Parking inspection method and device and inspection vehicle

Abstract

The invention relates to a parking space inspection method and device and an inspection vehicle. The method comprises the following steps: acquiring a real-time positioning coordinate of an inspection vehicle when a plurality of continuous parking spaces are inspected; a berth calibration table is inquired to obtain berth information of a target berth in the multiple continuous berths, the berth calibration table comprises the berth information of each berth, and the berth information at least comprises berth numbers and berth coordinates; when it is determined that the inspection vehicle approaches the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, berth detection is carried out on the collected video images, and a berth detection result is obtained; and when the parking space detection result indicates that the inspection vehicle arrives at the target parking space, performing vehicle detection on the collected video picture to obtain vehicle information, and obtaining an inspection matching result according to the parking space information of the target parking space and the vehicle information. By adopting the method, the accuracy of vehicle parking matching can be improved at low cost.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a berth inspection method, device, electronic device, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of urban roads and the increase in the number of cars, the demand for parking fees is gradually increasing, and a fast, convenient and low-cost way to manage parking fees is needed. The parking inspection vehicle is a device that integrates multiple technologies. It can monitor and manage parking spaces in real time through cameras and positioning sensors. It can replace traditional manual handheld terminals and assist parking administrators in automatically, efficiently and accurately recording parking information.

[0003] Some parking inspection and matching methods rely on the satellite positioning signal of the inspection vehicle. In the city, in scenes such as high-rise buildings, dense trees, and overpasses, the satellite positioning signal deteriorates, and the positioning deviation ranges from a few meters to more than ten meters, resulting in inaccurate parking matching. In order to correct the deviation, the relevant technology adds an RFID reader to the inspection vehicle, and installs RFID tags, Bluetooth and other auxiliary devices at each berth. The construction is complicated and expensive, and the RFID tags need to be regularly inspected and replaced if they are damaged. Summary of the invention

[0004] Based on this, it is necessary to provide a berth inspection method, device, electronic device, computer-readable storage medium and computer program product to address the above technical problems, which can improve the accuracy of berth matching vehicles at a low cost.

[0005] In a first aspect, the present application provides a berth inspection method, comprising:

[0006] When inspecting multiple consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle;

[0007] querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0008] When it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result;

[0009] When the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained based on the berth information of the target berth and the vehicle information.

[0010] In a second aspect, the present application also provides a berth inspection device, comprising:

[0011] A positioning module is used to obtain the real-time positioning coordinates of the inspection vehicle when inspecting multiple consecutive berths;

[0012] A query module, used for querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0013] A berth detection module, configured to perform berth detection on the collected video images to obtain a berth detection result when it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth;

[0014] The matching module is used to perform vehicle detection on the collected video images to obtain vehicle information when the berth detection result indicates that the inspection vehicle has arrived at the target berth, and obtain an inspection matching result according to the berth information of the target berth and the vehicle information.

[0015] In some embodiments, the berth information further includes a berth number of the next berth; the query module is further used to query the berth information of the target berth in the berth calibration table, and obtain the berth number of the next berth of the target berth from the berth information of the target berth; according to the berth number of the next berth, query the berth calibration table to obtain the berth information of the next berth, and the berth information of the next berth includes the berth coordinates of the next berth;

[0016] The berth detection module is further used to perform berth detection on the collected video images to obtain berth detection results;

[0017] The matching module is further configured to perform vehicle detection on the collected video images to obtain vehicle information when the berth detection result indicates that the inspection vehicle has arrived at the next berth, and obtain an inspection matching result based on the berth information of the next berth and the vehicle information.

[0018] In some embodiments, the berth inspection device further includes:

[0019] The calibration module is used to calibrate each berth in the plurality of continuous berths to obtain berth information of each berth; and generate a berth calibration table according to the berth information of each berth.

[0020] In some embodiments, the berth inspection device further includes:

[0021] The positioning accuracy determination module is used to determine the current positioning accuracy level according to the real-time positioning coordinates of the inspection vehicle; when the current positioning accuracy level is a non-fixed solution, execute the step of querying the berth calibration table to obtain the berth information of the target berth among the multiple continuous berths.

[0022] In some embodiments, the berth inspection device further includes:

[0023] A positioning matching module is used to calculate the distance between the real-time positioning coordinates and the berth coordinates of each of the multiple consecutive berths when the current positioning accuracy level is a fixed solution, determine the berth where the inspection vehicle is located according to the distance, perform vehicle detection on the collected video images to obtain vehicle information, and obtain an inspection matching result based on the berth information of the berth where the inspection vehicle is located and the vehicle information.

[0024] In some embodiments, the berth detection module is further used to calculate the distance between the real-time positioning coordinates and the berth coordinates of the target berth recorded in the berth calibration table; when the distance is less than a set threshold, it is determined that the inspection vehicle is close to the target berth.

[0025] In some embodiments, the berth detection module is further used to determine that the inspection vehicle has arrived at the target berth when it is determined according to the berth detection result that the area ratio of the berth area in the video picture is greater than a set threshold.

[0026] In some embodiments, the berth detection module is further used to control the inspection vehicle to skip the current berth when the berth detection results corresponding to multiple consecutive frames of video images indicate that the area ratio of the berth area in the video image is less than a set threshold.

[0027] In a third aspect, the present application further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0028] When inspecting multiple consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle;

[0029] querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0030] When it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result;

[0031] When the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained according to the berth information of the target berth and the vehicle information.

[0032] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0033] When inspecting multiple consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle;

[0034] Querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0035] When it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result;

[0036] When the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained according to the berth information of the target berth and the vehicle information.

[0037] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0038] When inspecting multiple consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle;

[0039] Querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0040] When it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result;

[0041] When the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained according to the berth information of the target berth and the vehicle information.

[0042] In a sixth aspect, the present application further provides an inspection vehicle, comprising a positioning device, a camera, a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0043] When inspecting multiple consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle;

[0044] Querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0045] When it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result;

[0046] When the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained according to the berth information of the target berth and the vehicle information.

[0047] The above-mentioned berth inspection method, device, electronic device, computer-readable storage medium, computer program product and inspection vehicle obtain the real-time positioning coordinates of the inspection vehicle when inspecting multiple consecutive berths; query the berth calibration table to obtain the berth information of the target berth among the multiple consecutive berths, the berth calibration table includes the berth information of each berth, and the berth information includes at least the berth number and the berth coordinates; when it is determined that the inspection vehicle is close to the target berth based on the real-time positioning coordinates and the berth coordinates of the target berth, berth detection is performed on the collected video images to obtain the berth detection result; when the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and the inspection matching result is obtained based on the berth information and vehicle information of the target berth.

[0048] Since the berth calibration table includes the berth information of each berth, and the berth information of each berth includes at least the berth number and the berth coordinates, during the berth inspection process, there is no need to rely on the real-time positioning coordinates to determine which specific berth has been reached. It is only necessary to determine that the inspection vehicle is currently close to the berth based on the real-time positioning coordinates. The berth detection result can be obtained by performing berth detection on the video footage collected when the inspection vehicle approaches the berth. When the berth detection result indicates that the inspection vehicle has arrived at the target berth, the vehicle information is obtained by performing vehicle detection on the collected video footage. The berth information and the vehicle information are matched to obtain an inspection matching result. In this way, even in the scenario of poor satellite signals, accurate matching of berth information and vehicle information can be achieved. There is no need to add new equipment or berth labels. Inspection of scenarios such as satellite signals within the city can be achieved based on the original inspection vehicle, effectively reducing equipment costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0050] Figure 1 is an application environment diagram of a berth inspection method in an embodiment;

[0051] Figure 2 A schematic diagram of a process of a berth inspection method in one embodiment;

[0052] Figure 3 A schematic diagram of a berth inspection method in a detailed embodiment;

[0053] Figure 4 A schematic diagram of an inspection vehicle performing a berth inspection in one embodiment;

[0054] Figure 5 A schematic diagram of a flow chart of a berth inspection method in another embodiment;

[0055] Figure 6 is a structural block diagram of a berth inspection device in one embodiment;

[0056] Figure 7 FIG. 4 is a diagram showing the internal structure of an electronic device in one embodiment. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0058] Typically, the inspection vehicle used for berth inspection has the following functions:

[0059] 1. It has high-precision satellite positioning capability, which is used to locate the inspection vehicle. According to the positioning coordinates of the inspection vehicle and the berth coordinates of the berth, it can determine which berth the inspection vehicle is currently located in.

[0060] 2. It has the ability to identify vehicles, which is used to identify the vehicle information of the vehicles parked in the berth, including license plate, model and other information.

[0061] 3. Combine the current time, berth information and vehicle information into a patrol matching result.

[0062] However, in urban areas with tall buildings, dense trees, overpasses, and other scenarios, the satellite positioning signal deteriorates, and the positioning error ranges from a few meters to more than ten meters, resulting in inaccurate positioning of the patrol vehicle and an inability to accurately identify which parking space it is currently in front of, leading to inaccurate parking space matching of vehicles.

[0063] The berth inspection method provided in the embodiment of the present application has berth information of each berth included in the berth calibration table, and the berth information of each berth includes at least a berth number and berth coordinates. During the berth inspection process, there is no need to rely on the real-time positioning coordinates to determine which berth has been reached. It is only necessary to determine that the inspection vehicle is currently close to the berth based on the real-time positioning coordinates. Then, a berth detection can be performed on the video image collected when the inspection vehicle is close to the berth to obtain a berth detection result. When the berth detection result indicates that the inspection vehicle has reached the target berth, a vehicle detection is performed on the collected video image to obtain vehicle information. The berth information and the vehicle information are matched to obtain an inspection matching result. In this way, even in a scenario with poor satellite signals, accurate matching of the berth information and the vehicle information can be achieved. There is no need to add new equipment or berth tags. Inspection of scenarios such as satellite signals within the city can be achieved based on the original inspection vehicle, thereby effectively reducing equipment costs.

[0064] The berth inspection method provided in the embodiment of the present application can be applied to Figure 1 The inspection vehicle 100 is shown.

[0065] In some embodiments, the inspection vehicle 100 includes at least one camera 101 , a positioning device 102 , and a central control processing unit 103 .

[0066] In some embodiments, two cameras are installed on the inspection vehicle 100, one camera is installed on the right front of the inspection vehicle, and the other camera is installed on the right rear of the inspection vehicle. In some embodiments, four cameras are installed on the inspection vehicle 100, one camera is installed on the right front of the inspection vehicle, one camera is installed on the right rear of the inspection vehicle, one camera is installed on the left front of the inspection vehicle, and one camera is installed on the left rear of the inspection vehicle, so that the inspection vehicle can inspect the parking spaces on the left and right sides of the inspection vehicle at the same time, thereby improving the inspection efficiency. Camera 101 is used to collect video images.

[0067] In some embodiments, the positioning device 102 is used to implement high-precision GNSS (Global Navigation Satellite System) positioning of the inspection vehicle to obtain real-time positioning coordinates. The positioning device 102 can provide centimeter-level GPS positioning services of no less than 20 Hz.

[0068] In some embodiments, the central control processing unit 103 is used to receive the video images captured by the camera 101. In some embodiments, the central control processing unit 103 is used to perform parking detection on the video images to obtain parking detection results. In some embodiments, the central control processing unit 103 is also used to perform vehicle detection on the video images to obtain vehicle information.

[0069] In some embodiments, the central control processing unit 103 is used to determine the current positioning accuracy level based on the real-time positioning coordinates of the inspection vehicle. When the current positioning accuracy level is a fixed solution, the distance between the real-time positioning coordinates and the berth coordinates of each berth in a plurality of consecutive berths is calculated respectively, and the berth of the inspection vehicle is determined based on the distance. Vehicle detection is performed on the collected video images to obtain vehicle information, and the inspection matching result is obtained based on the berth information and vehicle information of the berth where the inspection vehicle is located.

[0070] In some embodiments, the central control processing unit 103 is used to determine the current positioning accuracy level based on the real-time positioning coordinates of the inspection vehicle. When the current positioning accuracy level is a non-fixed solution, that is, when the positioning deviation is large due to the obstruction of the satellite signal, the berth calibration table can be queried to obtain the berth information of the target berth among multiple consecutive berths. When it is determined that the inspection vehicle is close to the target berth based on the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result. When it is determined that the inspection vehicle is close to the target berth based on the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result.

[0071] In some embodiments, the inspection vehicle 100 is equipped with electronic equipment, which includes a camera, a positioning device, and a central control processing unit.

[0072] In an exemplary embodiment, Figure 2 As shown, a berth inspection method is provided, which is applied to Figure 1 Taking the electronic device on the inspection vehicle 100 as an example, the following steps 202 to 208 are included. Among them:

[0073] Step 202, when inspecting a plurality of consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle.

[0074] The multiple consecutive parking spaces may be parking spaces on the roadside or in a parking lot. The patrol vehicle may be a two-wheel patrol vehicle or a four-wheel patrol vehicle. A positioning device is installed on the patrol vehicle, and the positioning device can realize real-time positioning of the patrol vehicle based on a positioning system (e.g., a global satellite navigation system). A camera is installed on the patrol vehicle, and the camera is used to collect video images.

[0075] Specifically, the electronic device can receive the real-time positioning coordinates sent by the positioning device after positioning the inspection vehicle. Positioning accuracy is affected by many factors, including the atmosphere, multipath effects, etc. In practical applications, due to the influence of these factors, the actual positioning accuracy may deviate. Especially in scenes such as high-rise buildings, dense trees, and overpasses in cities, the satellite positioning signal deteriorates, and the positioning deviation ranges from a few meters to more than ten meters. Since the distance between multiple consecutive berths is very close, the distance between the berth coordinates is also very close. If the real-time positioning coordinates deviate, it will cause the berth matched according to the real-time positioning coordinates to deviate, resulting in inaccurate berth matching of vehicles.

[0076] When electronic equipment locates the inspection vehicle through positioning equipment, it can determine the current positioning accuracy level based on the real-time positioning coordinates of the inspection vehicle. Among them, the positioning accuracy levels include fixed solution, floating solution and single point solution. The accuracy of the fixed solution can reach the centimeter level to the millimeter level, usually between 1~3 centimeters, the accuracy of the floating point solution is between the centimeter level and the meter level, and the accuracy of the single point solution is at the meter level, and the stability is relatively low.

[0077] Step 204, querying a berth calibration table to obtain berth information of a target berth among a plurality of consecutive berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate.

[0078] The berth calibration table includes berth information of each berth, and the berth information of each berth includes at least a berth number and a berth coordinate. Optionally, the berth information may also include the berth number of the next berth, the berth information may also include the berth type, the berth information may also include the berth number of the previous berth, the berth information may also include the berth numbers of the previous and next berths, the berth information may also include identification information of whether the berth is the first berth or the last berth, and so on. The target berth among multiple consecutive berths may be the first berth or the last berth among the multiple consecutive berths, so that the inspection vehicle can start the berth inspection from the first berth or the last berth among the multiple consecutive berths. Of course, the target berth among multiple consecutive berths may also be any designated berth among the multiple berths, and the inspection vehicle may start the berth inspection from the designated berth among the multiple consecutive berths.

[0079] In some embodiments, when the target berth is the first berth among multiple consecutive berths, querying the berth calibration table to obtain the berth information of the target berth among the multiple consecutive berths may be: querying the berth calibration table to obtain the berth information of the first berth among the multiple consecutive berths, the berth information includes the berth coordinates, so that the berth coordinates of the first berth can be obtained. In this way, the subsequent electronic device can determine whether the inspection vehicle is close to the first berth among the multiple consecutive berths according to the real-time positioning coordinates and the berth coordinates of the first berth, and inspect from the first berth in sequence.

[0080] In one embodiment, when the target berth is the last berth among multiple consecutive berths, querying the berth calibration table to obtain the berth information of the target berth among the multiple consecutive berths may be: querying the berth calibration table to obtain the berth information of the last berth among the multiple consecutive berths. In this way, the subsequent electronic device can determine whether the inspection vehicle is close to the last berth among the multiple consecutive berths according to the real-time positioning coordinates and the berth coordinates of the last berth, and inspect from the last berth in sequence.

[0081] In some embodiments, the method further includes: berth calibration for each berth in a plurality of continuous berths to obtain berth information of each berth; generating a berth calibration table according to the berth information of each berth. Among them, berth calibration is the process of determining the berth information of the berth by the calibration device in a stationary state, including berth coordinates, berth type, etc. In an obstructed environment, positioning in a stationary state is more accurate than positioning in a dynamic state. In some embodiments, when the inspection vehicle stops at the berth, the positioning device on the inspection vehicle can be used for positioning, and the positioning coordinates are used as the berth coordinates. In some embodiments, other high-precision positioning devices can also be used to stop at the berth for positioning, and the positioning coordinates are used as the berth coordinates.

[0082] In some embodiments, the berth information of each berth in the berth calibration table, in addition to the above-mentioned berth number and berth coordinates, may also include the berth numbers of the front and rear berths. By recording the berth numbers of the berths located before and after each berth in the berth calibration table, the berth number of the next berth or the previous berth can be obtained by querying the berth calibration table, thereby obtaining the berth information of the next berth or the previous berth. In this way, even in a scenario with poor satellite signals, the problem of inaccurate berth matching caused by low positioning accuracy can be overcome.

[0083] In some embodiments, the method further includes: determining the current positioning accuracy level based on the real-time positioning coordinates of the inspection vehicle; when the current positioning accuracy level is a non-fixed solution, executing the step of querying the berth calibration table to obtain the berth information of the target berth among multiple consecutive berths and subsequent steps.

[0084] Specifically, when the positioning accuracy level of the received real-time positioning coordinates is a non-fixed solution, that is, a floating point solution or a single point solution, it means that the positioning deviation is large at this time. The electronic device can perform berth detection through subsequent steps to achieve matching between the berth and the vehicle. This matching method can be called a berth identification inspection method.

[0085] In some embodiments, the method also includes: when the current positioning accuracy level is a fixed solution, respectively calculating the distance between the real-time positioning coordinates and the berth coordinates of each berth in a plurality of consecutive berths, determining the berth where the inspection vehicle is located based on the distance, performing vehicle detection on the collected video images to obtain vehicle information, and obtaining the inspection matching result based on the berth information and vehicle information of the berth where the inspection vehicle is located.

[0086] Specifically, when the positioning accuracy level of the received real-time positioning coordinates is a fixed solution, it means that the positioning accuracy is high at this time. Therefore, the electronic device can query the berth coordinates of each berth, calculate the distance between the real-time positioning coordinates and each berth coordinate, and take the berth corresponding to the berth coordinate with the closest distance and a distance less than the set threshold as the berth where the current inspection vehicle is located. The berth information of the berth is matched with the vehicle information to obtain an inspection matching result. This matching method can be called a berth positioning inspection method.

[0087] In other words, the accuracy of the current real-time positioning coordinates can be determined according to the positioning accuracy level of the real-time positioning coordinates. If it is accurate enough, the real-time positioning coordinates can be used to determine which berth the inspection vehicle is currently in. If it is not accurate enough, it is possible to first determine which berth it is approaching, and then determine which berth the inspection vehicle is currently in through berth detection, thereby achieving the ability to improve the accuracy of berth matching vehicles at a low cost when the positioning signal is weak.

[0088] Step 206 , when it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result.

[0089] In an embodiment of the present application, when the accuracy of the real-time positioning coordinates is not high, the real-time positioning coordinates are used to determine whether the inspection vehicle is close to a target berth among multiple consecutive berths, rather than to determine whether it has reached the target berth among multiple consecutive berths. When it is determined that the inspection vehicle is close to the target berth based on the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video screen to obtain a berth detection result. In some embodiments, the electronic device may call a berth detection model based on deep learning, perform a berth detection on the collected video screen, and obtain a berth detection result. The berth detection result indicates the location information of the area where the berth is located in the video screen. The berth detection model can be implemented based on a target detection algorithm. Optionally, the proportion of berths in the video screen can be calculated based on the location information.

[0090] In some embodiments, the method further includes: calculating the distance between the real-time positioning coordinates and the berth coordinates of the target berth recorded in the berth calibration table; and determining that the inspection vehicle is close to the target berth when the distance is less than a set threshold.

[0091] Specifically, after the electronic device obtains the berth information of the target berth among multiple consecutive berths by querying the berth calibration table, the berth information includes the berth coordinates of the target berth. The electronic device obtains the real-time positioning coordinates of the inspection vehicle and calculates the distance between the real-time positioning coordinates and the berth coordinates of the target berth. When the distance is less than a set threshold, it can be determined that the inspection vehicle is close to the target berth.

[0092] Step 208 , when the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained based on the berth information and vehicle information of the target berth.

[0093] The electronic device can determine whether the inspection vehicle has reached the target berth based on the berth detection results.

[0094] In some embodiments, the electronic device can determine that the inspection vehicle has reached the target berth when the area ratio of the berth area in the video screen is greater than a set threshold according to the berth detection result. For example, when the area ratio of the berth area in the video screen is greater than 90%, it can be determined that the inspection vehicle has reached the target berth.

[0095] In some embodiments, vehicle detection is performed on the collected video images to obtain vehicle information. Specifically, the electronic device may call a vehicle detection model based on deep learning to perform vehicle detection on the collected video images to obtain vehicle information. The vehicle detection model may be implemented based on a target detection algorithm. The vehicle information may include a license plate number. Optionally, the vehicle information may also include at least one of a vehicle model, a vehicle body color, a vehicle brand, and a position information of a 3D chassis of the vehicle in the video image.

[0096] In some embodiments, obtaining the inspection matching result according to the berth information and vehicle information of the target berth may be: generating an inspection matching result according to the berth number, license plate number, current time, date, and road name of the target berth.

[0097] In some embodiments, the electronic device can send the inspection matching result to the user terminal corresponding to the license plate number, and can also upload the inspection matching result to the berth management server so that the berth management server can manage the berth according to the inspection matching result, such as berth fee statistics, berth status statistics, etc.

[0098] In some embodiments, the method further includes: when the parking space detection results corresponding to the continuous multiple frames of video images indicate that the parking space area in the video image accounts for an area ratio less than a set threshold, controlling the inspection vehicle to skip the current parking space.

[0099] Specifically, when the area of ​​a berth appearing in a plurality of consecutive video frames is small, or even when the berth does not appear in a plurality of consecutive frames, the berth may be obstructed. In this case, the electronic device may skip (overlook) the inspection of the current berth and wait for the inspection vehicle to arrive at the next berth before performing berth detection in the video.

[0100] In the above-mentioned berth inspection method, since the berth calibration table includes the berth information of each berth, and the berth information of each berth includes at least the berth number and the berth coordinates, during the berth inspection process, there is no need to rely on the real-time positioning coordinates to determine which specific berth has been reached. It is only necessary to determine that the inspection vehicle is currently close to the berth based on the real-time positioning coordinates. The berth detection result can be obtained by performing berth detection on the video image collected when the inspection vehicle approaches the berth. When the berth detection result indicates that the inspection vehicle has arrived at the target berth, the vehicle detection is performed on the collected video image to obtain the vehicle information, and the berth information and the vehicle information are matched to obtain an inspection matching result. In this way, even in the scenario of poor satellite signals, accurate matching of berth information and vehicle information can be achieved. There is no need to add new equipment or berth tags. Inspection of scenarios such as satellite signals within the city can be achieved on the basis of the original inspection vehicle, effectively reducing equipment costs.

[0101] In some embodiments, the berth information also includes the berth number of the next berth; the method also includes: querying the berth information of the target berth, and obtaining the berth number of the next berth of the target berth from the berth information of the target berth; querying the berth calibration table according to the berth number of the next berth, and obtaining the berth information of the next berth, and the berth information of the next berth includes the berth coordinates of the next berth; performing berth detection on the collected video images to obtain the berth detection results; when the berth detection results indicate that the inspection vehicle has arrived at the next berth, performing vehicle detection on the collected video images to obtain vehicle information, and obtaining the inspection matching result according to the berth information and vehicle information of the next berth.

[0102] Specifically, after the electronic device obtains the berth information of the target berth among multiple consecutive berths by querying the berth calibration table, the berth information includes the berth coordinates of the target berth, and the electronic device obtains the real-time positioning coordinates of the inspection vehicle, calculates the distance between the real-time positioning coordinates and the berth coordinates of the target berth, and when the distance is less than a set threshold, it can be determined that the inspection vehicle is close to the target berth. The electronic device can perform vehicle detection on the collected video screen to obtain vehicle information, and obtain an inspection matching result based on the berth information and vehicle information of the target berth.

[0103] Then, the electronic device queries the berth calibration table, and obtains the berth number of the next berth of the target berth from the berth information of the target berth. Thus, according to the berth number of the next berth, the berth calibration table is queried to obtain the berth information of the next berth. Then, the electronic device can perform berthing detection on the collected video images to obtain the berthing detection result. The electronic device can judge whether the inspection vehicle has arrived at the next berth according to the berthing detection result. When the berthing detection result indicates that the inspection vehicle has arrived at the next berth, the vehicle detection is performed on the collected video images to obtain the vehicle information, and the inspection matching result is obtained according to the berthing information and vehicle information of the next berth.

[0104] By repeating this method continuously, as the inspection vehicle moves, the inspection vehicle can start from the target berth (for example, the first berth) and inspect multiple consecutive berths in sequence. Even in the current situation where the positioning deviation is large due to obstruction of the satellite signal, accurate matching of the berth and the vehicle can be achieved.

[0105] It can be understood that the method of judging whether the inspection vehicle has arrived at the next berth according to the berth detection result is consistent with the relevant content mentioned above and will not be repeated here.

[0106] like Figure 3 FIG. 1 is a flow chart of a berth inspection method in a detailed embodiment. The method can be executed by an electronic device on an inspection vehicle, and includes the following steps:

[0107] Step 302: berth calibration is performed on each berth of the plurality of consecutive berths to obtain berth information of each berth, where the berth information at least includes a berth number, berth coordinates and a berth number of the next berth.

[0108] Step 304: Generate a berth calibration table according to the berth information of each berth.

[0109] Step 306, when inspecting a plurality of consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle.

[0110] Step 308, determining the current positioning accuracy level according to the real-time positioning coordinates of the inspection vehicle.

[0111] Specifically, when the current positioning accuracy level is a non-fixed solution, execute step 310; when the current positioning accuracy level is a non-fixed solution, execute step 334.

[0112] Step 310: query the berth calibration table to obtain berth information of a target berth among a plurality of consecutive berths.

[0113] Step 312, calculating the distance between the real-time positioning coordinates and the berth coordinates of the target berth recorded in the berth calibration table.

[0114] Step 314, determine whether the distance is less than a set threshold. If so, execute step 316; if not, return to step 306.

[0115] Specifically, judging whether the distance is less than a set threshold is to determine whether the patrol vehicle is close to the target berth. When the distance is less than the set threshold, it can be determined that the patrol vehicle is close to the target berth.

[0116] Step 316, performing berth detection on the collected video image to obtain a berth detection result, wherein the berth detection result indicates position information of the area where the berth is located in the video image.

[0117] Step 318, judging whether the area ratio of the parking space in the video image is greater than a set threshold value according to the parking space detection result. If yes, executing step 320, if not, returning to step 316.

[0118] Specifically, judging whether the area ratio of the berth area in the video screen is greater than the set threshold according to the berth detection result is to determine whether the inspection vehicle has reached the target berth. When the area ratio of the berth area in the video screen is greater than the set threshold, it can be determined that the inspection vehicle has reached the target berth.

[0119] Step 320: Perform vehicle detection on the collected video images to obtain vehicle information.

[0120] Step 322: Obtain an inspection matching result based on the berth information and vehicle information of the target berth.

[0121] Step 324, when it is determined according to the berth detection result that the inspection vehicle has left the target berth, the berth information of the target berth in the berth calibration table is queried, and the berth number of the next berth of the target berth is obtained from the berth information of the target berth.

[0122] Specifically, when the area ratio of the berth area in the video picture gradually decreases, it can be determined that the inspection vehicle has left the target berth.

[0123] Step 326, according to the berth number of the next berth, query the berth calibration table to obtain the berth information of the next berth, and the berth information of the next berth includes the berth coordinates of the next berth.

[0124] Step 328, performing parking space detection on the collected video images to obtain parking space detection results.

[0125] Step 330: When the berth detection result indicates that the inspection vehicle has arrived at the next berth, vehicle detection is performed on the collected video image to obtain vehicle information, and an inspection matching result is obtained based on the berth information and vehicle information of the next berth.

[0126] Step 332, determine whether the current berth is the last berth among the multiple consecutive berths. If not, return to step 326 to continue execution, if yes, end the process.

[0127] Step 334, respectively calculate the distance between the real-time positioning coordinates and the berth coordinates of each of the multiple consecutive berths, determine the berth where the inspection vehicle is located based on the distance, perform vehicle detection on the collected video images to obtain vehicle information, and obtain the inspection matching result based on the berth information and vehicle information of the berth where the inspection vehicle is located.

[0128] Figure 4 It is a schematic diagram of a patrol vehicle performing a berth inspection in one embodiment.

[0129] Reference Figure 4 , inspection vehicles from multiple consecutive berths ( Figure 4The inspection starts near the first berth (there are 3 berths in total, which is only for illustration). The inspection vehicle can conduct berth inspection according to the designated route corresponding to the parking position of the berth. The berth information of each berth is recorded in the berth calibration table. The berth coordinates of the first berth are B, and the real-time positioning coordinates of the inspection vehicle are A. When the distance between AB is less than the set threshold L, the berth detection can be started on the video screen collected by the inspection vehicle. When the berth detection result indicates that the berth has occupied more than a preset proportion m (for example, m is 90%) of the video screen, it can be determined that the first berth has been reached. At this time, the vehicle detection can be performed on the video screen to obtain the vehicle information, and the first inspection matching result can be obtained based on the berth information of the first berth and the detected vehicle information.

[0130] As the inspection vehicle moves, the first berth will gradually move out of the picture. Based on the latest berth detection result, the inspection vehicle can determine that the berth is gradually moving out of the picture and the inspection vehicle is leaving the first berth. The inspection vehicle can obtain the berth information of the next berth of the first berth, that is, obtain the berth information of the second berth. At the same time, the inspection vehicle continues to perform berth detection on the collected video screen. When the berth detection result indicates that the berth has occupied more than the preset proportion of the video screen, it can be determined that the second berth has been reached. At this time, the video screen can be detected to obtain vehicle information, and the second inspection matching result is obtained based on the berth information of the second berth and the detected vehicle information. At this time, the inspection vehicle is triggered to query the berth calibration table to determine whether the current berth is marked as the last berth among the multiple consecutive berths. Since the second berth is not marked as the last berth, the inspection continues.

[0131] As the inspection vehicle moves, the second berth will gradually move out of the picture. Based on the latest berth detection result, the inspection vehicle can determine that the berth is gradually moving out of the picture and is leaving the second berth. The inspection vehicle can obtain the berth information of the next berth, that is, the berth information of the third berth. At the same time, the inspection vehicle continues to perform berth detection on the collected video screen. When the berth detection result indicates that the berth has occupied more than the preset proportion of the video screen, it can be determined that the third berth has been reached. At this time, the video screen can be detected for vehicles to obtain vehicle information, and the third inspection matching result is obtained based on the berth information of the third berth and the detected vehicle information. At this time, the inspection vehicle is triggered to query the berth calibration table to determine whether the current berth is marked as the last berth among the multiple consecutive berths. Since the third berth is marked as the last berth, the inspection ends.

[0132] like Figure 5 FIG. 1 is a flow chart of a berth inspection method in one embodiment.

[0133] 501. Berth marking.

[0134] Specifically, the inspection vehicle itself or other high-precision positioning can be used to calibrate the berths, and the berth information of each berth can be obtained when it is stationary, including GPS positioning coordinates. The positioning coordinate offset is smaller when it is stationary in an obstructed environment. The berth information can also include the berth type, berth number, whether it is the first berth or the last berth among multiple consecutive berths, and the berth numbers of the front and rear berths.

[0135] 502. Perform berth inspection on a plurality of consecutive berths and obtain the real-time positioning coordinates of the inspection vehicle.

[0136] 503. Determine whether the current positioning accuracy level is centimeter level.

[0137] If yes, adopt the berth positioning inspection method; if no, adopt the berth identification inspection method.

[0138] 504. Obtain the berth coordinates of the first berth from the berth calibration table.

[0139] 505. Obtain the real-time positioning coordinates of the inspection vehicle.

[0140] 506. Calculate the distance between the berth coordinates and the real-time positioning coordinates.

[0141] 507. Determine whether the inspection vehicle is close to the first berth based on whether the distance is less than or equal to a set threshold.

[0142] If yes, continue to step 508, if no, return to step 505.

[0143] 508. Perform berth detection on the collected video images to obtain berth detection results.

[0144] 509. Determine whether the proportion of the parking area in the video image is greater than a set threshold according to the parking detection result. If yes, execute step 510; if not, return to step 508.

[0145] Step 510: Perform vehicle detection on the collected video images to obtain vehicle information.

[0146] Step 511: The berth information and vehicle information are combined into a patrol matching result.

[0147] Step 512: Use the berth calibration table to query the next berth number and berth information of the next berth.

[0148] Step 513: determine whether the current berth is the last berth. If yes, end the process. If no, return to step 508.

[0149] In this embodiment, when the current berth has exited the video screen, the berth calibration table can be used to obtain the next berth number and berth information of the next berth, and the berths in the video screen can continue to be identified in real time. When the berth frame occupies more than or equal to 90% of the screen position, vehicle detection is performed to obtain vehicle information, and an inspection matching result is formed based on the berth information and the vehicle information. This is repeated until the continuous berth inspection is completed. Since the berth calibration table includes the berth information of each berth, and the berth information of each berth includes at least the berth number and the berth coordinates, during the entire berth inspection process, there is no need to rely on the real-time positioning coordinates to determine which specific berth has been reached. It is only necessary to determine that the inspection vehicle is currently close to the berth based on the real-time positioning coordinates. The berth detection result can be obtained by performing berth detection on the video footage collected when the inspection vehicle approaches the berth. When the berth detection result indicates that the inspection vehicle has arrived at the target berth, the vehicle information is obtained by performing vehicle detection on the collected video footage. The berth information and the vehicle information are matched to obtain an inspection matching result. In this way, even in scenarios with poor satellite signals, accurate matching of berth information and vehicle information can be achieved. There is no need to add new equipment or berth labels. Inspections of scenarios such as satellite signals within the city can be achieved based on the original inspection vehicle, effectively reducing equipment costs.

[0150] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0151] Based on the same inventive concept, the embodiment of the present application also provides a berth inspection device for implementing the berth inspection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more berth inspection device embodiments provided below can refer to the limitations of the berth inspection method above, and will not be repeated here.

[0152] In an exemplary embodiment, Figure 6 As shown, a berth inspection device 600 is provided, comprising: a positioning module 602, a query module 604, a berth detection module 606 and a matching module 608, wherein:

[0153] Positioning module 602, used to obtain the real-time positioning coordinates of the inspection vehicle when inspecting multiple consecutive berths;

[0154] A query module 604 is used to query a berth calibration table to obtain berth information of a target berth among a plurality of consecutive berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate;

[0155] The berth detection module 606 is used to perform berth detection on the collected video images to obtain a berth detection result when the inspection vehicle is determined to be close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth;

[0156] The matching module 608 is used to perform vehicle detection on the collected video images to obtain vehicle information when the berth detection result indicates that the inspection vehicle has arrived at the target berth, and obtain the inspection matching result according to the berth information and vehicle information of the target berth.

[0157] In some embodiments, the berth information further includes a berth number of the next berth; the query module 604 is further used to query the berth information of the target berth in the berth calibration table, and obtain the berth number of the next berth of the target berth from the berth information of the target berth; according to the berth number of the next berth, query the berth calibration table to obtain the berth information of the next berth, and the berth information of the next berth includes the berth coordinates of the next berth;

[0158] The parking space detection module 606 is further used to perform parking space detection on the collected video images to obtain parking space detection results;

[0159] The matching module 608 is further configured to perform vehicle detection on the collected video images to obtain vehicle information when the berth detection result indicates that the inspection vehicle has arrived at the next berth, and obtain an inspection matching result based on the berth information and vehicle information of the next berth.

[0160] In some embodiments, the berth inspection device 600 further includes:

[0161] The calibration module is used to calibrate each berth among a plurality of continuous berths to obtain berth information of each berth; and to generate a berth calibration table according to the berth information of each berth.

[0162] In some embodiments, the berth inspection device 600 further includes:

[0163] The positioning accuracy determination module is used to determine the current positioning accuracy level according to the real-time positioning coordinates of the inspection vehicle; when the current positioning accuracy level is a non-fixed solution, the step of querying the berth calibration table to obtain the berth information of the target berth among multiple consecutive berths is executed.

[0164] In some embodiments, the berth inspection device 600 further includes:

[0165] The positioning matching module is used to calculate the distance between the real-time positioning coordinates and the berth coordinates of each of the multiple consecutive berths when the current positioning accuracy level is a fixed solution, determine the berth where the inspection vehicle is located based on the distance, perform vehicle detection on the collected video images to obtain vehicle information, and obtain the inspection matching result based on the berth information and vehicle information of the berth where the inspection vehicle is located.

[0166] In some embodiments, the berth detection module 606 is further used to calculate the distance between the real-time positioning coordinates and the berth coordinates of the target berth recorded in the berth calibration table; when the distance is less than a set threshold, it is determined that the inspection vehicle is close to the target berth.

[0167] In some embodiments, the berth detection module 606 is further used to determine that the inspection vehicle has arrived at the target berth when it is determined according to the berth detection result that the area ratio of the berth area in the video image is greater than a set threshold.

[0168] In some embodiments, the parking space detection module 606 is further configured to control the inspection vehicle to skip the current parking space when the parking space detection results corresponding to multiple consecutive video frames indicate that the parking space area in the video frame accounts for less than a set threshold.

[0169] The above-mentioned berth inspection device 600, since the berth calibration table includes the berth information of each berth, and the berth information of each berth includes at least the berth number and the berth coordinates, during the berth inspection process, there is no need to rely on the real-time positioning coordinates to determine which specific berth has been reached. It is only necessary to determine that the inspection vehicle is currently close to the berth based on the real-time positioning coordinates. The berth detection can be performed on the video image collected when the inspection vehicle approaches the berth to obtain the berth detection result. When the berth detection result indicates that the inspection vehicle has arrived at the target berth, the vehicle detection is performed on the collected video image to obtain the vehicle information, and the berth information and the vehicle information are matched to obtain an inspection matching result. In this way, even in the scenario of poor satellite signals, the berth information and the vehicle information can be accurately matched. There is no need to add new equipment or berth tags. Inspections of scenarios such as satellite signals in cities can be realized on the basis of the original inspection vehicle, effectively reducing equipment costs.

[0170] Each module in the above-mentioned berth inspection device 600 can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in an electronic device in the form of hardware, or can be stored in a memory in an electronic device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0171] In an exemplary embodiment, an electronic device is provided. The electronic device may be an electronic device used for berth inspection on an inspection vehicle. The internal structure diagram thereof may be as shown in FIG. Figure 7 As shown. The electronic device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the electronic device is used to exchange information between the processor and an external device. The communication interface of the electronic device is used to communicate with an external device through a network connection. When the computer program is executed by the processor, a berth inspection method is implemented.

[0172] Those skilled in the art will understand that Figure 7 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] In an exemplary embodiment, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the berth inspection method provided in the above embodiment are implemented.

[0174] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the berth inspection method provided in the above embodiment are implemented.

[0175] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of the berth inspection method provided in the above embodiment when executed by a processor.

[0176] In one embodiment, an inspection vehicle is provided, including a positioning device, a camera, a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the berth inspection method provided in the above embodiment are implemented.

[0177] 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, stored data, displayed data, 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 relevant data must comply with relevant regulations.

[0178] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0179] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0180] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A berth inspection method, characterized in that: The method comprises: When inspecting multiple consecutive berths, obtain the real-time positioning coordinates of the inspection vehicle; Querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate; When it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth, a berth detection is performed on the collected video images to obtain a berth detection result; When the berth detection result indicates that the inspection vehicle has arrived at the target berth, vehicle detection is performed on the collected video images to obtain vehicle information, and an inspection matching result is obtained according to the berth information of the target berth and the vehicle information.

2. The method according to claim 1, characterized in that: The berth information also includes the berth number of the next berth; the method also includes: Querying the berth information of the target berth in the berth calibration table, and obtaining the berth number of the next berth of the target berth from the berth information of the target berth; According to the berth number of the next berth, query the berth calibration table to obtain berth information of the next berth, wherein the berth information of the next berth includes the berth coordinates of the next berth; Performing berth detection on the collected video images to obtain berth detection results; When the berth detection result indicates that the inspection vehicle has arrived at the next berth, vehicle detection is performed on the collected video image to obtain vehicle information, and an inspection matching result is obtained based on the berth information of the next berth and the vehicle information.

3. The method according to claim 1, characterized in that The method further comprises: Performing berth calibration on each of the plurality of continuous berths to obtain berth information of each berth; A berth calibration table is generated according to the berth information of each berth.

4. The method according to claim 1, characterized in that The method further comprises: Determine the current positioning accuracy level according to the real-time positioning coordinates of the inspection vehicle; In the case where the current positioning accuracy level is a non-fixed solution, the step of querying the berth calibration table to obtain berth information of the target berth among the multiple consecutive berths is performed.

5. The method according to claim 4, characterized in that The method further comprises: When the current positioning accuracy level is a fixed solution, the distance between the real-time positioning coordinates and the berth coordinates of each of the multiple consecutive berths is calculated respectively, the berth where the inspection vehicle is located is determined according to the distance, vehicle detection is performed on the collected video images to obtain vehicle information, and the inspection matching result is obtained based on the berth information of the berth where the inspection vehicle is located and the vehicle information.

6. The method according to claim 1, characterized in that The method further comprises: Calculating the distance between the real-time positioning coordinates and the berth coordinates of the target berth recorded in the berth calibration table; When the distance is less than a set threshold, it is determined that the inspection vehicle is close to the target berth.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: When it is determined according to the berth detection result that the area ratio of the berth region in the video picture is greater than a set threshold, it is determined that the inspection vehicle has arrived at the target berth.

8. The method according to claim 7, characterized in that The method further comprises: When the parking space detection results corresponding to the continuous multiple frames of video images indicate that the parking space area in the video image accounts for an area less than a set threshold in the video image, the inspection vehicle is controlled to skip the current parking space.

9. A berth inspection device, characterized in that: The device comprises: A positioning module is used to obtain the real-time positioning coordinates of the inspection vehicle when inspecting multiple consecutive berths; A query module, used for querying a berth calibration table to obtain berth information of a target berth among the plurality of continuous berths, wherein the berth calibration table includes berth information of each berth, and the berth information includes at least a berth number and a berth coordinate; A berth detection module, configured to perform berth detection on the collected video images to obtain a berth detection result when it is determined that the inspection vehicle is close to the target berth according to the real-time positioning coordinates and the berth coordinates of the target berth; The matching module is used to perform vehicle detection on the collected video images to obtain vehicle information when the berth detection result indicates that the inspection vehicle has arrived at the target berth, and obtain an inspection matching result according to the berth information of the target berth and the vehicle information.

10. A patrol vehicle, comprising a positioning device, a camera, a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

Images