CN110556022A - Parking lot parking space indication method and device based on artificial intelligence and electronic equipment - Google Patents

Abstract

Embodiments of the present invention provide an artificial intelligence-based method, device, and electronic device for indicating a parking space in a parking lot. The method includes: acquiring parking image information of a vehicle, the parking image information including a parking space identification image; Image recognition is performed on the information to identify the corresponding parking space logo; according to the parking space logo, the instruction information of the corresponding parking lot is formed; when the user's car pickup request is received, the instruction information is displayed to instruct the user. When the user needs to pick up the car, the user can give instructions according to the instruction information, the user can clearly know the parking location, the user does not need to remember the parking location when parking, and does not need to search according to the memory when picking up the car, saving the need for searching. A large number of comparisons confirm that the parking user's search time in a large parking lot is effectively reduced, thereby increasing the user's pick-up speed.

Description

Parking space indication method, device and electronic equipment based on artificial intelligence

technical field

The present invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based parking space indication method, device and electronic equipment.

Background technique

With the development of the economy, more and more families are equipped with one or more cars for the convenience of travel, so that the number of vehicles increases, which puts forward higher requirements for the infrastructure of vehicles, such as wider roads to meet the needs of cars. The traffic, the parking lot is required to be larger to meet the parking of cars, etc.

Nowadays, the capacity of parking spaces in various parking lots is increasing, and the layout of parking spaces in parking lots is becoming more and more complex. A parking lot may have multiple vehicle entrances and exits, multiple vehicle parking areas, and multiple supply places corresponding to each vehicle parking area. Parking users enter and exit the pedestrian passage of the parking lot, etc., the parking user needs to remember the location of the parking when parking, and when picking up the car, find the location of the vehicle in the complex parking lot according to the memory.

However, in the process of finding a vehicle parking location in a large parking lot, it will take more time to compare and confirm the environment, and when parking users enter and exit the parking lot through different pedestrian passages, it will take more time to confirm where they are. position. Therefore, in a large parking lot, the user needs to spend more time looking for the parking position of the vehicle when picking up the car.

Contents of the invention

An embodiment of the present invention provides an artificial intelligence-based method for indicating a parking space in a parking lot. By performing image recognition on the parking position, the characteristic mark of the parking position can be extracted to instruct the parking user, which effectively reduces the need for parking users in large parking lots. The search time in the car, thereby improving the speed of the user's car pickup.

In a first aspect, an embodiment of the present invention provides an artificial intelligence-based method for indicating a parking space in a parking lot, including:

Acquire the parking image information of the vehicle, the parking image information includes a parking space identification image; image recognition is performed on the parking image information by an image recognition engine to identify the corresponding parking space identification; form the corresponding parking lot indication information according to the parking space identification; receive When the user requests to pick up the car, the indication information is displayed to instruct the user.

In a second aspect, an embodiment of the present invention provides an artificial intelligence-based parking space indicating device, comprising: a first acquisition module, configured to acquire parking image information of a vehicle, the parking image information including a parking space identification image; Image recognition is performed on the parking image information by an image recognition engine to identify the corresponding parking space logo; the processing module is used to form the instruction information of the corresponding parking lot according to the parking space logo; the instruction module is used to receive the user's car pick-up When requested, display the instruction to instruct the user.

In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the computer program, the implementation of the present invention is realized. The steps in the parking space indication method based on artificial intelligence provided by the example.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the artificial intelligence-based parking lot provided by the embodiment of the present invention is realized. The steps in the parking space indication method.

In the embodiment of the present invention, the parking image information of the vehicle is acquired, and the parking image information includes a parking space identification image; image recognition is performed on the parking image information by an image recognition engine to identify the corresponding parking space identification; and a corresponding parking space is formed according to the parking space identification. The indication information of the field; when receiving the user's car pick-up request, the indication information is displayed to instruct the user. Because the parking image information is recognized, the parking space logo in the parking image information is obtained to generate instruction information. When the user needs to pick up the car, the user can give instructions according to the instruction information, and the user can clearly know the parking position. The parking position is memorized, and there is no need to search according to the memory when picking up the car, which saves a lot of comparison and confirmation in the search process, effectively reducing the search time of parking users in large parking lots, thereby increasing the speed of car picking for users.

Description of drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

1 is a schematic diagram of a system architecture based on an artificial intelligence-based parking space indication method application provided by an embodiment of the present invention;

Fig. 2 is a schematic flow chart of an artificial intelligence-based method for indicating a parking space in a parking lot provided by an embodiment of the present invention;

3 is a schematic flowchart of another artificial intelligence-based parking space indication method provided by an embodiment of the present invention;

4 is a schematic flowchart of another artificial intelligence-based parking space indication method provided by an embodiment of the present invention;

5 is a schematic flowchart of another artificial intelligence-based parking space indication method provided by an embodiment of the present invention;

Fig. 6 is a schematic structural diagram of an artificial intelligence-based parking space indicating device provided by an embodiment of the present invention;

Fig. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

In order to further clearly describe the inventive intent of the present invention, please refer to FIG. 1. FIG. 1 is a schematic diagram of an optional system architecture provided by an embodiment of the present invention. As shown in FIG. 1, the optional system architecture 100 includes a user terminal Devices 101, 102, 103, network 104, server 105 and vehicle terminal device 106. The network 104 is used to provide the medium of the communication link between the user terminal equipment 101, 102, 103 and the server 105, and the network 104 is also used to provide a communication link between the user terminal equipment 101, 102, 103 and the vehicle terminal equipment 106 The medium of the road. Network 104 may include various connection types, such as wires, wireless communication links, or fiber optic cables, among others.

The user can use the user terminal equipment 101, 102, 103 to interact with the server 105 through the network 104 to receive or send communication data information, etc. The image information collected by the vehicle-mounted terminal device 106 is acquired. Various client applications can be installed on the user terminal devices 101 , 102 , 103 , such as parking location indicating software and the like.

The user terminal equipment 101, 102, 103 can be various electronic devices that have a prompt function and support functions such as voice prompts and screen displays, including but not limited to smart phones, tablet computers, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III, moving picture experts compress standard audio layer 3), MP4 (Moving Picture Experts Group Audio Layer IV, moving picture experts compress standard audio layer 4) player, laptop portable computer and so on. In some possible embodiments, the above-mentioned user terminal devices 101, 102, 103 may also have an image collection function, such as a built-in camera.

The server 105 may be a server that provides various services, for example, a background server that provides support for parking position indication on the terminal devices 101 , 102 , 103 . It should be noted that the above-mentioned server 105 is optional. In some possible embodiments, the support provided by the parking position indication may also be a local application on the user terminal equipment 101, 102, 103, and the local application may carry an image The recognition engine recognizes the image information.

The vehicle-mounted terminal device 106 may be a device that provides an image acquisition function, for example, an image acquisition device such as a driving recorder, a vehicle-mounted camera, or a custom-installed camera. It should be noted that the above-mentioned vehicle-mounted terminal device 106 is optional. In some possible embodiments, the device that provides the image acquisition function may also be the user terminal device 101, 102, 103. For example, after the user parks, the user The terminal devices 101, 102, and 103 only need to take pictures of the parking positions.

It should be noted that the artificial intelligence-based parking space indication method provided in the embodiment of the present application is generally executed by a server/terminal device, and accordingly, the artificial intelligence-based parking space indication device is generally set in the server/terminal device.

It should be understood that the numbers of user terminal equipment, network, server, and vehicle terminal equipment in FIG. 1 are only illustrative. According to implementation requirements, there may be any number of user terminal devices, networks, servers, and vehicle-mounted terminal devices.

Please refer to FIG. 2. FIG. 2 is a schematic flowchart of an artificial intelligence-based parking space indication method provided by an embodiment of the present invention. The main body executing the method is the user terminal equipment 101, 102, and 103 in FIG. 1. In the embodiment of the invention, the user terminal equipment 101, 102, 103 has a built-in camera to take pictures of the parking position, and also has a built-in image recognition engine to recognize the parking image information, as shown in Figure 2, including the following steps:

201. Acquire parking image information of the vehicle.

Wherein, the above-mentioned parking image information can be taken by the user terminal devices 101, 102, 103 in FIG. The medium flash will shoot the parking position to obtain an image with the parking space mark. The user terminal devices 101, 102, 103 may take pictures of the parking position when the user is parking, either automatically or actively by the user. The above-mentioned automatic shooting may be that the user terminal devices 101, 102, 103 are connected to the vehicle central control system, and when the parking state of the vehicle is acquired, the user terminal devices 101, 102, 103 automatically take pictures of the parking position. The above-mentioned active shooting may be that the user holds the user terminal device 101 , 102 , 103 to take a picture of the parking location. In some possible embodiments, when the user terminal device 101, 102, 103 detects that the user leaves the vehicle, the user is prompted to take a picture of the current parking position. The above parking image information may be static image information or dynamic video stream information.

202. Preprocessing the parking image information.

The above preprocessing includes one or more of image correction, image enhancement, image illumination compensation, image cutting and other processing. It should be noted that step 202 is optional, and in some possible implementations, it is not necessary to preprocess the parking image information.

203. Perform image recognition on the parking image information through an image recognition engine.

Wherein, the above-mentioned image recognition engine is an image recognition engine provided in the user terminal equipment 101, 102, 103, through which the image recognition engine can perform image recognition on the parking image information. And because the image recognition engine is set in the user terminal equipment 101, 102, 103, the image can be recognized without uploading to the server, and the recognition speed is slowed down due to poor communication signals in the parking lot. question.

204. Judging whether there is a parking space mark.

After the image recognition, if there is a parking space mark, then step 204 is executed; if there is no parking space mark, the parking image information of the vehicle is reacquired, and a prompt is given to the user that the parking space mark is not recognized.

205. Form the instruction information corresponding to the parking lot according to the parking space mark.

Optionally, the above-mentioned parking space identification may be a parking space number, and the above-mentioned indication information may be a corresponding field type of parking space number. Specifically, after the parking image is recognized and the parking space mark in the parking image is recognized, the parking space mark in the image is converted into field-type indication information. The above-mentioned indication information may also be an image-type indication information, that is, it may be a photograph of the parking position captured. It should be noted that the photograph of the parking position captured includes a parking space mark, and the above-mentioned parking position may be It is a photo after image segmentation. The above instruction information may also be a route instruction, the end point of the route instruction is the parking location, and the starting point is the current location of the user. The above instruction information can also be a map instruction to obtain a parking space map of the parking lot. The parking space map uses the information on the distribution of the parking spaces in the parking lot, and marks the position corresponding to the parking space mark on the parking space map, so that the parking space corresponding to the user's parking position Different from other parking spaces.

206. When the user's request for picking up the car is received, display indication information to instruct the user.

When the user needs to pick up the car, the user opens the user terminal device 101 , 102 , 103 to make a request, for example, clicks a car pick-up button, and a car pick-up request will be generated. The user terminal devices 101 , 102 , 103 display the indication information, and the user can easily find the parking location according to the indication information displayed by the user terminal devices 101 , 102 , 103 .

Optionally, when the indication information is the parking space number of the field type, the parking space number of the field type can be displayed through the screen of the user terminal device 101, 102, 103, or through the voice function of the user terminal device 101, 102, 103 Carry out voice display so that the user can know the number of the parking space, and find the corresponding parking position according to the number of the parking space. It can prevent the user from forgetting the parking space number when parking, thereby improving the speed of the user's car pickup.

Optionally, when the indication information is a parking image, that is, a photo of the parking position, the photo of the parking position taken during parking will be displayed on the screen of the user terminal device 101, 102, 103, and the user can Find the corresponding parking location in the photo.

Optionally, when the instruction information is a route instruction, when the user needs to pick up the car, first obtain the current location of the user, which can be obtained through the GPS (Global Positioning System, English: GlobalPositioning System, English: GlobalPositioning System, GPS for short) to perform positioning, so as to obtain the current location of the user. In some possible embodiments, when the user enters the parking lot, he will enter through the pedestrian passage, and the entrance of the pedestrian passage will usually be provided with a passage mark, so that people can choose the corresponding pedestrian passage to enter and exit. The user can use the user terminal device 101 , 102, 103 scan or take pictures of the signs in the pedestrian passage, and recognize the position of the pedestrian passage in the parking lot through the image recognition engine, thereby obtaining the current location of the user. The user's current location is added to the route indication as the starting point of the route indication, and the user is instructed to reach the end point of the route indication, which is the user's parking position. The screens of the user terminal devices 101, 102, 103 display the route instructions with the user's current location as the starting point, so that the user can quickly pick up the car according to the route instructions.

In addition, in some possible implementations, after the parking space sign is recognized, a route indication from the position corresponding to the parking space sign to each pedestrian passageway will be generated in advance. The route indication starts from each pedestrian passageway, and the user's parking position as the end point. In this way, after the user scans or takes pictures of the signs in the pedestrian passage through the user terminal equipment 101, 102, 103, and recognizes the position of the pedestrian passage in the parking lot through the image recognition engine, according to the position of the pedestrian passage in the parking lot, directly It is enough to match the corresponding route instructions, and there is no need to add the current location to the route instructions.

Optionally, when the instruction information is a map instruction, when the user needs to pick up the car, first obtain the current location of the user, which can be obtained through the GPS (Global Positioning System, English: GlobalPositioning System, English: GlobalPositioning System, GPS for short) to perform positioning, so as to obtain the current location of the user. In some possible embodiments, when the user enters the parking lot, he will enter through the pedestrian passage, and the entrance of the pedestrian passage will usually be provided with a passage mark, so that people can choose the corresponding pedestrian passage to enter and exit. The user can use the user terminal device 101 , 102, 103 scan or take pictures of the signs in the pedestrian passage, and recognize the position of the pedestrian passage in the parking lot through the image recognition engine, thereby obtaining the current location of the user. Add the user's current location to the map, and display it differently to distinguish the user's location from the parking location. The user terminal equipment 101, 102, 103 displays a map indication with the user's current location as a starting point, so that the user can quickly pick up the car according to the map indication.

In the embodiment of the present invention, the parking image information of the vehicle is acquired, and the parking image information includes a parking space identification image; image recognition is performed on the parking image information by an image recognition engine to identify the corresponding parking space identification; and a corresponding parking space identification is formed according to the parking space identification. The instruction information of the parking lot; when receiving the user's car pick-up request, the instruction information is displayed to instruct the user. Because the parking image information is recognized, the parking space logo in the parking image information is obtained to generate instruction information. When the user needs to pick up the car, the user can give instructions according to the instruction information, and the user can clearly know the parking position. The parking position is memorized, and there is no need to search according to the memory when picking up the car, which saves a lot of comparison and confirmation in the search process, effectively reducing the search time of parking users in large parking lots, thereby increasing the speed of car picking for users.

Please refer to FIG. 3. FIG. 3 is a schematic flowchart of another artificial intelligence-based parking space indication method provided by an embodiment of the present invention. Compared with the embodiment in FIG. 2, in the embodiment of the present invention, the vehicle-mounted terminal device 106 in FIG. 1 is added to photograph the parking position, and the image recognition engine is built in the user terminal devices 101, 102, and 103 to recognize the parking image information, such as As shown in Figure 3, it includes the following steps:

301. The vehicle-mounted terminal device 106 detects a parking lot sign.

Wherein, the image detection engine can be set in the above-mentioned vehicle-mounted terminal device 106, and the above-mentioned parking lot sign can be the house number plate of the parking lot, the brake railing, etc. When using image features, it is judged that the vehicle is about to enter the parking lot.

In addition, an RFID radio frequency receiver can also be set in the above-mentioned vehicle-mounted terminal device 106, and a corresponding RFID radio-frequency transmitter (ie, an electronic tag) is also provided at the gate of the parking lot. When the radio frequency signal of the RFID radio frequency transmitter at the door is detected, it is judged that the vehicle is about to enter the parking lot.

302. The vehicle-mounted terminal device 106 shoots a video stream of the vehicle driving into the parking lot and parking.

The aforementioned video stream refers to the video stream from when the vehicle enters the parking lot to when the vehicle is parked in the parking space. Specifically, the way to determine the parking can be: the vehicle-mounted terminal disconnects the NFC connection, judges that the vehicle stops moving, detects the vehicle's flameout time, etc., if the method of detecting the vehicle's flameout time is used, then it needs to detect that the vehicle's flameout time exceeds the preset flameout time. , it can be judged that the vehicle is stopped.

303. The vehicle-mounted terminal device 106 sends the video stream to the user terminal devices 101, 102, and 103.

The above video streams can be sent to the user terminal devices 101, 102, 103 through the network 104 in FIG. 1 .

In some possible embodiments, the video stream may be sent to the user terminal devices 101, 102, 103 immediately after stopping shooting the video stream, or may be sent to the user terminal devices 101, 102, 103 in real time during the shooting process. .

304. The user terminal devices 101, 102, and 103 decode the video stream to obtain a first image frame.

It should be noted that the above-mentioned first image frame refers to image frames in all video streams, rather than a specific image frame.

305. The user terminal devices 101, 102, and 103 select the first image frame whose time stamp is at the last preset digit, and obtain the second image frame.

Wherein, the above-mentioned time stamp is used to indicate the time when the image frame is acquired, and the image frame with the reciprocal time stamp is the later image frame in the video stream, which can also be considered as the image frame when parking. It should be noted that, the above-mentioned second image frame may be one or more image frames in the video stream, and does not specifically refer to a certain image frame.

306. The user terminal devices 101, 102, and 103 detect whether the second image frame includes a parking space identification image.

The user terminal equipment 101, 102, 103 is provided with an image detection engine for detecting the parking space mark. If the parking space mark is detected, step 307 is executed. If the parking space mark is not detected, the second image frame is retaken for detection. Specifically, the second image frame is selected forward on the basis of the preset data bits of the inverted data.

307. The user terminal devices 101, 102, and 103 extract the corresponding second image frame to obtain a parking image.

The above parking images are used for image recognition.

Optionally, before parking image recognition, parking image preprocessing can be performed; image preprocessing includes image correction, image enhancement, image illumination compensation, etc. Parking image of the area. In addition, in combination with the above preprocessing, before the parking image recognition, the image quality can also be evaluated, and the image frame with higher image quality can be selected as the parking image.

308. The user terminal devices 101, 102, and 103 perform image recognition on the parking image.

The above-mentioned image recognition is mainly to identify the image area where the parking space sign is located, and recognize the semantics corresponding to the parking space sign, such as a number or a letter number.

309. The user terminal devices 101, 102, and 103 form indication information corresponding to the parking lot according to the parking space identification.

310. The user sends a car pickup request to the user terminal device 101, 102, 103.

The user can send a car pickup request to the user terminal device 101, 102, 103 by touching or clicking the car pickup button on the screen of the user terminal device 101, 102, 103, or send a car pickup request to the user terminal device 101, 102, 103 by voice. ask.

In some possible embodiments, when the user scans the sign of the pedestrian passage in the parking lot, the default is to send a request for picking up the car to the user terminal device 101 , 102 , 103 .

311. The user terminal devices 101, 102, and 103 display indication information to instruct the user.

In the embodiment of the present invention, the video stream is collected by the vehicle-mounted terminal equipment and sent to the user terminal equipment for identification processing, which can prevent the parking image from being unable to be collected when the user terminal is occupied (connecting to a phone, making a call, etc.). Because the parking image information is recognized, the parking space logo in the parking image information is obtained to generate instruction information. When the user needs to pick up the car, the user can give instructions according to the instruction information, and the user can clearly know the parking position. The parking position is memorized, and there is no need to search according to the memory when picking up the car, which saves a lot of comparison and confirmation in the search process, effectively reducing the search time of parking users in large parking lots, thereby increasing the speed of car picking for users.

Please refer to FIG. 4. FIG. 4 is a schematic flowchart of another artificial intelligence-based parking space indication method provided by an embodiment of the present invention. Compared with the embodiment in FIG. 2, in the embodiment of the present invention, the vehicle-mounted terminal device 106 in FIG. 1 is added to photograph the parking position, and the image recognition engine is built in the user terminal devices 101, 102, and 103 to recognize the parking image information, such as As shown in Figure 4, it includes the following steps:

401. The vehicle-mounted terminal device 106 captures a parking image during parking.

The way to determine the parking can be: the vehicle terminal disconnects the NFC connection, judges that the vehicle stops moving, detects the vehicle’s flameout time, etc. If the method of detecting the vehicle’s flameout time is used, then it needs to detect that the vehicle’s flameout time exceeds the preset flameout time. Determine vehicle parking. After it is judged that the car is parked, the vehicle-mounted terminal device 106 takes a picture of the car parked.

402. The vehicle-mounted terminal device 106 sends the parking image to the user terminal devices 101, 102, and 103.

The above-mentioned parking image can be sent to the user terminal devices 101, 102, 103 through the network 104 in FIG. 1 .

Optionally, before parking image recognition, parking image preprocessing can be performed; image preprocessing includes image correction, image enhancement, image illumination compensation, etc. Parking image of the area. If the parking image with the parking space identification area is not cut, the parking image will be acquired again, and a corresponding prompt will be given to the user.

Further, image correction is to correct the parking image according to the shaking parameters when the vehicle is parked; image enhancement is to enhance the area where the parking space sign in the parking image information is located; image illumination compensation is to illuminate the parking image according to the light conditions of the parking lot compensate.

When correcting the image, the shake parameter record when the vehicle is parked can be obtained, so that the obtained corresponding parking image can be corrected according to the shake parameter record, and the shake blur of the image can be reduced.

Image enhancement can directly enhance the image regardless of the reasons for image quality degradation. The image enhancement model can be pre-trained so that the image enhancement model can enhance the target area of interest, such as increasing the image quality of the area where the parking sign is located.

Image illumination compensation is to obtain the light conditions of the parking lot through the light sensor, and perform illumination compensation on the image according to the acquired light conditions. In some possible embodiments, it is also possible to perform illumination compensation when the vehicle-mounted terminal device 106 photographs parking, so as to obtain a parking image that does not require image illumination compensation.

403. The user terminal devices 101, 102, and 103 perform image recognition on the parking image.

The above-mentioned image recognition is mainly to identify the image area where the parking space sign is located, and recognize the semantics corresponding to the parking space sign, such as a number or a letter number.

404. The user terminal devices 101, 102, and 103 form indication information corresponding to the parking lot according to the parking space identification.

405. The user sends a car pickup request to the user terminal device 101, 102, 103.

The user can send a car pickup request to the user terminal device 101, 102, 103 by touching or clicking the car pickup button on the screen of the user terminal device 101, 102, 103, or can send a car pickup request to the user terminal device 101, 102, 103 by voice. ask.

In some possible embodiments, when the user scans the sign of the pedestrian passage in the parking lot, the default is to send a request for picking up the car to the user terminal device 101 , 102 , 103 .

406. The user terminal devices 101, 102, and 103 display indication information to instruct the user.

In the embodiment of the present invention, the parking image is collected by the vehicle-mounted terminal equipment and sent to the user terminal equipment for identification processing, which can prevent the parking image from being unable to be collected when the user terminal is occupied (connecting to a phone, making a call, etc.). In the embodiment of FIG. 3, data transmission is reduced. Because the parking image is recognized, the parking space mark in the parking image is obtained to generate instruction information. When the user needs to pick up the car, the user can give instructions according to the instruction information, and the user can clearly know the parking location, and the user does not need to check the parking location when parking. Carrying out memory does not need to search according to the memory when picking up the car, which saves a lot of comparison and confirmation in the search process, effectively reducing the search time of parking users in large parking lots, thereby increasing the speed of car picking for users.

Please refer to FIG. 5. FIG. 5 is a schematic flowchart of another artificial intelligence-based parking space indication method provided by an embodiment of the present invention. The main body executing the method is the server 105 in FIG. 1. Compared with the embodiment in FIG. 2 , in the embodiment of the present invention, the vehicle-mounted terminal device 106 in Fig. 1 is added to photograph the parking position, and an image recognition engine is built in the server 105 to recognize the parking image information, as shown in Fig. 5 , including the following steps:

501. The vehicle-mounted terminal device 106 detects a parking lot sign.

The above-mentioned parking lot identification may be the location, name and other identifications of the parking lot.

502. The vehicle-mounted terminal device 106 shoots a video stream of the vehicle driving into the parking lot and parking.

503. The vehicle-mounted terminal device 106 sends the video stream to the user terminal devices 101, 102, and 103.

504. The user terminal devices 101, 102, and 103 send the video stream to the server 105.

The aforementioned video stream can be sent to the server 105 through the network 104 in FIG. 1 .

In some possible embodiments, it may be sent to the user terminal equipment 101, 102, 103 immediately after stopping shooting the video stream, and then sent to the server 105 by the user terminal equipment 101, 102, 103, or it may be During the process, it is sent to the user terminal equipment 101, 102, 103 in real time, and the user terminal equipment 101, 102, 103 sends it to the server 105 in real time.

It should be noted that the above-mentioned steps 503 and 504 are optional, and in some possible embodiments, the video stream can be directly sent by the vehicle-mounted terminal device 106 to the server 105 without going through the client devices 101 and 102 , 103.

In some possible embodiments, the network 104 in step 503 can be different from the network 104 in step 504, for example, the network 104 in step 503 can be a bluetooth network, a vehicle-mounted WIFI wireless fidelity network, and the network 104 in step 504 Network 104 may be a mobile data network, a hotspot network, or the like. In this way, when the network condition is poor, the client device can first receive the video stream for storage, and then upload the video stream to the server when the network condition is good. It can avoid that the network signal of the underground parking lot is not good, and the user terminal equipment cannot upload the video stream to the server.

505. The server 105 decodes the video stream to obtain the first image frame.

506. The server 105 selects the first image frame corresponding to the last preset digit of the time stamp to obtain the second image frame.

507. The server 105 detects whether the second image frame includes a parking space identification image.

508. The server 105 extracts the corresponding second image frame to obtain the parking image.

509. The server 105 performs image recognition on the parking image.

510. The server 105 forms instruction information corresponding to the parking lot according to the parking space identification.

The above indication information includes at least one of parking space number, parking image, route indication and map indication.

In a possible implementation manner, the parking lot is provided with passage signs at designated positions of the pedestrian passage, for example, signs such as Exit A and Entrance A are set at the exit or entrance.

Correspondingly, before forming the instruction information corresponding to the parking lot, the server 105 obtains the information of the parking lot and forms a designated area for the exit or entrance of the pedestrian passage, for example, according to the identification information such as the name and address of the parking lot, the corresponding pedestrian passage information is obtained. Exit location or entrance location, and form the activation condition, when the user arrives at these exit locations or entrance locations, activate the prompt to the user, so that the user can confirm whether to park or pick up the car, when the user confirms to pick up the car, a pick-up request can be sent .

511. The user sends a car pick-up request to the user terminal device 101, 102, 103 in the designated area.

The above-mentioned specified area can be the pedestrian passage entrance of the parking lot. When the user comes to the pedestrian passage entrance of the parking lot, the user terminal equipment 101, 102, 103 will automatically send a car pickup request to the server 105. The car pickup request includes the current The designated area where it is located, for example, if the designated area is Entrance B of A parking lot, the corresponding pick-up request of the user at the B entrance of A parking lot will be sent.

512. The user terminal devices 101, 102, and 103 request the server 105 for indication information.

The above request indication information includes the current location of the user. The aforementioned current location of the user may be the current specified area, for example, the specified area is Entrance B of A parking lot.

513. The server 105 sends indication information to the user terminal devices 101, 102, and 103.

Specifically, after obtaining the request, the server will first authenticate the user terminal devices 101, 102, 103, and if the authentication succeeds, it will send instruction information to the user terminal devices 101, 102, 103.

514. The user terminal devices 101, 102, and 103 display indication information to instruct the user.

The above instruction information is instruction information from the designated area where the user is located to the parking space, and may be any one of route instructions and map instructions from the designated area to the parking space.

In a possible embodiment, when the exit and entrance of different directions or areas of the parking lot are the same, the server 105 obtains the information of the parking lot in advance and records the exit location. Whether it is in the designated area, if not, then instruct the user to go to the corresponding exit location, and then instruct the user to go to the corresponding parking space. If yes, then determine corresponding indication information according to the designated area where the user is located.

In addition, in a possible embodiment, when the first user parks the car and the second user borrows the first user's car to drive, the first user may forward the requested instruction information to the second user's user terminal device to instruct the second user to pick up the car.

In the embodiment of the present invention, the video stream is collected by the vehicle-mounted terminal equipment, sent to the user terminal equipment, and then forwarded to the server for identification processing, which can reduce the occupancy rate of computing resources and storage resources of the user terminal equipment. Because the parking image information is recognized, the parking space logo in the parking image information is obtained to generate instruction information. When the user needs to pick up the car, the user can give instructions according to the instruction information, and the user can clearly know the parking position. The parking position is memorized, and there is no need to search according to the memory when picking up the car, which saves a lot of comparison and confirmation in the search process, effectively reducing the search time of parking users in large parking lots, thereby increasing the speed of car picking for users.

Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of an artificial intelligence-based parking space indicating device provided by an embodiment of the present invention. As shown in FIG. 6, the device 600 includes:

The acquisition module 601 is used to acquire the parking image information of the vehicle, and the parking image information includes the parking space identification image; the recognition module 602 is used to perform image recognition on the parking image information through the image recognition engine to identify and obtain the corresponding parking space identification; the processing module 603 is used to form indication information corresponding to the parking lot according to the parking space identification; the indication module 604 is configured to display the indication information to instruct the user when receiving a car pick-up request from the user.

Optionally, the device 600 also includes:

The preprocessing module 605 is configured to preprocess the parking image information, and the preprocessing includes at least one of image correction and image enhancement.

Optionally, the instruction information includes a route instruction, and the instruction module 604 is also configured to obtain the user's current location information when receiving the user's car pickup request; add the user's current location information to the route instruction to obtain the current instruction route; display Current directions for directions to the user.

Optionally, the indication information includes a parking image, and the indication module 604 is further configured to display the parking image to instruct the user when receiving the user's request for picking up the car.

Optionally, the indication information includes the number of the parking space, and the indication module 604 is further configured to display the number of the parking space to instruct the user when receiving a request for picking up the car from the user.

Optionally, the obtaining module 601 is also used to obtain the video stream information when the vehicle enters the predetermined area of the parking lot; decode the video stream information to obtain the first image frame, and the first image frame includes a corresponding time stamp; select the time stamp Obtain a second image frame in the first image frame corresponding to the last preset digit; detect whether the second image frame includes a parking space identification image; if yes, extract the corresponding second image frame to obtain parking image information.

Optionally, the processing module 603 is also used to obtain the parking space map of the parking lot, and the parking space map includes the distribution position information of the parking spaces; the parking space identification is associated with the corresponding parking spaces in the parking space map; the parking spaces associated with the parking space identification are distinguished and identified, and the obtained An instruction map; forming corresponding instruction information based on the instruction map.

It should be noted that the artificial intelligence-based parking space indicating device provided in the embodiment of the present invention can be used in a user terminal device or a server device.

The artificial intelligence-based parking space indicator device in the parking lot provided by the embodiment of the present invention can realize various implementation modes and corresponding beneficial effects in the method embodiments shown in FIG. 2 to FIG. 5 . To avoid repetition, details are not repeated here.

Referring to FIG. 7, FIG. 7 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. As shown in FIG. A computer program that runs, wherein the processor 701 performs the following steps:

Obtain the parking image information of the vehicle, the parking image information includes the parking space identification image;

Carry out image recognition on the parking image information through the image recognition engine to identify and obtain the corresponding parking space sign;

Form the instruction information corresponding to the parking lot according to the parking space sign;

When the user's request for picking up the car is received, indication information is displayed to instruct the user. .

Optionally, before the processor 701 performs image recognition on the parking image information through the image recognition engine to identify the corresponding parking space mark, the processor 701 further executes the steps including:

Preprocessing the parking image information, the preprocessing includes at least one of image correction and image enhancement.

Optionally, the instruction information includes a route instruction, and when the processor 701 receives the user's car pickup request, it displays the instruction information to instruct the user, including:

When receiving the user's car pick-up request, obtain the user's current location information;

adding the user's current location information to the route indication to obtain the current indicated route;

Display the current indicated route to instruct the user.

Optionally, the instruction information includes a parking image, and when the processor 701 receives the user's car pickup request, the instruction information is displayed to instruct the user, including:

When the user's car pickup request is received, a parking image is displayed to instruct the user.

Optionally, the instruction information includes the parking space number, and when the processor 701 receives the user's car pickup request, displaying the instruction information to instruct the user includes:

When receiving the user's request to pick up the car, display the parking space number to instruct the user.

Optionally, the acquisition of parking image information of the vehicle executed by the processor 701 includes:

Obtain the video stream information when the vehicle enters the predetermined area of the parking lot;

Decoding the video stream information to obtain a first image frame, where the first image frame includes a corresponding time stamp;

Selecting the first image frame corresponding to the reciprocal preset digit of the time stamp to obtain the second image frame;

Detect whether the parking space identification image is included in the second image frame;

If so, extract the corresponding second image frame to obtain parking image information.

Optionally, the instructions executed by the processor 701 to form the corresponding parking lot according to the parking space identification include:

Obtain the parking space map of the parking lot, the parking space map includes the location information of the parking space distribution;

Associate the parking space logo with the corresponding parking space in the parking space map;

Differentiate the parking spaces associated with the parking space signs to obtain an instruction map;

Corresponding indication information is formed based on the indication map.

It should be noted that the electronic device provided by the embodiment of the present invention can be applied to an artificial intelligence-based parking space indication device, such as a user terminal device, a server, and other devices that can indicate a parking space.

The electronic device provided by the embodiment of the present invention can implement various implementation manners in the method embodiments in FIG. 1 to FIG. 5 and corresponding beneficial effects. To avoid repetition, details are not repeated here.

The embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method for indicating a parking space based on artificial intelligence provided by the embodiment of the present invention is implemented. Each process of the example, and can achieve the same technical effect, in order to avoid repetition, will not repeat them here.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the programs can be stored in a computer-readable storage medium. During execution, it may include the processes of the embodiments of the above-mentioned methods. Wherein, the storage medium may be a magnetic disk, an optical disk, a read-only memory (Read-Only Memory, ROM) or a random access memory (Random Access Memory, RAM for short).

The above disclosures are only preferred embodiments of the present invention, and certainly cannot limit the scope of rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope of the present invention.

Claims (10)

1. The utility model provides a parking area parking stall indicating method based on artificial intelligence which characterized in that includes:

Obtaining parking image information of a vehicle, wherein the parking image information comprises a parking space identification image;

Carrying out image recognition on the parking image information through an image recognition engine so as to obtain a corresponding parking space identifier through recognition;

Forming corresponding indication information according to the parking space identification;

and when a vehicle taking request of a user is received, displaying the indication information to indicate the user.

2. the method of claim 1, wherein before the image recognition of the parking image information by the image recognition engine to identify the corresponding parking space identifier, the method comprises:

Preprocessing the parking image information, wherein the preprocessing comprises at least one of image correction, image enhancement and image illumination compensation;

The image correction is to correct the parking image according to the jitter parameter when the vehicle parks;

The image enhancement is to enhance the area where the parking space identifier in the parking image information is located;

and the image illumination compensation is to perform illumination compensation on the parking image according to the light condition of the parking lot.

3. The method of claim 1, wherein the indication information includes a route indication, and wherein presenting the indication information to indicate to the user upon receiving a request to pick up a vehicle from the user comprises:

When a vehicle taking request of a user is received, acquiring current position information of the user;

Adding the current position information of the user into the route indication to obtain a current indication route;

Displaying the currently indicated route to indicate the user.

4. The method of claim 1, wherein the indicating information includes a parking image, and wherein presenting the indicating information to indicate to the user upon receiving a pickup request from the user comprises:

when a vehicle taking request of a user in a designated area is received, displaying the parking image to indicate the user, wherein the parking image is a small image which is cut and extracted according to the parking image information, the small image comprises the parking space identifier, and the designated area is designated by the user after parking or designated by the parking lot.

5. The method of claim 1, wherein the indication information includes a parking space number, and wherein presenting the indication information to indicate the user upon receiving a pick-up request from the user comprises:

When a vehicle taking request of a user in a designated area is received, displaying the parking space number in any form of voice, image and numbers to indicate the user, wherein the designated area is designated by the user after parking, and the designated area is designated by the user after parking or designated by the parking lot.

6. the method of claim 1, wherein the obtaining parking image information of the vehicle comprises:

acquiring video stream information when a vehicle drives into a preset area of a parking lot;

Decoding the video stream information to obtain a first image frame, wherein the first image frame comprises a corresponding timestamp;

Selecting a first image frame corresponding to the time stamp with a preset digit in the reciprocal to obtain a second image frame;

Detecting whether the second image frame comprises a parking space identification image or not;

and if so, extracting the corresponding second image frame to obtain the parking image information.

7. the method according to any one of claims 1 to 6, wherein the forming of the indication information of the corresponding parking lot according to the parking space identifier includes:

Acquiring a parking space map of a parking lot, wherein the parking space map comprises parking space distribution position information;

Associating the parking space identification with a corresponding parking space in the parking space map;

Distinguishing and identifying the parking spaces associated with the parking space identification to obtain an indication map;

And forming corresponding indication information based on the indication map.

8. The utility model provides a parking area parking stall indicating device based on artificial intelligence which characterized in that includes:

The system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring parking image information of a vehicle, and the parking image information comprises a parking space identification image;

The recognition module is used for carrying out image recognition on the parking image information through an image recognition engine so as to obtain a corresponding parking space identifier through recognition;

The processing module is used for forming indication information of a corresponding parking lot according to the parking space identifier;

and the indicating module is used for displaying the indicating information to indicate the user when receiving the vehicle taking request of the user.

9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the artificial intelligence based parking space indication method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the artificial intelligence based parking space indication method according to any one of claims 1 to 7.