Parking space information determination method and device, system, electronic equipment and computer medium

Abstract

The present disclosure provides a parking space information determination method and device, and particularly relates to the technical fields of image recognition, intelligent parking and intelligent transportation. The specific implementation scheme is as follows: obtaining parking space video data obtained by photographing a parking space area; wherein a camera device is installed near the parking space area; determining position information of the camera device and a fixed position relationship between the camera device and each parking space in the parking space area; and determining parking space information of each parking space in the parking space area based on the position information, the parking space video data and the fixed position relationship. The embodiment improves the accuracy of determining the parking space information.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer application, in particular to the technical field of image recognition, intelligent parking and intelligent transportation, and more particularly to a parking space information determination method and device, system, electronic equipment, computer readable medium and computer program product. BACKGROUND

[0002] With the development of China's economy, the vehicle market will continue to increase, and the parking problem will be further intensified, especially around hospitals, large shopping malls, tourist attractions, government departments, etc. The parking problem is more prominent.

[0003] The existing underground parking lot often uses ultrasonic, geomagnetic and other sensors to detect whether the parking space is occupied, and the parking space front indicator light displays the detection result. The driver determines whether the parking space is occupied according to the parking space front indicator light. For large parking lots, a certain number of ultrasonic or geomagnetic sensors and corresponding parking space indicator lights need to be purchased, which is high in cost. SUMMARY

[0004] A parking space information determination method and device, system, electronic equipment, computer readable medium and computer program product are provided.

[0005] According to a first aspect, a parking space information determination method is provided, which comprises: acquiring parking space video data obtained by photographing a parking space area; wherein a camera device is installed near the parking space area; determining position information of the camera device and a fixed position relationship between the camera device and each parking space in the parking space area; and determining parking space information of each parking space in the parking space area based on the position information, the parking space video data and the fixed position relationship.

[0006] According to a second aspect, a parking space information determination device is provided, which comprises: an acquisition unit configured to acquire parking space video data obtained by photographing a parking space area; wherein a camera device is installed near the parking space area; a relationship determination unit configured to determine position information of the camera device and a fixed position relationship between the camera device and each parking space in the parking space area; and an information determination unit configured to determine parking space information of each parking space in the parking space area based on the position information, the parking space video data and the fixed position relationship.

[0007] According to a third aspect, a parking space information determination system is provided, the system comprising: at least one camera device, each camera device corresponding to a parking space area of a garage, each parking space area comprising: a lane and a plurality of parking spaces located on both sides of the lane and distributed along a driving direction of the lane; each camera device configured to capture an image of the parking space area and obtain parking space video data of the parking space area; a control device connected to the at least one camera device, configured to, for each camera device, acquire parking space video data of the camera device; determine position information of the camera device and a fixed positional relationship between the camera device and each parking space in the corresponding parking space area; and determine parking space information of each parking space in each parking space area based on the position information, the parking space video data and the fixed positional relationship.

[0008] According to a fourth aspect, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in any implementation manner of the first aspect.

[0009] According to a fifth aspect, a non-transitory computer-readable storage medium storing computer instructions is provided, the computer instructions being used to cause a computer to perform the method described in any implementation manner of the first aspect.

[0010] According to a sixth aspect, a computer program product is provided, comprising a computer program, the computer program being used to implement the method described in any implementation manner of the first aspect when executed by a processor.

[0011] The parking space information determination method and device provided by the embodiments of the present disclosure first acquire parking space video data obtained by capturing a parking space area; wherein a camera device is installed near the parking space area; secondly, the position information of the camera device and the fixed positional relationship between the camera device and each parking space in the parking space area are determined; and finally, the parking space information of each parking space in the parking space area is determined based on the position information, the parking space video data and the fixed positional relationship. Thus, based on the position information of the camera device and the parking space video data, the parking space information of each parking space in the parking space area is determined, without the intervention of other parking space detection means, thereby saving the parking space information determination cost and improving the reliability of the obtained garage parking space information.

[0012] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0013] The accompanying drawings are used to better understand the present scheme and do not limit the present disclosure. Among them:

[0014] Figure 1 is a flow chart of one embodiment of the parking space information determination method according to the present disclosure;

[0015] Figure 2 is a schematic diagram of calculating coordinate offset value in the present disclosure;

[0016] Figure 3 is a flow chart of another embodiment of the parking space information determination method according to the present disclosure;

[0017] Figure 4 is a structural schematic diagram of one embodiment of the parking space information determination apparatus according to the present disclosure;

[0018] Figure 5 is a structural schematic diagram of one embodiment of the parking space information determination system according to the present disclosure;

[0019] Figure 6 is a schematic diagram of installing parking space area and camera in the garage of the present disclosure;

[0020] Figure 7 is another schematic diagram of installing parking space area and camera in the garage of the present disclosure;

[0021] Figure 8 is still another schematic diagram of installing parking space area and camera in the garage of the present disclosure;

[0022] Figure 9 is a block diagram of an electronic device for implementing the parking space information determination method according to the present embodiment. DETAILED DESCRIPTION

[0023] The exemplary embodiments of the present disclosure will be described hereinafter with reference to the accompanying drawings, in which various specific details are set forth in order to facilitate understanding. It should be understood, however, that the embodiments described herein are only by way of examples and should not be used to limit the proper scope of the present disclosure. Also, the description is only intended to illustrate the exemplary embodiments of the present disclosure and should not be used to limit the proper scope of the present disclosure. Therefore, it will be appreciated by those of ordinary skill in the art that various modifications and changes can be made thereto without departing from the scope and spirit of the present disclosure. Also, in the following description, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0024] In the present embodiment, "first", "second" are used only for the purpose of description, and should not be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include at least one of the features.

[0025] The present disclosure provides a parking space information determination method, Figure 1 A flow 100 of one embodiment of the parking space information determination method according to the present disclosure is shown, and the above parking space information determination method includes the following steps:

[0026] In step 101, vehicle space video data obtained by photographing a vehicle space region is acquired.

[0027] In this embodiment, a camera device is installed near the vehicle space region, and the camera device can photograph an image of the vehicle space region to obtain vehicle space video data.

[0028] In this embodiment, the vehicle space region includes a lane and a plurality of vehicle spaces arranged along the driving direction of the lane on both sides of the lane. The camera device can have a visual angle range covering the vehicle spaces in the vehicle space region, and the camera device can be installed on a marker overlooking the vehicle space region. The camera device can also be installed on the top wall of a garage including the vehicle space region, and the camera device has a visual range covering the vehicle space region.

[0029] In this embodiment, the vehicle space video data is composed of a plurality of vehicle space image data, and by analyzing the vehicle space image data in the vehicle space video data, vehicle space information of the vehicle spaces in the vehicle space region can be obtained.

[0030] In this embodiment, the vehicle space image data corresponds to a vehicle space image, and the vehicle space image includes a vehicle space image in the vehicle space region and images of different targets in the vehicle space region, wherein the targets can be images of objects around the vehicle spaces, persons, and traffic facilities. The execution subject on which the vehicle space information determination method runs can communicate with the camera device to obtain vehicle space video data obtained by the camera device in real time.

[0031] In step 102, the position information of the camera device and the fixed positional relationship between the camera device and each vehicle space in the vehicle space region are determined.

[0032] In this embodiment, the position information of the camera device is used to represent the actual position of the camera device, and the position information can include the position point of the camera device in different coordinate systems. The position information can also include the installation position of the camera device, which has different measurement standards with respect to different reference bodies. For example, when the camera device is fixed on a marker in the vehicle space region, the installation position of the camera device can be the width of the lane where the marker is located, the distance from the marker to the nearest vehicle space, etc. When the camera device is fixedly installed on the top wall of the garage, the installation position of the camera device can be the nearest distance from the projection point of the camera device on the lane to the edge of the lane.

[0033] In this embodiment, the fixed positional relationship between each vehicle space in the vehicle space region refers to the positional relationship between the vehicle spaces in the geographical coordinate system. For example, a plurality of vehicle spaces are arranged in sequence on one side of the lane, and adjacent vehicle spaces share the same side. Two vehicle spaces are located on both sides of the lane, and the two vehicle spaces have the same specifications.

[0034] In the embodiment, in the geographic coordinate system, each parking space position in the parking space area is fixed, and when the geographic coordinates of one parking space are determined, the geographic coordinates of other parking spaces in the parking space area can also be determined accordingly.

[0035] In step 103, based on the position information, the parking space video data and the fixed position relationship, the parking space information of each parking space in the parking space area is determined.

[0036] In the embodiment, the parking space information includes the actual position of each parking space in the geographic coordinate system, and the position information of the camera device reflects the actual installation position of the camera device. After the position information of the camera device is obtained, the first position of the camera device in the parking space image can be obtained by coordinate transformation on the position information of the camera device in the parking space video data. The conversion relationship between the first position and the actual position in the position information is determined, and based on the conversion relationship, the actual position of one parking space in the parking space area can be calculated. Further, based on the fixed position relationship between each parking space in the parking space area, the actual positions of all parking spaces in the parking space area can be determined.

[0037] Optionally, the parking space information can include relevant information, which can include the specifications of the parking space, the number of the parking space in the garage, the model of the parking space (for example, a child parking space, a single parking space, etc.), and the like. After the actual position of the parking space is obtained, the pre-set relevant information of each parking space can be bound to the actual position of the parking space, thereby enriching the parking space information.

[0038] The parking space information determination method provided by the embodiments of the present disclosure first acquires parking space video data obtained by photographing a parking space area, wherein a camera device is installed near the parking space area. Then, the position information of the camera device and the fixed position relationship between the camera device and each parking space in the parking space area are determined. Finally, based on the position information, the parking space video data and the fixed position relationship, the parking space information of each parking space in the parking space area is determined. Thus, based on the position information of the camera device and the parking space video data, the parking space information of each parking space in the parking space area is determined without the intervention of other parking space detection means, thereby saving the parking space information determination cost and improving the reliability of the obtained garage parking space information.

[0039] In some optional implementations of the present disclosure, the above position information includes the installation position corresponding to the parking space area and the geographic position coordinates in the geographic coordinate system, and the above determination of the parking space information of each parking space in the parking space area based on the position information, the parking space video data and the fixed position relationship includes processing the parking space video data to obtain parking space image data.

[0040] Based on the installation location and parking space image data, calculate the coordinate offset of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system; based on the coordinate offset and geographic coordinates, obtain the geographic coordinates of the center point of the first parking space; based on the fixed positional relationship and the geographic coordinates of the center point of the first parking space, determine the geographic coordinates of each parking space within the parking space area.

[0041] In this embodiment, the installation position of the camera device corresponding to the parking space area refers to the position of the camera device relative to the parking space area in the actual geographic coordinate system. For example, the installation position includes: the vertical height of the camera device relative to the parking space area, the horizontal distance of the camera device relative to the parking space area, etc. The geographic coordinates of the camera device are three-dimensional coordinates, and the camera device can be uniquely located on the Earth's surface through its geographic location. The projection point of the camera device refers to the projection point of the camera device in the image corresponding to the parking space image data. When the camera device is installed on the ceiling wall of the garage where the parking space area is located, the projection point of the camera device is the projection point of the installation point of the camera device on the ceiling wall in the parking space area; when the camera device is installed in the driveway of the parking space area through a marker, the intersection of the marker and the driveway of the parking space area is the projection point of the camera device.

[0042] In this optional implementation, the measured width of the parking space is w, and the length is h, as follows: Figure 2 As shown, there are two parking spaces. The first parking space has first endpoints P1 to P4, and the second parking space has second endpoints P5 and P6. That is, the actual line segments P1P3 = P2P4 = h; P1P2 = P5P6 = w.

[0043] In this embodiment, point P' is the projection point of the camera device in the parking space image data. The distance from projection point P' to the parking space is L, which is determined by the installation location of the camera device. The geographical coordinates of the camera device are known.

[0044] Given the geographic coordinates of the projection point, and knowing the offset of another point in the x and y directions of the geographic coordinate system relative to the projection point, the geographic coordinates of the other point can be determined.

[0045] Furthermore, since there is a fixed positional relationship between each parking space, the actual distance between one parking space and another in the parking area can be obtained. After obtaining the geographical coordinates of the center point of the first parking space, the geographical coordinates of the center point of the other parking space can be obtained based on the actual distance to the other parking space.

[0046] The optional implementation provides a method for determining parking information of each parking space within a parking area. After determining the location information of the camera device, it calculates the coordinate offset value of the center point of the first parking space relative to the camera device. The actual geographical location of the center point of the first parking space can be effectively obtained through the coordinate offset value, providing a reliable basis for parking space navigation.

[0047] In this embodiment, the location information requirements differ for different types of garages. When the garage containing the parking area is a multi-level garage with multiple parking spaces, the location information can be the distance from the camera device to the parking space in different directions in three-dimensional space. When the garage containing the parking area is a garage with only one level of parking spaces, the location information can simply be the horizontal distance from the installation point of the camera device to the nearest parking space.

[0048] In some optional implementations of this embodiment, the above-mentioned calculation of the coordinate offset value of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system based on the installation location and parking space image data includes: taking the lane direction corresponding to the installation location as the first coordinate axis of the geographic coordinate system based on the parking space image data; obtaining the first endpoint of the first parking space and the second endpoint of the second parking space, wherein the second parking space and the first parking space are distributed on both sides of the lane and the first parking space is set correspondingly to the second parking space; calculating the first blanking point in the direction of the first coordinate axis based on the first endpoint and the second endpoint; calculating the second blanking point in the direction perpendicular to the first coordinate axis based on the first endpoint; calculating the first offset value of the center point of the first parking space relative to the first coordinate axis based on the second blanking point and the installation location; calculating the second offset value of the center point of the first parking space in the vertical direction relative to the first coordinate axis based on the installation location and the first blanking point; and combining the first offset value and the second offset value to obtain the coordinate offset value of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system.

[0049] like Figure 2 As shown, in the image corresponding to the parking space image data, there is a projection point P' of the camera device. In the image corresponding to the parking space image data, let the lane direction be the first coordinate axis, and the first coordinate axis corresponds to the X direction, as follows. Figure 2 The straight line Z' in the diagram is the first coordinate axis, and the direction that is actually perpendicular to the X direction is the Y direction.

[0050] In the image corresponding to the parking space image data, the center point of the first parking space is C1. The first blanking point Z1 in the X direction (not shown in the figure) can be calculated through the first endpoint P1, P2 and the second endpoint P5, P6. The second blanking point Z2 in the Y direction (not shown in the figure) can be calculated through the first endpoint P1 to P4.

[0051] Figure 2 In the diagram, the intersection of line segment Z2P' and line segment P1P2 obtained from the second hidden point in the Y direction and the projection point P' is K1. The intersection of the line segment P1P2 obtained from the second hidden point in the Y direction and the center point C1 of the first parking space is K2. As shown in the diagram, the offset of the center point C1 of the first parking space relative to the projection point P' in the X direction is K1K2 / P1P2*w.

[0052] Generally, the offset value in the Y direction needs to be calculated by the line obtained by the first blanking point Z1 in the X direction and the projection point P', but through the actual installation position (the projection point P' of the camera and the center point C1 of the first parking space are located on the Y axis), it is known that the offset of all parking spaces in the Y direction can be fixed, that is, the length of the line segment P'K1 is equal to L, and the length of the line segment C1K2 is equal to h / 2, so the offset value of the center point C1 of the first parking space to the projection point P' on the Y axis is h / 2+L. In actual practice, the offset value can be calculated by the pixel distance in the parking space image data, for example, the farther away from the picture center, the more likely 100 pixel points are a parking space wide.

[0053] The method for calculating the coordinate offset value provided by the optional implementation finds the actual line closest to the actual line in reality through the blanking point, so as to minimize the error value of the calculation of the coordinate offset value, and improve the reliability of the calculation of the offset value.

[0054] In order to better determine the parking space occupation status in the parking lot and the like, Figure 3 The flow 300 of another embodiment of the parking space information determination method according to the present disclosure is shown, and the parking space information determination method comprises the following steps:

[0055] In step 301, parking space video data obtained by shooting a parking space area is acquired.

[0056] In this embodiment, a camera is installed near the parking space area.

[0057] In step 302, position information of the camera and a fixed position relationship between the camera and each parking space in the parking space area are determined.

[0058] In step 303, based on the position information, the parking space video data and the fixed position relationship, parking space information of each parking space in the parking space area is determined.

[0059] It should be understood that the operations and features in the above steps 301-303 correspond to the operations and features in steps 101-103 respectively, and therefore the description of the operations and features in steps 101-103 is also applicable to steps 301-303, and will not be repeated here.

[0060] In step 304, a target in the parking space video data is tracked to determine a relative position relationship between the target and each parking space.

[0061] In this embodiment, the target detection and tracking model can be used to track the target in the parking space video data. The target detection and tracking model includes a target detection model and a target tracking model. First, the parking space image data is extracted from the parking space video data. Second, the target detection model is used to detect the target in the parking space image data. After detecting the target in the parking space image, the target is uniquely identified and marked with a position marker. Finally, the target tracking model can obtain the target position of each target. The target tracking model records the unique identification of the target and the position of the target object of each frame of image of the parking space image data.

[0062] In this embodiment, the target detection model and the target tracking model can use different model architectures. The target detection model can use an R-CNN (Region-CNN) model, and the target tracking model can use a deep_sort model.

[0063] It should be noted that the target detection and tracking model can be configured on the camera device. After the camera device obtains the parking space video data of the parking space area, the target detection and tracking model in the camera device can be used to detect and track the target in the parking space video data.

[0064] In this embodiment, after obtaining the relative position relationship between the target and each parking space, the relative position relationship can be updated to the parking space information, or the parking space information of each parking space can be bound with the relative position relationship corresponding to the parking space.

[0065] The parking space information determination method provided in this embodiment tracks the target in the parking space video data, determines the relative position relationship between the target and each parking space, and can send the relative position relationship between the target and the parking space to a user operating the target, so that the user can quickly determine the parking space occupation situation, thereby improving the user experience.

[0066] Optionally, the relative position relationship between the target and each parking space can be reported to a garage management platform. Through the garage management platform, the idle parking space navigation without target can be performed in real time, and the specific position of the target (such as a vehicle) after the target occupies the parking space can be searched.

[0067] In some optional implementations of this embodiment, tracking the target in the parking space video data and determining the relative position relationship between the target and each parking space include:

[0068] Tracking the target in the parking space video data to obtain the motion state information of the target; and determining the relative position relationship between the target and each parking space based on the motion state information.

[0069] In the optional implementation, the relative position relationship includes: the target occupies the parking space, the target does not occupy the parking space, the target is entering the parking space, the target is removing the parking space, and the like. When the motion state information of the target is different, the relative position relationship is different.

[0070] The method for determining the relative position relationship between the target and the parking space provided by the optional implementation can effectively determine the relative position relationship between the target and the parking space by tracking the motion state of the target, and improves the reliability of the analysis of the parking space information.

[0071] In some optional implementations of the embodiment, the motion state information includes: a static state. Based on the motion state information, the method for determining the relative position relationship between the target and each parking space includes: constructing a three-dimensional model of the target when the target is in the static state; mapping the three-dimensional model to obtain a planar relationship graph reflecting the position relationship between the target and each parking space; and determining the relative position relationship between the target and each parking space based on the planar relationship graph.

[0072] In the optional implementation, the key points of the target are collected, the three-dimensional model of the target is established based on the key points of the target, the three-dimensional model is mapped to the parking space plane closest to the target to obtain a mapping contour of the target, and it is detected whether the mapping contour is completely located in the parking space frame of the parking space plane. If all of the mapping contour (the parking space frame of the parking space completely surrounds the mapping contour) or more than 50% of the mapping contour is located in the parking space frame of the parking space plane, it is determined that the target occupies the parking space, and the relative position relationship between the target and the parking space closest to the target is: the parking space is occupied.

[0073] If less than 50% of the mapping contour is located in the parking space frame of the parking space plane, it is determined that the target does not occupy the parking space, and the relative position relationship between the target and the parking space is: the parking space is idle.

[0074] The method for determining the relative position relationship between the target and the parking space provided by the optional implementation can effectively determine whether the target is completely located in the plane where the parking space is located by establishing the three-dimensional model of the target when the target is in the static state and including the target in the three-dimensional space where the parking space is located.

[0075] In some optional implementations of the embodiment, the motion state information includes: a motion state. Based on the motion state information, the method for determining the relative position relationship between the target and each parking space includes: tracking the distance between each parking space and the target when the target is in the motion state; and for each parking space, in response to the distance between the target and the parking space being less than or equal to a distance threshold and the distance state between the target and the parking space in the parking space video data lasting for more than a set time, it is determined that the target is entering or leaving the parking space.

[0076] When the target is in a moving state, the three-dimensional modeling manner cannot effectively reflect the relative position relationship between the target and the parking space. Therefore, when the target is in a moving state, the distance between the target and each parking space and the duration in the distance can be tracked to determine whether the target is entering or leaving the parking space.

[0077] In this embodiment, the distance threshold can be determined based on the size of the target volume and the parking space area, for example, the distance threshold is 1 m. The setting time can be determined by experience when the target is parked in the parking space, for example, the setting time is 20 min.

[0078] The method for determining the relative position relationship between the target and the parking space provided by the optional implementation provides a reliable basis for effectively determining whether the target enters or leaves the parking space by the distance between the target and the parking space and the duration in the distance state when the target is in a moving state.

[0079] In this embodiment, when tracking the target in the parking space video data, the target in the parking space image data can be recognized first, and after the target is recognized, the target is tracked to obtain the target position of the target. In some optional implementations of this embodiment, the target in the parking space video data is tracked to obtain the motion state information of the target, including: the parking space video data is intercepted at a preset frame rate interval to obtain a plurality of image frames; the target in the plurality of image frames is identified and tracked to obtain the target position of the target; and in response to the target position of the target in the plurality of image frames being a fixed position, it is determined that the target is in a stationary state.

[0080] In this embodiment, the target position of the target is a coordinate point in the image coordinate system, and when the coordinate points of the target positions in the plurality of image frames do not change, the target position is determined to be a fixed position.

[0081] The method for obtaining the motion state information of the target provided by the optional implementation analyzes the parking space video data, and the image frames in the parking space video data are subjected to target identification and tracking. When the target position of the target is a fixed position, it is determined that the target is in a stationary state.

[0082] Alternatively, the above-mentioned tracking of the target in the parking space video data to obtain the motion state information of the target can further include: the parking space video data is intercepted at a preset frame rate interval to obtain a plurality of image frames; the target in the plurality of image frames is identified and tracked, and it is detected whether the scene and objects around the target of each image frame of the plurality of image frames change, and in response to the scene and objects around the target not changing, it is determined that the target is in a stationary state.

[0083] Optionally, for a plurality of continuous image frames, the target is determined to be in a motion state in response to changes in the scenery around the target and the object.

[0084] In this embodiment, the target can be a vehicle, an animal, etc. When analyzing the parking space occupancy of the vehicle, the parking space and the license plate of the vehicle can be bound. In some optional implementations of this embodiment, the target includes a vehicle, and the camera is further configured to capture the license plate of the vehicle. After determining the relative positional relationship between the vehicle and each parking space, the method further includes: obtaining the license plate, identifying the parking space occupied by the vehicle, and binding the license plate with the parking space.

[0085] In this embodiment, since different garage systems have different recording methods for parking spaces, some garage systems use coding to record parking spaces, and some garages use addresses to record parking spaces. When binding the license plate with the parking space, the parking space code or the address of the parking space can be bound with the license plate accordingly.

[0086] In this embodiment, the camera can include a fisheye camera and a normal camera, and the visual ranges of the fisheye camera and the normal camera have an intersection. When the vehicle first appears, it first enters the monitoring range of the normal camera on both sides. The normal camera performs license plate recognition when tracking the target, and gives the corresponding license plate of the tracked target. When the tracked target enters the visual intersection of the fisheye and normal cameras, cross-camera tracking can be realized. In this way, the fisheye camera can track the target and obtain the corresponding license plate. The execution subject running on the parking space information determination can obtain the target and the license plate of the target from the fisheye camera in real time.

[0087] Optionally, the fisheye camera and the normal camera in the camera can be configurable items. For example, when the normal camera is not connected to the camera, the fisheye camera can be used to capture the parking space video data. For another example, when the fisheye camera is not connected to the camera, the normal camera can be used to capture the parking space video data. The parking space information determination method provided in this embodiment can use the target detection and tracking model in the normal camera to track the target, use the image recognition model in the normal camera to recognize the license plate, and then send the license plate and the target tracking result to the execution subject. The execution subject judges the relationship between the vehicle and the parking space and reports the related parking space state to the garage management background to complete real-time idle parking space navigation and vehicle specific position reverse search.

[0088] The parking garage management backend binds vehicle tracking results to license plates and publishes relevant navigation software in real time. When the vehicle owner has the relevant navigation software, they can use it to navigate to the corresponding parking lot. The navigation software can pinpoint the exact parking space, guiding the owner to park quickly. If the owner does not use the relevant navigation software, they can also view the distribution information of currently available parking spaces through a specific application or mini-program for quick parking. When the owner needs to find the specific location of their vehicle, they can enter the corresponding license plate number in the relevant application to find their parking space, avoiding searching for each space one by one and saving the owner's time.

[0089] The parking space information determination method provided by this optional implementation determines the relative positional relationship between the vehicle and each parking space, then captures the vehicle's license plate using a camera and binds the license plate to the parking space occupied by the vehicle. This allows users to promptly and effectively confirm the parking space occupancy status, facilitating user queries for vehicles and parking spaces and improving user experience.

[0090] Further reference Figure 4 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a parking space information determination device, which is similar to... Figure 1 Corresponding to the method embodiments shown, this device can be specifically applied to various electronic devices.

[0091] like Figure 4 As shown, the parking space information determination device 400 provided in this embodiment includes: an acquisition unit 401, a relationship determination unit 402, and an information determination unit 403. The acquisition unit 401 can be configured to acquire parking space video data obtained by capturing images of a parking space area; wherein a camera device is installed near the parking space area. The relationship determination unit 402 can be configured to determine the location information of the camera device and the fixed positional relationship between the camera device and each parking space in the parking space area. The information determination unit 403 can be configured to determine the parking space information of each parking space in the parking space area based on the location information, the parking space video data, and the fixed positional relationship.

[0092] In this embodiment, the specific processing of the acquisition unit 401, the relationship determination unit 402, and the information determination unit 403 in the parking space information determination device 400, and the resulting technical effects, can be found in the following references: Figure 1 The relevant descriptions of steps 101, 102, and 103 in the corresponding embodiments will not be repeated here.

[0093] In some optional implementations of the present embodiment, the position information includes: an installation position of the corresponding parking space area and a geographic position coordinate in a geographic coordinate system, and the information determination unit 403 is further configured to: process the parking space video data to obtain parking space image data; calculate a coordinate offset value of a projection point of a center point of a first parking space relative to the camera in the geographic coordinate system based on the installation position and the parking space image data, the projection point being a projection point of the camera in an image corresponding to the parking space image data, the first parking space being any one of the parking spaces in the parking space area; obtain a geographic coordinate of the center point of the first parking space based on the coordinate offset value and the geographic position coordinate; and determine the geographic coordinates of the parking spaces in the parking space area based on the fixed position relationship and the geographic coordinate of the center point of the first parking space.

[0094] In some optional implementations of the present embodiment, the information determination unit 403 is further configured to: take a lane direction corresponding to the installation position as a first coordinate axis of the geographic coordinate system based on the parking space image data; obtain a first end point of the first parking space and a second end point of a second parking space, the second parking space being distributed on a side opposite to the first parking space in the lane, and the first parking space and the second parking space being correspondingly arranged; calculate a first blanking point in the direction of the first coordinate axis based on the first end point and the second end point; calculate a second blanking point in a direction perpendicular to the first coordinate axis based on the first end point; calculate a first offset value of a center point of the first parking space relative to the first coordinate axis based on the second blanking point and the installation position; calculate a second offset value of the center point of the first parking space relative to a direction perpendicular to the first coordinate axis based on the installation position and the first blanking point; and combine the first offset value and the second offset value to obtain the coordinate offset value of the projection point of the center point of the first parking space relative to the camera in the geographic coordinate system.

[0095] In some optional implementations of the present disclosure, the device 400 further includes a tracking unit (not shown in the figure), wherein the tracking unit can be configured to track a target in the parking space video data and determine the relative position relationship between the target and each parking space.

[0096] In some optional implementations of the present disclosure, the tracking unit is further configured to track the target in the parking space video data to obtain motion state information of the target, and determine the relative position relationship between the target and each parking space based on the motion state information.

[0097] In some optional implementations of the present disclosure, the motion state information includes a stationary state, and the tracking unit is further configured to: construct a three-dimensional model of the target when the target is in the stationary state; map a planar relationship diagram reflecting the position relationship between the target and each parking space based on the three-dimensional model; and determine the relative position relationship between the target and each parking space based on the planar relationship diagram.

[0098] In some optional implementations of this disclosure, the motion state information includes: motion state, and the tracking unit is further configured to: track the distance between each parking space and the target when the target is in motion; for each parking space, in response to the distance between the parking space and the target being less than or equal to a distance threshold and the distance state between the parking space and the target in the parking space video data lasting for more than a set time, determine that the target is entering or leaving the parking space.

[0099] In some optional implementations of this disclosure, the tracking unit is further configured to: capture parking space video data at a preset frame rate interval to obtain multiple image frames; identify and track targets in the multiple image frames to obtain the target position of the target; and determine that the target is stationary in response to the target position of the target in the multiple image frames being a fixed position.

[0100] In some alternative implementations of this disclosure, the above-mentioned object includes: a vehicle, and the camera device is also used to capture the license plate of the vehicle; the device further includes: an identification unit (not shown in the figure), which can be configured to acquire the license plate, identify the parking space occupied by the vehicle, and bind the license plate to the parking space.

[0101] The parking space information determination device provided in the embodiments of this disclosure firstly acquires parking space video data obtained by shooting a parking space area; wherein a camera device is installed near the parking space area; secondly, a relationship determination unit 402 determines the location information of the camera device and the fixed positional relationship between the camera device and each parking space in the parking space area; finally, an information determination unit 403 determines the parking space information of each parking space in the parking space area based on the location information, the parking space video data, and the fixed positional relationship. Therefore, based on the location information of the camera device and the parking space video data, the parking space information of each parking space in the parking space area is determined without the need for other parking space detection methods, saving the cost of determining parking space information and improving the reliability of obtaining parking space information in the garage.

[0102] Further reference Figure 5 As an implementation of the methods shown in the above figures, this disclosure provides an embodiment of a parking space information determination system, which is similar to... Figure 1 Corresponding to the method embodiment shown, the system can be implemented using various electronic devices and camera devices.

[0103] like Figure 5 As shown, the parking space information determination system 500 provided in this embodiment includes: a camera device 501 and a control device 502, wherein the camera device may have at least one ( Figure 5 (Two or more were drawn in the middle) Figure 5Each camera 501 in the at least one camera corresponds to a parking area of the garage, and each parking area includes a lane and a plurality of parking spaces located on both sides of the lane and distributed along the driving direction of the lane; each camera 501 is configured to capture an image of the parking area and obtain parking video data of the parking area.

[0104] The control device 502 is connected to at least one camera 501, and for each camera 501, the control device 502 acquires parking video data of the camera 501, determines position information of the camera 501 and a fixed positional relationship between the camera 501 and each parking space in the parking area corresponding to the camera 501, and determines parking information of each parking space in each parking area based on the position information, the parking video data, and the fixed positional relationship.

[0105] The parking information determination system provided in the embodiment includes a control device and at least one camera, each camera in the at least one camera is configured to capture an image of a corresponding parking area, obtain parking video data of the parking area, and send the parking video data to the control device. After the control device acquires the parking video data of the camera, for each camera, the control device determines position information of the camera and a fixed positional relationship between the camera and each parking space in the parking area corresponding to the camera, and determines parking information of each parking space in each parking area based on the position information, the parking video data, and the fixed positional relationship. Since the parking information of the parking space can be obtained by only analyzing the position of the camera and the video data, the operation is simple and convenient, the cost of obtaining the parking information is saved, and the user experience is improved.

[0106] In some optional implementations of the embodiment, the camera includes an fisheye camera located on the lane of the parking area, and the fisheye camera is configured to capture all parking spaces in the parking area.

[0107] As shown in FIG. 1, a parking area and a camera installation schematic diagram are shown, and as shown in FIG. 2, a parking area is shown. Figure 6 As shown in FIG. 1, a parking area and a camera installation schematic diagram are shown, and as shown in FIG. 2, a parking area is shown. Figure 6 As shown in FIG. 1, a parking area and a camera installation schematic diagram are shown, and as shown in FIG. 2, a parking area is shown. Figure 6 As shown in FIG. 1, a parking area and a camera installation schematic diagram are shown, and as shown in FIG. 2, a parking area is shown.

[0108] In the embodiment, one fisheye camera can be used to monitor 1-12 parking spaces in the parking area.

[0109] The camera device provided in this embodiment uses a fisheye camera to capture images of all parking spaces in the parking area. Compared with using multiple ordinary cameras to capture images of the parking spaces in the parking area, this saves shooting costs and improves the utilization rate of garage resources.

[0110] In some optional implementations of this embodiment, the camera device includes a predetermined number of digital cameras located on the lane of the parking space area and arranged sequentially along the driving direction; the predetermined number is determined by the number of parking spaces in the parking space area and the field of view of the digital cameras.

[0111] In this embodiment, the number of digital cameras in the parking space area is a configurable option. Generally, the shooting angle of digital cameras is limited, and the number of parking spaces monitored by digital cameras is 1 to 3. When setting up digital cameras, the corresponding number of digital cameras can be configured according to the number of parking spaces.

[0112] like Figure 7 The diagram shown illustrates another installation of the parking space area and the camera device. Figure 7 The parking area shown has lanes, and four digital cameras, namely S1, S2, S3 and S4, are installed on the lanes. The four digital cameras are arranged in sequence along the driving direction W of the lanes.

[0113] The camera device provided in this embodiment uses a set number of digital cameras to capture images of all parking spaces in the parking area, which is easy to implement, simple to operate, and can reliably collect parking space information.

[0114] In some optional implementations of this embodiment, the camera device includes: digital cameras located on one or both sides of the fisheye camera, the digital cameras being arranged sequentially along the driving direction of the lane, and the field of view of the digital cameras and the fisheye camera overlapping.

[0115] like Figure 8 The diagram shown illustrates another installation of the parking area and the camera device. Figure 8 The parking area shown has a lane, on which a fisheye camera 801 and two digital cameras 802 are installed, with the two digital cameras 802 located on either side of the fisheye camera 801 along the driving direction T of the lane.

[0116] In this embodiment, the fisheye camera can monitor the situation of the parking space in the parking space area, for example, whether the parking space is occupied, and the digital camera can be used to shoot the detailed image (pattern text on the target, etc.) of the target entering the lane, and the detailed image is synchronized to the fisheye camera through the cross-camera tracking technology. When the target is a vehicle, the fisheye camera can monitor about 10-12 parking spaces, and the fisheye camera monitors the state of the parking spaces on both sides, whether each parking space has a vehicle parked; two digital cameras monitor the two sides of the lane, and when a vehicle enters from the two entrances of the lane, the corresponding license plate is identified through the image screen, and then the license plate information is synchronized to the fisheye camera through the cross-camera tracking technology.

[0117] It should be noted that the digital camera can be installed at a position corresponding to the parking space area according to actual conditions, and the digital camera can be installed one or two, and can be integrally installed with the fisheye camera or separately installed with the fisheye camera.

[0118] The camera device provided in this embodiment adopts the fisheye camera and the digital camera to shoot the images of all parking spaces in the parking space area, and since the fisheye camera and the digital camera have an intersection in the field of view, the two cameras share video information through the cross-camera tracking technology, and the comprehensiveness of the parking space information obtained is improved.

[0119] In some optional implementation manners of this embodiment, the camera device includes one fisheye camera and at least one digital camera, and the at least one digital camera is installed at the entrance of the garage and is used to shoot the license plate of the vehicle entering the garage.

[0120] In this embodiment, the fisheye camera is located on the lane of the parking space area, and the fisheye camera is used to shoot all parking spaces in the parking space area. The fisheye camera has a wider horizontal and vertical field of view than the digital camera, and thus can monitor more parking spaces, but the fisheye camera is not ideal in capturing the details of the image (cannot clearly see the license plate) relative to the digital camera.

[0121] The camera device provided in this embodiment adopts the fisheye camera and the digital camera to shoot the images of all parking spaces in the parking space area, wherein the fisheye camera is used to shoot the situation of the parking space in the parking space area, and the digital camera is located at the entrance of the garage to shoot the license plate of the vehicle entering the garage, so that the detailed image of all vehicles entering the garage can be effectively captured, and the comprehensiveness of the parking space information obtained is improved.

[0122] The fish-eye camera-based parking space information determination system improves the average number of parking spaces supervised by a single camera, avoids resource waste, and through the parking space information determination system, the relationship between the parking space and the back-end platform can be connected, information can be timely published, and the user experience of parking and taking the vehicle can be improved, the parking lot turnover rate is improved, the parking difficulty is alleviated, and the development of intelligent transportation and smart city is promoted.

[0123] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information comply with relevant laws and regulations and do not violate public order and good customs.

[0124] According to the embodiments of the present disclosure, the present disclosure further provides an electronic device, a readable storage medium and a computer program product.

[0125] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the present disclosure described and / or claimed in this document.

[0126] As shown in Figure 9 The device 900 includes a computing unit 901 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0127] A plurality of components in the device 900 are connected to the I / O interface 905, including: an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0128] The computing unit 901 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 901 performs various methods and processes described above, such as the parking space information determination method. For example, in some embodiments, the parking space information determination method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded to the RAM 903 and executed by the computing unit 901, one or more steps of the parking space information determination method described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the parking space information determination method by any other appropriate means, such as by means of firmware.

[0129] Various implementations of the systems and techniques described above herein can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0130] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be retrieved from a machine-readable medium or device and executed by a processor to produce a machine for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed as a stand-alone program, or in combination with other program modules, and / or as sub-routines or in combination with other applications, to produce a machine for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be stored in any type of computer-readable medium or memory, for example, but not limited to, volatile or non-volatile storage. Non-limiting examples of computer-readable mediums include a hard disk, floppy disk, RAM, ROM, EPROM, EEPROM, flash memory, compact disk, digital tape, etc. The program code can be loaded into a memory of a machine, such as a computer, to cause the machine to produce a machine implementing the functions / acts specified in the flowcharts and / or block diagrams.

[0131] In the context of the present disclosure, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium will include one or more lines of a computer program code, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0132] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0133] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0134] The computer system can include clients and servers. This relationship can be

[0135] It should be understood that the procedures shown above can be re-ordered, added to, or removed from, while still being within the scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the technology disclosed in the present disclosure are achieved, and are not limited herein.

[0136] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Accordingly, the disclosure is not limited to the specific embodiments described above.

Claims

1. A method for determining parking space information, the method comprising: Acquire parking space video data obtained by shooting the parking space area; wherein, a camera device is installed near the parking space area; The location information of the camera device and the fixed positional relationship between the camera device and each parking space in the parking area are determined. The location information includes: the installation location corresponding to the parking area and the geographical coordinates in the geographic coordinate system. The parking space video data is processed to obtain parking space image data; Based on the installation location and the parking space image data, calculate the coordinate offset value of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system. The projection point is the projection point of the camera device in the image corresponding to the parking space image data. The first parking space is any parking space in the parking space area. Based on the coordinate offset value and the geographic coordinates, the geographic coordinates of the center point of the first parking space are obtained; Based on the fixed positional relationship and the geographical coordinates of the center point of the first parking space, the geographical coordinates of each parking space within the parking space area are determined.

2. The method according to claim 1, wherein, The step of calculating the coordinate offset of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system based on the installation location and the parking space image data includes: Based on the parking space image data, the lane direction corresponding to the installation location is taken as the first coordinate axis of the geographic coordinate system; Obtain the first endpoint of the first parking space, obtain the second endpoint of the second parking space, the second parking space and the first parking space are distributed on both sides of the lane, and the first parking space and the second parking space are set correspondingly; Based on the first endpoint and the second endpoint, the first hidden point in the direction of the first coordinate axis is calculated; Based on the first endpoint, a second hidden point in a direction perpendicular to the first coordinate axis is calculated; Based on the second blanking point and the installation position, calculate the first offset value of the center point of the first parking space relative to the first coordinate axis; Based on the installation location and the first blanking point, calculate the second offset value of the center point of the first parking space in the vertical direction relative to the first coordinate axis; By combining the first offset value and the second offset value, the coordinate offset value of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system is obtained.

3. The method according to claim 1 or 2, further comprising: The target in the parking space video data is tracked to determine the relative positional relationship between the target and each parking space.

4. The method according to claim 3, wherein, The step of tracking targets in the parking space video data and determining the relative positional relationship between the targets and each parking space includes: The target in the parking space video data is tracked to obtain the motion state information of the target; Based on the motion state information, the relative positional relationship between the target and each parking space is determined.

5. The method according to claim 4, wherein, The motion state information includes: a stationary state. Based on the motion state information, determining the relative positional relationship between the target and each parking space includes: When the target is stationary, construct a three-dimensional model of the target; Based on the three-dimensional model, a planar relationship diagram reflecting the positional relationship between the target and each parking space is obtained; Based on the planar relationship diagram, the relative positional relationship between the target and each parking space is determined.

6. The method according to claim 4, wherein, The motion state information includes: motion state; and determining the relative positional relationship between the target and each parking space based on the motion state information includes: When the target is in motion, the distance between each parking space and the target is tracked. For each parking space, if the distance between the parking space and the target is less than or equal to a distance threshold and the distance status between the parking space and the target in the parking space video data persists for a set time or more, it is determined that the target is entering or leaving the parking space.

7. The method according to claim 4, wherein, The step of tracking the target in the parking space video data to obtain the target's motion state information includes: The parking space video data is extracted according to a preset frame rate interval to obtain multiple image frames; The targets in the multiple image frames are identified and tracked to obtain their target locations; In response to the target position being a fixed position in multiple image frames, it is determined that the target is in a stationary state.

8. The method according to any one of claims 3-7, wherein, The target includes: a vehicle, and the camera device is also used to capture the license plate of the vehicle; After determining the relative positional relationship between the vehicle and each parking space, the method further includes: obtaining the license plate, identifying the parking space occupied by the vehicle, and binding the license plate to the parking space.

9. A parking space information determination device, the device comprising: The acquisition unit is configured to acquire parking space video data obtained by shooting a parking space area; wherein, a camera device is installed near the parking space area; The relationship determination unit is configured to determine the location information of the camera device and the fixed positional relationship between the camera device and each parking space in the parking area. The location information includes: the installation location corresponding to the parking area and the geographical coordinates in the geographic coordinate system. An information determination unit is configured to process the parking space video data to obtain parking space image data; based on the installation location and the parking space image data, calculate the coordinate offset value of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system, wherein the projection point is the projection point of the camera device in the image corresponding to the parking space image data, and the first parking space is any parking space in the parking space area; based on the coordinate offset value and the geographic coordinates, obtain the geographic coordinates of the center point of the first parking space; and based on the fixed position relationship and the geographic coordinates of the center point of the first parking space, determine the geographic coordinates of each parking space in the parking space area.

10. The apparatus according to claim 9, wherein, The information determination unit is further configured to: based on the parking space image data, use the lane direction corresponding to the installation location as the first coordinate axis of the geographic coordinate system; Obtain the first endpoint of the first parking space, obtain the second endpoint of the second parking space, the second parking space and the first parking space are distributed on both sides of the lane, and the first parking space and the second parking space are set correspondingly, the first parking space is any one of the parking spaces in the parking space area; Based on the first endpoint and the second endpoint, the first hidden point in the direction of the first coordinate axis is calculated; Based on the first endpoint, a second hidden point in a direction perpendicular to the first coordinate axis is calculated; Based on the second blanking point and the installation position, calculate the first offset value of the center point of the first parking space relative to the first coordinate axis; Based on the installation location and the first blanking point, calculate the second offset value of the center point of the first parking space in the vertical direction relative to the first coordinate axis; By combining the first offset value and the second offset value, the coordinate offset value of the center point of the first parking space relative to the projection point of the camera device in the geographic coordinate system is obtained.

11. The apparatus according to claim 9, further comprising: The tracking unit is configured to track targets in the parking space video data and determine the relative positional relationship between the targets and each parking space.

12. The apparatus according to claim 11, wherein, The tracking unit is further configured to: track targets in the parking space video data to obtain motion state information of the targets; and determine the relative positional relationship between the targets and each parking space based on the motion state information.

13. A parking space information determination system, the system comprising: At least one camera device, each camera device corresponding to a parking space area in the garage, each parking space area including: a driveway and multiple parking spaces located on both sides of the driveway and distributed along the driving direction of the driveway; each camera device is used to capture images of the parking space area and obtain parking space video data of the parking space area; A control device, connected to the at least one camera device, acquires parking space video data for each camera device; determines the location information of the camera device and the fixed positional relationship between the camera device and each parking space in its corresponding parking space area, the location information including: the installation location corresponding to the parking space area and its geographical coordinates in a geographic coordinate system; processes the parking space video data to obtain parking space image data; calculates the coordinate offset value of the center point of a first parking space relative to the projection point of the camera device in the geographic coordinate system based on the installation location and the parking space image data, the projection point being the projection point of the camera device in the image corresponding to the parking space image data, the first parking space being any parking space in the parking space area; obtains the geographic coordinates of the center point of the first parking space based on the coordinate offset value and the geographical coordinates; and determines the geographic coordinates of each parking space in the parking space area based on the fixed positional relationship and the geographic coordinates of the center point of the first parking space.

14. The system according to claim 13, wherein, The camera device includes a fisheye camera located on the driveway of the parking area, the fisheye camera being used to capture images of all parking spaces in the parking area.

15. The system according to claim 13, wherein, The camera device includes a predetermined number of digital cameras located on the lane of the parking space area and arranged sequentially along the driving direction; the predetermined number is determined by the number of parking spaces in the parking space area and the field of view of the digital cameras.

16. The system according to claim 14, wherein, The camera device further includes: digital cameras located on one or both sides of the fisheye camera, the digital cameras being arranged sequentially along the driving direction of the lane, and the field of view of the digital cameras overlapping with that of the fisheye camera.

17. The system according to claim 14, wherein, The camera device further includes at least one digital camera, which is installed at the entrance of the garage and used to photograph the license plates of vehicles entering the garage.

18. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-8.

19. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-8.

20. A computer program product comprising a computer program that, when executed by a processor, implements the method of any one of claims 1-8.

Images