Parking space information detection method and device, electronic device and storage medium

Abstract

The invention relates to a parking space information detection method and device, an electronic device and a storage medium, and the method comprises the steps: obtaining a detection video image collected by a camera device, and determining a target vehicle object in the detection video image; determining a parking space detection distance corresponding to the detection video image according to a spatial relationship between the camera device and the target vehicle object; determining a target snapshot moment according to the parking space detection distance, and obtaining a snapshot event type corresponding to the target snapshot moment; and determining target parking space position information corresponding to the target vehicle object according to the snapshot event type and the device position information of the camera device at the target snapshot moment, obtaining a parking space state information list, and updating the parking space state information list according to the target parking space position information. According to the application, the problem of how to detect the parking space state in real time and record the parking space state information is solved, the accuracy and efficiency of parking space detection are improved, the automation degree is high, and resources are saved.

Description

Technical Field

[0001] The present application relates to the field of image detection, and in particular to a parking space information detection method, device, electronic device and storage medium. Background Art

[0002] With the advancement of science and technology, under the background of "smart city" and "safe city", "smart parking" has become inseparable from people's daily travel, and convenient parking has become an important indicator of residents' happiness index in urban life. Vehicle parking status monitoring is an important part of the "smart parking" business, and the accuracy of parking status recognition is a key indicator of parking management solutions. Its quality will directly affect people's travel experience. At present, some parking areas still use manual transcription to monitor and identify the parking space occupancy status, that is, the corresponding vehicles. This solution requires a large amount of manpower cost and is inefficient. Second, manual transcription of license plates is prone to errors, resulting in mismatches between parking spaces and license plate numbers, and low supervision accuracy. Therefore, in order to better create a standardized and convenient parking environment and strengthen the harmonious construction of "smart cities", a cost-effective, efficient and convenient vehicle parking status monitoring and management method is particularly important.

[0003] Currently, no effective solution has been proposed for the problem of how to detect the parking space status in real time and record the parking space status information in the relevant technology. Summary of the invention

[0004] The embodiments of the present application provide a parking space information detection method, device, electronic device and storage medium to at least solve the problem of how to detect the parking space status in real time and record the parking space status information in the related art.

[0005] In a first aspect, an embodiment of the present application provides a parking space information detection method.

[0006] In some embodiments, the parking space information detection method includes: Acquire a detection video image captured by a camera device, and determine a target vehicle object in the detection video image; Determining a parking space detection distance corresponding to the detection video image according to a spatial relationship between the camera device and the target vehicle object; Determine a target capture time according to the parking space detection distance, and obtain a capture event type corresponding to the target capture time; Determine the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; Acquire a parking space status information list, and update the parking space status information list according to the target parking space position information.

[0007] In some embodiments, before determining the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time, the method further includes: A satellite positioning terminal is arranged in the parking space area to be detected, and a satellite terminal signal received by the satellite positioning terminal and a ground base station signal corresponding to the parking space area to be detected are obtained; Determine the parking space satellite positioning information of the parking space area to be detected according to the satellite terminal signal and the ground base station signal; A parking space status information list is determined according to the parking space satellite positioning information.

[0008] In some embodiments, determining the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time includes: Determine the parking space position information to be corrected corresponding to the device position information according to the device position information and the parking space satellite positioning information; The target parking space position information corresponding to the target vehicle object is calculated according to the captured event type and the parking space position information to be corrected.

[0009] In some embodiments, the obtaining a parking space status information list and updating the parking space status information list according to the target parking space position information includes: Detect and identify the target vehicle object to determine the license plate information and vehicle type information of the target vehicle; A parking space status information list is obtained, and the parking space status information list is updated according to the target parking space position information, the license plate information and the vehicle type information.

[0010] In some embodiments, determining the parking space detection distance corresponding to the detected video image according to the spatial relationship between the camera device and the target vehicle object includes: Determining a target object recognition result corresponding to the target vehicle object according to the target vehicle object; The distance between the preset reference line corresponding to the camera device and the target object recognition result is determined as the parking space detection distance.

[0011] In some embodiments, determining the target capture time according to the parking space detection distance and obtaining the capture event type corresponding to the target capture time includes: Acquire n frames of detection video images captured by the camera device, and determine n parking space detection distances corresponding to the n frames of detection video images, where n is greater than or equal to 4; Determine a minimum parking space detection distance among the n parking space detection distances, and a reference video image frame corresponding to the minimum parking space detection distance; According to the minimum parking space detection distance and the reference video image frame, a target capture moment is determined, and a capture event type corresponding to the target capture moment is obtained.

[0012] In some embodiments, the parking space information detection method further includes: Acquire the capture area width of the camera device, and determine the cache trigger distance according to the capture area width; In a case where the minimum parking space detection distance is less than the cache trigger distance, determining the reference video image frame as a cache video image; The cached video image and the updated parking space status information list are sent to a parking space detection server.

[0013] In a second aspect, an embodiment of the present application provides a parking space information detection device.

[0014] In some embodiments, the parking space information detection device includes a target vehicle object determination module, a parking space detection distance determination module, a capture event type determination module, a target parking space position determination module and a parking space information list update module: The target vehicle object determination module is used to obtain the detection video image collected by the camera device and determine the target vehicle object in the detection video image; The parking space detection distance determination module is used to determine the parking space detection distance corresponding to the detection video image according to the spatial relationship between the camera device and the target vehicle object; The capture event type determination module is used to determine the target capture moment according to the parking space detection distance, and obtain the capture event type corresponding to the target capture moment; The target parking space position determination module is used to determine the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; The parking space information list updating module is used to obtain a parking space status information list and update the parking space status information list according to the target parking space position information.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the parking space information detection method as described in the first aspect above is implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the parking space information detection method as described in the first aspect above.

[0017] Compared with the related art, the parking space information detection method, device, electronic device and storage medium provided in the embodiments of the present application determine the target vehicle object and the parking space detection distance in the detection video image by acquiring the detection video image collected by the camera device, further determine the target capture moment according to the parking space detection distance, and obtain the capture event type corresponding to the target capture moment, determine the target parking space position information corresponding to the target vehicle object through the capture event type and the device position information of the camera device at the target capture moment, and update the parking space status information list according to the target parking space position information, thereby solving the problem of how to detect the parking space status in real time and record the parking space status information in the related art, improving the accuracy and efficiency of parking space detection, making the parking space detection more automated and saving resources.

[0018] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 is a hardware structure block diagram of a terminal according to a parking space information detection method of an embodiment of the present application; Figure 2 is a flow chart of a parking space information detection method according to an embodiment of the present application; Figure 3 is a flow chart of another parking space information detection method according to an embodiment of the present application; Figure 4 is a flow chart of a parking space information detection method according to a preferred embodiment of the present application; Figure 5 It is a structural block diagram of a parking space information detection device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated 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 intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

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

[0022] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation, and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application means greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in the present application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0023] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. Taking running on a terminal as an example, Figure 1 FIG. 1 is a hardware structure diagram of a terminal of a parking space information detection method according to an embodiment of the present invention. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0024] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the parking space information detection method in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0025] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0026] This embodiment provides a parking space information detection method. Figure 2 is a flow chart of a parking space information detection method according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps: Step S201, obtaining a detection video image captured by a camera device, and determining a target vehicle object in the detection video image.

[0027] In the embodiment of the present application, the camera device can be a vehicle-mounted binocular camera, which can perform mobile capture and recognition of vehicles in the electronic fence area corresponding to the parking space in a patrol manner, and collect and detect video images in real time. Furthermore, a YOLO (You Only Look Once) series of deep learning target detection methods is used, and a convolutional neural network detection model is built to train the target scene training data set. The trained detection model detects and locates the target vehicle in the parking space video image collected by the binocular patrol camera, thereby determining the target vehicle object.

[0028] Step S202: determining a parking space detection distance corresponding to the detected video image according to a spatial relationship between the camera device and the target vehicle object.

[0029] Specifically, based on the spatial distance relationship between the camera device and the target vehicle object when the camera device is at a certain shooting position, the parking space detection distance corresponding to the detection video image shot at the shooting position can be calculated.

[0030] Step S203, determining the target capture time according to the parking space detection distance, and obtaining the capture event type corresponding to the target capture time.

[0031] The parking space detection distance of each frame of the detection video image is calculated. According to the values ​​of multiple parking space detection distances and their changing trends, the target capture time can be determined and captured. Among them, multiple capture areas are configured within the monitoring field of view of the vehicle-mounted binocular camera, and the capture event type corresponding to the target capture time is determined based on the multiple capture areas. The multiple capture areas can be the left capture area, the middle capture area, and the right capture area.

[0032] Step S204, determining the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time.

[0033] After triggering the target capture, the device location information of the camera device at the target capture time is recorded. The device location information is determined by the satellite terminal signal and the ground base station signal obtained by the satellite positioning terminal. The target parking space location information corresponding to the target vehicle object can be determined through the device location information. The target parking space location information can be the preset parking space number of the target parking space.

[0034] Step S205, obtaining a parking space status information list, and updating the parking space status information list according to the target parking space position information.

[0035] In the embodiment of the present application, the parking space status information list can be determined by using satellite signals and ground base station signals based on real-time dynamic carrier phase differential, and the detailed process will be further described later. The parking space status information list includes the parking space location information of each parking space. After the target parking space location information is obtained through the above steps, the parking space location information of the target parking space in the parking space status information list is updated.

[0036] Through the above steps, in the vehicle parking space status monitoring scenario, the embodiment of the present application uses the on-board binocular camera to perform mobile capture and identification of vehicles in the parking space electronic fence area in a patrol manner, and determines the target vehicle object and the parking space detection distance in the detection video image by acquiring the detection video image collected by the camera device, and further determines the target capture time according to the parking space detection distance, and obtains the capture event type corresponding to the target capture time, and determines the target parking space position information corresponding to the target vehicle object through the mapping relationship between the capture event type and the device position information of the camera device at the target capture time, and updates the parking space status information list according to the target parking space position information, and associates the information of the target vehicle object with the corresponding parking space in the parking space status information list, so as to realize self-service parking space vehicle patrol monitoring, solves the problem of how to detect the parking space status in real time and record the parking space status information in the related technology, and improves the accuracy and efficiency of parking space detection compared with the traditional manual license plate transcribing method, so that the parking space detection is more automated and saves resources.

[0037] In some embodiments, before step S204, the method further includes: Step S210: a satellite positioning terminal is set in the parking space area to be detected, and a satellite terminal signal received by the satellite positioning terminal and a ground base station signal corresponding to the parking space area to be detected are obtained.

[0038] In the embodiment of the present application, the parking area to be detected includes multiple parking areas, and a satellite positioning terminal based on real-time dynamic carrier phase difference technology can be set at the outer vertex position of each parking space to receive satellite signals. Taking a rectangular parking space as an example, the outer vertex position of the parking space is the vertex position of the parking space close to the patrol camera device, and the satellite signal and ground base station signal corresponding to each parking space are obtained.

[0039] Step S211, determining the parking space satellite positioning information of the parking space area to be detected according to the satellite terminal signal and the ground base station signal.

[0040] Based on the carrier phase difference method, the satellite space coordinates of the outer vertex of the corresponding parking space are calculated according to the satellite signal and the ground base station signal received by the satellite positioning terminal, so as to determine the parking space satellite positioning information, that is, the parking space satellite positioning information can be the satellite space coordinates of the outer vertex of the parking space.

[0041] Step S212: determining a parking space status information list according to the parking space satellite positioning information.

[0042] The parking spaces are numbered and the parking space satellite positioning information is associated with the preset parking space numbers, so as to construct an electronic fence of the vehicle parking spaces in the parking area to be detected, and then a parking space status information list is established based on the sequential relationship between the satellite space coordinate points in the electronic fence and the preset parking space numbers.

[0043] When the number of valid satellite space coordinate points in the parking area to be detected is Num, the number of parking spaces in the constructed electronic fence is L=Num-1, and L is the length of the parking space status information list. The information mounted on each table node of the parking space status information list includes the preset parking space number, parking space occupancy status, vehicle type information and license plate information. In the initialization operation of the parking space status information list, the preset parking space number, parking space occupancy status and vehicle type information under the list are all initialized to -1. Since the license plate recognition part is a character type, the memory is initialized to 0. After the electronic fence is constructed, the preset parking space number under the list is numbered according to the sequential relationship between the satellite space coordinate points in the electronic fence to determine the preset parking space number, such as P1, P2, P3...PL. The parking space occupancy status has two status bits: occupied or idle. When it is judged to be occupied, it is updated to 1, and when it is idle, it is updated to 0. The vehicle type information has two category attributes: motor vehicle and non-motor vehicle. When the target vehicle object is judged to be a motor vehicle, it is updated to 0, and non-motor vehicle is updated to 1.

[0044] Through the above steps, the embodiment of the present application sets a satellite positioning terminal at the outer vertex position of each parking space, constructs an electronic fence of the parking space, and establishes a parking space status information list based on the sequential relationship between the satellite coordinate points within the fence; and merges the satellite signal coordinates received by the satellite positioning terminal with the ground base station information coordinates, and solves the spatial coordinates of the vehicle parking point by means of carrier phase difference, thereby constructing a parking space status information list. This embodiment only needs to be constructed once, and compared with the method of manually configuring the parking area by a fixed-point high-altitude camera, this configuration method is more accurate and efficient.

[0045] In some embodiments, step S204 includes: Step S2041, determining the parking space position information to be corrected corresponding to the device position information according to the device position information and the parking space satellite positioning information.

[0046] At the target capture moment, the satellite positioning information of the parking space closest to the position of the camera device is selected as the device position information, and the preset parking space number associated with the device position information is determined as the parking space position information to be corrected.

[0047] Step S2042, calculating the target parking space position information corresponding to the target vehicle object according to the captured event type and the parking space position information to be corrected.

[0048] According to the type of captured event and the parking space location information to be corrected, the preset parking space number of the parking space where the target vehicle object is located is mapped. Assume that the preset parking space number P of the parking space where the target vehicle object is located t , the preset parking space number P of the parking space to be corrected f Since the inspection vehicle equipped with a binocular camera is not allowed to go in reverse, in the embodiment of the present application, the inspection direction of the camera device is the front, and the parking space area to be inspected is located on the right side of the inspection vehicle. If the subscripts of the preset parking space numbers of the corresponding parking spaces increase in sequence along the inspection direction of the camera device, then: when the capture event type is left capture, P t =P f+1 ; When the capture event type is median capture, P t =P f ; When the capture event type is right capture, P t =P f-1 If the subscripts of the preset parking space numbers of the corresponding parking spaces decrease in sequence along the inspection direction of the camera device, then: when the capture event type is left capture, P t =P f-1 ; When the capture event type is median capture, P t =P f ; When the capture event type is right capture, P t =P f+1 .

[0049] Through the above steps, the embodiment of the present application combines the position information of the camera device at the moment of capturing and the type of capturing event, maps and infers the parking space position information of the target vehicle object, that is, the preset parking space number of the parking space, and performs parking space correction by distinguishing the mapping relationship of different capturing areas, so that the parking space position detection is more accurate and avoids the incorrect association of the target vehicle object and the parking space.

[0050] In some embodiments, step S205 includes: Step S2051, detect and identify the target vehicle object to determine the license plate information and vehicle type information of the target vehicle.

[0051] After the target vehicle object is determined based on the YOLO series of deep learning target detection methods, the license plate information and vehicle category information of the target vehicle object are further obtained. Among them, the vehicle type information includes motor vehicle target category and non-motor vehicle target category. In the case of detecting the license plate, the license plate information is recorded as the license plate number of the target vehicle object. In the case of not detecting the license plate, the license plate information is recorded as an unlicensed vehicle.

[0052] Step S2052, obtaining a parking space status information list, and updating the parking space status information list according to the target parking space position information, license plate information and vehicle type information.

[0053] Determine the table node corresponding to the target parking space position information in the parking space status information list, update the corresponding license plate information and vehicle type information to the table node, and update the parking space occupancy status information under the table node.

[0054] Through the above steps, the embodiment of the present application uses a deep learning network model to perform vehicle detection and license plate detection and recognition on the target vehicle object, determine the license plate information and vehicle type information, and update the information to the parking space status information list, thereby improving the association between the target vehicle object and the parking space, which is accurate and feasible, and has high information completeness.

[0055] In some embodiments, step S202 includes: Step S2021: Determine a target object recognition result corresponding to the target vehicle object according to the target vehicle object.

[0056] After the target vehicle object is determined based on the YOLO series of deep learning target detection methods, the vehicle detection frame of the target vehicle object is further obtained. The license plate recognition model obtained by deep learning training convolutional neural network is used to perform license plate detection and recognition on the vehicle detection frame, and the final target object recognition result of the target vehicle object is selected by fusing the license plate recognition results of multiple frames of images. When the license plate is detected, the target object recognition result may include the license plate detection frame; when the license plate is not detected, the target object recognition result may include the above-mentioned vehicle detection frame.

[0057] Step S2022: The distance between the preset reference line corresponding to the camera device and the target object recognition result is determined as the parking space detection distance.

[0058] The preset reference line of the camera device may be the center line of the capture area closest to the target object recognition result. When the target object recognition result is a license plate detection frame, the distance between the center of the bottom edge of the license plate detection frame and the center line of the closest capture area is determined as the parking space detection distance. When the target object recognition result is a vehicle detection frame, the distance between the center of the bottom edge of the vehicle detection frame and the center line of the closest capture area is determined as the parking space detection distance.

[0059] Through the above steps, vehicle detection and license plate detection and recognition are performed on the vehicle target object, and the target recognition object is determined to be a vehicle detection frame or a license plate detection frame. Then, the parking space detection distance is determined according to the distance between the preset baseline corresponding to the camera equipment and the vehicle detection frame or the license plate detection frame, which is highly feasible.

[0060] In some embodiments, step S203 includes: Step S2031: obtain n frames of detection video images captured by the camera device, and determine n parking space detection distances corresponding to the n frames of detection video images, where n is greater than or equal to 4.

[0061] Among them, the n-frame detection video images can be collected in real time by a camera device, and the multiple frames can be collected continuously or periodically at a certain interval of time / number of frames. It can be understood that multiple parking space detection distances can be obtained corresponding to the multiple-frame detection video images.

[0062] Step S2032, determining the minimum parking space detection distance among the n parking space detection distances, and the reference video image frame corresponding to the minimum parking space detection distance.

[0063] The n parking space detection distances are compared to obtain the minimum parking space detection distance, and the detection video image corresponding to the minimum parking space detection distance is determined as a reference video image frame.

[0064] Step S2033, determining the target capture moment according to the minimum parking space detection distance and the reference video image frame, and obtaining the capture event type corresponding to the target capture moment.

[0065] Specifically, when the reference video image frame is not the first frame in the n-frame detection video image, and the reference video image frame is not the last frame in the n-frame detection video image, it means that the parking space detection distance of the two adjacent frames of images has a process from decreasing to increasing in sequence, and at this time, the departure flag is determined to be 1. Based on the sampling difference method, two frames of images with an inter-frame distance of a preset inter-frame step can be used as adjacent images, and the preset inter-frame step can be 1. When the departure flag is 1, when there are at least 2 samplings in the capture area in which the parking space detection distance is increasing, the capture condition is triggered, the target capture is performed, the corresponding moment of the capture frame is recorded as the target capture moment, and the current capture event type is recorded. The capture event types include left-position capture, middle-position capture and right-position capture, which correspond to the captured image being located in the left-position capture area, the middle-position capture area and the right-position capture area, respectively.

[0066] Through the above steps, the approach and departure relationship between the target vehicle object and the set capture area position is judged according to the parking space detection distance, the target capture time and capture event type are determined, and the parking space status captured by the camera equipment can be judged in time to improve accuracy and efficiency.

[0067] This embodiment also provides a parking space information detection method. Figure 3 is a flow chart of another parking space information detection method according to an embodiment of the present application. Figure 3 As shown, the process includes the following steps in addition to step S201 to step S205: Step S301, obtaining the capture area width of the camera device, and determining the cache trigger distance according to the capture area width.

[0068] The cache trigger distance T is used to control the sensitivity of the captured image cache. The acquired capture area width is w, and the relationship between the trigger distance T and w is: Among them, α is the elastic coefficient, and its value range is (0,1 / 2].

[0069] Step S302: when the minimum parking space detection distance is less than the cache trigger distance, the reference video image frame is determined as the cache video image.

[0070] In the embodiment of the present application, the image closest to the designated snapshot centerline is determined to be a cached video image, which is used as the uploaded image reported by the system. When the minimum parking space detection distance is less than the cache trigger distance, the reference video image frame corresponding to the minimum parking space detection distance is determined as the cached video image. In addition, the cached image can also be determined by real-time detection calculation. When the parking space detection distance of the collected detection video image is less than or equal to the preset cache trigger distance, the image is cached. Only the frame with the smallest parking space detection distance is cached each time, that is, there will only be one cached image. If the parking space detection distance of the current frame is smaller, it will overwrite the previous cached result.

[0071] Step S303: sending the cached video image and the updated parking space status information list to the parking space detection server.

[0072] The parking space detection server is used to process the reporting and updating of inspection system events. The reporting event uses the parking space status information list constructed in the electronic fence as the information carrier. After each trigger capture, the information segments of the parking space occupancy status, vehicle type information and license plate information mounted under the corresponding table node in the parking space status information list are updated. The embodiment of the present application periodically sends the cached video image and the updated parking space status information list to the parking space detection server, and can control the update period corresponding to the frame number F by controlling the event warning sensitivity coefficient β based on the following formula: update , that is, every time F update The frame report is updated once, where f is the video acquisition frame rate.

[0073] Preferably, β is greater than 5 and less than 10.

[0074] Through the above steps, the embodiment of the present application obtains the detection video image closest to the specified snapshot center line as the uploaded cache image reported by the system, and periodically reports and updates the information results of each parking space table node in the parking space status information list in the inspection area to the system, so that the results are visualized and highly real-time.

[0075] The embodiments of the present application are described and illustrated below through preferred embodiments.

[0076] Figure 4 is a flow chart of a parking space information detection method according to a preferred embodiment of the present application. Figure 4 As shown, the parking space information detection method includes the following steps: Step S401, setting a satellite positioning terminal in the parking space area to be detected, obtaining a satellite terminal signal received by the satellite positioning terminal and a ground base station signal corresponding to the parking space area to be detected; Step S402, determining a parking space status information list according to the satellite terminal signal and the ground base station signal; Step S403, obtaining a detection video image captured by a camera device and a target vehicle object in the detection video image, and determining a target object recognition result corresponding to the target vehicle object; Step S404, determining the distance between the preset reference line corresponding to the camera device and the target object recognition result as the parking space detection distance; Step S405, determining the target capture time according to the parking space detection distance, and obtaining the capture event type corresponding to the target capture time; Step S406, determining the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; Step S407, obtaining a parking space status information list, determining the license plate information and vehicle type information of the target vehicle, and updating the parking space status information list according to the target parking space position information, license plate information and vehicle type information.

[0077] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0078] This embodiment also provides a parking space information detection device, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated here. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0079] Figure 5 is a structural block diagram of a parking space information detection device according to an embodiment of the present application, such as Figure 5As shown, the device includes a target vehicle object determination module 10, a parking space detection distance determination module 20, a capture event type determination module 30, a target parking space position determination module 40 and a parking space information list update module 50: The target vehicle object determination module 10 is used to obtain the detection video image collected by the camera device and determine the target vehicle object in the detection video image; The parking space detection distance determination module 20 is used to determine the parking space detection distance corresponding to the detection video image according to the spatial relationship between the camera device and the target vehicle object; The capture event type determination module 30 is used to determine the target capture time according to the parking space detection distance, and obtain the capture event type corresponding to the target capture time; The target parking space position determination module 40 is used to determine the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; The parking space information list updating module 50 is used to obtain the parking space status information list and update the parking space status information list according to the target parking space position information.

[0080] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0081] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0082] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0083] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program: Acquire a detection video image captured by a camera device, and determine a target vehicle object in the detection video image; Determine the parking space detection distance corresponding to the detection video image according to the spatial relationship between the camera device and the target vehicle object; Determine the target capture time according to the parking space detection distance, and obtain the capture event type corresponding to the target capture time; Determine the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; Get the parking space status information list and update the parking space status information list according to the target parking space location information.

[0084] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0085] In addition, in combination with the parking space information detection method in the above embodiment, the embodiment of the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any one of the parking space information detection methods in the above embodiment is implemented.

[0086] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described 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 specification.

[0087] 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.

[0088] The above-mentioned 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 invention patent. 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 patent of the present application shall be subject to the attached claims.

Claims

1. A parking space information detection method, characterized in that: The following steps are involved: Acquire a detection video image captured by a camera device, and determine a target vehicle object in the detection video image; Determining a parking space detection distance corresponding to the detection video image according to a spatial relationship between the camera device and the target vehicle object; Determine a target capture time according to the parking space detection distance, and obtain a capture event type corresponding to the target capture time; Determine the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; Acquire a parking space status information list, and update the parking space status information list according to the target parking space position information.

2. The parking space information detection method according to claim 1, characterized in that: Before determining the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time, the method further includes: A satellite positioning terminal is arranged in the parking space area to be detected, and a satellite terminal signal received by the satellite positioning terminal and a ground base station signal corresponding to the parking space area to be detected are obtained; Determine the parking space satellite positioning information of the parking space area to be detected according to the satellite terminal signal and the ground base station signal; A parking space status information list is determined according to the parking space satellite positioning information.

3. The parking space information detection method according to claim 2, characterized in that: Determining the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time includes: Determine the parking space position information to be corrected corresponding to the device position information according to the device position information and the parking space satellite positioning information; The target parking space position information corresponding to the target vehicle object is calculated according to the captured event type and the parking space position information to be corrected.

4. The parking space information detection method according to claim 3, characterized in that: The acquiring of the parking space status information list and updating the parking space status information list according to the target parking space position information includes: Detect and identify the target vehicle object to determine the license plate information and vehicle type information of the target vehicle; A parking space status information list is obtained, and the parking space status information list is updated according to the target parking space position information, the license plate information and the vehicle type information.

5. The parking space information detection method according to any one of claims 1 to 4, characterized in that: The determining, according to the spatial relationship between the camera device and the target vehicle object, a parking space detection distance corresponding to the detection video image comprises: According to the target vehicle object, determining a target object recognition result corresponding to the target vehicle object; The distance between the preset reference line corresponding to the camera device and the target object recognition result is determined as the parking space detection distance.

6. The parking space information detection method according to claim 5, characterized in that: Determining the target capture time according to the parking space detection distance, and obtaining the capture event type corresponding to the target capture time includes: Acquire n frames of detection video images captured by the camera device, and determine n parking space detection distances corresponding to the n frames of detection video images, where n is greater than or equal to 4; Determine a minimum parking space detection distance among the n parking space detection distances, and a reference video image frame corresponding to the minimum parking space detection distance; According to the minimum parking space detection distance and the reference video image frame, a target capture moment is determined, and a capture event type corresponding to the target capture moment is obtained.

7. The parking space information detection method according to claim 6, characterized in that: The method further comprises: Acquire the capture area width of the camera device, and determine the cache trigger distance according to the capture area width; In a case where the minimum parking space detection distance is less than the cache trigger distance, determining the reference video image frame as a cache video image; The cached video image and the updated parking space status information list are sent to a parking space detection server.

8. A parking space information detection device, characterized in that: It includes the target vehicle object determination module, the parking space detection distance determination module, the capture event type determination module, the target parking space position determination module and the parking space information list update module: The target vehicle object determination module is used to obtain the detection video image collected by the camera device and determine the target vehicle object in the detection video image; The parking space detection distance determination module is used to determine the parking space detection distance corresponding to the detection video image according to the spatial relationship between the camera device and the target vehicle object; The capture event type determination module is used to determine the target capture moment according to the parking space detection distance, and obtain the capture event type corresponding to the target capture moment; The target parking space position determination module is used to determine the target parking space position information corresponding to the target vehicle object according to the capture event type and the device position information of the camera device at the target capture time; The parking space information list updating module is used to obtain a parking space status information list and update the parking space status information list according to the target parking space position information.

9. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the parking space information detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the parking space information detection method according to any one of claims 1 to 7 when running.

Images