frame according to the respective information credibility of the various first vehicle information; based on the first vehicle information credibility of the current monitoring video frame and the first vehicle information credibility of the at least one historical monitoring video frame, determining the comprehensive credibility of the target vehicle in the parking area; determining the parking end time of the target vehicle in response to the condition that the comprehensive credibility meets a preset parking end condition; and generating resource consumption information of the target vehicle according to the parking starting time and the parking ending time. By adopting the method, the parking monitoring efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of parking monitoring technology, and in particular to a parking monitoring method, device, electronic equipment, storage medium, and program product. Background Technology

[0002] With the increasing ownership of vehicles, people's parking needs are also growing. Indoor parking lots can no longer meet this demand, leading to the emergence of various outdoor parking spaces. These include spaces set up in open areas or along the sides of roads. In indoor parking lots, gates at the entrance and exit are typically used for timing and charging. However, some outdoor parking spaces, considering space constraints and traffic impact, are not suitable for similar gates. In these cases, manual management is usually implemented. For example, an administrator patrols the area around the outdoor parking spaces, timing and charging vehicles when they enter or leave.

[0003] However, manual management suffers from low efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a parking monitoring method, device, electronic equipment, storage medium, and program product that can improve efficiency in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a parking monitoring method, including:

[0006] In response to detecting that a target vehicle has entered the parking area based on the received current monitoring video frame, the parking start time of the target vehicle is determined;

[0007] Based on the current surveillance video frames captured from the parking start time, monitor multiple first vehicle information of the target vehicle in the parking area and determine the information credibility of each first vehicle information.

[0008] The credibility of the first vehicle information in the current monitoring video frame is determined based on the credibility of each of the various types of first vehicle information.

[0009] Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, the overall credibility of the target vehicle being in the parking area is determined.

[0010] In response to the overall credibility meeting the preset parking end conditions, the parking end time of the target vehicle is determined;

[0011] Based on the parking start time and parking end time, the resource consumption information of the target vehicle is generated.

[0012] Secondly, this application also provides a parking monitoring device, comprising:

[0013] The starting information determination module is used to determine the parking start time of the target vehicle in response to detecting that the target vehicle has entered the parking area based on the received current monitoring video frame.

[0014] The parking area monitoring module is used to monitor multiple types of first vehicle information of the target vehicle in the parking area based on the current monitoring video frame captured from the parking start time, and determine the information credibility of each type of first vehicle information; determine the credibility of the first vehicle information in the current monitoring video frame based on the information credibility of each type of first vehicle information; and determine the overall credibility of the target vehicle being in the parking area based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame.

[0015] The end information determination module is used to determine the parking end time of the target vehicle in response to the comprehensive credibility meeting the preset parking end conditions;

[0016] The resource consumption information determination module is used to determine the parking end time of the target vehicle in response to the comprehensive credibility meeting the preset parking end conditions.

[0017] Thirdly, this application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0018] In response to detecting that a target vehicle has entered the parking area based on the received current monitoring video frame, the parking start time of the target vehicle is determined;

[0019] Based on the current surveillance video frames captured from the parking start time, monitor multiple first vehicle information of the target vehicle in the parking area and determine the information credibility of each first vehicle information.

[0020] The credibility of the first vehicle information in the current monitoring video frame is determined based on the credibility of each of the various types of first vehicle information.

[0021] Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, the overall credibility of the target vehicle being in the parking area is determined.

[0022] In response to the overall credibility meeting the preset parking end conditions, the parking end time of the target vehicle is determined;

[0023] Based on the parking start time and parking end time, the resource consumption information of the target vehicle is generated.

[0024] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0025] In response to detecting that a target vehicle has entered the parking area based on the received current monitoring video frame, the parking start time of the target vehicle is determined;

[0026] Based on the current surveillance video frames captured from the parking start time, monitor multiple first vehicle information of the target vehicle in the parking area and determine the information credibility of each first vehicle information.

[0027] The credibility of the first vehicle information in the current monitoring video frame is determined based on the credibility of each of the various types of first vehicle information.

[0028] Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, the overall credibility of the target vehicle being in the parking area is determined.

[0029] In response to the overall credibility meeting the preset parking end conditions, the parking end time of the target vehicle is determined;

[0030] Based on the parking start time and parking end time, the resource consumption information of the target vehicle is generated.

[0031] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0032] In response to detecting that a target vehicle has entered the parking area based on the received current monitoring video frame, the parking start time of the target vehicle is determined;

[0033] Based on the current surveillance video frames captured from the parking start time, monitor multiple first vehicle information of the target vehicle in the parking area and determine the information credibility of each first vehicle information.

[0034] The credibility of the first vehicle information in the current monitoring video frame is determined based on the credibility of each of the various types of first vehicle information.

[0035] Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, the overall credibility of the target vehicle being in the parking area is determined.

[0036] In response to the overall credibility meeting the preset parking end conditions, the parking end time of the target vehicle is determined;

[0037] Based on the parking start time and parking end time, the resource consumption information of the target vehicle is generated.

[0038] The aforementioned parking monitoring method, device, electronic equipment, storage medium, and program product monitor target vehicles by receiving monitoring video frames. Upon detecting a target vehicle entering a parking area, it automatically determines the parking start time of the target vehicle. Furthermore, since multiple pieces of first vehicle information are obtained based on monitoring the target vehicle in the parking area using the current monitoring video frames captured from the parking start time, determining the reliability of the first vehicle information in the current monitoring video frame confirms that the target vehicle was still in the parking area when the current monitoring video frame was captured. Moreover, the reliability of the first vehicle information integrates the individual reliability of multiple pieces of first vehicle information, improving the accuracy and stability of the first vehicle information reliability. Furthermore, in response to the target vehicle's overall reliability in the parking area satisfying preset parking end conditions, the parking end time of the target vehicle is automatically determined. This overall reliability is determined based on the reliability of the first vehicle information in the current monitoring video frame and at least one historical monitoring video frame, avoiding misjudgments caused by anomalies such as obstruction of the parking area in the current monitoring video frame, thus improving the accuracy of determining the parking end time. By automatically and accurately determining the parking start and end times, and automatically and accurately generating resource consumption information for the target vehicle, parking monitoring efficiency is improved. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 This is an application environment diagram of the parking monitoring method in one embodiment;

[0041] Figure 2 This is a flowchart illustrating a parking monitoring method in one embodiment;

[0042] Figure 3 This is an example schematic diagram of a monitored video frame in one embodiment;

[0043] Figure 4 This is a schematic diagram of the vehicle start-stop detection process in one embodiment;

[0044] Figure 5 This is a schematic diagram of the vehicle parking intermediate process monitoring flow in one embodiment;

[0045] Figure 6 This is a schematic diagram of the vehicle parking end detection process in one embodiment;

[0046] Figure 7 This is a structural block diagram of a parking monitoring device in one embodiment;

[0047] Figure 8 This is a diagram of the internal structure of an electronic device in one embodiment. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] The parking monitoring method provided in this application can be applied to, for example... Figure 1 In the application environment shown, electronic device 102 communicates with management platform 104 via a network. Electronic device 102 may have at least one camera, for example, it may have two cameras. Electronic device 102 may be installed at the parking area to be monitored; for example, it may be placed on the roadside to monitor at least one parking area within the roadside area. The installation position of the camera in electronic device 102 above the ground may be within a preset height range, which may be a low range, for example, 3 to 5 meters above the ground. Management platform 104 may run on a server, which may be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. It is understood that the parking monitoring method provided in this embodiment may also be executed independently by electronic device 102.

[0050] Based on such Figure 1In the illustrated application environment, electronic device 102 can, in response to detecting a target vehicle entering a parking area based on received current monitoring video frames, determine the parking start time of the target vehicle, monitor the parking area based on current monitoring video frames captured from the parking start time, determine the overall credibility of the target vehicle being in the parking area, and, in response to the overall credibility meeting preset parking end conditions, determine the parking end time of the target vehicle. It can then send the parking start time and parking end time to management platform 104 to instruct management platform 104 to generate resource consumption information for the target vehicle based on the parking start time and parking end time. Furthermore, management platform 104 can also push the resource consumption information to a mobile terminal bound to the target vehicle to receive resources provided by the mobile terminal according to the resource consumption information.

[0051] In one exemplary embodiment, such as Figure 2 As shown, a parking monitoring method is provided, which can be applied to... Figure 1 Taking electronic device 102 as an example, the explanation includes the following steps 202 to 212. Wherein:

[0052] Step 202: In response to detecting that the target vehicle has entered the parking area based on the received current monitoring video frame, determine the parking start time of the target vehicle.

[0053] The current monitoring video frame refers to the video frame captured by the camera of the electronic device at the current time. This means the camera can monitor the parking area in real-time in video mode, capturing video frames continuously. The parking area is a parking space used for parking vehicles. The parking area can be a rectangular area. The parking start time is the time when the target vehicle begins to park within the parking area.

[0054] For example, an electronic device can receive a current monitoring video frame captured by a camera. If a vehicle is detected in the parking area in the current monitoring video frame and no vehicle is detected in the parking area in at least one adjacent historical video frame before the current monitoring video frame, then the vehicle detected in the parking area in the current monitoring video frame is taken as the target vehicle, and it is determined that the target vehicle has entered the parking area. The shooting time of the current monitoring video frame can be determined as the parking start time of the target vehicle.

[0055] Step 204: Based on the current surveillance video frames captured from the start time of parking, monitor multiple types of first vehicle information of the target vehicle in the parking area and determine the information credibility of each type of first vehicle information.

[0056] The first vehicle information can be vehicle information monitored in the parking area from the start time of parking until the overall credibility meets the preset parking end conditions, obtained through the current monitoring video frame. This vehicle information can be used to identify the target vehicle and distinguish it from other vehicles. Vehicle information can also be referred to as structured vehicle information.

[0057] Multiple types of first vehicle information can be the first information under multiple preset vehicle information types. These preset vehicle information types can include vehicle location, license plate number, vehicle color, vehicle model, license plate color, or others. Multiple types of first vehicle information can also be specific information under multiple preset vehicle information types; for example, it could be a specific vehicle location, a specific license plate number, a specific vehicle color, a specific vehicle model, and a specific license plate color. The credibility of the first vehicle information refers to its degree of trustworthiness.

[0058] Different parameters can be used to represent the reliability of vehicle information under different preset vehicle information types. For vehicle location, the vehicle location can be the position of the bounding box of the target vehicle detected in the current monitoring video frame. This can be achieved by detecting the bounding box position of the target vehicle using an object detection model, along with the confidence level of that bounding box. The confidence level of the bounding box is then used as the reliability of the vehicle location information. The position of the bounding box can be represented by the coordinates of at least two vertices of the bounding box (e.g., the top-left corner and the bottom-right corner) relative to the current monitoring video frame. The object detection model can be the YOLOv5 model (version 5 of the YOLO series of object detection models), the YOLOv7 model (version 7 of the YOLO series of object detection models), or others.

[0059] For license plate numbers, a character recognition model can be used to identify the license plate number and the class probability of each character in the license plate number. The representative value of the class probability of each character in the license plate number can then be used as the reliability of the information. The character recognition model can be an OCR (Optical Character Recognition) model. The representative value of the class probability of each character can be the average of the class probabilities of each character, the minimum of the class probabilities of each character, or another value.

[0060] For each type of vehicle color, vehicle model, and license plate color, a classification model can be used to identify the type of information in an image. The probability of the category of the information for that type can be used as the confidence level of the information for that type. The classification model can employ a Convolutional Neural Network (CNN). The classification model for identifying the type of information in an image can be trained using a training set of images specific to that task, where the final output category of the CNN can be set as multiple specific pieces of information for that type. For example, the multiple specific pieces of information for vehicle color can include black, white, red, or others. The multiple specific pieces of information for vehicle model can include cars, trucks, or others. The multiple specific pieces of information for license plate color can include blue, green, black, or others.

[0061] In some scenarios, electronic devices include cameras, and may also include LiDAR, RFID sensors or other sensors. Electronic devices can capture surveillance video frames through cameras, and can also obtain vehicle outlines through LiDAR scanning. Based on the vehicle outlines, the vehicle model of the target vehicle can be identified. If the target vehicle has an electronic tag, the license plate number of the target vehicle can be read through an RFID sensor.

[0062] For example, the electronic device may receive each current monitoring video frame captured from the start time of parking, monitor multiple first vehicle information of the target vehicle in the parking area based on the received current detection video frames, and determine the information credibility of each first vehicle information.

[0063] In one embodiment, the electronic device may generate identification information of the target vehicle in response to determining the parking start time of the target vehicle, track the target according to the identification information, and during the target tracking process, monitor multiple first vehicle information of the target vehicle in the parking area based on the current monitoring video frames captured from the parking start time, and determine the information credibility of each first vehicle information.

[0064] The identification information may include ID (Identity). Target tracking can be implemented using the DeepSORT algorithm (Deep Simple Online and Realtime Tracking, a multi-target tracking algorithm improved based on SORT), the BoT-SORT algorithm (Robust Associations Multi-Pedestrian Tracking, a multi-target tracking algorithm proposed by Aharon et al. in 2022), or other algorithms.

[0065] In some scenarios, when generating the identification information of a target vehicle, the identification information of the parking area can also be obtained, and the identification information of the target vehicle can be associated with the identification information of the parking area to facilitate target tracking. The identification information of the parking area can include the ID of the parking area, and can also include the area where the parking area is identified in the camera's monitoring image. The identified area is used to mark the location of the parking area in the monitoring video frame. For example, in the real world, parking areas can be marked by lines, and the visual image of the lines can be identified in the monitoring image, thereby determining the identified area.

[0066] In one embodiment, the electronic device may receive each current monitoring video frame captured from the start time of parking, perform target detection based on the received current detection video frame, determine the bounding box of the target vehicle in the current detection video frame, when the center position of the bounding box is within the marked area of ​​the parking area in the current detection video frame, monitor multiple first vehicle information of the target vehicle in the parking area, and determine the information credibility of each first vehicle information.

[0067] Step 206: Determine the credibility of the first vehicle information in the current monitoring video frame based on the credibility of each of the various first vehicle information types.

[0068] Among them, the credibility of the first vehicle information represents the credibility of the combination of various first vehicle information of the target vehicle obtained based on the current monitoring video frame.

[0069] For example, the electronic device can obtain the pre-configured weights of each of the various first vehicle information, and perform a weighted calculation on the information credibility of each of the various first vehicle information according to the pre-configured weights of each of the various first vehicle information to obtain the credibility of the first vehicle information in the current monitoring video frame.

[0070] Here, the pre-configured weights are weights that are pre-configured. Specifically, the multiple first vehicle information types can be first information under multiple preset vehicle information types, and the pre-configured weights of each of the multiple first vehicle information types can be the pre-configured weights of their respective preset vehicle information types. For example, the multiple preset vehicle information types may include vehicle location, license plate number, vehicle color, vehicle model, and license plate color. The pre-configured weight of vehicle location can be greater than the pre-configured weights of license plate number, vehicle color, vehicle model, and license plate color. For example, the pre-configured weights of vehicle location, license plate number, vehicle color, vehicle model, and license plate color may be 0.5, 0.2, 0.1, 0.1, and 0.1, respectively. Alternatively, the multiple preset vehicle information types may include vehicle location, license plate number, and vehicle model, and their pre-configured weights may be 0.6, 0.2, and 0.2, respectively.

[0071] In one embodiment, the electronic device can perform a weighted calculation on the credibility of various types of first vehicle information, and then map the results to a preset numerical range using a nonlinear mapping function to obtain the credibility of the first vehicle information in the current monitored video frame. The nonlinear mapping function can be a Sigmoid function, a Softmax function, or others. The preset numerical range can be from 0 to 1.

[0072] In one embodiment, if the electronic device does not detect multiple first vehicle information of the target vehicle in the parking area based on the received current detection video frame, it can set the confidence level of the first vehicle information in the current monitoring video frame to empty or zero.

[0073] Step 208: Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, determine the overall credibility of the target vehicle being in the parking area.

[0074] Historical surveillance video frames are those captured before the current surveillance video frame was captured. At least one historical surveillance video frame can be one or more consecutive historical surveillance video frames adjacent to the current surveillance video frame. For example, at least one historical surveillance video frame can be two historical surveillance video frames adjacent to the current surveillance video frame. It can be understood that the camera can continuously capture surveillance video frames, obtaining various surveillance video frames arranged in chronological order of capture time; each surveillance video frame then has adjacent surveillance video frames according to the order of arrangement.

[0075] The overall reliability is used to determine whether a target vehicle has left the parking area. Since the reliability of the first vehicle information in the current monitoring video frame is determined based on the individual reliability of multiple first vehicle information sets, and these individual reliability sets are determined based on the target vehicle monitored in the parking area from the current monitoring video frame taken since the parking start time, the reliability of the first vehicle information in the current monitoring video frame can still meet the preset parking end conditions even if the target vehicle leaves the parking area or an anomaly occurs in the current monitoring video frame. Therefore, judging whether a target vehicle has left the parking area solely based on the reliability of the first vehicle information in the current monitoring video frame may result in misjudgment. However, by combining the reliability of the first vehicle information in the current monitoring video frame and at least one historical monitoring video frame, the probability of misjudgment can be reduced, and the accuracy of determining whether a target vehicle has left the parking area can be improved. An anomaly in the current monitoring video frame could be due to the target vehicle being obscured in the parking area during the capture of the current monitoring video frame, resulting in the target vehicle not appearing in the current monitoring video frame. Alternatively, it could be due to a surge in the number of vehicles captured by the camera during the capture of the current monitoring video frame, leading to a surge in the amount of information in the current monitoring video frame. This would result in an abnormality in the reliability of various primary vehicle information monitored based on the current monitoring video frame.

[0076] For example, the electronic device can perform a weighted calculation on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame to obtain the overall credibility of the target vehicle being in the parking area.

[0077] In the weighted calculation, the preset weights used for the credibility of the first vehicle information in the current monitoring video frame and at least one historical monitoring video frame can be positively correlated with the order in which the monitoring video frames were captured. That is, the later the capture time, the greater the preset weight. For example, the weight for the credibility of the first vehicle information in the current monitoring video frame can be a first preset weight, and the sum of the weights for the credibility of the first vehicle information in at least one historical monitoring video frame can be a second preset weight. The first preset weight can be greater than the second preset weight; for example, the first preset weight could be 0.75, and the second preset weight could be 0.25.

[0078] Step 210: In response to the overall credibility meeting the preset parking end conditions, determine the parking end time of the target vehicle.

[0079] The preset parking end condition can be the condition that must be met to determine if the target vehicle has ended parking. Starting from the parking start time, when the target vehicle leaves the parking area, it can be determined that the target vehicle has ended parking. In other words, the preset parking end condition can be the condition that must be met to determine if the target vehicle has left the parking area.

[0080] For example, the electronic device can compare the overall confidence level with a preset overall confidence value. When the overall confidence level is less than the preset overall confidence value, it can be determined that the overall confidence level meets the preset parking end condition, and the recording time of the current monitoring video frame can be determined as the parking end time of the target vehicle. The preset overall confidence value can be a value between 0 and 1, or between 0 and 100%, such as 5%, 10%, or others. The preset overall confidence value can be close to 0.

[0081] Step 212: Generate resource consumption information for the target vehicle based on the parking start time and parking end time.

[0082] The resource consumption information may include the amount of resources consumed by the target vehicle in the parking area, and may also include various vehicle information. The resource quantity can be the parking duration occupied by the target vehicle in the parking area, or the parking fee required for the target vehicle to park in the parking area. The parking duration can be the length of time from the start time to the end time of parking. The parking fee can be calculated based on the start time, end time, and the parking price per hour between the start and end times. The parking price per hour can be the cost per hour of parking. The parking price per hour can be a fixed value, or it can vary depending on the time period from the start time to the end time, and the parking price can be updated periodically.

[0083] For example, an electronic device can generate resource consumption information of a target vehicle based on the parking start time and parking end time, and push the resource consumption information to a mobile terminal bound to the target vehicle.

[0084] In one embodiment, the electronic device can send the parking start time and parking end time to the management platform, instructing the management platform to generate resource consumption information of the target vehicle based on the parking start time and parking end time. The management platform can then push the resource consumption information to the mobile terminal bound to the target vehicle.

[0085] In one embodiment, the management platform can periodically acquire historical parking data from the parking lot where the parking area is located, and based on the acquired historical parking data, calculate peak parking periods and off-peak parking periods, and adjust the parking unit price during peak and off-peak periods. The historical parking data can include the time periods during which each parking area in the parking lot was used over a past period. Peak parking periods are the periods when the utilization rate of each parking area in the parking lot reaches a first preset utilization rate. Off-peak parking periods are the periods when the utilization rate of each parking area in the parking lot is lower than a second preset utilization rate. The first preset utilization rate can be greater than the second preset utilization rate; for example, the first preset utilization rate can be 90%, and the second preset utilization rate can be 20%. When adjusting the parking unit price, the parking unit price during peak periods can be set as the first unit price, the parking unit price during off-peak periods can be set as the second unit price, and the parking unit price for periods other than peak and off-peak periods can be set as a third unit price. The first unit price can be greater than the third unit price, and the third unit price can be greater than the second unit price.

[0086] In the aforementioned parking monitoring method, target vehicles are monitored by receiving surveillance video frames. Upon detecting a target vehicle entering the parking area, the parking start time of the target vehicle is automatically determined. Furthermore, since multiple pieces of first vehicle information are obtained based on the current surveillance video frames captured from the parking start time, the reliability of the first vehicle information in the current surveillance video frame can be determined, confirming that the target vehicle was still in the parking area when the current surveillance video frame was captured. Moreover, the reliability of the first vehicle information integrates the individual reliability of multiple pieces of first vehicle information, improving the accuracy and stability of the first vehicle information reliability. Subsequently, in response to the overall reliability of the target vehicle being in the parking area satisfying the preset parking end conditions, the parking end time of the target vehicle is automatically determined. The overall reliability is determined based on the reliability of the first vehicle information in the current surveillance video frame and at least one historical surveillance video frame, avoiding misjudgments caused by anomalies such as the parking area being obscured in the current surveillance video frame, thus improving the accuracy of determining the parking end time. By automatically and accurately determining the parking start time and parking end time, the resource consumption information of the target vehicle is automatically and accurately generated, improving the efficiency of parking monitoring.

[0087] In an exemplary embodiment, step 202 may include: receiving a current monitoring video frame captured by a camera in a roadside area; the roadside area includes a parking area; in response to detecting a target vehicle entering the parking area based on the received current monitoring video frame, detecting multiple types of second vehicle information of the target vehicle based on the current monitoring video frame, and determining the information credibility of each type of second vehicle information; determining the credibility of the second vehicle information in the current monitoring video frame based on the information credibility of each type of second vehicle information; and determining the parking start time of the target vehicle if the credibility of the second vehicle information meets a preset credibility condition.

[0088] The roadside area is the area along one side of the road that can be used for parking. The roadside area may include multiple parking areas. The second vehicle information can be the vehicle information detected from the moment the target vehicle enters the parking area until the parking start time, obtained through the current monitoring video frame. Multiple types of second vehicle information can be second information under various preset vehicle information types. The credibility of the second vehicle information refers to its degree of reliability.

[0089] When acquiring information about a second vehicle, the target vehicle may only have a small portion of it entering the parking area, such as the front or rear of the vehicle entering the parking area while the center of the vehicle does not. Since the monitoring screen is larger than the parking area, the vehicle information can still be detected through the current monitoring video frame even if only a small portion of the target vehicle enters the parking area.

[0090] The credibility of second vehicle information characterizes the overall credibility of various second vehicle information about a target vehicle obtained from the current monitoring video frame. The preset credibility condition is the condition that must be met to determine the credibility of the various second vehicle information detected in the current monitoring video frame. When the credibility of the second vehicle information is greater than the preset credibility value, it can be determined that the credibility of the second vehicle information meets the preset credibility condition. The preset credibility value can be 75%, 80%, or other percentages, or it can be 0.75, 0.8, or other values ​​between 0 and 1. When the credibility of the second vehicle information meets the preset credibility condition, the recording time of the current monitoring video frame can be determined as the starting time of the target vehicle's parking.

[0091] In this embodiment, when a target vehicle is detected entering a parking area based on the received current monitoring video frame, various second vehicle information of the target vehicle is detected based on the current monitoring video frame, and the credibility of each type of second vehicle information is determined. Then, based on the credibility of each type of second vehicle information, the credibility of the second vehicle information in the current monitoring video frame is determined. This can improve the stability and accuracy of the credibility of the second vehicle information. Furthermore, if the credibility of the second vehicle information meets the preset credibility conditions, it can be indicated that the various second vehicle information identified for the target vehicle is credible. At this time, the parking start time of the target vehicle is determined, ensuring the accuracy of the parking start time of the target vehicle.

[0092] In an exemplary embodiment, when the credibility of the second vehicle information meets a preset credibility condition, the step of determining the parking start time of the target vehicle may include: monitoring the duration of the target vehicle's stay in the parking area based on the current monitoring video frame captured after the target vehicle enters the parking area; in response to determining that the stay duration first reaches a preset duration based on the current monitoring video frame, obtaining the first capture time of the current monitoring video frame; and determining the first capture time as the parking start time of the target vehicle when the credibility of the second vehicle information meets the preset credibility condition.

[0093] The preset duration can be 20 seconds, 30 seconds, or other values. The first shooting time can be the shooting time of the current monitoring video frame when the determined dwell time reaches the preset duration.

[0094] For example, after the target vehicle enters the parking area, the electronic device can continue to receive the captured current monitoring video frames. When it is first determined based on the current monitoring video frame that the center position of the target vehicle's bounding box is within the marked area of ​​the parking area, the capture time of the current monitoring video frame is determined as the first time. Whenever it is determined based on the current monitoring video frames captured from the first time that the center position of the target vehicle's bounding box is within the marked area of ​​the parking area, the capture time of the current monitoring video frame is determined as the second time. The time difference between the first time and the second time is determined as the duration of the target vehicle's stay in the parking area.

[0095] In this embodiment, after the target vehicle enters the parking area, in response to determining that the target vehicle's dwell time has reached a preset duration based on the current monitoring video frame, the first shooting time of the current monitoring video frame is obtained. If the credibility of the second vehicle information meets the preset credibility condition, the first shooting time is determined as the parking start time of the target vehicle. In this way, parking time can be avoided from starting as soon as the target vehicle passes through the parking area, thus ensuring the accuracy of the parking start time of the target vehicle.

[0096] In an exemplary embodiment, step 206 may include: obtaining the pre-configured weights of each of the various types of second vehicle information; performing a weighted calculation on the information credibility of each of the various types of second vehicle information according to the pre-configured weights of each of the various types of second vehicle information to obtain the initial vehicle information credibility of the current monitoring video frame; and non-linearly mapping the initial vehicle information credibility to a preset numerical range to obtain the second vehicle information credibility of the current monitoring video frame.

[0097] The various types of second vehicle information can be second information under various preset vehicle information types, and the pre-configured weights of each type of second vehicle information can be pre-configured weights of their respective preset vehicle information types. The preset numerical range can be 0 to 1. Nonlinear mapping can be implemented using a nonlinear mapping function. The nonlinear mapping function can be the Sigmoid function (S-shaped function), the Softmax function (normalized exponential function), or others. The Sigmoid function can be expressed as... Where S(x) can represent the output of the Sigmoid function, x on the right side of the equation can be used to substitute input values ​​(such as the initial vehicle information credibility in this embodiment), and e can represent the natural constant.

[0098] Nonlinear mapping can map an input value to a category that represents the probability of the trustworthy category in a binary classification (which may include trustworthy and untrustworthy categories). Thus, since the trustworthiness of the second vehicle information in the current monitoring video frame is obtained through nonlinear mapping, the ability of the trustworthiness of the second vehicle information in the current monitoring video frame to express whether it is trustworthy is improved.

[0099] In this embodiment, the credibility of each of the various types of second vehicle information is weighted according to their respective pre-configured weights. This allows for the reasonable fusion of the credibility of the various types of second vehicle information. Furthermore, the credibility of the initial vehicle information is non-linearly mapped to a preset numerical range to obtain the credibility of the second vehicle information in the current monitoring video frame. This improves the ability of the credibility of the second vehicle information in the current monitoring video frame to express whether it is credible.

[0100] In an exemplary embodiment, step 210 may include: in response to the overall credibility meeting a preset parking end condition, determining a second shooting time of the current monitoring video frame; detecting multiple third vehicle information of the target vehicle based on the target monitoring video frame shot after the second shooting time, and determining the credibility of each type of third vehicle information; determining the credibility of the third vehicle information of the target monitoring video frame based on the credibility of each type of third vehicle information; and determining the second shooting time as the parking end time of the target vehicle when the credibility of the third vehicle information meets a preset credibility condition.

[0101] The second capture time of the current monitoring video frame is the capture time when the overall credibility determined based on the current monitoring video frame meets the preset parking end conditions. The target monitoring video frame can be a monitoring video frame captured after the second capture time but before the target vehicle leaves the camera's monitoring screen.

[0102] Third-party vehicle information can be vehicle information of a target vehicle detected based on target surveillance video frames. Multiple types of third-party vehicle information can be third information under various preset vehicle information types. The credibility of third-party vehicle information refers to its degree of trustworthiness. The credibility of third-party vehicle information can characterize the overall credibility of multiple types of third-party vehicle information obtained based on target surveillance video frames.

[0103] In this embodiment, in response to the comprehensive credibility meeting the preset parking end condition, the second shooting time of the current monitoring video frame is determined. Furthermore, based on the target monitoring video frame after the second shooting time, the credibility of the third vehicle information of the target monitoring video frame is determined. When the credibility of the third vehicle information meets the preset credibility condition, it can be indicated that the multiple third vehicle information identified for the target vehicle is credible. At this time, the second shooting time is determined as the parking end time of the target vehicle, ensuring the accuracy of the parking end time of the target vehicle.

[0104] In an exemplary embodiment, when the credibility of the third vehicle information meets a preset credibility condition, and the relationship between multiple third vehicle information and multiple second vehicle information meets a preset matching condition, the second shooting time is determined as the parking end time of the target vehicle; based on one of the multiple third vehicle information or multiple second vehicle information, the parking start time, and the parking end time, the resource consumption information of the target vehicle is generated.

[0105] Among the various types of third-party vehicle information and various types of second-party vehicle information, those belonging to the same preset vehicle information type correspond to each other. When each type of third-party vehicle information and each type of second-party vehicle information is identical, it can be determined that the relationship between the various types of third-party vehicle information and various types of second-party vehicle information meets the preset matching conditions. The various types of third-party vehicle information or various types of second-party vehicle information can be combined with the resource quantity determined based on the parking start time and parking end time to form the resource consumption information of the target vehicle.

[0106] In an exemplary embodiment, after determining the credibility of the third vehicle information in the target monitoring video frame based on the credibility of each of the various third vehicle information, the parking monitoring method may further include: sending the target monitoring video frame, the various third vehicle information, and the credibility of the third vehicle information to a management platform, so as to instruct the management platform to generate an audit prompt message based on the various third vehicle information and the target monitoring video frame and push it to the audit terminal when the credibility of the third vehicle information does not meet the preset credibility conditions; and after receiving the audit success message for the audit prompt message through the management platform, determining the second shooting time as the parking end time of the target vehicle.

[0107] The review notification message can be a message prompting reviewers to verify the accuracy of various third-party vehicle information based on target surveillance video frames. The review terminal is the terminal used by the reviewers. This terminal can log into a client with a management platform, thus receiving review notification messages pushed by the management platform deployed on the server. A successful review message indicates that the accuracy of various third-party vehicle information has been confirmed after review based on the target surveillance video frames.

[0108] For example, the electronic device can send the target monitoring video frame, various third vehicle information, and the credibility of the third vehicle information to the management platform; the management platform can determine whether the credibility of the third vehicle information meets the preset credibility conditions. If the credibility of the third vehicle information does not meet the preset credibility conditions, it generates an audit prompt message based on the various third vehicle information and the target monitoring video frame, and pushes the audit prompt message to the audit terminal. After receiving the audit success message for the audit prompt message, it determines the second shooting time as the parking end time of the target vehicle.

[0109] In this embodiment, by cooperating with the management platform and the audit terminal, if the credibility of the third vehicle information does not meet the preset credibility conditions, the audit terminal will make a second judgment. After the management platform receives the audit success information for the audit prompt, it will determine the second shooting time as the parking end time of the target vehicle, which can improve the accuracy of the parking end time.

[0110] In one application scenario, the parking area can be located in a roadside area, where electronic devices can be installed. These devices can capture monitoring video frames using two cameras. An example diagram of the monitoring video frames can be shown below. Figure 3 As shown, it is understandable that, although Figure 3 Presented as a grayscale image, the actual surveillance video frame can be a color image, based on, for example... Figure 4 The diagram shown illustrates the vehicle start-stop detection process. Figure 5 The diagram shown illustrates the monitoring process during vehicle parking. Figure 6The diagram shown illustrates the vehicle parking detection process. The parking monitoring method described above may specifically include the following steps.

[0111] See Figure 4 The electronic device can receive current monitoring video frames captured by cameras on the roadside area, monitor whether a target vehicle has entered the parking area, and in response to the detection of a target vehicle entering the parking area based on the received current monitoring video frame, detect multiple types of second vehicle information of the target vehicle based on the current monitoring video frame, determine the credibility of each type of second vehicle information, and determine the credibility of the second vehicle information in the current monitoring video frame based on the credibility of each type of second vehicle information.

[0112] The electronic device can monitor whether the center position of the target vehicle is within the parking area based on the current monitoring video frame captured after the target vehicle enters the parking area. If not, it returns to the step of monitoring whether the target vehicle has entered the parking area based on the current monitoring video frame. If so, it starts monitoring the duration of the target vehicle's stay in the parking area.

[0113] The electronic device can respond to the determination that the dwell time has reached a preset duration based on the current monitoring video frame, obtain the first shooting time of the current monitoring video frame, and send the first shooting time of the current monitoring video frame and the credibility of the second vehicle information of the current monitoring video frame to the management platform.

[0114] The management platform can determine whether the credibility of the second vehicle information meets the preset credibility conditions to determine whether multiple pieces of second vehicle information are credible. If the credibility of the second vehicle information meets the preset credibility conditions, the first shooting time is determined as the parking start time of the target vehicle. If the credibility of the second vehicle information does not meet the preset credibility conditions, an audit prompt message is sent to the audit terminal to prompt the audit personnel to conduct an audit. If the audit is successful, the credibility of multiple pieces of second vehicle information is determined, and the first shooting time is determined as the parking start time of the target vehicle. If the audit fails, the system returns to the step of monitoring whether the target vehicle has entered the parking area based on the current monitoring video frame.

[0115] See Figure 5The electronic device can generate IDs for both the parking area and the target vehicle, and draw the marked area of ​​the parking area in the camera's monitoring screen (polygon drawing is supported). Target tracking of the target vehicle within the parking area is performed. Specifically, it can receive the current monitoring video frame captured from the parking start time, detect the bounding box of the target vehicle in the current monitoring video frame, and determine whether the center position of the target vehicle's bounding box is within the marked area of ​​the parking area based on the parking area ID, the target vehicle ID, the target vehicle's bounding box, and the marked area of ​​the parking area in the current monitoring video frame. If so, it monitors multiple pieces of first vehicle information for the target vehicle in the parking area and determines the credibility of each piece of first vehicle information. Based on the credibility of each piece of first vehicle information, it determines the credibility of the first vehicle information in the current monitoring video frame. Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, it determines the overall credibility of the target vehicle being in the parking area, and updates the overall credibility. If not, it returns to the steps of target tracking of the target vehicle in the parking area. If the overall confidence level is determined to be less than the preset overall confidence level, then the overall confidence level is determined to meet the preset parking end condition, and the parking end time of the target vehicle is determined accordingly; if the overall confidence level is determined to be not less than the preset overall confidence level, the target vehicle in the parking area continues to be tracked.

[0116] catch Figure 5 See Figure 6 In response to the overall credibility meeting the preset parking end condition, the second shooting time of the current monitoring video frame is determined; based on the credibility of each of the various third vehicle information, the credibility of the third vehicle information of the target monitoring video frame is determined; the target monitoring video frame, the various third vehicle information, and the credibility of the third vehicle information are sent to the management platform.

[0117] The management platform can determine whether the credibility of third-party vehicle information meets preset credibility conditions to assess the credibility of various third-party vehicle information. If the credibility of the third-party vehicle information meets the preset credibility conditions, the second shooting time is determined as the parking end time of the target vehicle. If the credibility of the third-party vehicle information does not meet the preset credibility conditions, an audit prompt message is generated based on various third-party vehicle information and the target monitoring video frame, and then pushed to the audit terminal to prompt the audit personnel to conduct manual audit. If a successful audit message is received in response to the audit prompt message, that is, the audit is confirmed to be passed, indicating that the various third-party vehicle information is credible, and the second shooting time is determined as the parking end time of the target vehicle. Based on the parking start time and the parking end time, resource consumption information of the target vehicle is generated.

[0118] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0119] Based on the same inventive concept, this application also provides a parking monitoring device for implementing the parking monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more parking monitoring device embodiments provided below can be found in the limitations of the parking monitoring method described above, and will not be repeated here.

[0120] In one exemplary embodiment, such as Figure 7 As shown, a parking monitoring device 700 is provided, including: a start information determination module 710, a parking area monitoring module 720, an end information determination module 730, and a resource consumption information determination module 740, wherein:

[0121] The starting information determination module 710 is used to determine the parking start time of the target vehicle in response to the detection of the target vehicle entering the parking area based on the received current monitoring video frame.

[0122] The parking area monitoring module 720 is used to monitor multiple types of first vehicle information of a target vehicle in the parking area based on the current monitoring video frame captured from the parking start time, and determine the information credibility of each type of first vehicle information; determine the credibility of the first vehicle information in the current monitoring video frame based on the credibility of each type of first vehicle information; and determine the overall credibility of the target vehicle being in the parking area based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame.

[0123] The end information determination module 730 is used to determine the parking end time of the target vehicle in response to the comprehensive credibility meeting the preset parking end conditions.

[0124] The resource consumption information determination module 740 is used to determine the parking end time of the target vehicle in response to the comprehensive credibility meeting the preset parking end conditions.

[0125] In an exemplary embodiment, the starting information determination module 710 is further configured to receive a current monitoring video frame captured by a camera in a roadside area; the roadside area includes a parking area; in response to detecting a target vehicle entering the parking area based on the received current monitoring video frame, the module detects multiple types of second vehicle information of the target vehicle based on the current monitoring video frame and determines the information credibility of each type of second vehicle information; based on the information credibility of each type of second vehicle information, the module determines the credibility of the second vehicle information in the current monitoring video frame; and if the credibility of the second vehicle information meets a preset credibility condition, the module determines the parking start time of the target vehicle.

[0126] In an exemplary embodiment, the starting information determination module 710 is further configured to monitor the duration of the target vehicle's stay in the parking area based on the current monitoring video frame captured after the target vehicle enters the parking area; in response to determining that the stay duration has reached a preset duration based on the current monitoring video frame, obtain the first shooting time of the current monitoring video frame; and, if the credibility of the second vehicle information meets the preset credibility condition, determine the first shooting time as the parking start time of the target vehicle.

[0127] In an exemplary embodiment, the initial information determination module 710 is further configured to obtain the pre-configured weights of each of the various types of second vehicle information; perform a weighted calculation on the information credibility of each of the various types of second vehicle information according to the pre-configured weights of each of the various types of second vehicle information to obtain the initial vehicle information credibility of the current monitoring video frame; and non-linearly map the initial vehicle information credibility to a preset numerical range to obtain the second vehicle information credibility of the current monitoring video frame.

[0128] In an exemplary embodiment, the end information determination module 730 is further configured to, in response to the comprehensive credibility meeting a preset parking end condition, determine the second shooting time of the current monitoring video frame; detect multiple third vehicle information of the target vehicle based on the target monitoring video frame shot after the second shooting time, and determine the information credibility of each third vehicle information; determine the third vehicle information credibility of the target monitoring video frame based on the information credibility of each of the multiple third vehicle information; and determine the second shooting time as the parking end time of the target vehicle when the third vehicle information credibility meets a preset credibility condition.

[0129] In an exemplary embodiment, the end information determination module 730 is further configured to send the target monitoring video frame, various third vehicle information and the credibility of the third vehicle information to the management platform, so as to instruct the management platform to generate an audit prompt message based on the various third vehicle information and the target monitoring video frame and push it to the audit terminal when the credibility of the third vehicle information does not meet the preset credibility conditions; after receiving the audit success information for the audit prompt message through the management platform, the second shooting time is determined as the parking end time of the target vehicle.

[0130] Each module in the aforementioned parking monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of the electronic device in hardware form or independent of it, or stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0131] In one exemplary embodiment, an electronic device is provided, the internal structure of which can be shown as follows: Figure 8 As shown, this electronic device includes a processor, memory, input / output interfaces, a communication interface, and a camera. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface and camera are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a parking monitoring method. The camera is used to capture monitoring video frames.

[0132] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0133] In one embodiment, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0134] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0135] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0136] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0137] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0138] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0139] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A parking monitoring method, characterized in that, The method includes: In response to detecting that a target vehicle has entered the parking area based on the received current monitoring video frame, the parking start time of the target vehicle is determined; Based on the current surveillance video frames captured from the parking start time, monitor multiple first vehicle information of the target vehicle in the parking area and determine the information credibility of each first vehicle information. The credibility of the first vehicle information in the current monitoring video frame is determined based on the credibility of each of the various types of first vehicle information. Based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame, the overall credibility of the target vehicle being in the parking area is determined. In response to the overall credibility meeting the preset parking end conditions, the parking end time of the target vehicle is determined; Based on the parking start time and parking end time, the resource consumption information of the target vehicle is generated.

2. The method according to claim 1, characterized in that, The response to detecting a target vehicle entering the parking area based on the received current monitoring video frame, and determining the parking start time of the target vehicle, includes: Receives current surveillance video frames captured from a roadside area; the roadside area includes parking areas. In response to detecting that a target vehicle has entered a parking area based on the received current monitoring video frame, the system detects multiple types of second vehicle information of the target vehicle based on the current monitoring video frame and determines the information credibility of each type of second vehicle information. The credibility of the second vehicle information in the current monitoring video frame is determined based on the credibility of each of the various types of second vehicle information. If the credibility of the second vehicle information meets the preset credibility conditions, the parking start time of the target vehicle is determined.

3. The method according to claim 2, characterized in that, Determining the parking start time of the target vehicle when the credibility of the second vehicle information meets a preset credibility condition includes: Based on the current surveillance video frames captured after the target vehicle enters the parking area, monitor the duration of the target vehicle's stay in the parking area; In response to determining that the dwell time has reached a preset duration based on the current monitoring video frame, the first shooting time of the current monitoring video frame is obtained; If the credibility of the second vehicle information meets the preset credibility conditions, the first shooting time is determined as the parking start time of the target vehicle.

4. The method according to claim 2, characterized in that, The step of determining the credibility of the second vehicle information in the current monitoring video frame based on the credibility of each of the various types of second vehicle information includes: Obtain the pre-configured weights of each of the various types of second vehicle information; Based on the pre-configured weights of the various types of second vehicle information, the credibility of each type of second vehicle information is weighted and calculated to obtain the initial vehicle information credibility of the current monitoring video frame. The initial vehicle information credibility is nonlinearly mapped to a preset numerical range to obtain the second vehicle information credibility of the current monitoring video frame.

5. The method according to any one of claims 1-4, characterized in that, The step of determining the parking end time of the target vehicle in response to the overall confidence level satisfying the preset parking end condition includes: In response to the overall credibility meeting the preset parking end condition, the second shooting time of the current monitoring video frame is determined; Based on the target surveillance video frames captured after the second shooting time, detect multiple third vehicle information of the target vehicle and determine the information credibility of each third vehicle information. Based on the credibility of each of the various third vehicle information, the credibility of the third vehicle information in the target monitoring video frame is determined. When the credibility of the third vehicle information meets the preset credibility conditions, the second shooting time is determined as the parking end time of the target vehicle.

6. The method according to claim 5, characterized in that, The method further includes: The target monitoring video frame, the various third vehicle information, and the credibility of the third vehicle information are sent to the management platform to instruct the management platform to generate an audit prompt message based on the various third vehicle information and the target monitoring video frame and push it to the audit terminal when the credibility of the third vehicle information does not meet the preset credibility conditions. After receiving the successful review information for the review prompt from the management platform, the second shooting time is determined as the parking end time of the target vehicle.

7. A parking monitoring device, characterized in that, The device includes: The starting information determination module is used to determine the parking start time of the target vehicle in response to detecting that the target vehicle has entered the parking area based on the received current monitoring video frame. The parking area monitoring module is used to monitor multiple types of first vehicle information of the target vehicle in the parking area based on the current monitoring video frame captured from the parking start time, and determine the information credibility of each type of first vehicle information; determine the credibility of the first vehicle information in the current monitoring video frame based on the information credibility of each type of first vehicle information; and determine the overall credibility of the target vehicle being in the parking area based on the credibility of the first vehicle information in the current monitoring video frame and the credibility of the first vehicle information in at least one historical monitoring video frame. The end information determination module is used to determine the parking end time of the target vehicle in response to the comprehensive credibility meeting the preset parking end conditions; The resource consumption information determination module is used to determine the parking end time of the target vehicle in response to the comprehensive credibility meeting the preset parking end conditions.

8. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images