Reverse vehicle searching method, system and device based on image recognition and medium

Abstract

The invention discloses a reverse vehicle searching method, system and device based on image recognition and a medium, mainly relates to the technical field of reverse vehicle searching, and is used for solving the problem that the existing traditional method for drawing signs and marked lines mainly utilizes the forgetting risk of driver memory; a Bluetooth positioning method needs to install a transmitting antenna capable of amplifying a signal at the top of a vehicle, and is unfriendly to a driver entering a parking lot for the first time; and data interaction needs to be carried out by using a better network when the query terminal is arranged in the parking lot. Comprising the following steps: detecting license plate information entering a parking lot and driver face information through an entrance camera, and matching; storing the corresponding relationship among the license plate information, the driver face information and the vehicle parking space; inputting face information or license plate information to determine a vehicle parking space; and determining and displaying a route map from the scanning position of the current two-dimensional code to the vehicle parking space based on the route map from the scanning position of the two-dimensional code to each parking space.

Description

Technical Field

[0001] The present application relates to the field of live broadcast auxiliary application technology, and in particular to a reverse vehicle search method, system, device and medium based on image recognition. Background Art

[0002] Modern technologies, such as GPS tracking systems, IoT devices, connected vehicles, and mobile applications, make vehicle search more efficient and accurate. These technologies can not only provide the real-time location of the vehicle, but also monitor the vehicle's status, thus providing more information support for the vehicle search process. In the field of commercial vehicles, an efficient vehicle search system plays an important role in improving operational efficiency, reducing costs, and improving safety.

[0003] At present, taking passenger cars as an example, there are several methods for reverse car search in parking lots: the first is the traditional method based on the markings and lines painted in the parking lot. This method relies on the driver's memory to search for the area where the vehicle is located and the specific parking space through the text and images on the ground and pillars. However, due to the large area of ​​the parking lot, low recognition or long parking time, it is difficult for the driver to find the vehicle location, the car search efficiency is low, and the time cost is high; the second is the Bluetooth positioning method, which mainly relies on the installation of a Bluetooth signal transmission module inside the car and the installation of a transmitting antenna on the top of the vehicle that can amplify the signal. When searching for a car, the driver needs to turn on the Bluetooth of the smartphone, and the portable monitoring device receives a specific signal to determine the exact location of the vehicle, and finally transmits the monitored vehicle location information to the owner's smartphone. The third is to set up a query terminal in the parking lot, using the parking space number and the license plate number for matching. The owner enters the license plate number to query the vehicle location, and the system provides the best route to pick up the car. The system software will give the parking location and the shortest route to find the car.

[0004] However, the traditional method of painting signs and markings mentioned above mainly relies on the driver's memory, which carries the risk of forgetting; the Bluetooth positioning method requires the installation of a transmitting antenna on the top of the vehicle that can amplify the signal, which is not friendly to drivers who enter the parking lot for the first time; the parking lot needs to use a good network to interact with GPS data in the query terminal, but the parking lot of large commercial vehicle fleets has a large area and may be located in a remote location with poor signal quality. The waiting time for GPS data transmission in the parking lot is long. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present application provides a reverse vehicle search system, method and medium based on image recognition to solve the problem that the traditional method of painting signs and markings mainly relies on the driver's memory and there is a risk of forgetting; the Bluetooth positioning method requires the installation of a transmitting antenna on the top of the vehicle that can amplify the signal, which is not friendly to drivers entering the parking lot for the first time; and the parking lot needs to use a better network for data interaction when setting up a query terminal.

[0006] In a first aspect, the present application provides a reverse vehicle search method based on image recognition, the method comprising: Obtain the scanning position of the QR code and the route map from the scanning position of the QR code to each parking space; detect the license plate information and driver's facial information entering the parking lot through the camera at the entrance, and match them; identify the vehicle parking space through the camera in the parking lot, and store the correspondence between the license plate information, the driver's facial information and the vehicle parking space; enter the information query interface through the QR code, and then enter the facial information or license plate information to determine the vehicle parking space; then based on the route map from the scanning position of the QR code to each parking space, determine and display the route map from the current QR code scanning position to the vehicle parking space.

[0007] Furthermore, the scanning positions of the QR code include at least: preset intersections and entrances and exits in the parking lot.

[0008] Furthermore, obtaining the scanning position of the QR code and the route map from the scanning position of the QR code to each parking space specifically includes: Get the route map from the scanning location of the QR code to each parking space through the preset picture acquisition interface.

[0009] Furthermore, before identifying the parking space of the vehicle by using a camera in the parking lot, the method further includes: Arrange the parking lot according to preset monitoring sub-areas, and install cameras in each preset monitoring sub-area; determine the preset neighboring cameras of each camera based on the positional relationship between the preset monitoring sub-areas; identify the parking space of the vehicle through the cameras in the parking lot, specifically including: tracking the vehicle entering the parking lot through the license plate information, after the vehicle enters the parking lot, identifying the preset neighboring camera of the last camera that recognized the license plate information, if the license plate information appears in the preset neighboring camera within the preset waiting time, repeat the previous step, if the license plate information does not appear in the preset neighboring camera within the preset waiting time, it is determined that the driver has completed parking, and identify the vehicle image last taken by the camera; identify the vehicle parking space in the vehicle image.

[0010] Furthermore, the information query interface is entered through the QR code, and then the face information or license plate information is input to determine the parking space of the vehicle, which specifically includes: Enter the information query interface through the QR code; When the face recognition module of the information query interface is triggered, the face information is obtained through the face information acquisition interface or the license plate information is obtained through the license plate information input interface; Through the correspondence between the license plate information, the driver's facial information and the vehicle parking space, the facial information or the license plate information is determined to determine the vehicle parking space.

[0011] In a third aspect, the present application provides a reverse vehicle search system based on image recognition, the system comprising: An acquisition module is used to acquire the scanning position of the QR code and a route map from the scanning position of the QR code to each parking space; The matching module is used to detect the license plate information and driver's face information of the vehicle entering the parking lot through the camera at the entrance and perform matching; A storage module, used to identify the parking space of the vehicle through the camera in the parking lot, and store the corresponding relationship between the license plate information, the driver's face information and the parking space of the vehicle; The route module is used to enter the information query interface through the QR code, and then input facial information or license plate information to determine the parking space for the vehicle; then based on the route map from the scanning position of the QR code to each parking space, determine and display the route map from the current scanning position of the QR code to the parking space for the vehicle.

[0012] Furthermore, the acquisition module includes an acquisition unit, Used to obtain the route map from the scanning location of the QR code to each parking space through the preset image acquisition interface.

[0013] Furthermore, the line module comprises a determination unit, Used to enter the information query interface through the QR code; When the face recognition module of the information query interface is triggered, the face information is obtained through the face information acquisition interface or the license plate information is obtained through the license plate information input interface; Through the correspondence between the license plate information, the driver's facial information and the vehicle parking space, the facial information or the license plate information is determined to determine the vehicle parking space.

[0014] In a third aspect, the present application provides a reverse vehicle search device based on image recognition, the device comprising: a processor; and a memory on which executable code is stored, and when the executable code is executed, the processor executes a reverse vehicle search method based on image recognition as described above.

[0015] In a fourth aspect, the present application provides a non-volatile computer storage medium having computer instructions stored thereon, which when executed implement a reverse vehicle search method based on image recognition as any of the above items.

[0016] Those skilled in the art can understand that the present application has at least the following beneficial effects: The present application proposes a reverse vehicle search method, system, device and medium based on image recognition, which enters the information query interface through a QR code, and then inputs facial information or license plate information to determine the vehicle parking space; then based on the route map from the scanning position of the QR code to each parking space, the route map from the current scanning position of the QR code to the vehicle parking space is determined and displayed, without using the driver's memory, which solves the problem that the traditional method of painting signs and markings mainly uses the driver's memory and there is a risk of forgetting. In addition, the vehicle does not need to be modified, which solves the problem that the Bluetooth positioning method needs to install a transmitting antenna that can amplify the signal on the top of the vehicle, which is not friendly to drivers entering the parking lot for the first time. In addition, the present application obtains the scanning position of the QR code and the route map from the scanning position of the QR code to each parking space in advance, and then directly issues the route map based on the corresponding relationship, without GPS data interaction, avoiding the problem of poor signal quality and long waiting time for GPS data transmission set up in the parking lot. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Some embodiments of the present disclosure are described below with reference to the accompanying drawings, in which: Figure 1 This is a flow chart of a reverse vehicle search method based on image recognition provided in an embodiment of the present application.

[0018] Figure 2 It is a schematic diagram of the internal structure of a reverse vehicle search system based on image recognition provided in an embodiment of the present application.

[0019] Figure 3 It is a schematic diagram of the internal structure of a reverse vehicle search device based on image recognition provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] It should be understood by those skilled in the art that the embodiments described below are only preferred embodiments of the present disclosure, and do not mean that the present disclosure can only be implemented through the preferred embodiments. The preferred embodiments are only used to explain the technical principles of the present disclosure, and are not used to limit the protection scope of the present disclosure. Based on the preferred embodiments provided by the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work should still fall within the protection scope of the present disclosure.

[0021] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0022] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0023] The present application embodiment provides a reverse vehicle search method based on image recognition, such as Figure 1 As shown, the method provided in the embodiment of the present application mainly includes the following steps: Step 110: Obtain the scanning position of the QR code and the route map from the scanning position of the QR code to each parking space.

[0024] It should be noted that the scanning position of the QR code at least includes: preset intersections and personnel entrances and exits in the parking lot. In addition, those skilled in the art can determine the scanning position of the QR code according to actual needs, and at the same time, the scanning position of the QR code needs to be uploaded to the route map of each parking space.

[0025] The solution for uploading the scanning position of the QR code to the route map of each parking space in this step can be: obtaining the route map of the scanning position of the QR code to each parking space through a preset image acquisition interface.

[0026] Step 120: Detect the license plate information and driver's face information entering the parking lot through the camera at the entrance and match them.

[0027] Step 130: Identify the parking space of the vehicle through the camera in the parking lot, and store the corresponding relationship between the license plate information, the driver's face information and the parking space of the vehicle.

[0028] In addition, before the parking space of the vehicle is identified by a camera in the parking lot, the method further includes: The parking lot is divided into preset monitoring sub-areas, and a camera is installed in each preset monitoring sub-area; based on the positional relationship between the preset monitoring sub-areas, the preset adjacent cameras of each camera are determined.

[0029] For example, cameras corresponding to several adjacent areas are preset neighboring cameras.

[0030] Among them, the parking space of the vehicle is identified by the camera in the parking lot, which can be specifically: Vehicles entering the parking lot are tracked through license plate information. After the vehicle enters, the preset adjacent camera of the last camera that recognized the license plate information is identified. If the license plate information appears in the preset adjacent camera within the preset waiting time, the previous step is repeated. If the license plate information does not appear in the preset adjacent camera within the preset waiting time, it is determined that the driver has completed parking, and the vehicle image last taken by the camera is identified; the vehicle parking space in the vehicle image is identified.

[0031] Step 140, enter the information query interface through the QR code, and then input facial information or license plate information to determine the parking space for the vehicle; then based on the route map from the scanning position of the QR code to each parking space, determine and display the route map from the current scanning position of the QR code to the parking space for the vehicle.

[0032] Among them, enter the information query interface through the QR code, and then enter the face information or license plate information to determine the parking space of the vehicle, which can be specifically: Enter the information query interface through the QR code; when the face recognition module of the information query interface is triggered, obtain the face information through the face information acquisition interface or obtain the license plate information through the license plate information input interface; through the correspondence between the license plate information, the driver's face information and the vehicle parking space, determine the face information or the license plate information to determine the vehicle parking space.

[0033] besides, Figure 2 The present application provides a reverse vehicle search system based on image recognition. Figure 2 As shown, the system provided in the embodiment of the present application mainly includes: The acquisition module 210 is used to acquire the scanning position of the QR code and the route map from the scanning position of the QR code to each parking space.

[0034] The acquisition module 210 includes an acquisition unit, which is used to acquire a route map from the scanning position of the QR code to each parking space through a preset picture acquisition interface.

[0035] The matching module 220 is used to detect the license plate information and driver's face information entering the parking lot through the camera at the entrance and perform matching.

[0036] The storage module 230 is used to identify the parking space of the vehicle through the camera in the parking lot, and store the corresponding relationship between the license plate information, the driver's face information and the parking space of the vehicle.

[0037] The line module 240 is used to enter the information query interface through the QR code, and then input facial information or license plate information to determine the parking space for the vehicle; then based on the route map from the scanning position of the QR code to each parking space, determine and display the route map from the current QR code scanning position to the vehicle parking space.

[0038] The line module 240 includes a determination unit, Used to enter the information query interface through the QR code; when the face recognition module of the information query interface is triggered, the face information is obtained through the face information acquisition interface or the license plate information is obtained through the license plate information input interface; through the correspondence between the license plate information, the driver's face information and the vehicle parking space, the face information or the license plate information is determined to determine the vehicle parking space.

[0039] The above is a method embodiment of the present application. Based on the same inventive concept, the present application embodiment also provides a reverse vehicle search device based on image recognition. Figure 3 As shown, the device includes: a processor; and a memory on which executable codes are stored. When the executable codes are executed, the processor executes a reverse vehicle search method based on image recognition as in the above-mentioned embodiment.

[0040] Specifically, the server obtains the scanning position of the QR code and the route map from the scanning position of the QR code to each parking space; detects the license plate information and driver's facial information entering the parking lot through the camera at the entrance, and matches them; identifies the parking space of the vehicle through the camera in the parking lot, and stores the correspondence between the license plate information, the driver's facial information and the vehicle parking space; enters the information query interface through the QR code, and then inputs the facial information or license plate information to determine the vehicle parking space; and then based on the route map from the scanning position of the QR code to each parking space, determines and displays the route map from the current scanning position of the QR code to the vehicle parking space.

[0041] In addition, an embodiment of the present application further provides a non-volatile computer storage medium on which executable instructions are stored. When the executable instructions are executed, a reverse vehicle search method based on image recognition as described above is implemented.

[0042] So far, the technical solutions of the present disclosure have been described in combination with the above multiple embodiments, but it is easy for those skilled in the art to understand that the protection scope of the present disclosure is not limited to these specific embodiments. Without departing from the technical principles of the present disclosure, those skilled in the art can split and combine the technical solutions in the above-mentioned various embodiments, and can also make equivalent changes or replacements to the relevant technical features. Any changes, equivalent replacements, improvements, etc. made within the technical concept and / or technical principle of the present disclosure will fall within the protection scope of the present disclosure.

Claims

1. A reverse vehicle search method based on image recognition, characterized in that: The method comprises: Get the scanning location of the QR code and the route map from the scanning location of the QR code to each parking space; The camera at the entrance detects the license plate information and driver's face information of the vehicle entering the parking lot and performs a match; The parking spaces of vehicles are identified through the cameras in the parking lot, and the corresponding relationship between the license plate information, the driver's face information and the parking spaces of vehicles is stored; Enter the information query interface through the QR code, and then enter the facial information or license plate information to determine the vehicle parking space; then based on the route map from the scanning position of the QR code to each parking space, determine and display the route map from the current QR code scanning position to the vehicle parking space.

2. The reverse vehicle search method based on image recognition according to claim 1 is characterized in that: The scanning locations of the QR code include at least: preset intersections and entrances and exits in the parking lot.

3. The reverse vehicle search method based on image recognition according to claim 1 is characterized in that: Get the scanning location of the QR code and the route map from the scanning location of the QR code to each parking space, including: Get the route map from the scanning location of the QR code to each parking space through the preset picture acquisition interface.

4. The reverse vehicle search method based on image recognition according to claim 1, characterized in that: Before identifying the parking space of the vehicle by a camera in the parking lot, the method further includes: Arrange the parking lot according to the preset monitoring sub-areas, install a camera in each preset monitoring sub-area; determine the preset neighboring cameras of each camera based on the positional relationship between the preset monitoring sub-areas; The parking spaces of vehicles are identified by cameras in the parking lot, including: Vehicles entering the parking lot are tracked through license plate information. After the vehicle enters, the preset adjacent camera of the last camera that recognized the license plate information is identified. If the license plate information appears in the preset adjacent camera within the preset waiting time, the previous step is repeated. If the license plate information does not appear in the preset adjacent camera within the preset waiting time, it is determined that the driver has completed parking, and the vehicle image last taken by the camera is identified; the vehicle parking space in the vehicle image is identified.

5. The reverse vehicle search method based on image recognition according to claim 1, characterized in that: Enter the information query interface through the QR code, and then enter the face information or license plate information to determine the parking space for the vehicle, including: Enter the information query interface through the QR code; When the face recognition module of the information query interface is triggered, the face information is obtained through the face information acquisition interface or the license plate information is obtained through the license plate information input interface; Through the correspondence between the license plate information, the driver's facial information and the vehicle parking space, the facial information or the license plate information is determined to determine the vehicle parking space.

6. A reverse vehicle search system based on image recognition, characterized in that: The system comprises: An acquisition module is used to acquire the scanning position of the QR code and a route map from the scanning position of the QR code to each parking space; The matching module is used to detect the license plate information and driver's face information of the vehicle entering the parking lot through the camera at the entrance and perform matching; A storage module, used to identify the parking space of the vehicle through the camera in the parking lot, and store the corresponding relationship between the license plate information, the driver's face information and the parking space of the vehicle; The route module is used to enter the information query interface through the QR code, and then input facial information or license plate information to determine the parking space for the vehicle; then based on the route map from the scanning position of the QR code to each parking space, determine and display the route map from the current scanning position of the QR code to the parking space for the vehicle.

7. The reverse vehicle search system based on image recognition according to claim 6 is characterized in that: The acquisition module includes an acquisition unit, Used to obtain the route map from the scanning location of the QR code to each parking space through the preset image acquisition interface.

8. The reverse vehicle search system based on image recognition according to claim 6, characterized in that: The line module includes a determination unit, Used to enter the information query interface through the QR code; When the face recognition module of the information query interface is triggered, the face information is obtained through the face information acquisition interface or the license plate information is obtained through the license plate information input interface; Through the correspondence between the license plate information, the driver's facial information and the vehicle parking space, the facial information or the license plate information is determined to determine the vehicle parking space.

9. A reverse vehicle search device based on image recognition, characterized in that: The device comprises: processor; and a memory having executable codes stored thereon, which, when executed, causes the processor to execute a reverse vehicle search method based on image recognition as described in any one of claims 1 to 5.

10. A non-volatile computer storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the reverse vehicle search method based on image recognition as described in any one of claims 1-5 is implemented.

Images