Parking system based on computer vision algorithm

Abstract

The invention provides a parking system based on a computer vision algorithm, which comprises a map module, a parking space module, a control module and a data module, and is characterized in that the map module comprises a map construction unit, a map calling unit, a path navigation unit and an image pushing unit; the parking space module comprises a video acquisition unit, an area camera shooting unit, an entrance camera shooting unit and an area monitoring unit, the control module comprises a main control unit, an area control unit and a parking space detection unit, the data module comprises a server unit, a data transmission unit and a data safety unit, and an auxiliary storage unit is arranged in the area control unit. Edge detection algorithms are preset in the auxiliary storage unit and the parking space detection unit; according to the invention, based on a computer vision algorithm, the calculation process is simplified, the parking lot map is divided into regions, the regions are taken as units, and the regions with many idle parking spaces are taken as navigation targets, so that parking navigation guidance is provided for the user, the user can find the parking spaces quickly and conveniently, and the touring experience of the user is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of scenic spot parking systems, and in particular to a parking system based on computer vision algorithms. Background Art

[0002] Tourist attractions refer to places with certain natural landscapes, cultural landscapes or historical and cultural values, which are developed and managed and provided for tourists to visit. Tourist attractions can be natural scenery areas, historical and cultural sites, theme parks, zoos, botanical gardens, museums and many other types, and tourist attraction parking lots refer to special parking facilities provided for tourists in tourist attractions. These parking lots are usually located at or near the entrance of the scenic area, making it convenient for tourists to park and enter the scenic area for sightseeing. The design and management of tourist attraction parking lots are crucial to improving the tourist experience and ensuring traffic safety.

[0003] With the rapid improvement of the economy, the scale of my country's automobile market has continued to increase, and the number of cars has also increased dramatically. It has become a common phenomenon for a family to own multiple cars, making the problem of parking more and more common. Self-driving tours are very popular at present, and then in scenic spots, it is often difficult to find parking spaces, resulting in users having to spend more time parking before visiting scenic spots. Therefore, the present invention proposes a parking system based on computer vision algorithm to solve the problems existing in the prior art. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to propose a parking system based on computer vision algorithm, which has the advantage of facilitating users to find vacant parking spaces and solves the problems existing in the prior art.

[0005] To achieve the purpose of the present invention, the present invention is implemented through the following technical solutions: a parking system based on a computer vision algorithm, comprising a map module, a parking space module, a control module and a data module, wherein the map module, the parking space module, the control module and the data module are connected through a communication module, the map module comprises a map construction unit, a map calling unit, a path navigation unit and an image pushing unit, the parking space module comprises a video acquisition unit, a regional camera unit, an entrance camera unit and a regional monitoring unit, the control module comprises a main control unit, a regional control unit and a parking space detection unit, the data module comprises a server unit, a data transmission unit and a data security unit, the regional control unit is provided with a plurality of groups, and the plurality of groups of regional control units are controlled by a group of main control units, an auxiliary storage unit is provided in the regional control unit, and an edge detection algorithm is preset in the auxiliary storage unit and the parking space detection unit.

[0006] A further improvement is that the control module also includes a system interaction platform, the system interaction platform is connected to the regional control unit through the main control unit, and a group of the regional control units corresponds to a group of parking space detection units.

[0007] A further improvement is that the regional camera unit, the entrance camera unit and the regional monitoring unit are all connected to the regional control unit via the video acquisition unit, and the regional monitoring unit is connected to the image pushing unit via the regional control unit.

[0008] A further improvement is that the map module also includes an area division unit, the area division unit is connected to the path navigation unit through the map calling unit, the path navigation unit has path navigation rules preset therein, and the path navigation unit is connected to the system interaction platform through the main control unit.

[0009] A further improvement is that: the path navigation rule is: taking the area with the most vacant parking spaces as the priority navigation end point, and taking the user's vehicle entry position as the starting point to plan the navigation path.

[0010] A further improvement is that the communication module includes a wireless communication unit for communicating with mobile devices, a wired communication unit for communicating with devices within the system, and a remote access unit for remote communication with personnel.

[0011] A further improvement is that the control module also includes a two-dimensional code connection unit, and the two-dimensional code connection unit is connected to the system interaction platform.

[0012] A further improvement is that the data module also includes an external interface unit for connecting to an external system and an uploading unit for uploading data.

[0013] The beneficial effects of the present invention are as follows: the parking system based on computer vision algorithm is based on computer vision algorithm and simplifies the calculation process. By dividing the parking lot map data into regions, and taking regions as units, and taking regions with many vacant parking spaces as navigation targets, the parking navigation guidance is provided for users, so that users can quickly find vacant parking spaces and improve the user's sightseeing experience. At the same time, the distributed computing method is introduced, and the regional control unit is used for calculation to improve the responsiveness of the system and better serve tourists. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is a schematic diagram of the system structure of the present invention.

[0015] Figure 2 It is a schematic diagram after the area division of the present invention. DETAILED DESCRIPTION

[0016] In order to deepen the understanding of the present invention, the present invention will be further described in detail below in conjunction with examples. The examples are only used to explain the present invention and do not constitute a limitation on the protection scope of the present invention.

[0017] according to Figure 1 As shown, this embodiment proposes a parking system based on computer vision algorithm, including a map module, a parking space module, a control module and a data module, and the map module, the parking space module, the control module and the data module are connected through a communication module.

[0018] The map module includes:

[0019] A map construction unit used to construct a parking lot map. When this system is applied, the staff uses the geographic information system (GIS) software to construct a map based on the area of ​​the scenic area's parking lot planning. After the map is created, it is regularly checked against the actual area, and updated in a timely manner when an abnormal situation occurs.

[0020] The map calling unit is used for the system to call map data. When this system is in use, some modules will call the created map data, and then provide the corresponding data interface through the map calling unit. During the operation of this system, the constructed map data can be called.

[0021] A path navigation unit for providing user navigation. When this system is used, path navigation rules are preset in the path navigation unit, and the path navigation rules are: the area with the most vacant parking spaces is the priority navigation end point, and the user's vehicle entry position is the starting point (the user's vehicle entry position is usually the entrance of the parking lot. This system collects the GPS positioning information of the user's mobile phone. If the GPS positioning information of the user's mobile phone cannot be obtained, the entrance of the parking lot is first used as the starting point. When the positioning information is obtained, the route is re-planned). The navigation path is planned. Because this system adopts the method of regional division to conduct parking guidance in the scenic area, in order to facilitate the parking management of the scenic area and avoid concentrated parking in one area, this path navigation rule is set in this system. When the traffic volume is large, the traffic volume can be evenly distributed to the divided areas.

[0022] The area division unit is used to divide the area according to the map data. The area division unit is connected to the path navigation unit through the map calling unit. That is, the area division unit divides the area based on the data called by the map calling unit. Then, the path navigation unit calls the divided data when performing navigation guidance. Figure 2As shown, for an entire parking lot, area division can better manage vehicles. Further, the path navigation unit is connected to the system interaction platform through the main control unit. When the user enters and interacts with the system interaction platform, its path navigation unit can push the navigation path to the system interaction platform and display it to the user through the system interaction platform.

[0023] An image push unit is used to push video surveillance images. When the system is in use, it adopts a direct display method to facilitate users to find parking spaces. When the user's vehicle enters the corresponding area, the area control unit in the corresponding area pushes the monitoring image of the current area through the image push unit. The object of the monitoring image is the parking space status in the area. Therefore, after the user's vehicle enters the corresponding area, the mobile phone can intuitively see where there are empty parking spaces in the area, and guide the user to that direction. Compared with using empty parking spaces as the navigation target end point, this system is more direct. Users can see the parking space status of the area through monitoring without having to go around in the area. At the same time, it can reduce the amount of calculation of the system, thereby reducing the probability of system calculation errors, bringing a good experience to users.

[0024] The parking space module includes:

[0025] The video acquisition unit used to collect video information corresponds to a video acquisition card, which serves to transmit the collected video information to the corresponding module, that is, the regional camera unit, the entrance camera unit and the regional monitoring unit are all connected to the regional control unit through the video acquisition unit.

[0026] The regional camera unit is used to shoot the parking space conditions in the area. The regional camera unit is not limited to one, and is set accordingly according to the size of the regional division and the design of the actual parking area. However, its goal is to monitor the overview of the parking spaces. At least one group of regional camera units is set for each group of areas, and at least one group of regional camera units is arranged at the entrance of the area. In this way, when the user receives the picture pushed by the image push unit through the mobile phone, the parking space conditions in the area can be seen from the perspective of the user's vehicle entering, which is convenient for the user to identify its direction and improve efficiency.

[0027] The entrance camera unit is used for shooting at the entrance of the area. When the system is working, the entrance camera unit is used to shoot the license plate information of the user's vehicle and extract the license plate number of the user's vehicle. When the system is working, after the user enters the scenic area, he logs in to the system interaction platform through the mobile phone, and the system interaction platform requires the user to enter the corresponding vehicle number. Furthermore, when the user's vehicle enters the guided area, the entrance camera unit will shoot the license plate number of the user's vehicle again and match it with the vehicle number entered by the user. After the match, the area control unit will start the image push unit to push the picture. During this process, the area control unit in any area of ​​the parking lot will perform the vehicle number comparison operation after the user's vehicle enters, and start the corresponding image push unit after the match.

[0028] The regional monitoring unit is used to connect with the image push unit. When the system is working, the regional monitoring unit obtains the real-time monitoring data in the regional camera unit and transmits it to the regional control unit. At the same time, the regional monitoring unit is connected to the image push unit through the regional control unit.

[0029] The control module includes:

[0030] The main control unit is used for overall calculation and control. When the system is working, the main control unit is the main computer, which can be responsible for all the work of the system.

[0031] A regional control unit for regional calculation and control is an auxiliary computer. When the system is working, a distributed computing method is introduced. An auxiliary storage unit is provided in the regional control unit. The auxiliary storage unit is used for data storage, program algorithm storage, etc. Then, after the user's vehicle enters the corresponding area, the regional control unit performs independent calculations and obtains the license plate information of the user's license plate through the edge detection algorithm. Then, the regional control unit compares the information and performs subsequent operations, thereby improving the working efficiency of the system. Furthermore, the regional control unit is provided with several groups, and several groups of regional control units are controlled by one group of main control units. In this embodiment, four groups of regional control units are provided.

[0032] The parking space detection unit for identifying parking spaces in an area, that is, the auxiliary storage unit and the parking space detection unit are preset with an edge detection algorithm. By utilizing the edge detection algorithm, the number of vacant parking spaces in the area is identified. Then, in the planning process of the path navigation unit, the area with the largest number of vacant parking spaces is first confirmed and then set as the end point for subsequent planning. At the same time, a group of area control units corresponds to a group of parking space detection units, and the area control units perform independent calculations and then transmit their data to the main control unit.

[0033] The system interaction platform is used to interact with users. The system interaction platform is connected to the regional control unit through the main control unit. When the user logs into the system interaction platform, the main control unit acts as a relay. According to the user's vehicle entering the corresponding area, the regional control unit of the area is assigned to calculate and control the results, which are then displayed by the main control unit through the system interaction platform.

[0034] A QR code connection unit is used to scan the code to connect to the system interaction platform. When the system is working, the QR code connection unit is connected to the system interaction platform. When the user's vehicle enters the park, the user is required to scan the QR code to log in. The login verification method is based on the license plate number of the user's vehicle.

[0035] Data module:

[0036] A server unit for overall data storage is included, which has a large data storage capacity.

[0037] The data transmission unit used for data transmission between modules mainly plays the role of data transmission between units. For example, the regional control unit transmits data to the main control unit, and the main control unit transmits data to the server unit, etc. It mainly cooperates with the communication module to perform corresponding data transmission.

[0038] The data security unit mainly ensures the security and integrity of data within the server unit to prevent unauthorized access and data leakage.

[0039] The external interface unit used to link with the external system provides data access between the external system and this system. The main purpose of this system is to facilitate the guidance of users' parking, and then it can be connected with the external billing system or other systems to perform corresponding data interaction.

[0040] An upload unit for uploading data. The upload unit is mainly used to upload data to the cloud or other platforms.

[0041] The communication module includes a wireless communication unit for communicating with mobile devices, a wired communication unit for communicating with devices within the system, and a remote access unit for remote communication with personnel.

[0042] In this embodiment, the system is based on an edge detection algorithm, which is a computer vision algorithm. During the use of the edge detection algorithm, the control module (i.e., the corresponding computing part) processes the collected image or video data, specifically graying, binarizing, and denoising the collected image, and then uses the edge detection algorithm to perform corresponding feature extraction, and then the license plate information of the user's vehicle can be obtained. Accordingly, when the vehicle feature can be extracted from a parking space, it means that the parking space is occupied. Similarly, when the vehicle feature cannot be extracted from the parking space, it means that the parking space is idle, and then corresponding statistics can be performed.

[0043] At the same time, this system adopts a direct push method, which makes it convenient for users to observe the status of parking spaces in the area from a monitoring perspective, so as to obtain the corresponding direction, which is more efficient.

[0044] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the framework and scope of application of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A parking system based on computer vision algorithm, characterized in that: It includes a map module, a parking space module, a control module and a data module, wherein the map module, the parking space module, the control module and the data module are connected via a communication module, the map module includes a map construction unit, a map calling unit, a path navigation unit and an image pushing unit, the parking space module includes a video acquisition unit, a regional camera unit, an entrance camera unit and a regional monitoring unit, the control module includes a main control unit, a regional control unit and a parking space detection unit, the data module includes a server unit, a data transmission unit and a data security unit, the regional control unit is provided with several groups, and the several groups of regional control units are controlled by one group of main control units, an auxiliary storage unit is provided in the regional control unit, and an edge detection algorithm is preset in the auxiliary storage unit and the parking space detection unit.

2. A parking system based on computer vision algorithm according to claim 1, characterized in that: The control module also includes a system interaction platform, which is connected to the regional control unit through the main control unit, and a group of the regional control units corresponds to a group of parking space detection units.

3. The parking system based on computer vision algorithm according to claim 1, characterized in that: The regional camera unit, the entrance camera unit and the regional monitoring unit are all connected to the regional control unit via the video acquisition unit, and the regional monitoring unit is connected to the image pushing unit via the regional control unit.

4. The parking system based on computer vision algorithm according to claim 2, characterized in that: The map module also includes an area division unit, which is connected to a path navigation unit via a map calling unit. Path navigation rules are preset in the path navigation unit, and the path navigation unit is connected to a system interaction platform via a main control unit.

5. The parking system based on computer vision algorithm according to claim 4, characterized in that: The path navigation rule is: taking the area with the most vacant parking spaces as the priority navigation end point, taking the user's vehicle entry position as the starting point, and planning the navigation path.

6. The parking system based on computer vision algorithm according to claim 1, characterized in that: The communication module includes a wireless communication unit for communicating with mobile devices, a wired communication unit for communicating with devices within the system, and a remote access unit for remote communication with personnel.

7. The parking system based on computer vision algorithm according to claim 2, characterized in that: The control module also includes a two-dimensional code connection unit, and the two-dimensional code connection unit is connected to the system interaction platform.

8. The parking system based on computer vision algorithm according to claim 1, characterized in that: The data module also includes an external interface unit for connecting to an external system and an uploading unit for uploading data.

Images