Intelligent building vehicle management method and system
Through real-time monitoring, shooting and image recognition technology of the building environment, the problem of on-ground parking space management is solved, statistics on parking space usage and vehicle identity verification are realized, and parking efficiency and user experience are improved.
Patent Information
- Application Number
- CN202411173060.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-26
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The ground parking spaces in the existing building system lack sensors, and the use of parking spaces cannot be counted, resulting in the inability to coordinate management.
By conducting real-time monitoring and shooting of the building environment, using image recognition technology to judge the use of parking spaces, and verify the identities of the vehicle and the parking space owner to generate a parking space guide plan to reduce the occupancy of parking spaces.
Effective management of on-ground parking spaces has been achieved, parking efficiency and user experience have been improved, and parking space occupancy has been reduced.
Smart Images

Figure CN119068706A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of computer technology, and in particular relates to a smart building vehicle management method and system. Background Art
[0002] The core of intelligent building is 5A system. Intelligent building is to integrate these five systems organically through communication network system, integrating structure, system, service, management and their optimal combination, so that the building has the characteristics of safety, convenience, high efficiency and energy saving. Intelligent building is a marginal and cross-disciplinary subject, involving computer technology, automatic control, communication technology, construction technology, etc., and more and more new technologies are applied in intelligent buildings.
[0003] In the current building system, parking spaces are provided, and parking spaces are generally divided into underground parking spaces and ground parking spaces. For underground parking spaces, sensors are installed above the underground parking spaces for the convenience of management. The sensors can obtain the usage status of each parking space, thereby facilitating statistics.
[0004] However, there are also a large number of ground parking spaces. Due to the lack of sensors, it is impossible to count the usage of the parking spaces and to carry out overall management. Summary of the invention
[0005] The purpose of the embodiments of the present invention is to provide a smart building vehicle management method, aiming to solve the problems raised in the background technology.
[0006] The embodiment of the present invention is implemented as follows: a smart building vehicle management method, the method comprising:
[0007] Collecting real-time monitoring images and obtaining parking space registration information, wherein the parking space registration information includes a corresponding relationship table between parking spaces and vehicles;
[0008] Performing content recognition on the real-time monitoring image to obtain a content recognition result, wherein the content recognition result includes a parking space recognition result and a license plate recognition result;
[0009] Determine the parking space usage based on the content recognition results and upload the parking space usage to the backend;
[0010] Determine the match between the parking space and the license plate based on the content recognition result. If there is no match, issue a parking space occupancy notification;
[0011] After the step of uploading the parking space usage to the background, the method further includes generating a parking space navigation plan according to the usage of all current parking spaces.
[0012] Preferably, the step of performing content recognition on the real-time monitoring screen to obtain the content recognition result specifically includes:
[0013] Perform grayscale processing on the real-time monitoring image and adjust the contrast of the image to obtain a pre-processed image;
[0014] Identify the parking space lines in the pre-processed image and determine whether there is a vehicle in the parking space;
[0015] When there is a vehicle in the parking space, the vehicle body is identified based on the real-time monitoring image and the license plate information on the vehicle body is read.
[0016] Preferably, the step of determining the parking space usage according to the content recognition result and uploading the parking space usage to the backend specifically includes:
[0017] Determine the usage of all parking spaces within the monitoring range based on the content recognition results;
[0018] When the parking space usage does not match the background data, the parking space usage is uploaded to the background.
[0019] Preferably, the step of determining the match between the parking space and the license plate according to the content recognition result and issuing a parking space occupancy notification when there is no match specifically includes:
[0020] According to the parking space recognition result, retrieve the registered license plate number of the vehicle corresponding to the parking space from the background;
[0021] Read the actual license plate number in the license plate recognition result, and determine whether the actual license plate number matches the registered license plate number;
[0022] When the actual license plate number does not match the registered license plate number, a parking space occupancy notification is issued, and the parking space occupancy notification includes a real-time monitoring screen and the registered license plate number.
[0023] Preferably, the parking space occupancy notification is sent to both the parking lot manager and the registered parking space owner.
[0024] Preferably, the step of determining the match between the parking space and the license plate based on the content recognition result, and issuing a parking space occupancy notification when there is no match, also includes issuing a reminder voice message.
[0025] Preferably, after sending out the reminder voice message, the method further includes sending out available parking space guidance information.
[0026] Preferably, the step of generating a parking guidance plan according to the current usage of all parking spaces specifically includes:
[0027] Analyze and determine the best parking space based on the usage of all parking spaces;
[0028] Generate all guided routes according to the location of the best guided parking space;
[0029] Calculate the length of the guidance route and generate a parking guidance plan.
[0030] Another object of an embodiment of the present invention is to provide a smart building vehicle management system, the system comprising:
[0031] An information collection module is used to collect real-time monitoring images and obtain parking space registration information, wherein the parking space registration information includes a corresponding relationship table between parking spaces and vehicles;
[0032] A content recognition module is used to perform content recognition on the real-time monitoring picture to obtain a content recognition result, wherein the content recognition result includes a parking space recognition result and a license plate recognition result;
[0033] The parking space situation judgment module is used to judge the parking space usage according to the content recognition results and upload the parking space usage to the backend;
[0034] The occupancy notification module is used to determine the match between the parking space and the license plate based on the content recognition result. If there is no match, a parking space occupancy notification is issued;
[0035] The navigation scheme generation module is used to generate a parking navigation scheme based on the current usage of all parking spaces.
[0036] Preferably, the content identification module includes:
[0037] The image preprocessing unit is used to perform grayscale processing on the real-time monitoring image and adjust the contrast of the image to obtain a preprocessed image;
[0038] A parking space line recognition unit is used to recognize the parking space lines in the pre-processed image and determine whether there is a vehicle in the parking space;
[0039] The license plate reading unit is used to identify the vehicle body according to the real-time monitoring picture when there is a vehicle in the parking space, and read the license plate information on the vehicle body.
[0040] Preferably, the parking space situation judgment module includes:
[0041] A parking space status determination unit, used to determine the usage status of all parking spaces within the monitoring range according to the content recognition result;
[0042] The data uploading unit is used to upload the parking space usage to the background when the parking space usage does not match the background data.
[0043] An intelligent building vehicle management method provided by an embodiment of the present invention photographs the environment between buildings through monitoring devices installed between buildings, thereby determining the usage of each parking space through image recognition technology, and verifying the identities of the vehicle and the parking space owner, thereby further reducing the situation of occupying parking spaces and making it more convenient to use. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A flow chart of a smart building vehicle management method provided by an embodiment of the present invention;
[0045] Figure 2 A flowchart of the steps of performing content recognition on a real-time monitoring screen to obtain a content recognition result provided by an embodiment of the present invention;
[0046] Figure 3 A flowchart of the steps of determining parking space usage according to content recognition results and uploading the parking space usage to the backend provided in an embodiment of the present invention;
[0047] Figure 4 A flowchart of the steps of determining the matching between a parking space and a license plate according to the content recognition result and issuing a parking space occupancy notification when there is no match provided by an embodiment of the present invention;
[0048] Figure 5 An architecture diagram of a smart building vehicle management system provided by an embodiment of the present invention;
[0049] Figure 6 An architectural diagram of a content identification module provided by an embodiment of the present invention;
[0050] Figure 7 This is an architecture diagram of a parking space situation determination module provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0051] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0052] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.
[0053] In the current building system, parking spaces are set up, which are generally divided into underground parking spaces and ground parking spaces. For underground parking spaces, sensors are set up above the underground parking spaces for the convenience of management. The sensors can obtain the usage of each parking space, so as to facilitate statistics. However, there are also a large number of ground parking spaces. Since there are no sensors, it is impossible to count the usage of parking spaces and conduct overall management.
[0054] In the present invention, the environment between the buildings is photographed by monitoring devices installed between the buildings, so that the usage of each parking space is determined by image recognition technology, and the identities of the vehicle and the parking space owner are verified, which further reduces the situation of occupying parking spaces and makes it more convenient to use.
[0055] like Figure 1 FIG. 1 is a flow chart of a smart building vehicle management method provided by an embodiment of the present invention, and the method includes:
[0056] S100, collecting real-time monitoring images and obtaining parking space registration information, wherein the parking space registration information includes a corresponding relationship table between parking spaces and vehicles.
[0057] In this step, real-time monitoring screens are collected, and images are collected within the monitoring range using the established monitoring. Parking spaces within the monitoring range can be directly obtained from the real-time monitoring screens. At the same time, parking space registration information is obtained. The parking space registration information records the relationship between all vehicles and parking spaces. In the management process of smart buildings, some parking spaces in the parking lot will be rented out or sold to car owners, and the car owners will bind their vehicles to the parking spaces. After binding, records and parking space registration information will be stored in the background.
[0058] S200, performing content recognition on the real-time monitoring image to obtain a content recognition result, wherein the content recognition result includes a parking space recognition result and a license plate recognition result.
[0059] In this step, content recognition is performed on the real-time monitoring screen. At a certain time step, a frame is selected from the real-time monitoring screen. By identifying the content in the frame, it is determined whether each parking space in the current monitoring range is occupied. If occupied, the corresponding parking space is recorded as occupied in the parking space recognition result. When the parking space is occupied, the license plate is recognized, and the license plate recognition result is obtained by recognizing the license plate.
[0060] S300, determining the parking space usage according to the content recognition result, and uploading the parking space usage to the backend.
[0061] In this step, the usage of parking spaces is determined based on the content recognition results, which include information on whether the parking space is occupied. Since there may be multiple parking spaces within the monitoring range, it is necessary to determine all parking spaces within the monitoring range, and finally upload the usage of all parking spaces to the background. In the background, all parking spaces can be numbered, and the number of occupied parking spaces and the number of vacant parking spaces can be counted based on the usage of the parking spaces. In order to further improve the level of intelligence, guide signs can be set between buildings to prompt vehicles that need to park based on the locations of the vacant parking spaces in the background, so as to reduce the time required for vehicle parking, improve parking efficiency, and provide a better user experience.
[0062] S400, judging the matching between the parking space and the license plate according to the content recognition result, and issuing a parking space occupancy notification when there is no match.
[0063] In this step, the matching situation of the parking space and the license plate is determined based on the content recognition result. When the parking space is occupied, it is necessary to determine whether the current parking space is a parking space that has been rented out or sold. If the parking space is a parking space that has been rented out or sold, then no parking space occupation notification is issued. If the parking space is not a parking space that has been rented out or sold, then it is determined whether the current vehicle matches the vehicle information corresponding to the parking space. If the two match, it means that the current vehicle has the right to park in the parking space, and no parking space occupation notification is issued. When the current vehicle does not match the vehicle information corresponding to the parking space, it means that the current vehicle has no right to occupy the parking space, and an occupation notification is issued. The occupation notification is sent to the parking lot manager and the registered parking space owner at the same time, and a reminder voice message is sent at the same time to inform the current vehicle that this is a dedicated parking space and parking is not allowed. After the reminder, available parking space guidance information is sent to guide the current vehicle to park in an available parking space.
[0064] S500: Generate a parking guidance plan based on the current usage of all parking spaces.
[0065] In this step, in order to ensure that the current car owner can park as quickly as possible and thus reduce his / her occupation of the lane, a comprehensive analysis is conducted based on the usage of the parking space to generate a parking guidance plan to guide him / her to park quickly.
[0066] As a preferred embodiment of the present invention, the step of generating a parking space navigation scheme according to the current usage of all parking spaces specifically includes:
[0067] S501, analyzing and determining the best guided parking space according to the usage of all parking spaces.
[0068] In this step, the usage of all parking spaces is first counted to generate a simulated parking space map, and corresponding paths are generated in the simulated parking space map. The parking spaces that allow parking are marked in the simulated parking space map to select the best guide parking space.
[0069] S502: Generate all guided routes according to the position of the best guiding parking space.
[0070] S503, calculating the length of the guidance route and generating a parking guidance plan.
[0071] In this step, all the guidance routes are traversed according to the current position of the vehicle and the position of the best guidance parking space. During the traversal process, the length of each guidance route is counted to calculate the shortest guidance route and regard it as the parking guidance plan. At this time, the corresponding display device is controlled according to the above parking guidance plan to display the vehicle's license plate number and indicate the guidance route.
[0072] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of performing content recognition on the real-time monitoring picture to obtain the content recognition result specifically includes:
[0073] S201, grayscale processing is performed on the real-time monitoring picture, and the contrast of the picture is adjusted to obtain a pre-processed picture.
[0074] In this step, the real-time monitoring screen is gray-scaled so that it becomes a black and white image. During processing at this time, the amount of data processing will be reduced, and then the contrast is adjusted. By changing the contrast, the contrast between the parking space line and the road surface in the pre-processed image is made stronger, so as to facilitate the identification of the parking space line and improve the recognition rate.
[0075] S202, identifying the parking space lines in the pre-processing image, and determining whether there is a vehicle in the parking space.
[0076] In this step, the parking space lines in the pre-processing image are identified, and the initial image is taken using surveillance. The image of each parking space is recorded in the initial image, so the parking space lines of each parking space are also fixed. When the parking space lines are blocked, it is considered that the parking space is occupied by a vehicle, so as to judge whether there is a vehicle in the parking space. If the parking space lines are blocked and the vehicle cannot be identified, it is considered to be blocked by foreign objects. At this time, a foreign object blockage notification is issued to notify relevant personnel to handle it.
[0077] S203, when there is a vehicle in the parking space, the vehicle body is identified according to the real-time monitoring image, and the license plate information on the vehicle body is read.
[0078] In this step, when there is a vehicle in the parking space, the vehicle is identified based on the real-time monitoring image, the license plate position on the vehicle body is located, and the license plate information is further extracted, the license plate information includes license plate color information and license plate number information.
[0079] like Figure 3As shown, as a preferred embodiment of the present invention, the step of determining the parking space usage according to the content recognition result and uploading the parking space usage to the background specifically includes:
[0080] S301, determining the usage status of all parking spaces within the monitoring range according to the content recognition result.
[0081] In this step, the usage of all parking spaces within the monitoring range is determined based on the content recognition results. There are a large number of parking spaces, so multiple monitoring devices are needed for identification. After all monitoring devices have completed data uploading, the usage of all parking spaces is summarized.
[0082] S302, when the parking space usage does not match the background data, the parking space usage is uploaded to the background.
[0083] In this step, when uploading data, it is only uploaded when the parking space usage does not match the background data. If the parking space usage matches the background data, it means that the vehicle parked in the current parking space is legal, so there is no need to upload, and there is no need to update the background data, thereby reducing the amount of data transmission.
[0084] like Figure 4 As shown, as a preferred embodiment of the present invention, the step of determining the matching between the parking space and the license plate according to the content recognition result and issuing a parking space occupancy notification when there is no match specifically includes:
[0085] S401, retrieve the registered license plate number of the vehicle corresponding to the parking space from the background according to the parking space recognition result.
[0086] In this step, the registered license plate number of the vehicle corresponding to the parking space is retrieved from the background according to the parking space recognition result. The parking space registration information is set in the background. The parking space recognition result can locate the information of the current parking space, and retrieve the registered license plate number in the background according to the parking space information for comparison.
[0087] S402, reading the actual license plate number in the license plate recognition result, and determining whether the actual license plate number matches the registered license plate number.
[0088] In this step, the actual license plate number in the license plate recognition result is read, and the actual license plate number of the current vehicle is identified through image recognition technology, and compared with the registered license plate number. First, the color of the license plate is compared. If the colors of the two are different, the license plate numbers are not compared and are directly regarded as mismatched. If the license plate colors are the same, the license plate numbers are compared bit by bit.
[0089] S403, when the actual license plate number does not match the registered license plate number, a parking space occupancy notification is issued, wherein the parking space occupancy notification includes a real-time monitoring screen and the registered license plate number.
[0090] In this step, when the actual license plate number does not match the registered license plate number, a parking space occupation notice is issued. The parking space occupation notice is sent to both the parking space manager and the parking space owner to resolve the problem through negotiation between the two parties. The parking space occupation notice contains the real-time monitoring screen and the registered license plate number to facilitate contact and record with the vehicle occupying the parking space.
[0091] like Figure 5 As shown, a smart building vehicle management system provided by the present invention includes:
[0092] The information collection module 100 is used to collect real-time monitoring images and obtain parking space registration information, wherein the parking space registration information includes a corresponding relationship table between parking spaces and vehicles.
[0093] In this system, the information acquisition module 100 collects real-time monitoring images and uses the established monitoring to collect images within its monitoring range. The parking spaces within the monitoring range can be directly obtained from the real-time monitoring images. At the same time, the parking space registration information is obtained, and the parking space registration information records the relationship between all vehicles and parking spaces.
[0094] The content recognition module 200 is used to perform content recognition on the real-time monitoring picture to obtain a content recognition result, wherein the content recognition result includes a parking space recognition result and a license plate recognition result.
[0095] In this system, the content recognition module 200 performs content recognition on the real-time monitoring screen. At a certain time step, a frame is selected from the real-time monitoring screen, and the content in the frame is recognized to determine whether each parking space within the current monitoring range is occupied. If occupied, the corresponding parking space is recorded as occupied in the parking space recognition result. When the parking space is occupied, the license plate is recognized, and the license plate recognition result is obtained by recognizing the license plate.
[0096] The parking space situation determination module 300 is used to determine the parking space usage situation according to the content recognition result, and upload the parking space usage situation to the background.
[0097] In this system, the parking space situation judgment module 300 judges the parking space usage according to the content recognition result. The content recognition result includes information on whether the parking space is occupied. Since there may be multiple parking spaces within the monitoring range, it is necessary to judge all parking spaces within the monitoring range, and finally upload the usage of all parking spaces to the background; in the background, all parking spaces can be numbered, and the number of occupied parking spaces and the number of vacant parking spaces can be counted in combination with the parking space usage. In order to further improve the degree of intelligence, guide signs can be set between buildings to prompt vehicles that need to park according to the location of the vacant parking spaces in the background, so as to reduce the time required for vehicle parking, improve parking efficiency, and provide a better user experience.
[0098] The occupancy notification module 400 is used to determine the matching situation between the parking space and the license plate according to the content recognition result, and issue a parking space occupancy notification when there is no match.
[0099] In this system, the occupancy notification module 400 determines the matching situation of the parking space and the license plate based on the content recognition result. When the parking space is occupied, it is necessary to determine whether the current parking space is a parking space that has been rented out or sold. If the parking space is a parking space that has been rented out or sold, then no parking space occupancy notification will be issued. If the parking space is not a parking space that has been rented out or sold, then it is determined whether the vehicle information corresponding to the current vehicle and the parking space are consistent. If the two are consistent, it means that the current vehicle has the right to park in the parking space, and no parking space occupancy notification will be issued. When the current vehicle does not match the vehicle information corresponding to the parking space, it means that the current vehicle has no right to occupy the parking space, and an occupancy notification will be issued.
[0100] The navigation scheme generating module 500 is used to generate a parking navigation scheme according to the current usage of all parking spaces.
[0101] like Figure 6 As shown, as a preferred embodiment of the present invention, the content identification module 200 includes:
[0102] The picture preprocessing unit 201 is used to perform grayscale processing on the real-time monitoring picture and adjust the contrast of the picture to obtain a preprocessed picture.
[0103] In this module, the image preprocessing unit 201 performs grayscale processing on the real-time monitoring image, so that the real-time monitoring image becomes a black and white image. When processing at this time, the data processing amount will be reduced, and then the contrast adjustment is performed. By changing the contrast, the contrast between the parking space line and the road surface in the preprocessing image is made stronger, so as to facilitate the identification of the parking space line and improve the recognition rate.
[0104] The parking space line recognition unit 202 is used to recognize the parking space lines in the pre-processed image and determine whether there is a vehicle in the parking space.
[0105] In this module, the parking space line recognition unit 202 recognizes the parking space lines in the pre-processing image and uses monitoring to take an initial image. The initial image records the image of each parking space, so the parking space lines of each parking space are also fixed. When the parking space lines are blocked, it is regarded as the parking space is occupied by a vehicle, so as to judge whether there is a vehicle in the parking space. If the parking space lines are blocked and the vehicle cannot be identified, it is regarded as blocked by foreign objects. At this time, a foreign object blocking notification is issued to notify relevant personnel to handle it.
[0106] The license plate reading unit 203 is used to identify the vehicle body according to the real-time monitoring picture and read the license plate information on the vehicle body when there is a vehicle in the parking space.
[0107] In this module, when there is a vehicle in the parking space, the license plate reading unit 203 identifies the vehicle based on the real-time monitoring image, locates the license plate position on the vehicle body, and further extracts the license plate information, which includes the license plate color information and the license plate number information.
[0108] like Figure 7 As shown, as a preferred embodiment of the present invention, the parking space situation judgment module 300 includes:
[0109] The parking space status determination unit 301 is used to determine the usage status of all parking spaces within the monitoring range according to the content recognition result.
[0110] In this module, the parking space status determination unit 301 determines the usage status of all parking spaces within the monitoring range based on the content recognition results. There are a large number of parking spaces, so multiple monitoring devices are required for identification. After all monitoring devices have completed data uploading, the usage status of all parking spaces is summarized.
[0111] The data uploading unit 302 is used to upload the parking space usage status to the background when the parking space usage status does not match the background data.
[0112] In this module, when the data uploading unit 302 uploads data, it will only upload when the parking space usage does not match the background data. If the parking space usage matches the background data, it means that the vehicle parked in the current parking space is legal, so there is no need to upload or update the background data, thereby reducing the amount of data transmission.
[0113] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.
[0114] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0115] 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.
[0116] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
[0117] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. A smart building vehicle management method, characterized in that: The method comprises: Collecting real-time monitoring images and obtaining parking space registration information, wherein the parking space registration information includes a corresponding relationship table between parking spaces and vehicles; Performing content recognition on the real-time monitoring image to obtain a content recognition result, wherein the content recognition result includes a parking space recognition result and a license plate recognition result; Determine the parking space usage based on the content recognition results and upload the parking space usage to the backend; Determine the match between the parking space and the license plate based on the content recognition result. If there is no match, issue a parking space occupancy notification; After the step of uploading the parking space usage to the background, the method further includes generating a parking space navigation plan according to the usage of all current parking spaces.
2. The smart building vehicle management method according to claim 1, characterized in that: The step of performing content recognition on the real-time monitoring screen to obtain the content recognition result specifically includes: Perform grayscale processing on the real-time monitoring image and adjust the contrast of the image to obtain a pre-processed image; Identify the parking space lines in the pre-processed image and determine whether there is a vehicle in the parking space; When there is a vehicle in the parking space, the vehicle body is identified based on the real-time monitoring image and the license plate information on the vehicle body is read.
3. The smart building vehicle management method according to claim 1, characterized in that: The step of determining the parking space usage according to the content recognition result and uploading the parking space usage to the background specifically includes: Determine the usage of all parking spaces within the monitoring range based on the content recognition results; When the parking space usage does not match the background data, the parking space usage is uploaded to the background.
4. The smart building vehicle management method according to claim 1, characterized in that: The step of determining the matching between the parking space and the license plate according to the content recognition result and issuing a parking space occupancy notification when there is no match specifically includes: According to the parking space recognition result, retrieve the registered license plate number of the vehicle corresponding to the parking space from the background; Read the actual license plate number in the license plate recognition result, and determine whether the actual license plate number matches the registered license plate number; When the actual license plate number does not match the registered license plate number, a parking space occupancy notification is issued, and the parking space occupancy notification includes a real-time monitoring screen and the registered license plate number.
5. The smart building vehicle management method according to claim 1, characterized in that: The parking space occupancy notification is sent to both the parking lot manager and the registered parking space owner.
6. The smart building vehicle management method according to claim 1, characterized in that: The step of determining the matching between the parking space and the license plate according to the content recognition result and issuing a parking space occupancy notification when there is no match also includes issuing a reminder voice message.
7. The smart building vehicle management method according to claim 1, characterized in that: The step of generating a parking space guidance plan according to the current usage of all parking spaces specifically includes: Analyze and determine the best parking space based on the usage of all parking spaces; Generate all guided routes according to the location of the best guided parking space; Calculate the length of the guidance route and generate a parking guidance plan.
8. A smart building vehicle management system, characterized in that: The system comprises: An information collection module is used to collect real-time monitoring images and obtain parking space registration information, wherein the parking space registration information includes a corresponding relationship table between parking spaces and vehicles; A content recognition module is used to perform content recognition on the real-time monitoring picture to obtain a content recognition result, wherein the content recognition result includes a parking space recognition result and a license plate recognition result; The parking space situation judgment module is used to judge the parking space usage according to the content recognition results and upload the parking space usage to the backend; The occupancy notification module is used to determine the match between the parking space and the license plate based on the content recognition result. If there is no match, a parking space occupancy notification is issued; The navigation scheme generation module is used to generate a parking navigation scheme based on the current usage of all parking spaces.
9. The intelligent building vehicle management system according to claim 8, characterized in that: The content identification module comprises: The image preprocessing unit is used to perform grayscale processing on the real-time monitoring image and adjust the contrast of the image to obtain a preprocessed image; A parking space line recognition unit is used to recognize the parking space lines in the pre-processed image and determine whether there is a vehicle in the parking space; The license plate reading unit is used to identify the vehicle body according to the real-time monitoring picture when there is a vehicle in the parking space, and read the license plate information on the vehicle body.
10. The smart building vehicle management system according to claim 8, characterized in that: The parking space situation judgment module includes: A parking space status determination unit, used to determine the usage status of all parking spaces within the monitoring range according to the content recognition result; The data uploading unit is used to upload the parking space usage to the background when the parking space usage does not match the background data.
