WO2023231360A1 - 支付方法、装置以及车辆 - Google Patents

支付方法、装置以及车辆 Download PDF

Info

Publication number
WO2023231360A1
WO2023231360A1 PCT/CN2022/137558 CN2022137558W WO2023231360A1 WO 2023231360 A1 WO2023231360 A1 WO 2023231360A1 CN 2022137558 W CN2022137558 W CN 2022137558W WO 2023231360 A1 WO2023231360 A1 WO 2023231360A1
Authority
WO
WIPO (PCT)
Prior art keywords
payment
vehicle
user
information
license plate
Prior art date
Application number
PCT/CN2022/137558
Other languages
English (en)
French (fr)
Inventor
赵亚西
廖晓锋
汤秋缘
徐文康
王振阳
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023231360A1 publication Critical patent/WO2023231360A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/08Payment architectures
    • G06Q20/14Payment architectures specially adapted for billing systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/30Payment architectures, schemes or protocols characterised by the use of specific devices or networks
    • G06Q20/32Payment architectures, schemes or protocols characterised by the use of specific devices or networks using wireless devices
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00Payment architectures, schemes or protocols
    • G06Q20/38Payment protocols; Details thereof
    • G06Q20/40Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/60Type of objects
    • G06V20/62Text, e.g. of license plates, overlay texts or captions on TV images

Definitions

  • the present application relates to the field of smart cars, and more specifically, to a payment method, device and vehicle.
  • the phenomenon of parking charges is common.
  • the main ways to pay parking fees are cash payment, scan code payment and contactless payment (binding the license plate and payment account in advance).
  • the cash payment method has the worst user experience, and the touchless payment method has the best user experience.
  • the parking lot management system can obtain the user's identity information through the camera, thereby querying the user's parking fee to be paid, and making payment using the user's pre-bound account. In this way, the parking system may cause user identification errors or deduction errors, resulting in losses to the user's property.
  • Embodiments of the present application provide a payment method, device and vehicle, which can avoid theft or wrong deduction of the user's account due to errors in the parking lot system.
  • a payment method includes: detecting that a vehicle enters or leaves a parking lot; acquiring first image information through a first camera device, where the first image information is image information outside the vehicle, The first image information includes a first payment code; identify the first payment code to obtain the parking fee to be paid for the vehicle; obtain the user's first biometric information through a second camera device, and the second camera device A camera device that acquires images of the interior of the vehicle; when the first biometric information matches the second biometric information, the first user's account is used to pay the parking fee to be paid, and the second biometric
  • the characteristic information is the biological characteristic information preset in the vehicle by the first user, including the first user.
  • the vehicle can obtain the vehicle's positioning and signal strength through a global navigation satellite system (GNSS) sensor deployed on the vehicle, thereby determining whether the vehicle has entered or left the parking lot.
  • GNSS global navigation satellite system
  • the GNSS sensor when the GNSS sensor detects that the vehicle is located near a parking lot and the signal strength of the vehicle's communication is less than or equal to the first threshold, the GNSS sensor can send the first instruction message to the vehicle's cockpit controller to inform the vehicle to enter the parking lot. field.
  • the GNSS sensor detects that the vehicle is located near a parking lot and the signal strength of the vehicle's communication is greater than the second threshold, the GNSS sensor can send a second instruction message to the vehicle's cockpit controller to inform the vehicle to leave the parking lot. field.
  • the GNSS sensor when the GNSS sensor detects that the vehicle's communication signal is good and the vehicle is located at the edge of the parking lot or at the entrance or exit, the GNSS sensor can send third indication information to the cockpit controller 320 to inform the vehicle that it is entering or leaving the parking lot. field.
  • visual recognition can be used to determine whether the vehicle enters or leaves the parking lot.
  • the vehicle can collect image information outside the vehicle through the first camera device, and subdivide the collected images into multiple feature areas, and match each feature area with the identification target object (for example, parking lot sign, parking pole) , and calculate the matching probability.
  • the matching probability is greater than or less than the preset threshold, it can be determined that the vehicle is entering or leaving the parking lot.
  • a wireless signal transmitting device can be installed at the entrance or exit of the parking lot. After the vehicle receives the wireless signal transmitted by the wireless signal transmitting device, it can be determined that the vehicle is entering or leaving the parking lot.
  • the first camera device may be a camera deployed outside the vehicle, such as an AVM surround view camera or a DVR camera.
  • the first payment code may be a QR code, a barcode, or other payment code with payment functions.
  • Various methods may also be used for the vehicle to obtain the first image information through the first camera device.
  • the vehicle when the vehicle detects entering or leaving the parking lot, the vehicle can automatically collect the first image information around the vehicle through the first camera device.
  • the user when a user drives a vehicle into or out of a parking lot, he or she discovers that there are parking payment codes around the vehicle. At this time, the user can actively trigger the first camera device to take pictures to obtain the first image information. If the first camera device is a driving recorder, the method of obtaining the first image information may also be to intercept a certain part of the video recorded by the driving recorder. frame image.
  • the second camera device may be a depth camera with payment authentication capabilities, such as a 3D (time of flight, TOF) camera or a 3D structured light camera.
  • the first biometric information may be the user's facial feature information. When the first biometric information is consistent with the second biometric information preset by the first user in the vehicle, the first user's account is used to pay the parking fee.
  • the first biometric information can also be iris feature information or biometric information. If the first biometric information is the above two, corresponding iris recognition equipment or voiceprint recognition equipment should be configured on the vehicle.
  • the vehicle when it is detected that a vehicle enters or leaves the parking lot, the vehicle actively calls the first camera device of the vehicle to obtain the first image information, and identifies the first payment code in the first image information to query the parking lot. Then, the user's identity information is verified by calling the second camera device, thereby completing the payment of the parking fee. In this way, the entire QR code payment process is executed by the vehicle, which can avoid theft or wrong deduction of the user's account due to errors in the parking lot system.
  • the method further includes: when the first biometric information does not match the second biometric information, and the first biometric information does not match the second biometric information. If the three biometric information match, the second user's account is used to pay the parking fee to be paid, and the third biometric information is the biometric information preset by the second user in the vehicle, The user includes the second user.
  • the vehicle when the verification using the first biometric information and the second biometric information fails, the vehicle can query whether the identified first biometric information is associated with the third biometric information of the second user. In this case, use the second user’s account to complete the payment of parking fees. In this way, parking fee payment services can be provided for multiple users in the car, which avoids the need for users to manually log in to their accounts and enter passwords to complete payment after failed biometric information verification, improving payment efficiency.
  • the method before acquiring the first image information through the first camera device, the method further includes: acquiring a second image through the first camera device Information; when the parking fee to be paid by the vehicle cannot be identified through the second image information, obtain the first image information through the first camera device.
  • the payment code acquired by the first camera device may be distorted, resulting in failure in recognition of the payment code.
  • the position of the first camera device can be adjusted to reduce or avoid distortion of the payment code in the first image information.
  • the first payment code may be located at the edge of the second image information, and the first payment code is incompletely displayed in the second image information. In this way, the vehicle may not be able to recognize the information carried on the first payment code due to the incompleteness of the first payment code.
  • the first image information can be obtained by adjusting the position of the first camera device so that the first payment code is completely presented in the first image information.
  • the position of the payment code in the image information can be adjusted, so that the payment code recognition is successful. In this way, the recognition rate of payment codes can be enhanced and the user's payment experience can be improved.
  • the second image information includes the first payment code, and the parking lot to be paid for the vehicle cannot be identified through the second image information.
  • obtaining the first image information through the first camera device includes: determining based on the position coordinates of the first payment code in the second image and the center position coordinates of the second image information. Control parameters of the first camera device; control the first camera device to obtain the first image information according to the control parameters, and the first payment code is at the center of the first image information.
  • the first image information is obtained by adjusting the position of the first camera device so that the first payment code is located at the center of the first image. In this way, when the payment code is distorted, the payment code can always be maintained at the center of the first image, thereby better identifying the first payment code.
  • the method before using the first user's account to pay the parking fee to be paid, the method further includes: obtaining the first license plate information, the first One license plate information is the license plate information of the vehicle; wherein, using the first user's account to pay the parking fee to be paid includes: when the first license plate information is consistent with the second license plate information, using The first user's account pays the parking fee to be paid, and the second license plate information is the license plate information bound to the first user's account.
  • the processor on the vehicle can obtain the first license plate information, and automatically input the first license plate information into the license plate information input box of the payment website identified by the first payment code, and pass the first license plate information.
  • the website searches whether the second license plate information recognized by the parking lot system is consistent with the first license plate information, and only pays the parking fee to be paid if they are consistent.
  • the entire actions of obtaining the first license plate information, entering the first license plate information on the payment website, and querying the second license plate information are all performed by the vehicle.
  • the method before using the first user's account to pay the parking fee to be paid, the method further includes: obtaining the first license plate information, the first One license plate information is the license plate information of the vehicle; when the first license plate information is inconsistent with the second license plate information, prompt the first user that the first license plate information is not bound to the first user account. It is determined that the second license plate information is the license plate information bound to the first user account; wherein the using the first user's account to pay the parking fee includes: detecting that the first user's account is used to pay the parking fee. When the user binds the first license plate information to the first user's account, the user pays the parking fee to be paid.
  • the vehicle can prompt the user to bind the first license plate in various ways.
  • the vehicle may display a prompt message on the vehicle's display screen to inform the user that the first license plate information and the second license plate information are inconsistent.
  • the vehicle can inform the user that the first license plate information and the second license plate information are inconsistent through a voice message through a vehicle-mounted speaker.
  • the vehicle can prompt the user that the license plate has not yet been bound to the account.
  • the user has bound a license plate to the account, but the bound license plate and the recognized license plate information are inconsistent. At this time, the vehicle can prompt the user to bind the newly recognized license plate or refuse to pay.
  • the vehicle before paying the parking fee, it is necessary to verify whether the license plate of the vehicle to be paid is consistent with the license plate bound in the user account. If the verification fails, the vehicle can prompt the user to bind the identified license plate information. When the vehicle detects The payment process can only be triggered after the recognized license plate information is bound. In this way, setting verification measures before parking fee payment can prevent users from failing to pay parking fees or paying parking fees incorrectly, which not only ensures user account security but also improves users' payment experience.
  • the first image information further includes a second payment code
  • the first payment code corresponds to the first payment platform
  • the second payment code corresponds to the second Payment platform
  • the use of the first user's account to pay the parking fee to be paid includes: when the first user's payment frequency using the first payment platform is greater than the frequency of payment using the second payment platform Next, use the first payment platform to pay the parking fee to be paid.
  • the vehicle can recommend the optimal payment method to the user based on the user's payment habits.
  • the user can complete the payment of the parking fee through the recommended payment method. In this way, the payment of the parking fee can be completed more conveniently. , and can effectively improve the user's payment experience.
  • the method before acquiring the first image information through the first camera device, the method further includes: acquiring third image information through the first camera device, The first pixel proportion in the third image information is greater than the first threshold; the brightness of the vehicle light is adjusted to the first brightness according to the first pixel proportion; the acquisition by the first camera device
  • the first image information includes: acquiring the first image information through the first camera device at the first brightness.
  • the first pixel ratio may be a low pixel ratio, and its range may be preset.
  • the pixel value of an image ranges from 0 to 255, with 0 pixels representing the darkest image and 255 pixels representing the brightest image. You can preset 0 to 40 as the low pixel range.
  • the first pixel proportion may be the ratio of the average frequency of 0 to 40 pixels and the average value of the frequency of 0 to 255 pixels.
  • the specific value of the first threshold can be preset according to the actual situation. If the performance of the QR code recognition device is good, the first threshold can be set higher. If the performance of the QR code recognition device is poor, the first threshold can be set higher. The threshold is set lower.
  • different processes are performed by determining the relationship between the first pixel ratio and the first threshold in the image captured by the camera device.
  • the proportion of low-brightness low pixels is greater than the first threshold, the vehicle's lights are used to fill in the QR code.
  • additional fill-in equipment for example, parking lot lights
  • the first camera device is a driving recorder or a surround-view camera
  • the second camera device is a depth camera
  • a payment method includes: obtaining the parking fee to be paid for the vehicle; obtaining the user's first biometric information; when the first biometric information does not match the second biometric information, And if the first biometric information matches the third biometric information, the second user's account is used to pay the parking fee to be paid.
  • the second biometric information is the biometric information preset by the first user in the vehicle
  • the third biometric information is the biometric information preset by the second user in the vehicle.
  • Users include the first user and the second user.
  • parking fee payment services can be provided for multiple users in the car, which avoids the need for users to manually log in to their accounts and enter passwords after verification failure, and improves the efficiency of payment.
  • a payment device which device includes: a detection unit for detecting that a vehicle enters or leaves a parking lot; and an acquisition unit for acquiring first image information through a first camera device, the first The image information is image information outside the vehicle, and the first image information includes a first payment code; a processing unit used to identify the first payment code and obtain the parking fee to be paid for the vehicle; the acquisition unit , and is also used to obtain the user's first biometric information through a second camera device, which is a camera device that acquires images of the interior of the vehicle; when the first biometric information matches the second biometric information
  • the processing unit is also configured to use the first user's account to pay the parking fee to be paid, and the second biometric information is the biometric feature preset by the first user in the vehicle. Information, the user includes the first user.
  • the processing unit when the first biometric information does not match the second biometric information, and the first biometric information matches the third biometric information, If matched, the processing unit is also configured to use the second user's account to pay the parking fee to be paid, and the third biometric information is the biometric preset by the second user in the vehicle. Characteristic information, the user includes the second user.
  • the acquisition unit is further configured to acquire the second image information through the first camera device; the acquisition unit is specifically configured to obtain the second image information through the first camera. If the parking fee to be paid by the vehicle cannot be identified from the second image information, the first image information is obtained through the first camera device.
  • the second image information includes the first payment code
  • the processing unit is further configured to process the second payment according to the first payment code.
  • the position coordinates in the image and the center position coordinates of the second image information determine the control parameters of the first camera device; the processing unit is also configured to control the first camera device to obtain the data according to the control parameters.
  • the first image information is provided, and the first payment code is at the center of the first image information.
  • the acquisition unit is also used to acquire first license plate information, where the first license plate information is the license plate information of the vehicle; the processing unit, specifically Used to pay the parking fee to be paid using the first user's account when the first license plate information is consistent with the second license plate information, and the second license plate information is the same as the first user account.
  • the bound license plate information is also used to acquire first license plate information, where the first license plate information is the license plate information of the vehicle; the processing unit, specifically Used to pay the parking fee to be paid using the first user's account when the first license plate information is consistent with the second license plate information, and the second license plate information is the same as the first user account.
  • the acquisition unit is also used to acquire first license plate information, where the first license plate information is the license plate information of the vehicle; the processing unit is further Used to prompt the first user that the first license plate information is not bound to the first user account when the first license plate information is inconsistent with the second license plate information, and the second license plate information is The license plate information bound to the first user account; the processing unit is specifically configured to pay all the fees when detecting that the first user binds the first license plate information to the first user's account. Describe the parking fees to be paid.
  • the first image information further includes a second payment code
  • the first payment code corresponds to the first payment platform
  • the second payment code corresponds to the second payment code.
  • the processing unit is specifically configured to use the first payment platform to pay all the fees when the frequency of payment by the first user using the first payment platform is greater than the frequency of payment by using the second payment platform. Describe the parking fees to be paid.
  • the acquisition unit is further configured to acquire third image information through the first camera device, and the first pixel proportion in the third image information Greater than the first threshold; the processing unit is further configured to adjust the brightness of the vehicle light to the first brightness according to the first pixel ratio; the processing unit is specifically configured to adjust the brightness of the vehicle light to the first brightness under the first brightness.
  • the first image information is acquired through the first camera device.
  • the first camera device is a driving recorder or a surround-view camera
  • the second camera device is a depth camera
  • a payment device which device includes: an acquisition unit, used to acquire the parking fee to be paid by the vehicle; the acquisition unit is also used to acquire the first biometric information of the user; and a processing unit, used in If the first biometric information does not match the second biometric information, and the first biometric information matches the third biometric information, the second user's account is used to pay the to-be-paid amount. Parking fee.
  • the second biometric information is the biometric information preset by the first user in the vehicle
  • the third biometric information is the biometric information preset by the second user in the vehicle.
  • Users include the first user and the second user.
  • a payment device in a fifth aspect, includes: at least one processor and a memory.
  • the at least one processor is coupled to the memory and is used to read and execute instructions in the memory.
  • the device is configured to Implement the methods in each of the above aspects.
  • a computer-readable medium stores program code.
  • the computer program code When the computer program code is run on a computer, it causes the computer to perform the methods in the above aspects.
  • a chip in a seventh aspect, includes: at least one processor and a memory.
  • the at least one processor is coupled to the memory and is used to read and execute instructions in the memory.
  • the device is used to execute methods in each of the above aspects.
  • a vehicle in an eighth aspect, includes: at least one processor and a memory, the at least one processor is coupled to the memory, and is used to read and execute instructions in the memory.
  • the device is used to execute methods in each of the above aspects.
  • the technical solution provided by the embodiment of the present application enables the vehicle to actively call the first camera device to obtain the first image information and identify the first payment code in the first image information when the vehicle detects the vehicle entering or leaving the parking lot. Check parking rates. Then, the user's identity information is verified by calling the second camera device to obtain the first biometric information, thereby completing the payment of the parking fee.
  • the entire QR code payment process is performed by the vehicle, which can avoid theft or wrong deduction of the user's account due to errors in the parking lot system.
  • the position of the first camera is adjusted so that the first payment code is located at the center of the first image.
  • the vehicle can query whether the identified first biometric information is associated with the third biometric information of the second user, and in the case of association, use the third biometric information.
  • the vehicle can query whether the identified first biometric information is associated with the third biometric information of the second user, and in the case of association, use the third biometric information.
  • Figure 1 is a functional schematic diagram of a vehicle provided by an embodiment of the present application.
  • Figure 2 is a comparison chart of the efficiency and operating costs of different parking fee payment methods provided by this application.
  • FIG. 3 is a system architecture diagram of a payment method provided by this application.
  • Figure 4 is an application scenario diagram of the payment method provided by this application.
  • Figure 5 is another application scenario diagram of the payment method provided by this application.
  • Figure 6 is another application scenario diagram of the payment method provided by this application.
  • Figure 7 is another application scenario diagram of the payment method provided by this application.
  • Figure 8 is another application scenario diagram of the payment method provided by this application.
  • Figure 9 is a schematic flow chart of a payment method provided by this application.
  • FIG. 10 is a schematic flow chart of another payment method provided by this application.
  • Figure 11 is a schematic flow chart of a surround-view camera QR code adaptive recognition method provided by this application.
  • Figure 12 is a schematic flow chart provided by this application for realizing QR code center detection through PID control of the camera motor
  • Figure 13 is a schematic flow chart of a low-resolution QR code recognition method provided by this application.
  • Figure 14 is a schematic diagram of a super-resolution algorithm provided by this application to enhance the resolution of QR codes
  • Figure 15 is a method of filling light for QR codes under low illumination provided by this application.
  • Figure 16 is a histogram of images before and after fill light provided by this application.
  • Figure 17 is an interactive method for multiple QR code selection and payment provided by this application.
  • Figure 18 is a schematic flow chart of a parking lot scan code payment method provided by this application.
  • Figure 19 is a schematic diagram of a payment device provided by this application.
  • FIG 20 is a schematic diagram of another payment device provided by this application.
  • FIG. 1 is a functional schematic diagram of a vehicle 100 provided by an embodiment of the present application. It should be understood that FIG. 1 and related descriptions are only examples and do not limit the vehicle in the embodiment of the present application.
  • the vehicle 100 may be configured in a fully or partially autonomous driving mode, or may be manually driven by a user.
  • the vehicle 100 can obtain its surrounding environment information through the sensing system 120, and obtain an autonomous driving strategy based on the analysis of the surrounding environment information to achieve fully autonomous driving, or present the analysis results to the user to achieve partially autonomous driving.
  • Vehicle 100 may include various subsystems, such as perception system 120 , computing platform 130 , and display device 140 .
  • vehicle 100 may include more or fewer subsystems, and each subsystem may include one or more components.
  • each subsystem and component of vehicle 100 may be interconnected through wired or wireless means.
  • Sensing system 120 may include several types of sensors that sense information about the environment surrounding vehicle 100 .
  • the sensing system 120 may include a positioning system, and the positioning system may be a global positioning system (GPS), Beidou system, or other positioning systems.
  • the sensing system 120 may include one or more of an inertial measurement unit (IMU), lidar, millimeter wave radar, ultrasonic radar, and camera device 121.
  • IMU inertial measurement unit
  • lidar lidar
  • millimeter wave radar millimeter wave radar
  • ultrasonic radar ultrasonic radar
  • the camera device 121 may be used to capture image information of the surrounding environment of the vehicle 100 .
  • the camera device 121 may include a monocular camera, a binocular camera, a structured light camera, a panoramic camera, etc.
  • the image information acquired by the camera device 121 may include still image information or video stream information.
  • the image information can be stored in the form of images or videos, or in the form of parameters of images or videos, such as brightness, grayscale, color distribution, contrast, pixels and other parameter information of the image.
  • the computing platform 130 may include processors 131 to 13n (n is a positive integer).
  • a processor is a circuit with signal processing capabilities.
  • the processor may be a circuit with instruction reading and execution capabilities.
  • CPU central processing unit
  • microprocessor graphics processing unit
  • GPU graphics processing unit
  • DSP digital signal processor
  • the processor can realize certain functions through the logical relationship of the hardware circuit. The logical relationship of the hardware circuit is fixed or can be reconstructed.
  • the processor is an application-specific integrated circuit (application-specific integrated circuit). ASIC) or programmable logic device (PLD) implemented hardware circuit, such as FPGA.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • the process of the processor loading the configuration file and realizing the hardware circuit configuration can be understood as the process of the processor loading instructions to realize the functions of some or all of the above units.
  • it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing Unit (deep learning processing unit, DPU), etc.
  • the computing platform 130 may also include a memory, which is used to store instructions. Some or all of the processors 131 to 13n may call instructions in the memory to execute the quality to implement corresponding functions.
  • Computing platform 130 may control functionality of vehicle 100 based on input received from various subsystems (eg, perception system 120 ). In some embodiments, computing platform 130 is operable to provide control of many aspects of vehicle 100 and its subsystems.
  • An autonomous vehicle traveling on the road can identify objects within its surrounding environment to determine adjustments to its current speed.
  • the objects may be other vehicles, traffic control equipment, or other types of objects.
  • each identified object can be considered independently and based on the object's respective characteristics, such as its current speed, acceleration, distance from the vehicle, etc., can be used to determine the speed to which the autonomous vehicle will adjust.
  • the vehicle 100 or a sensing and computing device associated with the vehicle 100 may perform the processing based on the characteristics of the identified object and the state of the surrounding environment (eg, traffic, rain, ice on the road, etc. etc.) to predict the behavior of the identified object.
  • each recognized object depends on the behavior of each other, so it is also possible to predict the behavior of a single recognized object by considering all recognized objects together.
  • the vehicle 100 is able to adjust its speed based on the predicted behavior of the identified objects.
  • the autonomous vehicle is able to determine what stable state the vehicle will need to adjust to (eg, accelerate, decelerate, or stop) based on the predicted behavior of the object.
  • other factors may also be considered to determine the speed of the vehicle 100, such as the lateral position of the vehicle 100 in the road on which it is traveling, the curvature of the road, the proximity of static and dynamic objects, and so on.
  • the computing device may also provide instructions to modify the steering angle of the vehicle 100 so that the autonomous vehicle follows a given trajectory and/or maintains contact with objects in the vicinity of the autonomous vehicle (e.g., , the safe lateral and longitudinal distance between cars in adjacent lanes on the road).
  • objects in the vicinity of the autonomous vehicle e.g., , the safe lateral and longitudinal distance between cars in adjacent lanes on the road.
  • the above-mentioned vehicle 100 may be a car, a truck, a motorcycle, a public vehicle, a boat, an airplane, a helicopter, a lawnmower, an entertainment vehicle, a playground vehicle, construction equipment, a tram, a golf cart, a train, etc., in the embodiment of the present application No special restrictions are made.
  • scan code payment also includes active scan code payment when leaving the venue (leaving the parking lot) and automatic scan code payment when leaving the venue.
  • Figure 2 is a comparison chart of the efficiency and operating costs of different parking fee payment methods provided by this application.
  • the parking lot management system can obtain the user's identity information through the camera, thereby querying the user's parking fee to be paid, and making payment using the user's pre-bound account. In this way, the parking system may cause user identification errors or payment errors, resulting in losses to the user's property. In addition, since the entire parking fee payment process is controlled by the parking lot management system, users have a poor payment experience and high trust costs.
  • Embodiments of the present application provide a payment method, device and vehicle, which can reduce the risk of wrong or stolen deductions in the user's account when paying parking fees, and improve the user's payment experience.
  • FIG. 3 is a system architecture diagram of a payment method provided by this application.
  • the system architecture 300 can be applied to the vehicle 100 of FIG. 1 .
  • the system architecture can be composed of two parts: a driving recorder 310 (digital video recorder, DVR) and a cockpit domain controller 320 (cockpit domain controller, CDC).
  • the DVR 310 can collect video stream data in front of the vehicle or image information in front of the vehicle in real time, and send the collected data to the CDC 320 for processing.
  • CDC 320 is a platform with computing capabilities that can perform subscription management, video compression, driving records, QR code scanning and recognition, face payment and other operations on the video stream data transmitted from DVR 310.
  • the CDC 320 may include: a video stream subscription management module 321, a video compression module 322, a driving record module 323, a QR code scanning and identification module 324, and a face payment module 325.
  • cockpit domain controller 320 is used as an example for description in this system architecture, and the cockpit domain controller 320 can also be replaced with other controllers.
  • the vehicle when the vehicle detects entering or leaving the parking lot, it calls the DVR 310 to automatically obtain a full-frame high-definition photo (luma-chroma, YUV), and subscribes to the full-frame high-definition photo through the video stream
  • the management module 321 sends it to the QR code scanning and identification module 324 for processing. After obtaining the photo, the QR code scanning and identification module 324 can scan and identify the photo.
  • CDC 320 can call the relevant interface to control the vehicle's display interface to jump to the payment interface, and the face payment module 325 can control the interior of the vehicle The camera performs face recognition on the user and completes the parking fee payment after successful verification.
  • the CDC 320 can provide feedback to the user, and the user can actively click on the required one on the vehicle's display screen. QR code. If the recognition result of the QR code scanning identification module 324 shows that the scanned QR code is a web page QR code, the CDC 320 can call the relevant H5 container to display the corresponding web page information on the vehicle's display screen. The user can Perform operations such as clicking and typing.
  • the high-definition full-frame photos can be obtained by the user actively triggering the DVR 310 to take pictures, or by the CDC 320 controlling the interception of a certain frame of image in the YUV video.
  • driving recorder 310 can also be replaced with a surround view camera.
  • QR code is used as an example to illustrate the situation of querying and paying parking fees.
  • the QR code can also be replaced by a payment code with payment capabilities such as a barcode.
  • Figure 4 is an application scenario diagram of the payment method provided by this application.
  • the vehicle is located in a parking space in a parking lot.
  • the display interface 400 includes user account login information 401, Bluetooth function icon 404, Wi-Fi function icon 403, cellular network signal icon 404, vehicle map application search box 405, switch to a card displaying all applications installed in the vehicle 406, Switch to a card 407 that displays the car music application, a card 408 that displays the vehicle's remaining power and remaining mileage, and a card 409 that displays the vehicle's 360-degree (°) surround function.
  • the vehicle map application search box 405 may include a home control 4051 and a go to work control 4052 set by the user.
  • the function bar 410 includes an icon 411 for switching to display the central control large screen desktop, a vehicle internal circulation icon 412, a main driver seat heating function icon 413, a main driver area air conditioning temperature display icon 414, a passenger area air conditioning temperature display icon 415, and a passenger seat heating function icon 413.
  • the vehicle can automatically collect the first image information around the vehicle through the first camera device (for example, driving recorder DVR, surround view camera AVM, etc.).
  • the first image information includes After parking and paying for the QR code, the vehicle can automatically scan and recognize the payment QR code, and display the scanned results on the vehicle's display.
  • the detection and recognition process of the QR code may be that the vehicle crops the payment QR code area in the first image information, and inputs the cropped QR code into the QR code recognition network to obtain the QR code.
  • QR code information and access the address of the parking fee information carried in the QR code information, thereby guiding the user to complete the payment of the parking fee.
  • the QR code detection network and the QR code recognition network can be deep learning networks (for example, convolutional neural network (CNN) model or recurrent neural network (Recurrent Neural Network, RNN)), and the neural network model can Pre-acquired through dataset training.
  • CNN convolutional neural network
  • RNN Recurrent Neural Network
  • the graphical user interface shows that after the vehicle automatically scans and recognizes the parking payment QR code, the parking fee payment interface can be displayed on the vehicle's display screen.
  • the parking fee payment interface includes a user account option 418, a license plate number option 419, an amount to be paid option 420, and a prompt box 421 facing the camera in the car.
  • the in-car camera can collect the user's biometric information, and the biometric information may be facial feature information.
  • this figure represents the user's facial feature information collected through the second camera device.
  • the vehicle can compare the collected facial feature information with the vehicle's preset facial feature information, and complete the verification after success. Payment of parking fees.
  • the GUI is a parking fee payment interface.
  • the parking fee payment interface includes a prompt box 422 prompting the user that the payment is successful. After the user's biometric information is verified, the GUI is displayed on the vehicle's display screen to inform the user of successful payment.
  • the vehicle can automatically obtain the information displayed in the account number option 418, the license plate number option 419, and the amount to be paid option 420, without the need for manual input operations by the user.
  • the vehicle can obtain the above information by having the parking lot identify the vehicle and then carry the above information in the payment QR code.
  • the QR code can be a dynamic QR code. It can also be that after the user scans the payment QR code, the parking lot obtains the above information of the vehicle, transfers the above information to the vehicle, and displays it on the vehicle's display screen.
  • biometric information can also be iris feature information or biometric information. If the biometric information is the above two types, the vehicle should be equipped with corresponding iris recognition equipment or voiceprint recognition equipment.
  • the vehicle when the vehicle enters or leaves the parking lot, the vehicle can automatically collect and identify the parking payment QR code vehicle, and automatically obtain the license plate information and the amount to be paid. Moreover, the vehicle can obtain and complete the payment of parking fees based on the user's biometric information. In this way, when paying parking fees, the risk of wrong or stolen deductions in the user's account can be reduced, and the user's payment experience can be improved.
  • Figure 5 is another application scenario diagram of the payment method provided by this application.
  • the vehicle can automatically collect the first image information around the vehicle through the first camera device (for example, driving recorder DVR, surround view camera AVM, etc.).
  • the first image information includes After parking and paying for the QR code, the vehicle can automatically scan and identify the payment QR code, and notify the user of the scan result through the on-board display, and the user can choose whether to enter the scanning page.
  • the vehicle can obtain the vehicle's positioning and signal strength through a global navigation satellite system (GNSS) sensor deployed on the vehicle to determine whether the vehicle enters or leaves the parking lot, for example
  • GNSS global navigation satellite system
  • the GNSS sensor detects that the position of the vehicle is near a parking lot, and the signal strength of the vehicle's communication is less than or equal to the first threshold
  • the GNSS sensor can send the first indication information to the cockpit controller 320 of the vehicle to inform the vehicle to enter the parking lot. field.
  • the GNSS sensor detects that the vehicle is located near a parking lot and the signal strength of the vehicle's communication is greater than the second threshold
  • the GNSS sensor can send second instruction information to the vehicle's cockpit controller 320 to inform the vehicle to leave. PARKING LOT.
  • the GNSS sensor when the GNSS sensor detects that the vehicle's communication signal is good and the vehicle is located at the edge of the parking lot or at the entrance or exit, the GNSS sensor can send third indication information to the cockpit controller 320 to inform the vehicle that it is entering or leaving the parking lot. field.
  • visual recognition can be used to determine whether the vehicle enters or leaves the parking lot.
  • the vehicle can collect image information outside the vehicle through the first camera device, and subdivide the collected images into multiple feature areas, and match each feature area with the identification target object (for example, parking lot sign, parking pole) , and calculate the matching probability.
  • the matching probability is greater than or less than the preset threshold, it can be determined that the vehicle is entering or leaving the parking lot.
  • One possible implementation method is to set up a wireless signal transmitting device at the entrance or exit of the parking lot. After the vehicle receives the wireless signal transmitted by the wireless signal transmitting device, it can determine that the vehicle is entering or leaving the parking lot.
  • the process of detecting and identifying the QR code may be that the vehicle crops the payment QR code area in the first image information, and inputs the cropped QR code into the QR code recognition network to obtain the QR code information, and Access the address of the parking fee information carried in the QR code information to guide the user to complete the payment of the parking fee.
  • the QR code detection network and QR code recognition network can be deep learning network CNN models or RNN models, and the models can be obtained in advance through data set training.
  • the GUI includes a notification bar 501.
  • the user can be notified whether to enter the recognition page through the notification bar 501 on the vehicle display screen.
  • a GUI as shown in (b) of Figure 5 may be displayed on the vehicle's display screen.
  • the vehicle can automatically obtain the information displayed in the account number option 418, the license plate number option 419, and the amount to be paid option 420.
  • the vehicle can obtain the above information by identifying the vehicle in the parking lot.
  • the above information is carried in the payment QR code.
  • the parking lot obtains the above information of the vehicle, transfers the above information to the vehicle, and displays it on the vehicle's display screen.
  • the GUI also includes a touchless payment control 502 and a manual payment control 503. If the user clicks on the touchless payment control 502, the vehicle can pay in the manner (c) to (e) in Figure 4.
  • the manual payment control 503 the GUI shown in (c) in Figure 5 may be displayed on the vehicle's display screen.
  • the GUI is a parking fee payment interface, including a password input option 504 and a software disk control 505.
  • the user can enter a password in the password input option 504 by clicking on the number on the software disk control 505. After the password input is completed, click the OK control on the software disk, and the GUI shown in (d) in Figure 5 will be displayed on the vehicle's display screen.
  • the GUI is a parking fee payment interface, including a prompt box 506 indicating that the parking fee payment is successful.
  • the prompt box 506 is displayed on the display screen of the vehicle to inform the user that the payment is successful.
  • the vehicle when there is a parking payment QR code around the vehicle, the vehicle can automatically scan and identify the QR code, and notify the user of the scan result, and the user can actively choose whether to enter the identification interface.
  • users can choose to use contactless payment or manual payment. In this way, users can be provided with diversified payment modes during the process of paying parking fees, thereby improving the user's payment experience.
  • Figure 6 is another application scenario diagram of the payment method provided by this application.
  • the user When the user drove the vehicle into or out of the parking lot, he found a parking payment QR code around the vehicle.
  • the user can obtain the first image information around the vehicle through the first camera device deployed outside the vehicle (for example, driving recorder DVR, surround view camera AVM, etc.), and use the QR code scanning function to identify the first image information payment QR code.
  • the vehicle can automatically obtain the first image information around the vehicle through the first camera device, and automatically scan and identify the payment QR code in the first image information.
  • the method of scanning and identifying the payment QR code can either be automatically scanned and identified by the vehicle and automatically enter the identification page (for example, the method introduced in Figure 4), or it can be automatically scanned and identified by the vehicle and the scanned result is passed through
  • the on-board display notifies the user, and the user actively chooses whether to enter the page (for example, the method introduced in Figure 5).
  • the GUI shown in Figure 6(a) can be displayed on the vehicle's display screen.
  • the GUI includes an interactive assistant 601 and an interactive text 602.
  • the interactive assistant 601 and interactive text 602 can be displayed on the display screen of the vehicle to notify the user that the license plate number has not been bound to the account. Number.
  • the interactive assistant 601 and the interactive text 602 can be displayed on the vehicle's display screen to notify the user to add and bind a new license plate number to the account.
  • the vehicle recognizes the dynamic QR code. Since the dynamic QR code can be updated in real time, the vehicle can obtain the currently recognized license plate information after scanning the dynamic QR code and determine whether the user's account is bound. Recognized license plate number information.
  • the above QR code can also be a fixed QR code. After the vehicle scans the fixed QR code, the parking lot system identifies the license plate number information of the vehicle to be paid, and then the parking system records the license plate number. The information is sent to the vehicle through signaling interaction, and the recognized license plate number information is displayed on the vehicle's display screen. In this case, since the vehicle needs to communicate with the parking lot, the vehicle needs to enable corresponding external communication permissions in actual applications.
  • the GUI as shown in (b) of Figure 6 can be displayed on the vehicle display screen.
  • the GUI is a parking fee inquiry interface.
  • the interface includes: input license plate number option 603 and binding control 604.
  • the GUI shown in (c) in Figure 6 can be displayed on the vehicle display screen.
  • the GUI includes the license plate number input box 605 and the software disk control 606.
  • the user can enter the license plate number input box in the license plate number input box. Enter the abbreviation of the license plate in the first input box of 605, and enter letters and numbers in the following input boxes.
  • the GUI shown in Figure 6(d) can be displayed on the vehicle display screen. From the GUI interface, the user can learn the parking fee information that needs to be paid, and can choose to pay by way of non-inductive payment or manual payment. If the user chooses the sensorless payment method, the vehicle can pay the parking fee through sensorless payment methods such as face payment or iris payment when it detects that the user has bound a new license plate.
  • the user can input the license plate number in the license plate number input box 605 manually through the vehicle display screen, or by sending a voice command to the interactive assistant 601, and so on.
  • the vehicle can prompt the user when the user has not bound the license plate number or the bound license plate number is inconsistent with the recognized license plate number. And after detecting that the user has bound the new license plate information, the parking fee to be paid will be paid. In this way, users can avoid the situation where the user fails to pay the parking fee or pays the parking fee incorrectly, which not only ensures the security of the user's account, but also improves the user's payment experience.
  • Figure 7 is another application scenario diagram of the payment method provided by this application.
  • the application scenario shown in Figure 7 is performed when the vehicle prompts the user that the license plate number is not bound.
  • the GUI is a parking fee query interface.
  • the interface includes historical license plate options 701.
  • the vehicle display screen can The GUI shown in (b) in Figure 7 is displayed. The user can learn the parking fee information that needs to be paid according to the GUI, and can choose to pay by means of non-inductive payment or manual payment.
  • the user when the user's account has not been bound to a license plate number, the user can click on the payment or search record of the historical license plate to directly query the parking fee information and pay. In this way, the parking fee payment process can be made simpler and more efficient.
  • Figure 8 is another application scenario diagram of the payment method provided by this application.
  • the user When the user drove the vehicle into or out of the parking lot, he found a parking payment QR code around the vehicle.
  • the user can obtain the first image information around the vehicle through the first camera device deployed outside the vehicle (for example, driving recorder DVR, surround view camera AVM, etc.), and use the QR code scanning function to identify the first image information payment QR code.
  • the vehicle can automatically obtain the first image information around the vehicle through the first camera device, and automatically scan and identify the payment QR code in the first image information.
  • the method of scanning and identifying the payment QR code can either be automatically scanned and identified by the vehicle and automatically enter the identification page (for example, the method introduced in Figure 4), or it can be automatically scanned and identified by the vehicle and the scanned result is passed through
  • the on-board display notifies the user, and the user actively chooses whether to enter the page (for example, the method introduced in Figure 5).
  • the GUI shown in Figure 8(a) can be displayed on the vehicle's display screen.
  • the GUI is a parking fee inquiry interface.
  • the interface includes an in-vehicle payment option 801 and a send to mobile phone option 802.
  • the vehicle can use the in-vehicle payment option in Figure 4 The contactless payment method shown in (c) or the manual payment method shown in (c) in Figure 5.
  • the vehicle can send the parking fee payment information to the user's mobile phone.
  • the user's mobile phone can display the GUI on the mobile phone after receiving the parking fee payment message sent by the vehicle.
  • the GUI includes a prompt box 403 and a determination control 404.
  • the prompt box 403 is used to prompt the user that the vehicle sends a parking fee payment message to the mobile phone and asks the user to pay and enter the payment page.
  • the OK control 404 the GUI shown in Figure 8(c) can be displayed on the mobile phone.
  • the GUI includes a prompt box 805 for prompting the user to face the camera of the mobile phone.
  • the prompt box 805 for prompting the user to face the camera of the mobile phone.
  • the vehicle after the vehicle obtains the parking fee information to be paid by the user, the vehicle can send the parking fee information to the user's mobile phone according to the user's instructions, and the user can complete the payment of the parking fee through the mobile phone.
  • the vehicle can send the parking fee information to the user's mobile phone according to the user's instructions, and the user can complete the payment of the parking fee through the mobile phone.
  • users can be provided with more diversified payment methods to meet users' personalized needs for payment methods.
  • Figure 9 is a schematic flow chart of a payment method provided by this application.
  • the payment method shown in Figure 9 can be applied to the vehicle 100 of Figure 1 .
  • the method 900 can include the following steps.
  • the vehicle can obtain the vehicle's positioning and signal strength through a global navigation satellite system (GNSS) sensor deployed on the vehicle, thereby determining whether the vehicle has entered or left the parking lot.
  • GNSS global navigation satellite system
  • the GNSS sensor when the GNSS sensor detects that the vehicle is located near a parking lot and the signal strength of the vehicle's communication is less than or equal to the first threshold, the GNSS sensor can send the first instruction message to the vehicle's cockpit controller to inform the vehicle to enter the parking lot. field.
  • the GNSS sensor detects that the vehicle is located near a parking lot and the signal strength of the vehicle's communication is greater than the second threshold, the GNSS sensor can send a second instruction message to the vehicle's cockpit controller to inform the vehicle to leave the parking lot. field.
  • the GNSS sensor when the GNSS sensor detects that the vehicle's communication signal is good and the vehicle is located at the edge of the parking lot or at the entrance or exit, the GNSS sensor can send third indication information to the cockpit controller 320 to inform the vehicle that it is entering or leaving the parking lot. field.
  • visual recognition can be used to determine whether the vehicle enters or leaves the parking lot.
  • the vehicle can collect image information outside the vehicle through the first camera device, and subdivide the collected images into multiple feature areas, and match each feature area with the identification target object (for example, parking lot sign, parking pole) , and calculate the matching probability.
  • the matching probability is greater than or less than the preset threshold, it can be determined that the vehicle is entering or leaving the parking lot.
  • a wireless signal transmitting device can be installed at the entrance or exit of the parking lot. After the vehicle receives the wireless signal transmitted by the wireless signal transmitting device, it can be determined that the vehicle is entering or leaving the parking lot.
  • the first camera device may be a camera deployed outside the vehicle, such as an AVM surround view camera or a DVR camera.
  • the first payment code may be a QR code, a barcode, or other payment code with payment functions.
  • Various methods may also be used for the vehicle to obtain the first image information through the first camera device.
  • the vehicle when the vehicle detects entering or leaving the parking lot, the vehicle can automatically collect the first image information around the vehicle through the first camera device.
  • the user when a user drives a vehicle into or out of a parking lot, he or she discovers that there are parking payment codes around the vehicle. At this time, the user can actively trigger the first camera device to take pictures to obtain the first image information. If the first camera device is a driving recorder, the method of obtaining the first image information may also be to intercept a certain part of the video recorded by the driving recorder. frame image.
  • the first image information is acquired through the first camera device. Compared with the situation where the first camera device is always working, the energy consumption of the first camera device can be reduced and the efficiency of the first camera device in acquiring the first image information can be improved.
  • multiple methods can be used to identify the payment code.
  • the user can trigger the payment code scanning function through an application on the vehicle display screen to scan the code for identification.
  • the vehicle after acquiring the first image information, can automatically scan and identify the first payment code, and notify the user of the scan result on the vehicle display screen, and the user can decide whether to enter the identification page.
  • the payment code detection and recognition process may be that the vehicle crops the first payment code area in the first image information, and inputs the cropped payment code into the payment code identification network to obtain the payment code. code information, and access the address of the parking fee information carried in the payment code information, thereby guiding the user to complete the payment of the parking fee.
  • the payment code detection network and payment code recognition network can be deep learning networks (for example, CNN models or RNN models), and the models can be obtained in advance through data set training.
  • S904 Obtain the user's first biometric information through the second camera device.
  • This step can call the second camera device to obtain the user's first biometric information through a data management supervisor (DMS) or content management system (CMS).
  • DMS data management supervisor
  • CMS content management system
  • the second camera device may be a depth camera used to obtain images of the interior of the vehicle, such as a 3D (time of flight, TOF) camera or a 3D structured light camera.
  • the first biometric information may be the user's facial feature information.
  • the first biometric information can also be iris feature information or biometric information. If the first biometric information is the above two, corresponding iris recognition equipment or voiceprint recognition equipment should be configured on the vehicle.
  • the second biometric information is the biometric information preset by the first user in the vehicle.
  • the user's facial feature information (a type of biometric information) is collected through the second camera device, and the collected facial feature information is compared with the preset facial feature information in the vehicle system. After successful verification, it is directly bound from the user. Debit the account.
  • an interface as shown in Figure 5(c) may be displayed on the vehicle display screen, and the user may be prompted to manually enter a password for payment.
  • the vehicle when it is detected that a vehicle enters or leaves the parking lot, the vehicle actively calls the first camera device of the vehicle to obtain the first image information, and identifies the first payment code in the first image information to query the parking lot. Then, the user's identity information is verified by calling the second camera device, thereby completing the payment of the parking fee. In this way, the entire QR code payment process is executed by the vehicle, which can avoid theft or wrong deduction of the user's account due to errors in the parking lot system.
  • step S905 further includes: when the first biometric information does not match the second biometric information, and the first biometric information matches the third biometric information.
  • the second user's account is used to pay the parking fee to be paid
  • the third biometric information is the biometric information preset by the second user in the vehicle, and the user includes the third biometric information. Two users.
  • the vehicle when the verification using the first biometric information and the second biometric information fails, the vehicle can query whether the identified first biometric information is associated with the third biometric information of the second user. In this case, use the second user’s account to complete the payment of parking fees. In this way, parking fee payment services can be provided for multiple users in the car, which avoids the need for users to manually log in to their accounts and enter passwords to complete payment after failed biometric information verification, improving payment efficiency.
  • the method before step S902, the method further includes: obtaining second image information through the first camera device; if the parking fee to be paid by the vehicle cannot be identified through the second image information, In this case, the first image information is acquired through the first camera device.
  • the payment code acquired by the first camera device may be distorted, resulting in failure in recognition of the payment code.
  • the position of the first camera device can be adjusted to reduce or avoid distortion of the payment code in the first image information.
  • the first payment code may be located at the edge of the second image information, and the first payment code is incompletely displayed in the second image information. In this way, the vehicle may not be able to recognize the information carried on the first payment code due to the incompleteness of the first payment code.
  • the first image information can be obtained by adjusting the position of the first camera device, so that the first payment code is completely presented in the first image information.
  • the position of the payment code in the image information can be adjusted, so that the payment code recognition is successful. In this way, the recognition rate of payment codes can be enhanced and the user's payment experience can be improved.
  • the second image information includes the first payment code
  • the parking fee to be paid by the vehicle is collected through the first payment code.
  • the camera device obtains the first image information, including: determining the control of the first camera device based on the position coordinates of the first payment code in the second image and the center position coordinates of the second image information. Parameter: control the first camera device to acquire the first image information according to the control parameter, and the first payment code is at the center of the first image information.
  • the first image information is obtained by adjusting the position of the first camera device so that the first payment code is located at the center of the first image. In this way, when the payment code is distorted, the payment code can always be maintained at the center of the first image, thereby better identifying the first payment code.
  • the method before using the first user's account to pay the parking fee to be paid, the method further includes: obtaining first license plate information, where the first license plate information is the vehicle's License plate information; wherein said using the first user's account to pay the parking fee to be paid includes: when the first license plate information is consistent with the second license plate information, using the first user's account to pay The parking fee to be paid, the second license plate information is the license plate information bound to the first user account.
  • the processor on the vehicle can obtain the first license plate information, and automatically input the first license plate information into the license plate information input box of the payment website identified by the first payment code, and pass the first license plate information.
  • the website searches whether the second license plate information recognized by the parking lot system is consistent with the first license plate information, and only pays the parking fee to be paid if they are consistent.
  • the entire actions of obtaining the first license plate information, entering the first license plate information on the payment website, and querying the second license plate information are all performed by the vehicle.
  • the method before using the first user's account to pay the parking fee to be paid, the method further includes: obtaining first license plate information, where the first license plate information is the vehicle's License plate information; when the first license plate information is inconsistent with the second license plate information, prompt the first user that the first license plate information is not bound to the first user account, and the second license plate information It is the license plate information bound to the first user account; wherein the using the first user's account to pay the parking fee includes: after detecting that the first user transfers the first license plate information to When bound to the first user's account, the parking fee to be paid is paid.
  • the vehicle can prompt the user to bind the first license plate in various ways.
  • the vehicle may display a prompt message on the vehicle's display screen to inform the user that the first license plate information and the second license plate information are inconsistent.
  • the vehicle can inform the user that the first license plate information and the second license plate information are inconsistent through a voice message through a vehicle-mounted speaker.
  • the vehicle can prompt the user that the license plate has not yet been bound to the account.
  • the user has bound a license plate to the account, but the bound license plate and the recognized license plate information are inconsistent. At this time, the vehicle can prompt the user to bind the newly recognized license plate or refuse to pay.
  • the vehicle before paying the parking fee, it is necessary to verify whether the license plate of the vehicle to be paid is consistent with the license plate bound in the user account. If the verification fails, the vehicle can prompt the user to bind the identified license plate information. When the vehicle detects The payment process can only be triggered after the recognized license plate information is bound. In this way, setting verification measures before parking fee payment can prevent users from failing to pay parking fees or paying parking fees incorrectly, which not only ensures user account security but also improves users' payment experience.
  • the first image information further includes a second payment code
  • the first payment code corresponds to the first payment platform
  • the second payment code corresponds to the second payment platform
  • the use of the first payment code Paying the parking fee to be paid with the user's account includes: using the first payment platform when the frequency of payment by the first user using the first payment platform is greater than the frequency of payment by using the second payment platform. The platform pays the parking fees to be paid.
  • the vehicle can recommend the optimal payment method to the user based on the user's payment habits.
  • the user can complete the payment of the parking fee through the recommended payment method. In this way, the payment of the parking fee can be completed more conveniently. , and can effectively improve the user's payment experience.
  • the method before acquiring the first image information through the first camera device, the method further includes: acquiring third image information through the first camera device, and the third image information is The first pixel ratio is greater than the first threshold; adjusting the brightness of the vehicle light to the first brightness according to the first pixel ratio; obtaining the first image information through the first camera device includes: The first image information is acquired through the first camera device under the first brightness.
  • the first pixel ratio may be a low pixel ratio, and its range may be preset.
  • the pixel value of an image ranges from 0 to 255, with 0 pixels representing the darkest image and 255 pixels representing the brightest image. You can preset 0 to 40 as the low pixel range.
  • the first pixel proportion may be the ratio of the average frequency of 0 to 40 pixels and the average value of the frequency of 0 to 255 pixels.
  • the specific value of the first threshold can be preset according to the actual situation. If the performance of the QR code recognition device is good, the first threshold can be set higher. If the performance of the QR code recognition device is poor, the first threshold can be set higher. The threshold is set lower.
  • different processes are performed by determining the relationship between the first pixel ratio and the first threshold in the image captured by the camera device.
  • the proportion of low-brightness low pixels is greater than the first threshold, the vehicle's lights are used to fill in the QR code.
  • additional fill-in equipment for example, parking lot lights
  • the first camera device is a driving recorder or a surround-view camera
  • the second camera device is a depth camera
  • Figure 10 is a schematic flow chart of another payment method provided by this application.
  • the payment method in Figure 10 can be applied to the vehicle 100 in Figure 1 .
  • the method can include the following steps.
  • the QR code scanning interface A can be displayed on the vehicle's display screen.
  • the DVR deployed outside the vehicle can collect the first image information in front of the vehicle. For example, if there is a QR code for parking payment in front of the vehicle, a DVR can be used to take a picture of the QR code in this step.
  • step S1002 after using a DVR to take a picture of the QR code in front of the vehicle, the vehicle can obtain a YUV photo of the QR code.
  • the high-definition full-frame photos can be obtained by the user actively triggering the DVR 310 to take pictures, or by the CDC 320 controlling the interception of a certain frame of image in the YUV video.
  • the QR code scanning result interface is displayed on the vehicle's display screen, and the QR code scanning interface A is closed.
  • step S1006 it is determined whether the YUV photo obtained in step S1004 has low illumination. If this situation exists, step S1006 needs to be performed. If this situation does not exist, step S1007 can be performed directly.
  • the low illumination of a photo can mean that the physical environment surrounding the object being photographed is poorly illuminated when taking the photo, which results in a lower brightness of the photo taken.
  • vehicle lights can be used to perform fill light processing on the photo in this step.
  • the QR code in the YUV photo is detected.
  • step S1011 determine whether the QR code in the YUV photo has low resolution. If this situation exists, the low-resolution QR code needs to be processed to improve its resolution. If this situation does not exist, you can Proceed directly to step S1011.
  • the image super-resolution algorithm can be used to improve the resolution of the QR code and obtain a high-definition QR code.
  • the image super-resolution algorithm can take advantage of the similarity in high-frequency details of different images, obtain the relationship between high-resolution and low-resolution images through a learning algorithm, and guide the reconstruction of high-resolution images.
  • the high-definition QR code obtained in step S1009 is output to the QR code scanning and identification module 324 in the vehicle for processing.
  • the QR code scanning and identification module 324 in the vehicle identifies the obtained QR code.
  • the CDC 320 in the vehicle can perform different processing by judging the number of recognized QR codes. If it is determined that no valid QR code is recognized, step S1013 and step S1017 are performed. If it is determined that a valid QR code is recognized, step S1015 to step S1017 will be directly performed. If it is determined that more than two valid QR codes are recognized, step S1014 to step S1017 are performed.
  • the vehicle can display a prompt message on the vehicle's display screen to inform the user that there is no valid QR code.
  • the vehicle can inform the vehicle that there is no valid QR code through a voice message through the on-board speaker.
  • step S1012 when it is determined that the number of recognized QR codes is more than two, the vehicle sends a prompt message to the user, prompting the user to actively select one of the recognized QR codes on the page of the vehicle's display.
  • the parking fee payment page is displayed.
  • a payment page as shown in (c) in FIG. 4 is displayed on the display screen of the vehicle.
  • S1016 Call the face recognition function to compare the recognized face information with multiple face information preset by the vehicle.
  • the CDC 320 in the vehicle calls the face payment module 325 to identify the user's face to obtain the face information, and compares it with multiple preset face information of the vehicle. If the recognized face information is consistent with multiple preset face information, When one face information in the face information is consistent, steps S1019 to S1020 are performed. If the recognized face information is inconsistent with multiple preset face information, steps S1017 to S1020 are performed.
  • CDC 320 when CDC 320 determines that the recognized face information is inconsistent with the preset face information in the vehicle system, it can query whether other accounts preset in the vehicle with the recognized face information are related. If there is association, proceed to step S1018.
  • CDC 320 can automatically log in to the account associated with the recognized face information and complete face verification.
  • the corresponding parking fee is paid.
  • the first image information in front of the vehicle is obtained through the DVR, and the QR code in the image information is scanned and recognized so that the user knows the parking fee that needs to be paid, thereby calling the vehicle's face recognition payment function to complete the payment.
  • the risk of wrong or stolen deductions to the user's account can be reduced, and the user's payment experience can be improved.
  • Figure 11 is a schematic flow chart of a surround-view camera QR code adaptive recognition method provided by this application. This method can be applied to the vehicle 100 in Figure 1 . The method can include the following steps.
  • multiple video streams are obtained through the 360-degree surround view system on the vehicle, that is, video stream data is collected through cameras distributed in all directions of the vehicle.
  • the 360 surround view system allows the system on the vehicle to collect images around the vehicle at the same time. After processing by the intelligent algorithm of the image processing unit, a panoramic top view of the surroundings of the vehicle is finally formed and displayed on the screen, intuitively showing the location of the vehicle. and surrounding conditions.
  • the algorithm model is used to detect whether there is QR code information in the multi-channel video stream. If there is QR code information, step S1103 is performed.
  • the model for detecting QR codes can be a deep learning model. For example, convolutional neural network CNN model, recurrent neural network RNN model, deep belief network (deep belief network, DBN) model, etc.
  • determine the camera where the QR code information is located For example, by detecting the video stream, it is found that the QR code information is obtained through the vehicle's front-view camera. At this time, it is determined that the camera where the QR code is located is the vehicle's front-view camera.
  • the camera can be used to detect the position of the QR code, where the actual position of the center point of the detected QR code can be on the two-dimensional plane. Expressed by coordinates (x, y).
  • the position of the camera can be adaptively adjusted according to the position of the QR code.
  • the purpose of the adjustment is to keep the center of the QR code in the middle of the camera and avoid the influence of image distortion of the QR code.
  • the purpose of the adaptive adjustment may be to calculate the corresponding motor control signal using the obtained position difference and speed difference of the camera moving from the initial position to the target position, and control the movement of the camera motor position according to the motor control signal.
  • the specific adjustment method can be implemented through steps S1106 to S1108.
  • the coordinates (X, Y) of the preset target image center point on the two-dimensional plane are obtained.
  • the target image center point may refer to the center point of the first image information.
  • S1107 Calculate the difference between the actual position of the center point of the QR code and the position of the center point of the target image.
  • step S1107 After the difference between the actual position of the center point of the QR code and the position of the center point of the target image is calculated through step S1107, the difference is used to output the corresponding camera in the x direction using a proportion-integration-differentiation (PID) adjustment algorithm. and y-direction motion signals. CDC 320 uses this control signal to control the movement of the camera, causing the center area of the QR code to approach and reach the preset target image center area.
  • PID proportion-integration-differentiation
  • step 1108 the position of the center point of the QR code is detected again to determine whether the center area of the QR code is close to and reaches the preset target image center area.
  • CDC320 controls to turn on the recognition function of the QR code and recognize the QR code.
  • the difference between the two positions can be calculated based on the actual position of the QR code in the camera screen and the center position of the target image, and the camera position can be adjusted through PID control based on the difference, so that the QR code always remains At the center of the image information, in this way, the imaging distortion rate of the QR code can be effectively reduced and the recognition rate of the QR code can be enhanced.
  • Figure 12 is a schematic flow chart provided by this application for realizing QR code center detection through PID control of the camera motor.
  • the method of controlling the camera motor in FIG. 12 can be applied to steps S1106 to S1108 in FIG. 11 .
  • the target position 1201 may be the center position coordinates (X, Y) of the target image.
  • the target ring 1202 can adjust the target position to a target speed, which can be the speed at which the motor-controlled camera moves to the center of the target image determined based on the target position.
  • the speed loop 1203 can adjust the target speed to the input voltage of the motor.
  • the motor 1204 can control the position of the camera according to the input voltage.
  • the actual speed 1205 may be the actual speed at which the motor-controlled camera moves to the center of the QR code determined based on the actual position
  • the actual position 1206 may be the actual position coordinates (x, y) of the QR code.
  • the target position 1201 and the actual position 1206 are compared to obtain the position error, and the position error is used as the input of the target ring 1202 to obtain the target speed. Compare the target speed with the actual speed 1206 to get the speed error. Input the speed error into the position loop to obtain the voltage required by the motor to control the camera to move to the center of the QR code. Finally, the voltage is input into the motor to control the camera to move to the center of the QR code.
  • the position of the camera is adjusted through PID control so that the QR code is always kept in the middle position of the camera. In this way, the imaging distortion rate of the QR code can be effectively reduced and the recognition rate of the QR code can be enhanced. .
  • Figure 13 is a schematic flow chart of a low-resolution QR code recognition method provided by this application.
  • the method in Figure 13 can be applied to the vehicle 100 in Figure 1 .
  • the method can include the following steps.
  • the video stream data of the image to be recognized is collected through the camera.
  • the camera can refer to the 360 surround view system on the vehicle or the vehicle DVR.
  • the CDC 320 in the vehicle performs QR code detection on the collected video stream data
  • the QR code detection model can be a deep learning model.
  • convolutional neural network model For example, convolutional neural network model, recurrent neural network model, deep belief network model, etc.
  • the CDC 320 in the vehicle can calculate the resolution of the QR code pattern, and compare the calculated resolution of the QR code with the preset threshold. If the resolution of the QR code is greater than the preset threshold, it means that the QR code is If the resolution meets the recognition requirements, the QR code will be output to the QR code recognition algorithm. If the resolution of the QR code is less than the preset threshold, it means that the resolution of the QR code is too low and step S1304 needs to be performed.
  • the value of the preset threshold can be determined according to the function of the QR code recognition algorithm. If the QR code recognition algorithm has high resolution requirements in actual applications, the value of the preset threshold can be set to a relatively large value. If the QR code recognition algorithm does not have high resolution requirements in actual applications, the preset threshold value can be set to a relatively small value.
  • the image super-resolution algorithm in Figure 14 can be used to enhance the resolution of the QR code.
  • a high-definition QR code with improved resolution can be obtained.
  • the image super-resolution algorithm can be divided into a normal feature extraction layer (Normal Part) and an upsampling part (Upsampling Part) in terms of network structure.
  • Each layer of the normal feature extraction layer can be connected through dense connections (Dense Concat) and depth convolution. (Depthwise Convolution) and other technologies improve performance to better extract features from QR codes.
  • Each layer of the upsampling layer improves performance through technologies such as inverse convolution (Deconvolution) and residual learning (Residual Learning), thereby increasing the resolution of the QR code.
  • L 2 can be the norm loss function, which can also be called the least square error, which can minimize the sum of squares of the difference between the target value and the estimated value.
  • L 1 can be a norm loss function, which can also be called the minimum absolute value deviation, which can minimize the sum of the differences between the target value and the estimated value.
  • the basic principle of increasing the binary constraint loss to improve the performance of the objective function is that considering that the QR code is essentially a code of 0 (black) and 1 (white); cross-entropy loss can be introduced in the optimization problem of recovering the QR code function to prompt the model to optimize the possibility that the area is black or white during the learning process; if the possibility of white is higher, the colors of nearby small areas will be unified into the same color to reduce the impact of noise; where the binary value
  • the constrained (cross-entropy) loss function can be:
  • the high-definition QR code obtained in step S1304 is input to the QR code scanning and identification module 324 for processing.
  • the image super-resolution algorithm is used to enhance the low-resolution QR code, which can enhance the resolution and image quality of the QR code, and can effectively enhance the recognition rate of the QR code.
  • Figure 15 is a method of filling light for QR codes under low illumination provided by this application.
  • the method in Figure 15 can be applied to the vehicle 100 in Figure 1 .
  • the method can include the following steps.
  • the video stream data of the image to be recognized is collected through the camera.
  • the camera can refer to the 360 surround view system on the vehicle or the vehicle DVR.
  • the algorithm histogram can describe the distribution of the brightness of the image, and can more intuitively display the proportion of each brightness level in the image.
  • the abscissa of the histogram can be the pixel value (from 0 to 255), where 0 pixel represents the darkest image, 255 pixels represents the brightest image, and the ordinate can be the pixel value. frequency of occurrence.
  • the proportion of low-brightness pixels in the image to the overall image pixels is calculated based on the data in the histogram.
  • 0 to 40 can be preset as the low pixel range.
  • the low pixel ratio may be the ratio of the average frequency of 0 to 40 pixels and the average frequency of 0 to 255 pixels.
  • step S1505 can be performed. If the proportion of low-brightness pixels is greater than the first threshold, steps S1506 to S1507 can be performed.
  • the specific value of the first threshold can be preset according to the actual situation. If the performance of the QR code recognition device is good, the first threshold can be set higher. If the performance of the QR code recognition device is poor, the first threshold can be set higher. Set the first threshold lower.
  • the QR code scanning and recognition module 324 identifies the QR code with normal brightness, and then jumps to the corresponding parking fee display interface.
  • a mapping relationship between the proportion of low pixels and the vehicle light intensity parameter can be established.
  • the mapping relationship can be a linear mapping relationship.
  • the intensity parameters of the car light may include: power, current, voltage, luminous flux, illumination, etc.
  • the vehicle can control the brightness of the vehicle lights according to the intensity parameters of the vehicle lights to supplement the light for the QR code. After the fill light is completed, steps S1501 to S1504 can be repeated until the proportion of low-brightness pixels in the re-recognized QR code image is less than or equal to the first threshold.
  • different processes are performed by determining the relationship between the proportion of low pixels in the QR code image and the first threshold.
  • the proportion of low-brightness low pixels is greater than the first threshold, the vehicle's lights are used to fill in the QR code.
  • additional fill-in equipment for example, parking lot lights
  • Figure 17 is an interactive method for multiple QR code selection and payment provided by this application. This method can be applied to the vehicle 100 in Figure 1 . The method can include the following steps.
  • the video stream data of the image to be recognized is collected through the camera.
  • the camera can refer to the 360 surround view system on the vehicle or the vehicle DVR.
  • the CDC 320 in the vehicle performs QR code detection on the collected video stream data
  • the QR code detection model can be a deep learning model.
  • convolutional neural network model For example, convolutional neural network model, recurrent neural network model, deep belief network model, etc.
  • step S1704 it is determined whether there is a QR code in the video stream data. If it exists, step S1704 is performed. If it does not exist, step S1701 is performed again.
  • step S1706 jump to the payment platform corresponding to step S1705 to initiate payment.
  • step S1709 it is determined whether there is a default platform for the user account. If there is a default platform, step S1709 is performed. If there is no default platform, steps S1710 to S1712 are performed.
  • CDC 320 controls the jump to a third-party payment platform to pay the parking fee.
  • step S1708 it is determined that there is no user's default platform, and the CDC 320 controls the identification of the third-party payment platform.
  • the vehicle finds that the user uses the first payment platform 10 times, the second payment platform 5 times, and the third payment platform 3 times, then the vehicle can It is determined that the first payment platform has a higher priority than the second payment platform and the third payment platform, and when the user needs to pay parking fees, it is recommended to the user to use the first payment platform for payment.
  • the optimal payment method can be recommended to the user according to the user's payment habits.
  • the user can complete the payment of the parking fee through the recommended payment method. In this way, the payment of the parking fee can be completed more conveniently. And can effectively improve the user's payment experience.
  • Figure 18 is a schematic flow chart of a parking lot scan code payment method provided by this application. This method can be applied to the vehicle 100 in Figure 1 . The method can include the following steps.
  • the video stream data of the image to be recognized is collected through the camera.
  • the camera can refer to the 360 surround view system on the vehicle or the vehicle DVR.
  • the CDC 320 in the vehicle performs QR code detection on the collected video stream data
  • the QR code detection model can be a deep learning model.
  • convolutional neural network model For example, convolutional neural network model, recurrent neural network model, deep belief network model, etc.
  • steps S1804 to S1814 will be performed. If it is determined that the recognized QR code is not a payment QR code, the payment process will be exited.
  • the license plate information for which parking fees need to be paid can be queried.
  • step S1807 if the license plate information identified through the payment QR code is consistent with the license plate information bound to the account, proceed to step S1807; if the license plate information identified through the payment QR code is inconsistent with the license plate information bound to the account, proceed to step S1808 to S1814.
  • the license plate information recognized by the payment QR code may be inconsistent with the license plate information bound to the account due to various circumstances.
  • the user has not bound the payment account to the license plate in advance.
  • the user binds the payment account to the license plate in advance, but the bound license plate number is different from the license plate number information identified through the QR code.
  • step S1806 if it is determined that the license plate information in the payment QR code is consistent with the license plate information bound to the account, then in this step, CDC 320 can call the vehicle's built-in camera to complete the parking fee through face recognition. payment. Alternatively, CDC 320 can jump to the corresponding payment page on the vehicle display screen, and the user can manually enter the account number and password for payment.
  • delivering the voice information to the user may be by broadcasting the voice information to the user through a vehicle-mounted voice assistant.
  • the user takes the initiative to confirm whether the license plate information in the payment QR code is consistent with the license plate information bound to the account. If there is an error, proceed to steps S1813 and S1814. If correct, proceed to steps S1810 to S1814.
  • the specific way for the user to confirm may be that the user clicks on the interactive interface on the vehicle display screen to confirm, or sends a voice message to the vehicle voice assistant for confirmation.
  • step S1809 the user actively confirms that the license plate information in the payment QR code is consistent with the license plate information bound to the account. In this step, it is judged whether to enter a new license plate. If it is judged not to enter a new license plate, proceed to step S1814. If it is judged that a new license plate needs to be entered, proceed to steps S1811, S1812 and S1814.
  • users can operate through the human-computer interaction interface on the vehicle display screen to bind the license plate information recognized through the QR code with the user's payment account.
  • CDC 320 can call the vehicle's built-in camera to complete the payment of parking fees through face recognition and other non-inductive payment methods.
  • CDC 320 can jump to the corresponding payment page on the vehicle display screen, and the user can manually enter the account number and password for payment.
  • users can actively enter their account number and password on the vehicle's display screen to make payment.
  • the vehicle can notify the user to process it. In this way, the vehicle can notify the user when the recognized license plate information is incorrect or the license plate information does not exist. Intervention can effectively improve the accuracy of user payment.
  • Embodiments of the present application also provide a device for implementing any of the above methods.
  • a device is provided that includes units (or means) for implementing each step performed by the device or vehicle in any of the above methods.
  • Figure 19 is a schematic diagram of the payment device 1900 provided by the embodiment of the present application.
  • the device 1900 may be implemented in the vehicle 100 of FIG. 1 .
  • the device 1900 may include a detection unit 1910, an acquisition unit 1920 and a processing unit 1930.
  • the detection unit 1910 is used to detect the environment outside the vehicle.
  • the acquisition unit 1920 can implement corresponding communication functions.
  • the acquisition unit 1920 can also be called a communication interface or a communication unit for acquiring data.
  • the processing unit 1930 is used for data processing.
  • the processing unit 1930 can read the instructions and/or data in the storage unit, so that the device implements the foregoing method embodiments.
  • the device 1900 also includes a storage unit for storing corresponding instructions and/or data,
  • the device 1900 includes: a detection unit 1910, used to detect that a vehicle enters or leaves the parking lot; an acquisition unit 1920, used to acquire the first image information through the first camera device, the first The image information is image information outside the vehicle, and the first image information includes a first payment code; the processing unit 1930 is used to identify the first payment code and obtain the parking fee to be paid for the vehicle; the acquisition Unit 1920 is also configured to obtain the user's first biometric information through a second camera device, which is a camera device that acquires images of the interior of the vehicle; between the first biometric information and the second biometric information If the information matches, the processing unit 1930 is also configured to use the first user's account to pay the parking fee to be paid, and the second biometric information is preset by the first user in the vehicle. biometric information, and the user includes the first user.
  • the processing Unit 1930 is also configured to use the second user's account to pay the parking fee to be paid.
  • the third biometric information is the biometric information preset by the second user in the vehicle. The user includes the second user.
  • the acquisition unit 1920 is further configured to acquire second image information through the first camera; the acquisition unit 1920 is specifically configured to obtain the second image information when the second image information cannot be identified.
  • the first image information is acquired through the first camera device.
  • the second image information includes the first payment code
  • the processing unit 1930 is further configured to calculate the first payment code according to the position coordinates of the first payment code in the second image and the The center position coordinates of the second image information are used to determine the control parameters of the first camera device; the processing unit 1930 is also used to control the first camera device to obtain the first image information according to the control parameters, The first payment code is at the center of the first image information.
  • the obtaining unit 1920 is also used to obtain the first license plate information, where the first license plate information is the license plate information of the vehicle; the processing unit 1930 is specifically used to obtain the first license plate information in the vehicle.
  • the first license plate information is consistent with the second license plate information, use the first user's account to pay the parking fee to be paid, and the second license plate information is the license plate information bound to the first user account.
  • the obtaining unit 1920 is also used to obtain the first license plate information, where the first license plate information is the license plate information of the vehicle; the processing unit 1930 is also used to obtain the first license plate information in the vehicle.
  • the first license plate information is inconsistent with the second license plate information, the first user is prompted that the first license plate information is not bound to the first user account, and the second license plate information is not bound to the first user account.
  • the license plate information bound to the account; the processing unit 1930 is specifically configured to pay the parking fee to be paid when it is detected that the first user binds the first license plate information to the first user's account. cost.
  • the first image information also includes a second payment code
  • the first payment code corresponds to the first payment platform
  • the second payment code corresponds to the second payment platform
  • the processing unit 1930 specifically used to use the first payment platform to pay the parking fee to be paid when the frequency of payment by the first user using the first payment platform is greater than the frequency of payment by using the second payment platform.
  • the acquisition unit 1920 is further configured to acquire third image information through the first camera device, where the first pixel proportion in the third image information is greater than a first threshold;
  • the processing unit 1930 is further configured to adjust the brightness of the vehicle light to a first brightness according to the first pixel ratio; the processing unit 1930 is specifically configured to pass the first brightness under the first brightness.
  • the camera acquires the first image information.
  • the first camera device is a driving recorder or a surround-view camera
  • the second camera device is a depth camera
  • the device 1900 includes: an acquisition unit 1920, used to acquire the parking fee to be paid by the vehicle; the acquisition unit 1920 is also used to acquire the user's first biometric information; a processing unit 1930, using In the case where the first biometric information does not match the second biometric information, and the first biometric information matches the third biometric information, the second user's account is used to pay the to-be-received fee. Paid parking fees.
  • the second biometric information is the biometric information preset by the first user in the vehicle
  • the third biometric information is the biometric information preset by the second user in the vehicle.
  • Users include the first user and the second user.
  • each unit in the above device is only a division of logical functions.
  • the units may be fully or partially integrated into a physical entity, or may be physically separated.
  • the unit in the device can be implemented in the form of a processor calling software; for example, the device includes a processor, the processor is connected to a memory, instructions are stored in the memory, and the processor calls the instructions stored in the memory to implement any of the above methods.
  • the processor is, for example, a general-purpose processor, such as a graphics processing unit (GPU) or a microprocessor
  • the memory is a memory within the device or a memory outside the device.
  • the units in the device can be implemented in the form of hardware circuits, and some or all of the functions of the units can be implemented through the design of the hardware circuits, which can be understood as one or more processors; for example, in one implementation,
  • the hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units through the design of the logical relationships of the components in the circuit; for another example, in another implementation, the hardware circuit is It can be realized by programmable logic device (PLD), taking field programmable gate array (FPGA) as an example, which can include a large number of logic gate circuits, and the logic gate circuits are configured through configuration files. connection relationships, thereby realizing the functions of some or all of the above units. All units of the above device may be fully realized by the processor calling software, or may be fully realized by hardware circuits, or part of the units may be realized by the processor calling software, and the remaining part may be realized by hardware circuits.
  • PLD programmable logic device
  • FPGA field programmable gate
  • the processing unit 1930 may be the processor 131 shown in FIG. 1 .
  • the above-mentioned processing unit 1930 may be the processor 2020 in FIG. 20
  • the above-mentioned storage unit may be the memory 2010 in FIG. 20
  • the above-mentioned acquisition unit 1920 may be the communication interface 2030 in FIG. 20 .
  • Figure 20 is a schematic diagram of a payment device 2000 provided by an embodiment of the present application.
  • the device 2000 may be applied in the vehicle 100 of FIG. 1 .
  • the payment device 2000 includes: a memory 2010, a processor 2020, and a communication interface 2030.
  • the memory 2010, the processor 2020, and the communication interface 2030 are connected through an internal connection path.
  • the memory 2010 is used to store instructions
  • the processor 2020 is used to execute the instructions stored in the memory 2020 to control the input/output interface 2030 to receive/send. at least some parameters of the second channel model.
  • the memory 2010 can be coupled with the processor 2020 through an interface, or can be integrated with the processor 2020 .
  • the above-mentioned communication interface 2030 uses a transceiver device such as but not limited to a transceiver to implement communication between the communication device 1000 and other devices or communication networks.
  • the above-mentioned communication interface 2030 may also include an input/output interface.
  • Processor 2020 stores one or more computer programs including instructions. When the instruction is executed by the processor 2020, the payment device 2000 is caused to execute the technical solutions of the payment methods in the above embodiments.
  • the device 1900 or the device 2000 may be located in the vehicle 100 in FIG. 1 .
  • the device 1900 or the device 2000 may be the computing platform 130 in the vehicle in FIG. 1 .
  • each step of the above method can be completed by instructions in the form of hardware integrated logic circuits or software in the processor 2020 .
  • the method disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory 2010.
  • the processor 2020 reads the information in the memory 2010 and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.
  • Embodiments of the present application also provide a computer-readable medium.
  • the computer-readable medium stores program code.
  • the computer program code When the computer program code is run on a computer, it causes the computer to execute any of the above-mentioned Figures 9 to 18. a way.
  • An embodiment of the present application also provides a chip, including: at least one processor and a memory.
  • the at least one processor is coupled to the memory and is used to read and execute instructions in the memory to execute the above-mentioned Figures 9 to 9. Either method in Figure 18.
  • An embodiment of the present application also provides an intelligent vehicle, including: at least one processor and a memory.
  • the at least one processor is coupled to the memory and is used to read and execute instructions in the memory to execute the above-mentioned Figure 9 to any method in Figure 18.
  • An embodiment of the present application also provides an intelligent vehicle, including any payment device shown in Figure 19 or Figure 20 .
  • the processor is a circuit with signal processing capabilities.
  • the processor may be a circuit with instruction reading and execution capabilities, such as a CPU, a microprocessor, a GPU, or Digital signal processor (DSP), etc.; in another implementation, the processor can implement certain functions through the logical relationship of the hardware circuit. The logical relationship of the hardware circuit is fixed or can be reconstructed, such as processing
  • the controller is a hardware circuit implemented by ASIC or PLD, such as FPGA.
  • the process of the processor loading the configuration file and realizing the hardware circuit configuration can be understood as the process of the processor loading instructions to realize the functions of some or all of the above units.
  • it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning Processing unit (deep learning processing unit, DPU), etc.
  • NPU neural network processing unit
  • TPU tensor processing unit
  • DPU deep learning processing unit
  • each step of the above method can be completed by instructions in the form of hardware integrated logic circuits or software in the processor.
  • the method disclosed in conjunction with the embodiments of the present application can be directly implemented by a hardware processor for execution, or can be executed by a combination of hardware and software modules in the processor.
  • the software module can be located in random access memory, flash memory, read-only memory, programmable read-only memory or power-on erasable programmable memory, registers and other mature storage media in this field.
  • the storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.
  • the memory may include a read-only memory and a random access memory, and provide instructions and data to the processor.
  • the size of the sequence numbers of the above-mentioned processes does not mean the order of execution.
  • the execution order of each process should be determined by its functions and internal logic, and should not be implemented in this application.
  • the implementation of the examples does not constitute any limitations.
  • a component may be, but is not limited to, a process, a processor, an object, an executable file, a thread of execution, a program and/or a computer running on a processor.
  • applications running on the computing device and the computing device may be components.
  • One or more components can reside in a process and/or thread of execution and a component can be localized on one computer and/or distributed between 2 or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon.
  • a component may, for example, be based on a signal having one or more data packets (eg, data from two components interacting with another component, a local system, a distributed system, and/or a network, such as the Internet, which interacts with other systems via signals) Communicate through local and/or remote processes.
  • data packets eg, data from two components interacting with another component, a local system, a distributed system, and/or a network, such as the Internet, which interacts with other systems via signals
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code. .

Abstract

本申请实施例提供了一种支付方法、装置以及车辆,该方法包括:检测到车辆进入或驶离停车场;通过第一摄像装置获取第一图像信息,所述第一图像信息为所述车辆外部的图像信息,所述第一图像信息包括第一支付码;识别所述第一支付码,得到所述车辆待缴纳的停车费用;通过第二摄像装置获取用户的第一生物特征信息,所述第二摄像装置为获取所述车辆内部图像的摄像装置;在所述第一生物特征信息与第二生物特征信息匹配的情况下,使用第一用户的账户支付所述待缴纳的停车费用。通过这样的方式,能够避免因停车场系统出现错误导致的用户的账户被盗扣或者错扣等情况。

Description

支付方法、装置以及车辆
本申请要求于2022年5月30日提交中国专利局、申请号为202210600490.3、申请名称为“支付方法、装置以及车辆”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能车领域,并且更具体地,涉及一种支付方法、装置以及车辆。
背景技术
随着车辆在日常生活中被广泛应用,停车收费的现象普遍存在。当前,支付停车费的主要方式是现金支付、扫码支付以及无感支付(提前绑定车牌与支付账户)。其中,现金支付的方式用户体验最差,无感支付的方式用户体验最好。
然而,无感支付方式在使用的过程中,需要用户将车牌与支付账户进行绑定并签约代扣协议。在支付停车费时,停车场管理系统能够通过摄像头获取用户的身份信息,从而查询用户待支付的停车费,并使用用户预先绑定的账号进行支付。通过这样的方式,停车场系统可能出现用户的身份识别错误或者扣款错误情况,从导致用户的财产遭受损失。
发明内容
本申请实施例提供一种支付方法、装置以及车辆,能够避免因停车场系统出现错误导致的用户的账户被盗扣或者错扣等情况。
第一方面,提供一种支付方法,该方法包括:检测到车辆进入或驶离停车场;通过第一摄像装置获取第一图像信息,所述第一图像信息为所述车辆外部的图像信息,所述第一图像信息包括第一支付码;识别所述第一支付码,得到所述车辆待缴纳的停车费用;通过第二摄像装置获取用户的第一生物特征信息,所述第二摄像装置为获取所述车辆内部图像的摄像装置;在所述第一生物特征信息与第二生物特征信息匹配的情况下,使用第一用户的账户支付所述待缴纳的停车费用,所述第二生物特征信息为所述第一用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户。
其中,车辆检测到进入或驶离停车场可以采用多种方式。
一种可能的实现方式中,车辆可以通过部署在车辆上的全球导航卫星系统(global navigation satellite system,GNSS)传感器来获取车辆的定位和信号强度,从而判断车辆是否进入或驶离停车场。
例如,GNSS传感器检测到车辆的位置在某个停车场附近,并且车辆进行通信的信号强度小于或等于第一阈值时,GNSS传感器可以向车辆的座舱控制器发送第一指示信息,告知车辆进入停车场。同样的,GNSS传感器检测到车辆的位置在某个停车场附近,并且车辆进行通信的信号强度大于第二阈值时,GNSS传感器可以向车辆的座舱控制器发送第 二指示信息,告知车辆驶离停车场。又例如,GNSS传感器检测到车辆进行通信的信号良好,车辆的位置在停车场的边缘或者进出口位置时,GNSS传感器可以向座舱控制器320发送第三指示信息,告知车辆正在进入或驶离停车场。
一种可能的实现方式中,可以通过视觉识别的方法来判断出车辆是否进入或驶离停车场。例如,车辆可以通过第一摄像装置采集车辆外部的图像信息,并且将采集的图像细分为多个特征区域,对每个特征区域与识别标的物(例如,停车场标志、停车杆)进行匹配,并计算匹配概率,在匹配概率大于或小于预设阈值时,可以判断出车辆正在进入或驶离停车场。
一种可能的实现方式中,可以在停车场入口或出口处设置无线信号发射装置,在车辆接收到无线信号发射装置发射的无线信号后,可以判断出车辆正在进入或驶离停车场。
其中,第一摄像装置可以是部署在车辆外部的摄像头,例如AVM环视摄像头或者DVR摄像头等。第一支付码可以是二维码、条形码等具备支付功能的支付码。
车辆通过第一摄像装置获取第一图像信息也可以采用多种方式。
一种可能的实现方式中,当车辆检测到进入或驶离停车场时,车辆可以通过第一摄像装置,自动采集车辆周围的第一图像信息。
一种可能的实现方式中,当用户驾驶车辆进入或驶离停车场的过程中,发现车辆周围设有停车支付码。此时,用户可以主动触发第一摄像装置进行拍照获取第一图像信息,如果第一摄像装置是行车记录仪,获取第一图像信息的方式也可以是截取行车记录仪记录的视频中的某一帧图像。
其中,第二摄像装置可以是具备支付认证能力的深度摄像头,例如,3D(time of flight,TOF)摄像头或者3D结构光摄像头等。第一生物特征信息可以是用户的面部特征信息。在第一生物特征信息与第一用户在车辆中预设的第二生物特征信息一致的情况下,使用第一用户的账户进行停车费的支付。
应理解,第一生物特征信息也可以是虹膜特征信息或者生物特征信息,如果第一生物特征信息为上述两种,在车辆上应当配置相应的虹膜识别设备或者声纹识别设备。
本申请实施例中,在检测到车辆进入或者驶离停车场的情况下,由车辆主动调用车第一摄像装置获取第一图像信息,并识别第一图像信息中的第一支付码来查询停车费,然后,通过调用第二摄像装置进行用户的身份信息验证,从而完成停车费的支付。通过这样的方式,整个扫码支付的过程都由车辆执行,能够避免因停车场系统出现错误导致的用户的账户被盗扣或者错扣等情况。
结合第一方面,在第一方面的某些实现方式中,该方法还包括:在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,使用第二用户的账户支付所述待缴纳的停车费用,所述第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第二用户。
本申请实施例中,在使用第一生物特征信息与第二生物特征信息验证失败时,车辆能够查询识别的第一生物特征信息是否与第二用户的第三生物特征信息相关联,在相关联的情况下,使用第二用户的账户完成停车费的支付。通过这样的方式,能够为车内的多个用户提供停车费支付的服务,避免了生物特征信息验证失败后需要用户手动登录账户并输入密码完成支付的情况,提高了支付的效率。
结合第一方面,在第一方面的某些实现方式中,在所述通过所述第一摄像装置获取第一图像信息之前,所述方法还包括:通过所述第一摄像装置获取第二图像信息;在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用的情况下,通过所述第一摄像装置获取所述第一图像信息。
其中,通过第二图像信息识别不出待缴纳的停车费用存在多种情况。
一种可能的实现方式中,由于车辆在整个扫码识别过程是移动的,第一摄像装置获取的支付码可能产生畸变,从而导致支付码的识别失败。在此种情况下,可以通过调节第一摄像装置的位置使得减少或避免第一图像信息中出现支付码的畸变情况。
一种可能的实现方式中,第一支付码可以位于第二图像信息的边缘位置,第一支付码在第二图像信息中显示不完整。这样,车辆可能因第一支付码的不完整而识别不出第一支付码上承载的信息。在此种情况下,可以通过调节第一摄像装置的位置获取第一图像信息使得第一支付码在第一图像信息中完整呈现。
本申请实施例中,车辆的扫描装置识别不出支付码时,可以调整支付码在图像信息中的位置,进而使支付码识别成功。通过这样的方式,能够增强支付码的识别率,提高用户的支付体验。
结合第一方面,在第一方面的某些实现方式中,所述第二图像信息包括所述第一支付码,所述在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用时,通过所述第一摄像装置获取所述第一图像信息,包括:根据所述第一支付码在所述第二图像中的位置坐标与所述第二图像信息的中心位置坐标,确定所述第一摄像装置的控制参数;根据所述控制参数控制所述第一摄像装置获取所述第一图像信息,所述第一支付码在所述第一图像信息的中心位置。
本申请实施例中,在通过第二图像信息识别不出支付码的情况下,通过调节第一摄像装置的位置获取第一图像信息使得第一支付码位于第一图像的中心位置。通过这样的方式,能够在支付码发生畸变的情况下,使得支付码始终保持在第一图像的中心位置,从而更好的识别第一支付码。
结合第一方面,在第一方面的某些实现方式中,在所述使用第一用户的账户支付所述待缴纳的停车费用之前,所述方法还包括:获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;其中,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:在所述第一车牌信息与第二车牌信息一致的情况下,使用所述第一用户的账户支付所述待缴纳的停车费用,所述第二车牌信息为与所述第一用户账户绑定的车牌信息。
此种实施方式在实际应用中,车辆上的处理器能够获取第一车牌信息,并将该第一车牌信息自动输入至第一支付码识别出的支付网站的车牌信息输入框中,并通过该网站检索停车场系统识别到的第二车牌信息与第一车牌信息是否一致,在一致的情况下才支付待缴纳的停车费。整个获取第一车牌信息、在支付网站上输入第一车牌信息和查询第二车牌信息的动作均由车辆执行。
本申请实施例中,在支付停车费之前,需要验证待缴费车辆的车牌与用户账户中绑定的车牌是否一致,在验证通过的情况下,才支付待缴纳的停车费用。通过这样的方式,在停车费支付前设置验证措施,能够进一步的提升停车费缴纳过程中的安全性。
结合第一方面,在第一方面的某些实现方式中,在所述使用第一用户的账户支付所述 待缴纳的停车费用之前,所述方法还包括:获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;在所述第一车牌信息与第二车牌信息不一致的情况下,向所述第一用户提示所述第一车牌信息未与所述第一用户账户绑定,所述第二车牌信息为与所述第一用户账户绑定的车牌信息;其中,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:在检测到所述第一用户将所述第一车牌信息与所述第一用户的账号绑定时,支付所述待缴纳的停车费用。
其中,在验证第一车牌信息和第二车牌信息不一致后,车辆可以通过多种方式提示用户绑定第一车牌。例如,车辆可以在车辆的显示屏上显示提示消息来告知用户第一车牌信息和第二车牌信息不一致。又例如,车辆可以通过车载扬声器用语音信息的方式告知用户第一车牌信息和第二车牌信息不一致。
第一车牌信息和第二车牌信息不一致也可以存在多种情况。例如,用户在账户中没有绑定任何车牌,此时,车辆可以向用户提示账户中尚未绑定车牌。又例如,用户已经在账户中绑定车牌,但是绑定的车牌和识别的车牌信息不一致,此时,车辆可以向用户提示绑定新识别的车牌或者拒绝支付。
本申请实施例中,在支付停车费之前,需要验证待缴费车辆的车牌与用户账户中绑定的车牌是否一致,如果验证不通过,车辆可以提示用户绑定识别的车牌信息,在车辆检测到识别的车牌信息被绑定后,才能触发支付流程。通过这样的方式,在停车费支付前设置验证措施,可以避免用户缴纳停车费失败或者错误缴纳停车费的情况,既保障了用户的账户安全,又提高了用户的支付体验。
结合第一方面,在第一方面的某些实现方式中,所述第一图像信息还包括第二支付码,所述第一支付码对应第一支付平台,所述第二支付码对应第二支付平台,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:在所述第一用户使用所述第一支付平台支付的频率大于使用所述第二支付平台支付的频率情况下,使用所述第一支付平台支付所述待缴纳的停车费用。
本申请实施例中,车辆能够根据用户的支付习惯,为用户推荐最优的支付方式,用户可以通过推荐的支付方式完成停车费的支付,通过这样的方式,能够更加便捷的完成停车费的支付,并能够有效的提升用户的支付体验。
结合第一方面,在第一方面的某些实现方式中,在通过所述第一摄像装置获取第一图像信息之前,所述方法还包括:通过所述第一摄像装置获取第三图像信息,所述第三图像信息中的第一像素占比大于第一阈值;根据所述第一像素占比,将所述车灯的亮度调整为第一亮度;所述通过所述第一摄像装置获取第一图像信息包括:在所述第一亮度下通过所述第一摄像装置获取所述第一图像信息。
其中,第一像素占比可以是低像素占比,其范围可以被预先设定。例如,图像的像素值在0至255区间,0像素表示图像最暗,255像素表示图像最亮。可以预先设定0至40为低像素范围。则此时第一像素占比可以是0至40像素出现的频率的平均值与0至255像素出现的频率的平均值的比值。
第一阈值的具体数值可以根据实际的情况进行预先设定,如果二维码识别设备性能较好可以将第一阈值设置的较高,如果二维码识别设备的性能较差,可以将第一阈值设置的较低。
本申请实施例中,通过判断摄像装置拍摄的图像中的第一像素占比与第一阈值的大小关系,进而进行不同的处理。当低亮度低像素占比大于第一阈值时,利用车辆的车灯对二维码进行补光,通过这样的方式,能够降低二维码图像对额外的补光设备(例如,停车场的灯光)的依赖性,有效增强低亮度二维码的识别率。
结合第一方面,在第一方面的某些实现方式中,所述第一摄像装置为行车记录仪或环视摄像头,所述第二摄像装置为深度摄像头。
第二方面,提供一种支付方法,该方法包括:获取车辆待缴纳的停车费用;获取用户的第一生物特征信息;在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,使用第二用户的账户支付所述待缴纳的停车费用。其中,所述第二生物特征信息为第一用户在所述车辆中预设的生物特征信息,第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户和所述第二用户。
本申请实施例中,能够为车内的多个用户提供停车费支付的服务,避免了验证失败后需要用户手动登录账户输入密码的情况,提高了支付的效率。
第三方面,提供了一种支付装置,该装置包括:检测单元,用于检测到车辆进入或驶离停车场;获取单元,用于通过第一摄像装置获取第一图像信息,所述第一图像信息为所述车辆外部的图像信息,所述第一图像信息包括第一支付码;处理单元,用于识别所述第一支付码,得到所述车辆待缴纳的停车费用;所述获取单元,还用于通过第二摄像装置获取用户的第一生物特征信息,所述第二摄像装置为获取所述车辆内部图像的摄像装置;在所述第一生物特征信息与第二生物特征信息匹配的情况下,所述处理单元,还用于使用第一用户的账户支付所述待缴纳的停车费用,所述第二生物特征信息为所述第一用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户。
结合第三方面,在第三方面的某些实现方式中,在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,所述处理单元,还用于使用第二用户的账户支付所述待缴纳的停车费用,所述第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第二用户。
结合第三方面,在第三方面的某些实现方式中,所述获取单元,还用于通过所述第一摄像装置获取第二图像信息;所述获取单元,具体用于在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用的情况下,通过所述第一摄像装置获取所述第一图像信息。
结合第三方面,在第三方面的某些实现方式中,所述第二图像信息包括所述第一支付码,所述处理单元,还用于根据所述第一支付码在所述第二图像中的位置坐标与所述第二图像信息的中心位置坐标,确定所述第一摄像装置的控制参数;所述处理单元,还用于根据所述控制参数控制所述第一摄像装置获取所述第一图像信息,所述第一支付码在所述第一图像信息的中心位置。
结合第三方面,在第三方面的某些实现方式中,所述获取单元,还用于获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;所述处理单元,具体用于在所述第一车牌信息与第二车牌信息一致的情况下,使用所述第一用户的账户支付所述待缴纳的停车费用,所述第二车牌信息为与所述第一用户账户绑定的车牌信息。
结合第三方面,在第三方面的某些实现方式中,所述获取单元,还用于获取第一车牌 信息,所述第一车牌信息为所述车辆的车牌信息;所述处理单元,还用于在所述第一车牌信息与第二车牌信息不一致的情况下,向所述第一用户提示所述第一车牌信息未与所述第一用户账户绑定,所述第二车牌信息为与所述第一用户账户绑定的车牌信息;所述处理单元,具体用于在检测到所述第一用户将所述第一车牌信息与所述第一用户的账号绑定时,支付所述待缴纳的停车费用。
结合第三方面,在第三方面的某些实现方式中,所述第一图像信息还包括第二支付码,所述第一支付码对应第一支付平台,所述第二支付码对应第二支付平台,所述处理单元,具体用于在所述第一用户使用所述第一支付平台支付的频率大于使用所述第二支付平台支付的频率情况下,使用所述第一支付平台支付所述待缴纳的停车费用。
结合第三方面,在第三方面的某些实现方式中,所述获取单元,还用于通过所述第一摄像装置获取第三图像信息,所述第三图像信息中的第一像素占比大于第一阈值;所述处理单元,还用于根据所述第一像素占比,将所述车灯的亮度调整为第一亮度;所述处理单元,具体用于在所述第一亮度下通过所述第一摄像装置获取所述第一图像信息。
结合第三方面,在第三方面的某些实现方式中,所述第一摄像装置为行车记录仪或环视摄像头,所述第二摄像装置为深度摄像头。
第四方面,提供一种支付装置,该装置包括:获取单元,用于获取车辆待缴纳的停车费用;所述获取单元,还用于获取用户的第一生物特征信息;处理单元,用于在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,使用第二用户的账户支付所述待缴纳的停车费用。其中,所述第二生物特征信息为第一用户在所述车辆中预设的生物特征信息,第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户和所述第二用户。
第五方面,提供一种支付装置,该装置包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,该装置用于执行上述各个方面中的方法。
第六方面,提供一种计算机可读介质,所述计算机可读介质存储有程序代码,当所述计算机程序代码在计算机上运行时,使得计算机执行上述各个方面中的方法。
第七方面,提供一种芯片,该芯片包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,该装置用于执行上述各个方面中的方法。
第八方面,提供一种车辆,该车辆包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,该装置用于执行上述各个方面中的方法。
本申请实施例提供的技术方案能够车辆检测到车辆进入或者驶离停车场的情况下,由车辆主动调用第一摄像装置获取第一图像信息,并识别第一图像信息中的第一支付码来查询停车费。然后,通过调用第二摄像装置获取第一生物特征信息进行用户身份信息的验证,从而完成停车费的支付。整个扫码支付的过程都由车辆执行,能够避免因停车场系统出现错误导致的用户的账户被盗扣或者错扣等情况。在通过第二图像信息识别不出支付码的情况下,通过调节第一摄像装置的位置使得第一支付码位于第一图像的中心位置。通过这样的方式,能够在支付码发生畸变的情况下,使得支付码始终保持在第一图像的中心位置, 更好的识别第一支付码。在使用第一生物特征信息与第二生物特征信息验证失败时,车辆能够查询识别的第一生物特征信息是否与第二用户的第三生物特征信息相关联,在相关联的情况下,使用第二用户的账户完成停车费的支付。能够为车内的多个用户提供停车费支付的服务,避免了生物特征信息验证失败后需要用户手动登录账户输入密码的情况,提高了支付的效率。
附图说明
图1是本申请实施例提供的车辆功能性示意图;
图2是本申请提供的不同停车费支付方式的效率和操作成本对比图。
图3是本申请提供的一种支付方法的系统架构图;
图4是本申请提供的支付方法的应用场景图;
图5是本申请提供的支付方法的另一应用场景图;
图6是本申请提供的支付方法的另一应用场景图;
图7是本申请提供的支付方法的另一应用场景图;
图8是本申请提供的支付方法的另一应用场景图;
图9是本申请提供的一种支付方法的示意性流程图;
图10是本申请提供的另一种支付方法的示意性流程图;
图11是本申请提供的一种环视摄像头二维码自适应识别方法的示意性流程图;
图12是本申请提供的一种通过PID控制摄像头电机实现二维码居中检测的示意性流程图;
图13是本申请提供的一种低分辨率二维码识别方法的示意性流程图;
图14是本申请提供的一种超分别率算法增强二维码分辨率的示意图;
图15是本申请提供的一种低照度下二维码补光的方法;
图16是本申请提供的补光前后图像的直方图;
图17是本申请提供的一种多二维码选择支付的交互方法;
图18是本申请提供的一种停车场扫码支付方法的示意性流程图;
图19是本申请提供的一种支付装置示意图;
图20是本申请提供的另一种支付装置示意图。
具体实施方式
下面将结合附图,对本申请中的技术方案进行描述。
为了便于理解,下文结合图1,以智能驾驶的场景为例,介绍本申请实施例适用的示例场景。
图1是本申请实施例提供的车辆100的一个功能性示意图。应理解,图1及相关描述仅为一种举例,并不对本申请实施例中的车辆进行限定。
在实施过程中,车辆100可以被配置为完全或部分自动驾驶模式,也可以由用户进行人工驾驶。例如:车辆100可以通过感知系统120获取其周围的环境信息,并基于对周边环境信息的分析得到自动驾驶策略以实现完全自动驾驶,或者将分析结果呈现给用户以实现部分自动驾驶。
车辆100可包括多种子系统,例如感知系统120、计算平台130和显示装置140。可选地,车辆100可包括更多或更少的子系统,并且每个子系统都可包括一个或多个部件。另外,车辆100的每个子系统和部件可以通过有线或者无线的方式实现互连。
感知系统120可包括感测关于车辆100周边的环境的信息的若干种传感器。例如,感知系统120可以包括定位系统,定位系统,定位系统可以是全球定位系统(global positioning system,GPS),也可以是北斗系统或者其他定位系统。感知系统120可以包括惯性测量单元(inertial measurement unit,IMU)、激光雷达、毫米波雷达、超声雷达以及摄像装置121中的一种或者多种。
摄像装置121可用于捕捉车辆100的周边环境的图像信息。摄像装置121可以包括单目相机、双目相机、结构光相机以及全景相机等,摄像装置121获取的图像信息可以包括静态图像信息,也可以包括视频流信息。其中,图像信息可以以图像或视频的形式存储,也可以以图像或视频的参数的形式存储,例如图像的亮度、灰度、色彩分布、对比度、像素等参数信息。
车辆100的部分或所有功能可以由计算平台130控制。计算平台130可包括处理器131至13n(n为正整数),处理器是一种具有信号的处理能力的电路,在一种实现中,处理器可以是具有指令读取与运行能力的电路,例如中央处理单元(central processing unit,CPU)、微处理器、图形处理器(graphics processing unit,GPU)(可以理解为一种微处理器)、或数字信号处理器(digital signal processor,DSP)等;在另一种实现中,处理器可以通过硬件电路的逻辑关系实现一定功能,该硬件电路的逻辑关系是固定的或可以重构的,例如处理器为专用集成电路(application-specific integrated circuit,ASIC)或可编程逻辑器件(programmable logic device,PLD)实现的硬件电路,例如FPGA。在可重构的硬件电路中,处理器加载配置文档,实现硬件电路配置的过程,可以理解为处理器加载指令,以实现以上部分或全部单元的功能的过程。此外,还可以是针对人工智能设计的硬件电路,其可以理解为一种ASIC,例如神经网络处理单元(neural network processing unit,NPU)、张量处理单元(tensor processing unit,TPU)、深度学习处理单元(deep learning processing unit,DPU)等。此外,计算平台130还可以包括存储器,存储器用于存储指令,处理器131至13n中的部分或全部处理器可以调用存储器中的指令,执行质量,以实现相应的功能。
计算平台130可基于从各种子系统(例如,感知系统120)接收的输入来控制车辆100的功能。在一些实施例中,计算平台130可操作来对车辆100及其子系统的许多方面提供控制。
可选地,上述组件只是一个示例,实际应用中,上述各个模块中的组件有可能根据实际需要增添或者删除,图1不应理解为对本申请实施例的限制。
在道路行进的自动驾驶车辆,如上面的车辆100,可以识别其周围环境内的物体以确定对当前速度的调整。所述物体可以是其它车辆、交通控制设备、或者其它类型的物体。在一些示例中,可以独立地考虑每个识别的物体,并且基于物体的各自的特性,诸如它的当前速度、加速度、与车辆的间距等,可以用来确定自动驾驶车辆所要调整的速度。
可选地,车辆100或者与车辆100相关联的感知和计算设备(例如,计算平台130)可以基于所识别的物体的特性和周围环境的状态(例如,交通、雨、道路上的冰、等等)来 预测所述识别的物体的行为。可选地,每一个所识别的物体都依赖于彼此的行为,因此还可以将所识别的所有物体全部一起考虑来预测单个识别的物体的行为。车辆100能够基于预测的所述识别的物体的行为来调整它的速度。换句话说,自动驾驶车辆能够基于所预测的物体的行为来确定车辆将需要调整到(例如,加速、减速、或者停止)什么稳定状态。在这个过程中,也可以考虑其它因素来确定车辆100的速度,诸如,车辆100在行驶的道路中的横向位置、道路的曲率、静态和动态物体的接近度等等。
除了提供调整自动驾驶车辆的速度的指令之外,计算设备还可以提供修改车辆100的转向角的指令,以使得自动驾驶车辆遵循给定的轨迹和/或维持与自动驾驶车辆附近的物体(例如,道路上的相邻车道中的轿车)的安全横向和纵向距离。
上述车辆100可以为轿车、卡车、摩托车、公共车辆、船、飞机、直升飞机、割草机、娱乐车、游乐场车辆、施工设备、电车、高尔夫球车、火车等,本申请实施例不做特别的限定。
随着车辆在日常生活中被广泛应用,停车收费的现象普遍存在。当前,支付停车费的主要方式是现金支付、扫码支付以及无感支付(提前绑定车牌与支付账户)。其中,扫码支付还包括离场时(离开停车场)主动扫码支付和离场时自动扫码支付。
图2是本申请提供的不同停车费支付方式的效率和操作成本对比图。
如图2所示,在几种支付方式的支付效率和操作成本比较的过程中可以发现,由于用户需要携带现金以及在支付过程中存在找零钱的情况,离场时现金支付的操作成本较高,离场的效率也最低。扫码支付虽然避免了用户携带现金以及找零钱的情况,但是用户需要操作手机进行扫码,离场的效率比现金支付高,操作的成本也比现金支付低。而无感支付只需提前将用户的车牌与支付账户进行绑定并签订代扣协议,用户驾驶车辆驶离停车场后,支付账户可以自动扣除停车费,无需用户进行任何操作。因此,无感支付在几种支付方式中,离场效率最高,操作成本最低。
但是,无感支付方式在实际应用的过程中,需要用户将车牌与支付账户进行绑定并签约代扣协议。在支付停车费时,停车场管理系统能够通过摄像头获取用户的身份信息,从而查询用户待支付的停车费,并使用用户预先绑定的账号进行支付。通过这样的方式,停车场系统可能出现用户的身份识别错误或者扣款错误情况,从而致使用户的财产遭受损失。此外,由于整个停车费的支付流程均由停车场管理系统掌控,用户的支付体验较差,信任成本较高。
本申请实施例提供一种支付方法、装置以及车辆,能够在支付停车费时,降低用户的账户存在被错扣或者盗扣等风险,提高用户的支付体验。
图3是本申请提供的一种支付方法的系统架构图,该系统架构300可应用于图1的车辆100中。
如图3所示,该系统架构可以由行车记录仪310(digital video recorder,DVR)和座舱域控制器320(cockpit domain controller,CDC)两个部分组成。DVR 310可以实时采集车辆前方的视频流数据或者采集车辆前方的图像信息,并把采集的数据发送给CDC 320处理。CDC 320是带有计算能力的平台,可以对DVR 310传来的视频流数据进行订阅管理、视频压缩、行车记录、二维码扫描识别、人脸支付等操作。其中,CDC 320中可以包括:视频流订阅管理模块321、视频压缩模块322、行车记录模块323、二维码扫描识别 模块324、人脸支付模块325。
应理解,该系统架构中以座舱域控制器320为示例进行说明,座舱域控制器320也可以替换成其他的控制器。
该支付方法的系统架构在实际应用过程中,车辆在检测到进入或驶离停车场时调用DVR 310自动获取一张全幅高清照片(luma-chroma,YUV),并把全幅高清照片经过视频流订阅管理模块321发送给二维码扫描识别模块324处理。二维码扫描识别模块324获取到该照片后,能够对该照片进行扫描识别。如果识别的结果表明,二维码上承载的信息为有效的支付链接,此时,CDC 320可以调用相关接口,控制车辆的显示屏界面跳转到支付界面,人脸支付模块325可以控制车辆内部的摄像头对用户进行人脸识别,验证成功后完成停车费的支付。
在二维码扫描识别模块324对二维码进行扫描识别的过程中,如果涉及获取到多个二维码,CDC 320可以向用户进行反馈,由用户在车辆的显示屏上主动点选需要的二维码。如果二维码扫描识别模块324的识别结果表明,扫描的二维码为网页二维码,CDC 320可以调用相关的H5容器,在车辆的显示屏上展示相应的网页信息,用户可以在网页上进行点选、输入等操作。
应理解,高清全幅照片的获取方式可以是由用户主动触发DVR 310进行拍照,也可以是CDC 320控制截取YUV视频中某一帧图像。
还应理解,行车记录仪310也可以替换成环视摄像头。
还应理解,本申请实施例中以二维码为例对查询和支付停车费的情况加以说明,二维码也可以替换成条形码等具备支付能力的支付码。
图4是本申请提供的支付方法的应用场景图。
如图4中的(a)所示,车辆位于停车场的停车位中。
如图4中的(b)所示,车辆位于停车位时,车辆的中控大屏显示显示界面400以及功能栏410。该显示界面400上包括用户账号登录信息401、蓝牙功能图标404、Wi-Fi功能图标403、蜂窝网络信号图标404、车载地图应用搜索框405、切换至显示车辆安装的所有应用程序的卡片406、切换至显示车载音乐应用的卡片407、车辆剩余电量以及剩余行驶里程的显示卡片408、车辆360度(°)环影功能的显示卡片409。其中,车载地图应用搜索框405中可以包括用户设置的回家控件4051和去公司控件4052。功能栏410中包括切换至显示中控大屏桌面的图标411、车辆内循环图标412、主驾座椅加热功能图标413,主驾区域空调温度显示图标414、副驾区域空调温度显示图标415、副驾座椅加热功能图标416以及音量设置图标417。
当车辆检测到进入或驶离停车场时,车辆可以通过第一摄像装置(例如,行车记录仪DVR、环视摄像头AVM等),自动采集车辆周围的第一图像信息,当第一图像信息中包括停车支付二维码后,车辆可以自动扫描并识别该支付二维码,并将扫描的结果显示在车辆的显示屏上。
示例性地,二维码的检测与识别过程可以是车辆将第一图像信息中的支付二维码区域进行裁剪,并将经过裁剪的二维码输入到二维码识别网络中获取该二维码信息,并访问二维码信息中承载的停车费信息的地址,从而指导用户完成停车费的支付。其中,二维码检测网络与二维码识别网络可以是深度学习网络(例如,卷积神经网络(convolutional neural  network,CNN)模型或循环神经网络(Recurrent Neural Network,RNN)),神经网络模型可以通过数据集训练预先获取。
如图4中的(c)所示的图形用户界面(graphical user interface,GUI),车辆自动扫描识别停车支付二维码后,车辆的显示屏上能够显示停车费支付界面。该停车费支付界面包括用户账号选项418、车牌号选项419、需缴费金额选项420和面向车内摄像头提示框421。其中,当用户根据提示框421的提示面对车内摄像头时,车内摄像头能够采集用户的生物特征信息,该生物特征信息可以是面部特征信息。
如图4中的(d)所示,该图表示通过第二摄像装置采集的用户的面部特征信息,车辆可以根据采集的面部特征信息与车辆预设的面部特征信息进行比较,验证成功后完成停车费的支付。
如图4中的(e)所示的GUI,该GUI为停车费支付界面。该停车费支付界面包括提示用户支付成功的提示框422。在验证完成用户的生物特征信息后,在车辆的显示屏上显示该GUI,用于告知用户的缴费成功。
应理解,在识别出支付二维码后,车辆可以自动获取账号选项418、车牌号选项419、需缴费金额选项420中显示的信息,无需用户进行手动的输入操作。车辆获取上述信息的方式可以是由停车场识别该车辆后,将上述信息承载在支付二维码中,该二维码可以是动态二维码。也可以是用户扫描支付二维码后,由停车场获取该车辆的上述信息,并将上述信息传递给车辆,并在车辆的显示屏上显示。
还应理解,生物特征信息也可以是虹膜特征信息或者生物特征信息,如果生物特征信息为上述两种,在车辆上应当配置相应的虹膜识别设备或者声纹识别设备。
本申请实施例中,当车辆进入或驶离停车场时,车辆可以自动采集并识别停车支付二维码车辆,并自动获取车牌信息和待缴费的金额。并且,车辆可以获取并根据用户的生物特征信息完成停车费的支付。通过这样的方式,能够在支付停车费时,减少用户的账户存在被错扣或者盗扣等风险,提高用户的支付体验。
图5是本申请提供的支付方法的另一应用场景图。
当车辆检测到进入或驶离停车场时,车辆可以通过第一摄像装置(例如,行车记录仪DVR、环视摄像头AVM等),自动采集车辆周围的第一图像信息,当第一图像信息中包括停车支付二维码后,车辆可以自动扫描并识别该支付二维码,并将扫描的结果通过车载显示屏上通知用户,由用户选择是否进入扫描页面。
其中,车辆检测到进入或驶离停车场可以采用多种方式。
一种可能的实现方式中,车辆可以通过部署在车辆上的全球导航卫星系统(global navigation satellite system,GNSS)传感器来获取车辆的定位和信号强度,从而判断车辆是否进入或驶离停车场,例如,GNSS传感器检测到车辆的位置在某个停车场附近,并且车辆进行通信的信号强度小于或等于第一阈值时,GNSS传感器可以向车辆的座舱控制器320发送第一指示信息,告知车辆进入停车场。同样的,GNSS传感器检测到车辆的位置在某个停车场附近,并且车辆进行通信的信号强度大于第二阈值时,GNSS传感器可以向车辆的座舱控制器320发送第二指示信息,告知车辆驶离停车场。又例如,GNSS传感器检测到车辆进行通信的信号良好,车辆的位置在停车场的边缘或者进出口位置时,GNSS传感器可以向座舱控制器320发送第三指示信息,告知车辆正在进入或驶离停车场。
一种可能的实现方式中,可以通过视觉识别的方法来判断出车辆是否进入或驶离停车场。例如,车辆可以通过第一摄像装置采集车辆外部的图像信息,并且将采集的图像细分为多个特征区域,对每个特征区域与识别标的物(例如,停车场标志、停车杆)进行匹配,并计算匹配概率,在匹配概率大于或小于预设阈值时,可以判断出车辆正在进入或驶离停车场。
一种可能的实现方式,可以在停车场入口或出口处设置无线信号发射装置,在车辆接收到无线信号发射装置发射的无线信号后,可以判断出车辆正在进入或驶离停车场。
二维码的检测与识别过程可以是车辆将第一图像信息中的支付二维码区域进行裁剪,并将经过裁剪的二维码输入到二维码识别网络中获取该二维码信息,并访问二维码信息中承载的停车费信息的地址,从而指导用户完成停车费的支付。其中,二维码检测网络与二维码识别网络可以是深度学习网络CNN模型或RNN模型,模型可以通过数据集训练预先获取。
如图5中的(a)所示的GUI,该GUI包括通知栏501,当车辆自动扫描并识别支付二维码后,可以通过车载显示屏上的通知栏501上的通知用户是否进入识别页面。当用户点击通知栏501上的进入控件时,车辆的显示屏上可以显示如图5中的(b)所示的GUI。
如图5中的(b)所示的GUI,车辆可以自动获取账号选项418、车牌号选项419、需缴费金额选项420中显示的信息,车辆获取上述信息的方式可以是由停车场识别该车辆后,将上述信息承载在支付二维码中。也可以是用户扫描支付二维码后,由停车场获取该车辆的上述信息,并将上述信息传递给车辆,并在车辆的显示屏上显示。此外,该GUI还包括无感支付控件502和手动缴费控件503,如果用户点击无感支付控件502后,车辆可采用如图4中的(c)至(e)的方式进行支付。当用户点击手动缴费控件503后,车辆的显示屏上可以显示如图5中的(c)所示的GUI。
如图5中的(c)所示的GUI,该GUI为停车费支付界面,包括密码输入选项504和软件盘控件505。用户可以通过点击软件盘控件505上的数字,在密码输入选项504中输入密码。当密码输入完成后,点选软件盘上的确定控件,在车辆的显示屏上可以显示如图5中的(d)所示的GUI。
如图5中的(d)所示的GUI,该GUI为停车费支付界面,包括停车费支付成功的提示框506。在验证完成用户输入的密码后,在车辆的显示屏上显示该提示框506,用于告知用户的缴费成功。
本申请实施例中,在车辆周围存在停车支付二维码时,车辆可以自动扫描并识别该二维码,并将扫描的结果通知用户,由用户主动选择是否进入识别界面。并且,在支付的过程中用户可以选择使用无感支付或者手动缴费。通过这样的方式,在支付停车费的过程中,能够给用户提供多样化的支付模式,从而提高用户的支付体验。
图6是本申请提供的支付方法的另一应用场景图。
当用户驾驶该车辆进入或驶离停车场的过程中,发现车辆周围设有停车支付二维码。此时,用户可以通过部署在车辆外的第一摄像装置(例如,行车记录仪DVR、环视摄像头AVM等)获取车辆周围的第一图像信息,并使用二维码扫描功能识别第一图像信息中的支付二维码。或者车辆检测到进入或驶离停车场时,车辆可以通过第一摄像装置自动获取车辆周围的第一图像信息,并自动扫描识别第一图像信息中的支付二维码。
其中,扫描和识别支付二维码的方式既可以由车辆自动扫描和识别,并且自动进入识别页面(例如,图4中介绍的方法),也可以由车辆自动扫描识别,并将扫描的结果通过车载显示屏通知用户,由用户主动选择是否进入页面(例如,图5中介绍的方法)。在对二维码进行扫描识别后,车辆的显示屏上可以显示如图6(a)所示的GUI。
如图6中的(a)所示的GUI,该GUI包括交互助手601和交互文本602。在车辆扫描并识别支付二维码后,如果用户的账户中尚未绑定车牌号信息,在车辆的显示屏上可以显示交互助手601以及交互文本602,用于通知用户尚未在账户中绑定车牌号。另外一种情况下,用户虽然在账户中绑定了车牌号,但是车辆获取的待缴费车辆的车牌号和用户在账户中绑定的车牌号不一致。此时,可以在车辆的显示屏上显示交互助手601以及交互文本602,用于通知用户在账户中添加绑定新车牌号。
在上述的情况中,车辆识别的是动态二维码,动态二维码由于可以实时更新,所以车辆在扫描动态二维码后可以获得当前识别的车牌信息,并判断出用户的账户是否绑定识别的车牌号信息。在另外的一种情况下,上述二维码也可以是固定二维码,车辆在扫描固定二维码后,由停车场系统识别待缴费车辆的车牌号信息,然后停车场系统将该车牌号信息通过信令交互的方式发送给车辆,并在车辆的显示屏上显示该识别的车牌号信息。在此种情况下,由于需要车辆和停车场通信,所以在实际应用时需要车辆开启相应的对外通信权限。
当用户点击如图6中的(a)所示的GUI中的车牌号选项419时,车载显示屏上可以显示如图6中的(b)所示的GUI。
如图6中的(b)所示的GUI,该GUI为停车费查询界面。该界面中包括:输入车牌号选项603,绑定控件604。
当用户点击输入车牌号选项603时,车载显示屏上可以显示如图6中的(c)所示的GUI,该GUI包括车牌号输入框605和软件盘控件606,用户可以在车牌号输入框605的第一个输入框内输入车牌的简称,并在后几位输入框内输入字母和数字,在输入完成车牌号信息后,用户点击软键盘控件606上的确定控件。车载显示屏上可以显示如图6中(d)所示的GUI,从该GUI的界面上用户可以获知需要缴纳的停车费信息,并可以选择无感支付或者手动缴费的方式进行支付。如果用户选择无感支付方式,车辆可以在检测到用户绑定新车牌时,通过人脸支付或者虹膜支付等无感支付方式缴纳停车费用。
应理解,用户在车牌号输入框605中输入车牌号可以是通过车载显示屏进行手动输入,也可以向交互助手601发送语音指令的方式进行输入等等。
本申请实施例中,车辆可以在用户未绑定车牌号或者绑定车牌号与识别的车牌号不一致的情况下,向用户进行提示。并在检测到用户绑定新车牌信息后,支付待缴纳的停车费用。通过这样的方式,可以避免用户缴纳停车费失败或者错误缴纳停车费的情况,既保障了用户的账户安全,又提高了用户的支付体验。
图7是本申请提供的支付方法的另一应用场景图,图7中所示的应用场景是在车辆提示用户没有绑定车牌号的情况下进行的。
如图7中的(a)所示的GUI,该GUI为查询停车费界面,该界面上包括历史车牌选项701,当用户点击历史车牌选项701中任一条历史搜索记录时,车载显示屏上可以显示如图7中(b)所示的GUI,用户可以根据该GUI获知需要缴纳的停车费信息,并可以选择无 感支付或者手动缴费的方式进行支付。
本申请实施例中,在用户的账号尚未绑定车牌号的情况下,用户可以点击历史车牌的缴费或搜索记录直接查询停车费信息并缴费。通过这样的方式,能够使得停车费支付过程更加简单高效。
图8是本申请提供的支付方法的另一应用场景图。
当用户驾驶该车辆进入或驶离停车场的过程中,发现车辆周围设有停车支付二维码。此时,用户可以通过部署在车辆外的第一摄像装置(例如,行车记录仪DVR、环视摄像头AVM等)获取车辆周围的第一图像信息,并使用二维码扫描功能识别第一图像信息中的支付二维码。或者车辆检测到进入或驶离停车场时,车辆可以通过第一摄像装置自动获取车辆周围的第一图像信息,并自动扫描识别第一图像信息中的支付二维码。
其中,扫描和识别支付二维码的方式既可以由车辆自动扫描和识别,并且自动进入识别页面(例如,图4中介绍的方法),也可以由车辆自动扫描识别,并将扫描的结果通过车载显示屏通知用户,由用户主动选择是否进入页面(例如,图5中介绍的方法)。在对二维码进行扫描识别后,车辆的显示屏上可以显示如图8(a)所示的GUI。
如图8(a)所示的GUI,该GUI为查询停车费界面,在该界面中包括车载支付选项801和发送至手机选项802,当用户点击车载支付选项时,车辆可以使用图4中的(c)所示的无感支付方法或者图5中的(c)所示的手动缴费方法。当用户点击发送至手机802选项时,车辆可以将停车费缴费信息发送到用户的手机上。
如图8(b)所示的GUI,用户的手机在接收到车辆发送的缴纳停车费消息后,可以在手机上显示该GUI。该GUI包括提示框403和确定控件404。提示框403用于向用户提示车辆向手机发送一条停车费支付消息,询问用户支付进入支付页面。当用户点击确定控件404后,手机上可以显示如图8(c)所示的GUI。
如图8(c)所示的GUI,该GUI包括提示框805,用于提示用户面向手机摄像头,当用户根据提示框805面向手机的摄像头后,可以完成停车费的支付。
本申请实施例中,在车辆获取到用户待支付的停车费信息后,车辆可以根据用户的指示将停车费信息发送到用户的手机上,用户通过手机可以完成停车费的支付。通过这样的方式,能够给用户提供更加多样化的支付方式,从而满足用户对支付方式的个性化需求。
图9是本申请提供的一种支付方法的示意性流程图,图9所示的支付方法可应用于图1的车辆100中,方法900可以包括如下步骤。
S901,检测到车辆进入或驶离停车场
其中,车辆检测到进入或驶离停车场可以采用多种方式。
一种可能的实现方式中,车辆可以通过部署在车辆上的全球导航卫星系统(global navigation satellite system,GNSS)传感器来获取车辆的定位和信号强度,从而判断车辆是否进入或驶离停车场,
例如,GNSS传感器检测到车辆的位置在某个停车场附近,并且车辆进行通信的信号强度小于或等于第一阈值时,GNSS传感器可以向车辆的座舱控制器发送第一指示信息,告知车辆进入停车场。同样的,GNSS传感器检测到车辆的位置在某个停车场附近,并且车辆进行通信的信号强度大于第二阈值时,GNSS传感器可以向车辆的座舱控制器发送第二指示信息,告知车辆驶离停车场。又例如,GNSS传感器检测到车辆进行通信的信号良 好,车辆的位置在停车场的边缘或者进出口位置时,GNSS传感器可以向座舱控制器320发送第三指示信息,告知车辆正在进入或驶离停车场。
一种可能的实现方式中,可以通过视觉识别的方法来判断出车辆是否进入或驶离停车场。例如,车辆可以通过第一摄像装置采集车辆外部的图像信息,并且将采集的图像细分为多个特征区域,对每个特征区域与识别标的物(例如,停车场标志、停车杆)进行匹配,并计算匹配概率,在匹配概率大于或小于预设阈值时,可以判断出车辆正在进入或驶离停车场。
一种可能的实现方式中,可以在停车场入口或出口处设置无线信号发射装置,在车辆接收到无线信号发射装置发射的无线信号后,可以判断出车辆正在进入或驶离停车场。
S902,通过第一摄像装置获取第一图像信息,所述第一图像信息包括第一支付码
其中,第一摄像装置可以是部署在车辆外部的摄像头,例如AVM环视摄像头或者DVR摄像头等。第一支付码可以是二维码、条形码等具备支付功能的支付码。
车辆通过第一摄像装置获取第一图像信息也可以采用多种方式。
一种可能的实现方式中,当车辆检测到进入或驶离停车场时,车辆可以通过第一摄像装置,自动采集车辆周围的第一图像信息。
一种可能的实现方式中,当用户驾驶车辆进入或驶离停车场的过程中,发现车辆周围设有停车支付码。此时,用户可以主动触发第一摄像装置进行拍照获取第一图像信息,如果第一摄像装置是行车记录仪,获取第一图像信息的方式也可以是截取行车记录仪记录的视频中的某一帧图像。
本申请实施例中,车辆在检测到进入或者驶离停车场的情况下,通过第一摄像装置获取第一图像信息。相比于第一摄像装置一直工作的情况,能够降低第一摄像装置使用能耗,提高第一摄像装置获取第一图像信息的工作效率。
S903,识别第一支付码,得到车辆待缴纳的停车费用
其中,识别支付码也可以是采用多种方式。
一种可能的实现方式中,在获取到第一图像信息后,用户可以通过车载显示屏上的应用程序触发支付码扫描功能进行扫码识别。
一种可能的实现方式中,车辆在获取第一图像信息后,可以自动扫描并识别第一支付码,并将扫描的结果在车载显示屏上通知用户,由用户决定是否进入识别页面。
一种可能的实现方式中,支付码的检测与识别过程可以是车辆将第一图像信息中的第一支付码区域进行裁剪,并将经过裁剪的支付码输入到支付码识别网络中获取该支付码信息,并访问支付码信息中承载的停车费信息的地址,从而指导用户完成停车费的支付。其中,支付码检测网络与支付码识别网络可以是深度学习网络(例如,CNN模型或RNN模型),模型可以通过数据集训练预先获取。
S904,通过第二摄像装置获取用户的第一生物特征信息。
该步骤可以通过数据管理监控程序(data management supervisor,DMS)或者内容管理系统(content management system,CMS)调用第二摄像装置获取用户的第一生物特征信息。
其中,第二摄像装置可以是用于获取车辆内部图像的深度摄像头,例如,3D(time of flight,TOF)摄像头或者3D结构光摄像头等。第一生物特征信息可以是用户的面部特征 信息。
应理解,第一生物特征信息也可以是虹膜特征信息或者生物特征信息,如果第一生物特征信息为上述两种,在车辆上应当配置相应的虹膜识别设备或者声纹识别设备。
S905,在第一生物特征信息与第二生物特征信息匹配的情况下,使用第一用户的账户支付停车费用。
其中,第二生物特征信息为第一用户在车辆中预设的生物特征信息。
例如,通过第二摄像装置采集用户的面部特征信息(生物特征信息的一种),并且将采集的面部特征信息与车辆系统中预设的面部特征信息进行对比,验证成功后直接从用户绑定的账户中进行扣款。
如果第二摄像装置获取的第一生物特征信息和车辆中预设的生物特征信息不一致,可以在车辆显示屏上显示如图5(c)所示的界面,并提示用户手动输入密码进行支付。
本申请实施例中,在检测到车辆进入或者驶离停车场的情况下,由车辆主动调用车第一摄像装置获取第一图像信息,并识别第一图像信息中的第一支付码来查询停车费,然后,通过调用第二摄像装置进行用户的身份信息验证,从而完成停车费的支付。通过这样的方式,整个扫码支付的过程都由车辆执行,能够避免因停车场系统出现错误导致的用户的账户被盗扣或者错扣等情况。
一种可能的实现方式中,在步骤S905还包括:在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,使用第二用户的账户支付所述待缴纳的停车费用,所述第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第二用户。
本申请实施例中,在使用第一生物特征信息与第二生物特征信息验证失败时,车辆能够查询识别的第一生物特征信息是否与第二用户的第三生物特征信息相关联,在相关联的情况下,使用第二用户的账户完成停车费的支付。通过这样的方式,能够为车内的多个用户提供停车费支付的服务,避免了生物特征信息验证失败后需要用户手动登录账户并输入密码完成支付的情况,提高了支付的效率。
一种可能的实现方式中,在步骤S902之前该方法还包括:通过所述第一摄像装置获取第二图像信息;在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用的情况下,通过所述第一摄像装置获取所述第一图像信息。
其中,通过第二图像信息识别不出待缴纳的停车费用存在多种情况。
一种可能的实现方式中,由于车辆在整个扫码识别过程是移动的,第一摄像装置获取的支付码可能产生畸变,从而导致支付码的识别失败。在此种情况下,可以通过调节第一摄像装置的位置使得减少或避免第一图像信息中出现支付码的畸变情况。
一种可能的实现方式中,第一支付码可以位于第二图像信息的边缘位置,第一支付码在第二图像信息中显示不完整。这样,车辆可能因第一支付码的不完整而识别不出第一支付码上承载的信息。在此种情况下,可以通过调节第一摄像装置的位置获取第一图像信息,使得第一支付码在第一图像信息中完整呈现。
本申请实施例中,车辆的扫描装置识别不出支付码时,可以调整支付码在图像信息中的位置,进而使支付码识别成功。通过这样的方式,能够增强支付码的识别率,提高用户的支付体验。
一种可能的实现方式中,所述第二图像信息包括所述第一支付码,所述在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用时,通过所述第一摄像装置获取所述第一图像信息,包括:根据所述第一支付码在所述第二图像中的位置坐标与所述第二图像信息的中心位置坐标,确定所述第一摄像装置的控制参数;根据所述控制参数控制所述第一摄像装置获取所述第一图像信息,所述第一支付码在所述第一图像信息的中心位置。
本申请实施例中,在通过第二图像信息识别不出支付码的情况下,通过调节第一摄像装置的位置获取第一图像信息使得第一支付码位于第一图像的中心位置。通过这样的方式,能够在支付码发生畸变的情况下,使得支付码始终保持在第一图像的中心位置,从而更好的识别第一支付码。
一种可能的实现方式中,在所述使用第一用户的账户支付所述待缴纳的停车费用之前,所述方法还包括:获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;其中,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:在所述第一车牌信息与第二车牌信息一致的情况下,使用所述第一用户的账户支付所述待缴纳的停车费用,所述第二车牌信息为与所述第一用户账户绑定的车牌信息。
此种实施方式在实际应用中,车辆上的处理器能够获取第一车牌信息,并将该第一车牌信息自动输入至第一支付码识别出的支付网站的车牌信息输入框中,并通过该网站检索停车场系统识别到的第二车牌信息与第一车牌信息是否一致,在一致的情况下才支付待缴纳的停车费。整个获取第一车牌信息、在支付网站上输入第一车牌信息和查询第二车牌信息的动作均由车辆执行。
本申请实施例中,在支付停车费之前,需要验证待缴费车辆的车牌与用户账户中绑定的车牌是否一致,在验证通过的情况下,才支付待缴纳的停车费用。通过这样的方式,在停车费支付前设置验证措施,能够进一步的提升停车费缴纳过程中的安全性。
一种可能的实现方式中,在所述使用第一用户的账户支付所述待缴纳的停车费用之前,所述方法还包括:获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;在所述第一车牌信息与第二车牌信息不一致的情况下,向所述第一用户提示所述第一车牌信息未与所述第一用户账户绑定,所述第二车牌信息为与所述第一用户账户绑定的车牌信息;其中,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:在检测到所述第一用户将所述第一车牌信息与所述第一用户的账号绑定时,支付所述待缴纳的停车费用。
其中,在验证第一车牌信息和第二车牌信息不一致后,车辆可以通过多种方式提示用户绑定第一车牌。例如,车辆可以在车辆的显示屏上显示提示消息来告知用户第一车牌信息和第二车牌信息不一致。又例如,车辆可以通过车载扬声器用语音信息的方式告知用户第一车牌信息和第二车牌信息不一致。
第一车牌信息和第二车牌信息不一致也可以存在多种情况。例如,用户在账户中没有绑定任何车牌,此时,车辆可以向用户提示账户中尚未绑定车牌。又例如,用户已经在账户中绑定车牌,但是绑定的车牌和识别的车牌信息不一致,此时,车辆可以向用户提示绑定新识别的车牌或者拒绝支付。
本申请实施例中,在支付停车费之前,需要验证待缴费车辆的车牌与用户账户中绑定的车牌是否一致,如果验证不通过,车辆可以提示用户绑定识别的车牌信息,在车辆检测到识别的车牌信息被绑定后,才能触发支付流程。通过这样的方式,在停车费支付前设置 验证措施,可以避免用户缴纳停车费失败或者错误缴纳停车费的情况,既保障了用户的账户安全,又提高了用户的支付体验。
一种可能的实现方式中,所述第一图像信息还包括第二支付码,所述第一支付码对应第一支付平台,所述第二支付码对应第二支付平台,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:在所述第一用户使用所述第一支付平台支付的频率大于使用所述第二支付平台支付的频率情况下,使用所述第一支付平台支付所述待缴纳的停车费用。
本申请实施例中,车辆能够根据用户的支付习惯,为用户推荐最优的支付方式,用户可以通过推荐的支付方式完成停车费的支付,通过这样的方式,能够更加便捷的完成停车费的支付,并能够有效的提升用户的支付体验。
一种可能的实现方式中,在通过所述第一摄像装置获取第一图像信息之前,所述方法还包括:通过所述第一摄像装置获取第三图像信息,所述第三图像信息中的第一像素占比大于第一阈值;根据所述第一像素占比,将所述车灯的亮度调整为第一亮度;所述通过所述第一摄像装置获取第一图像信息包括:在所述第一亮度下通过所述第一摄像装置获取所述第一图像信息。
其中,第一像素占比可以是低像素占比,其范围可以被预先设定。例如,图像的像素值在0至255区间,0像素表示图像最暗,255像素表示图像最亮。可以预先设定0至40为低像素范围。则此时第一像素占比可以是0至40像素出现的频率的平均值与0至255像素出现的频率的平均值的比值。
第一阈值的具体数值可以根据实际的情况进行预先设定,如果二维码识别设备性能较好可以将第一阈值设置的较高,如果二维码识别设备的性能较差,可以将第一阈值设置的较低。
本申请实施例中,通过判断摄像装置拍摄的图像中的第一像素占比与第一阈值的大小关系,进而进行不同的处理。当低亮度低像素占比大于第一阈值时,利用车辆的车灯对二维码进行补光,通过这样的方式,能够降低二维码图像对额外的补光设备(例如,停车场的灯光)的依赖性,有效增强低亮度二维码的识别率。
一种可能的实现方式中,所述第一摄像装置为行车记录仪或环视摄像头,所述第二摄像装置为深度摄像头。
图10是本申请提供的另一种支付方法的示意性流程图,图10中的支付方法可应用于图1的车辆100中,该方法可以包括如下步骤。
S1001,显示二维码扫描界面A
具体地,当用户通过车载显示屏上的HMI快捷入口,主动触发二维码扫描功能时,车辆的显示屏上能够显示二维码扫描界面A。
S1002,使用DVR拍照
具体地,部署在车辆外部的DVR能够采集车辆前方的第一图像信息。例如,车辆前方存在停车支付的二维码,则在此步骤中可以使用DVR对二维码进行拍照。
S1003,得到YUV照片
具体地,在步骤S1002中,使用DVR对车辆前方的二维码进行拍照后,车辆可以获得该二维码的YUV照片。
应理解,高清全幅照片的获取方式可以是由用户主动触发DVR 310进行拍照,也可 以是CDC 320控制截取YUV视频中某一帧图像。
S1004,显示扫码界面,同时关闭界面A
具体地,在车辆的显示屏上显示二维码的扫描结果界面,并关闭二维码的扫描界面A。
S1005,判断当前照片是否低照度
具体地,在该步骤中判断步骤S1004获取的YUV照片是否是存在低照度的情况,如果存在该情况,则需要进行步骤S1006,如果不存在该情况,可以直接进行步骤S1007。
应理解,照片的低照度可以指拍照时,拍照的对象周围的物理环境照明效果不佳,表现的结果为拍摄出的照片亮度较低。
S1006,汽车灯光进行补光
具体地,在步骤S1005判断照片存在低照度时,在此步骤中可以利用车辆灯光对照片进行补光处理。
S1007,二维码检测
具体地,对获取YUV照片中的二维码进行检测。
S1008,判断二维码是否存在低分辨率的情况
具体地,判断YUV照片中的二维码是否存在低分辨率的情况,如果存在该情况,则需要对低分辨率的二维码进行处理,提高其分辨率,如果不存在该情况,则可以直接进行步骤S1011。
S1009,超分辨率算法增强
具体地,可以通过图像超分辨率算法提高二维码的分辨率,并得到高清的二维码。
应理解,图像超分辨率算法可以利用不同图像在高频细节上的相似性,通过学习算法获得高分辨率与低分辨率图像之间关系,并指导高分辨率图像的重建。
S1010,输出高清二维码
具体地,将步骤S1009中获取的高清二维码输出给车辆中的二维码扫描识别模块324进行处理。
S1011,开启二维码识别
具体地,车辆中的二维码扫描识别模块324对获取的二维码进行识别。
S1012,判断有效二维码数量
具体地,车辆中的CDC 320可以通过判断识别出二维码的数量进而进行不同的处理。如果判断出没有识别到有效的二维码,则进行步骤S1013、步骤S1017。如果判断出识别到一个有效的二维码则直接进行步骤S1015至步骤S1017。如果判断出识别到两个以上有效的二维码,则进行步骤S1014至步骤S1017。
S1013,提示用户没有有效的二维码
其中,向用户提示没有有效的二维码可以采用多种方式,例如,车辆可以在车辆的显示屏上显示提示消息来告知用户没有有效的二维码。又例如,车辆可以通过车载扬声器用语音信息的方式告知没有有效的二维码。
S1014,在页面上选择二维码
具体地,在步骤S1012中,判断出识别到的二维码数量上为两个以上时,车辆向用户发出提示信息,提示用户在车辆的显示器的页面上主动选择一个识别到的二维码。
S1015,显示支付页面
具体地,在车辆的显示屏上,停车费的支付页面。例如,在车辆的显示屏上显示如图4中的(c)所示的支付页面。
S1016,调用人脸识别功能判断识别的人脸信息与车辆预设的多个人脸信息进行对比。
具体地,车辆中的CDC 320调用人脸支付模块325识别用户的人脸得到人脸信息,并与车辆预设的多个人脸信息进行对比,若识别的人脸信息与多个预设的人脸信息中的一个人脸信息一致时,则进行步骤S1019至S1020。若识别的人脸信息与多个预设的人脸信息均不一致,则进行步骤S1017至S1020。
S1017,查询识别的人脸与其他账号是否存在关联
具体地,CDC 320在判断识别的人脸信息与车辆系统中预设的人脸信息不一致时,可以查询识别的人脸信息车内预设的其他账户是否存在关联。如果存在关联,则进行步骤S1018。
S1018,自动登录其他账号完成人脸验证
具体地,CDC 320能够自动登录与识别的人脸信息存在关联的账户,并完成人脸验证。
S1019支付停车费
具体地,在人脸验证成功后,支付相应的停车费用。
S1020,关闭页面
本申请实施例中,通过DVR获取车辆前方的第一图像信息,并通过扫描识别图像信息中的二维码,使用户获知需要支付的停车费,从而调用车辆的人脸识别支付功能完成支付,通过这样的方式,能够在支付停车费时,降低用户的账户存在被错扣或者盗扣等风险,提高用户的支付体验。
图11是本申请提供的一种环视摄像头二维码自适应识别方法的示意性流程图,该方法可应用于图1的车辆100中,该方法可以包括如下步骤。
S1101,360环视系统获取多路视频流
具体地,通过车辆上的360环视系统获取多路视频流,即通过分布在车辆各个方向上摄像头采集视频流数据。
应理解,360环视系统能够车辆上的系统同时采集车辆四周的影像,经过图像处理单元的智能算法处理,最终形成一幅车辆四周的全景俯视图显示在屏幕上,直观地呈现出车辆所处的位置和周边情况。
S1102,对多路视频流进行二维码检测
具体地,通过算法模型检测多路视频流中是否存在二维码信息,如果存在二维码信息,则进行步骤S1103。其中,进行二维码的检测模型可以是深度学习模型。例如,卷积神经网络CNN模型、循环神经网络RNN模型、深度信念网络(deep Belief network,DBN)模型等。
S1103,判断二维码所在的摄像头
具体地,判断二维码信息所在的摄像头。例如,通过检测视频流发现,该二维码信息是通过车辆的前视摄像头获取,此时,确定二维码所在的摄像头为车辆的前视摄像头。
S1104,二维码位置检测
具体地,在步骤S1103中确定了二维码所在的摄像头后,可以使用该摄像头对二维码 的位置进行检测,其中,检测出二维码的中心点的实际位置可以在二维平面上可以用坐标(x,y)表示。
S1105,摄像头位置自适应调节
具体地,摄像头的位置可以根据二维码的位置进行自适应的调节,调节的目的是使二维码的中心位置保持在摄像头的中间位置,规避二维码图像畸变的影响。
其中,自适应调节的目的可以是利用获取的摄像头从初始位置移动至目标位置的位置差和速度差计算出对应的电机控制信号,并根据电机控制信号控制摄像头电机位置的移动。
具体的调节方式可通过步骤S1106至步骤S1108实现。
S1106,摄像头目标位置计算
具体地,获取预设的目标图像中心点的在二维平面上的坐标(X,Y),本申请实施例中目标图像中心点可以指第一图像信息的中心点。
S1107,计算二维码中心点实际位置和目标图像中心点位置的差异。
S1108,向摄像头传递运动信号
具体地,在通过步骤S1107计算出二维码中心点实际位置和目标图像中心点位置的差异后,将该差异利用比例-积分-微分(proportion integration differentiation,PID)调节算法输出对应摄像头在x方向和y方向的运动信号,CDC 320通过该控制信号,控制摄像头移动,致使二维码的中心区域接近并达到预设的目标图像中心区域。
S1109,二维码居中检测
具体地,进行在步骤1108之后,再次对二维码中心点的位置进行检测,确定二维码的中心区域是否接近并达到预设的目标图像中心区域。
S1110,开启二维码识别
具体地,在检测到二维码的中心区域接近并达到预设的目标图像中心区域后,CDC320控制开启二维码的识别功能,识别二维码。
S1111,识别结束摄像头调回原位
本申请实施例中,可以根据二维码在摄像头画面中的实际位置和目标图像的中心位置,计算两者位置的差异,并根据该差异通过PID控制实现摄像头位置调整,使二维码始终保持在图像信息的中心位置,通过这样的方式,能够有效降低二维码的成像畸变率,增强二维码的识别率。
图12是本申请提供的一种通过PID控制摄像头电机实现二维码居中检测的示意性流程图。图12中的控制摄像头电机方法可应用于图11的步骤S1106至S1108中。
其中,目标位置1201可以是目标图像的中心位置坐标(X,Y)。目标环1202可以将目标位置调整为目标速度,目标速度可以是根据目标位置确定的电机控制摄像头移动至目标图像中心的速度。速度环1203可以将目标速度调整为电机的输入电压。电机1204的可以根据输入的电压控制摄像头的位置。实际速度1205可以是根据实际位置确定的电机控制摄像头移动至二维码中心的实际速度,实际位置1206可以是二维码的实际位置坐标(x,y)。
图12中的控制方法在实际的应用中,首先,将目标位置1201和实际位置1206进行比较,得到位置误差,将位置误差作为目标环1202的输入,得到目标速度。将目标速度与实际速度1206相比较,得到速度误差。将速度误差输入到位置环中,得到电机控制摄 像头移动至二维码中心位置所需电压。最后,将电压输入到电机中,实现电机控制摄像头移动至二维码中心位置。
本申请实施例中,通过PID控制实现摄像头位置的调整,使二维码始终保持在摄像头的中间位置,通过这样的方式,能够有效降低二维码的成像畸变率,增强二维码的识别率。
图13是本申请提供的一种低分辨率二维码识别方法的示意性流程图,图13中的方法可应用于图1的车辆100中,该方法可以包括如下步骤。
S1301,摄像头采集当前图像
具体地,通过摄像头采集要识别图像的视频流数据。其中,摄像头可以指车辆上的360环视系统,也可以指车载DVR。
S1302,二维码检测
具体地,车辆中的CDC 320对采集的视频流数据进行二维码检测,进行二维码的检测模型可以是深度学习模型。例如,卷积神经网络模型、循环神经网络模型、深度信念网络模型等。
S1303,判断二维码是否低分辨率
具体地,车辆中的CDC 320可以计算二维码图案的分辨率,计算出的二维码的分辨率和预设阈值进行比较,如果二维码分辨率大于预设阈值,说明二维码的分别率满足识别要求,则将二维码输出到二维码识别算法中。如果二维码的分辨率小于预设阈值,说明二维码分辨率过低则需要进行步骤S1304。
其中,预设阈值的数值可以根据二维码识别算法的功能加以确定,若实际应用中二维码识别算法对分辨率要求较高,可以将预设阈值的数值设置的相对较大。若实际应用中二维码识别算法对分辨率要求不高,可以将预设阈值的数值设置的相对较小。
S1304,超分辨率算法增强二维码分辨率
具体地,可以使用图14中的图像超分别率算法增强二维码的分辨率。如图14所示,低分辨率的二维码在输入到超分辨率网络后,能够得到分辨率提高后的高清二维码。其中,图像超分辨率算法在网络结构上可以分为正常特征提取层(Normal Part)和上采样层(Upsampling Part),正常特征提取层的各层可以通过密集连接(Dense Concat)、深度卷积(Depthwise Convolution)等技术提升性能,从而更好的对二维码进行特征提取。上采样层的各层通过反向卷积(Deconvolution)、残差学习(Residual Learning)等技术改善性能,从而提高二维码的分辨率。
在超分辨率网络模型训练方面,对于目标函数,针对二维码二值化的特点,除了考虑L 2/L 1损失外,增加二值约束损失,优化目标函数。其中,L 2可以是范数损失函数,也可以被称为最小平方误差,它可以把目标值与估计值的差值的平方和最小化。L 1可以是范数损失函数,也可以被称为最小绝对值偏差,它可以把目标值与估计值的差值的总和最小化。在此步骤中,由于增加了二值约束损失,使目标函数的性能得到提高,从而得到高清二维码。
增加二值约束损失使目标函数的性能得到提高基本原理是,考虑到二维码本质上是0(黑色),1(白色)的编码;在恢复二维码的优化问题中可以引入交叉熵损失函数来促使模型在学习过程中去优化该区域是黑色或者白色的可能性;若白色的可能性更高,会将附近的小区域颜色统一为同一颜色从而达到减小噪声的影响;其中二值约束(交叉熵)损失 函数可以是:
Figure PCTCN2022137558-appb-000001
其中,
Figure PCTCN2022137558-appb-000002
是模型预测样本是正例的概率,y是样本标签,如果样本属于正例,取值为1否则取值为0。
S1305,输出高清二维码
具体地,将步骤S1304中得到的高清二维码输入到二维码扫描识别模块324进行处理。
S1306,开启二维码识别
本申请实施例中,利用图像超分辨率算法对低分辨率二维码进行增强处理,能够增强二维码的分辨率和图像质量,并且能够有效增强二维码的识别率。
图15是本申请提供的一种低照度下二维码补光的方法,图15中的方法可应用于图1的车辆100中,该方法可以包括如下步骤。
S1501,摄像头采集当前图像
具体地,通过摄像头采集要识别图像的视频流数据。其中,摄像头可以指车辆上的360环视系统,也可以指车载DVR。
S1502,分析当前算法直方图
其中,算法直方图能够描述图像的亮度的分布情况,能够较为直观地展示出图像中各个亮度级所占比例。如图16(a)所示的直方图,直方图的横坐标可以是像素值(从0至255),其中,0像素表示图像最暗,255像素表示图像最亮,纵坐标可以是像素值出现的频率。
S1503,统计低亮度像素占比
具体地,根据直方图中的数据统计图像中低亮度像素占总体图像像素的比例。例如可以预先设定0至40为低像素范围。则此时低像素占比可以是0至40像素出现的频率的平均值与0至255像素出现的频率平均值的比值。
S1504,判断低亮度像素占比是否超过第一阈值
具体地,如果低亮度像素占比小于第一阈值,说明图像的亮度正常,此时可以进行步骤S1505,如果低亮度像素占比大于第一阈值则进行步骤S1506至S1507。
应理解,第一阈值的具体数值可以根据实际的情况进行预先设定,如果二维码识别设备性能较好可以将第一阈值设置的较高,如果二维码识别设备的性能较差,可以将第一阈值设置的较低。
S1505,二维码扫描识别模块324对亮度正常的二维码进行识别,进而跳转到相应的停车费显示界面。
S1506,根据当前低像素占比映射车灯强度参数
具体地,在步骤S1504判断出低亮度低像素占比大于第一阈值后,可以建立低像素占比和车灯强度参数的映射关系。例如,该映射关系可以是线性映射关系,低像素占比越大,车灯的强度参数越大。其中,车灯的强度参数可以包括:功率、电流、电压、光通量、照度等。
S1507,根据强度参数控制车灯亮度
具体地,车辆可以根据车灯的强度参数控制车灯的亮度,对二维码进行补光。补光完成后可以重复进行步骤S1501至步骤S1504,直到再次识别的二维码图像中低亮度像素占比小于或等于第一阈值。
如图16(b)所示的算法直方图,从图中可以看出,根据车灯调整图像亮度后,经过调整后的图像的低像素占比,明显低于调整前的低像素占比。
本申请实施例中,通过判断二维码图像中的低像素占比与第一阈值的大小关系,进而进行不同的处理。当低亮度低像素占比大于第一阈值时,利用车辆的车灯对二维码进行补光,通过这样的方式,能够降低二维码图像对额外的补光设备(例如,停车场的灯光)的依赖性,有效增强低亮度二维码的识别率。
图17是本申请提供的一种多二维码选择支付的交互方法,该方法可应用于图1的车辆100中,该方法可以包括如下步骤。
S1701,摄像头采集当前图像
具体地,通过摄像头采集要识别图像的视频流数据。其中,摄像头可以指车辆上的360环视系统,也可以指车载DVR。
S1702,二维码检测
具体地,车辆中的CDC 320对采集的视频流数据进行二维码检测,进行二维码的检测模型可以是深度学习模型。例如,卷积神经网络模型、循环神经网络模型、深度信念网络模型等。
S1703,判断是否存在二维码
具体地,判断视频流数据中是否存在二维码,如果存在则进行步骤S1704,如果不存在则重新进行步骤S1701。
S1704,存在多个二维码
具体地,判断视频流数据中是否存在多个二维码,如果不存在多个二维码则进行步骤S1705至步骤S1706,如果存在多个二维码则进行步骤S1707至步骤S1712。
S1705,识别单个二维码的默认支付平台
S1706,跳转到步骤S1705对应的支付平台发起支付
S1707,识别多个二维码对应的支付平台
S1708,判断是否存在用户账号默认平台
具体地,判断是否存在用户账号默认平台,如果存在默认平台则进行步骤S1709,如果不存在默认平台,则进行步骤S1710至S1712。
S1709,跳转对应的支付平台发起支付
具体地,在步骤S1708中判断用户存在默认平台后,CDC 320控制跳转到第三方支付平台进行停车费的支付。
S1710,识别第三方的支付平台
具体地,在步骤S1708中判断不存在用户的默认平台,CDC 320控制识别第三方的支付平台。
S1711,根据第三方支付平台的调用频率获取支付优先级
例如,车辆通过采取用户过去一周内使用支付平台的频率,发现用户使用第一支付平台频率为10次,第二支付平台的频率为5次,第三支付平台的频率为3次,则车辆可以判断出第一支付平台的优先级大于第二支付平台和第三支付平台,并在用户需要支付停车费时,向用户推荐使用第一支付平台进行支付。
S1712,调整到支付优先级最高的支付平台进行支付
本申请实施例中,能够根据用户的支付习惯,为用户推荐最优的支付方式,用户可以通过推荐的支付方式完成停车费的支付,通过这样的方式,能够更加便捷的完成停车费的支付,并能够有效的提升用户的支付体验。
图18是本申请提供的一种停车场扫码支付方法的示意性流程图,该方法可应用于图1的车辆100中,该方法可以包括如下步骤。
S1801,摄像头采集当前图像
具体地,通过摄像头采集要识别图像的视频流数据。其中,摄像头可以指车辆上的360环视系统,也可以指车载DVR。
S1802,二维码检测
具体地,车辆中的CDC 320对采集的视频流数据进行二维码检测,进行二维码的检测模型可以是深度学习模型。例如,卷积神经网络模型、循环神经网络模型、深度信念网络模型等。
S1803,判断是否为支付二维码
具体地,在此步骤中如果判断识别的二维码为支付二维码则进行步骤S1804至S1814,如果判断识别的二维码不是支付二维码,则退出该支付流程。
S1804,查询支付二维码中车牌信息
具体地,通过扫描并识别支付二维码,查询需要缴纳停车费的车牌信息。
S1805,获取账号绑定的车牌信息
具体地,获取用户的支付账户绑定的车牌信息。
S1806,判断支付二维码中的车牌信息和账号绑定的车牌信息是否一致
具体地,若通过支付二维码识别的车牌信息与账号绑定的车牌信息一致,则进行步骤S1807,若通过支付二维码识别的车牌信息与账号绑定的车牌信息不一致,则进行步骤S1808至S1814。
应理解,支付二维码识别的车牌信息与账号绑定的车牌信息不一致可以是多种情况,例如,用户没有提前将支付账号与车牌绑定。又例如,用户提前将支付账号与车牌绑定,但是绑定的车牌号与通过二维码识别的车牌号信息不同。
S1807,开启支付流程
具体地,在步骤S1806中,判断支付二维码中的车牌信息和账号绑定的车牌信息一致,则在此步骤中,CDC 320可以调用车辆内置的摄像头,通过人脸识别的方式完成停车费的支付。或者,CDC 320可以在车辆显示屏上跳转到相应的支付页面,由用户手动输入账号和密码进行支付。
S1808,向用户发送语音信息,通知用户车牌信息有误
具体地,向用户传递语音信息可以是通过车载语音助手向用户播报语音信息。
S1809,待用户确认车牌信息是否有误
具体地,由用户主动确认支付二维码中的车牌信息和账号绑定的车牌信息是否一致。如果有误,则进行步骤S1813、S1814。如果无误则进行步骤S1810至S1814。具体的由用户确认的方式可以是,用户在车载显示屏上的交互界面上进行点选确认,或者向车载语音助手发送语音信息进行确认。
S1810,判断是否录入新车牌
在步骤S1809中,用户主动确认支付二维码中的车牌信息和账号绑定的车牌信息一致后。在此步骤中判断是否录入新车牌,如果判断不录入新车牌,则进行步骤S1814,如果判断需要录入新车牌则进行步骤S1811、S1812和S1814。
S1811,新车牌录入
具体地,用户可以通过车载显示屏上的人机交互界面进行操作,将通过二维码识别的车牌信息与用户的支付账户进行绑定。
S1812,开启支付流程
具体地,CDC 320可以调用车辆内置的摄像头,通过人脸识别等无感支付的方式完成停车费的支付。或者,CDC 320可以在车辆显示屏上跳转到相应的支付页面,由用户手动输入账号和密码进行支付。
S1813,用户确认车牌信息有误
S1814,进行人工支付处理。
具体地,用户可以在车载的显示屏上主动输入账号和密码进行支付。
本申请实施例中,能够判断支付二维码中的车牌信息和账号绑定的车牌信息是否一致,进而进行不同的处理。当支付二维码中的车牌信息和账号绑定的车牌信息不一致时,车辆能够通知用户进行处理,通过这样的方式,能够在识别的车牌信息有误或者车牌信息不存在的情况下,通知用户介入,能够有效提高用户支付的准确率。
本申请实施例还提供用于实现以上任一种方法的装置,例如,提供一种装置包括用以实现以上任一种方法中装置或车辆所执行的各步骤的单元(或手段)。
图19是本申请实施例提供的支付装置1900示意图。该装置1900可应用于图1的车辆100中。
该装置1900可以包括检测单元1910、获取单元1920和处理单元1930。检测单元1910用于检测车辆外部的环境。获取单元1920可以实现相应的通信功能,获取单元1920还可以称为通信接口或通信单元用于获取数据。处理单元1930用于进行数据处理。处理单元1930可以读取存储单元中的指令和/或数据,以使得装置实现前述方法实施例。
可选地,该装置1900还包括存储单元,用于存储相应的指令和/或数据,
一种可能的实现方式中,该装置1900包括:检测单元1910,用于检测到车辆进入或驶离停车场;获取单元1920,用于通过第一摄像装置获取第一图像信息,所述第一图像信息为所述车辆外部的图像信息,所述第一图像信息包括第一支付码;处理单元1930,用于识别所述第一支付码,得到所述车辆待缴纳的停车费用;所述获取单元1920,还用于通过第二摄像装置获取用户的第一生物特征信息,所述第二摄像装置为获取所述车辆内部图像的摄像装置;在所述第一生物特征信息与第二生物特征信息匹配的情况下,所述处理单元1930,还用于使用第一用户的账户支付所述待缴纳的停车费用,所述第二生物特征信息为所述第一用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户。
一种可能的实现方式中,在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,所述处理单元1930,还用于使用第二用户的账户支付所述待缴纳的停车费用,所述第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第二用户。
一种可能的实现方式中,所述获取单元1920,还用于通过所述第一摄像装置获取第 二图像信息;所述获取单元1920,具体用于在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用的情况下,通过所述第一摄像装置获取所述第一图像信息。
一种可能的实现方式中,所述第二图像信息包括所述第一支付码,所述处理单元1930,还用于根据所述第一支付码在所述第二图像中的位置坐标与所述第二图像信息的中心位置坐标,确定所述第一摄像装置的控制参数;所述处理单元1930,还用于根据所述控制参数控制所述第一摄像装置获取所述第一图像信息,所述第一支付码在所述第一图像信息的中心位置。
一种可能的实现方式中,所述获取单元1920,还用于获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;所述处理单元1930,具体用于在所述第一车牌信息与第二车牌信息一致的情况下,使用所述第一用户的账户支付所述待缴纳的停车费用,所述第二车牌信息为与所述第一用户账户绑定的车牌信息。
一种可能的实现方式中,所述获取单元1920,还用于获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;所述处理单元1930,还用于在所述第一车牌信息与第二车牌信息不一致的情况下,向所述第一用户提示所述第一车牌信息未与所述第一用户账户绑定,所述第二车牌信息为与所述第一用户账户绑定的车牌信息;所述处理单元1930,具体用于在检测到所述第一用户将所述第一车牌信息与所述第一用户的账号绑定时,支付所述待缴纳的停车费用。
一种可能的实现方式中,所述第一图像信息还包括第二支付码,所述第一支付码对应第一支付平台,所述第二支付码对应第二支付平台,所述处理单元1930,具体用于在所述第一用户使用所述第一支付平台支付的频率大于使用所述第二支付平台支付的频率情况下,使用所述第一支付平台支付所述待缴纳的停车费用。
一种可能的实现方式中,所述获取单元1920,还用于通过所述第一摄像装置获取第三图像信息,所述第三图像信息中的第一像素占比大于第一阈值;所述处理单元1930,还用于根据所述第一像素占比,将所述车灯的亮度调整为第一亮度;所述处理单元1930,具体用于在所述第一亮度下通过所述第一摄像装置获取所述第一图像信息。
一种可能的实现方式中,所述第一摄像装置为行车记录仪或环视摄像头,所述第二摄像装置为深度摄像头。
一种可能的实现方式中,该装置1900包括:获取单元1920,用于获取车辆待缴纳的停车费用;所述获取单元1920,还用于获取用户的第一生物特征信息;处理单元1930,用于在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,使用第二用户的账户支付所述待缴纳的停车费用。其中,所述第二生物特征信息为第一用户在所述车辆中预设的生物特征信息,第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户和所述第二用户。
应理解,以上装置中各单元的划分仅是一种逻辑功能的划分,实际实现时可以全部或部分集成到一个物理实体上,也可以物理上分开。此外,装置中的单元可以以处理器调用软件的形式实现;例如装置包括处理器,处理器与存储器连接,存储器中存储有指令,处理器调用存储器中存储的指令,以实现以上任一种方法或实现该装置各单元的功能,其中处理器例如为通用处理器,例如,图形处理器(graphics processing unit,GPU)或微处理 器,存储器为装置内的存储器或装置外的存储器。或者,装置中的单元可以以硬件电路的形式实现,可以通过对硬件电路的设计实现部分或全部单元的功能,该硬件电路可以理解为一个或多个处理器;例如,在一种实现中,该硬件电路为专用集成电路(application-specific integrated circuit,ASIC),通过对电路内元件逻辑关系的设计,实现以上部分或全部单元的功能;再如,在另一种实现中,该硬件电路为可以通过可编程逻辑器件(programmable logic device,PLD)实现,以现场可编程门阵列(field programmable gate array,FPGA)为例,其可以包括大量逻辑门电路,通过配置文件来配置逻辑门电路之间的连接关系,从而实现以上部分或全部单元的功能。以上装置的所有单元可以全部通过处理器调用软件的形式实现,或全部通过硬件电路的形式实现,或部分通过处理器调用软件的形式实现,剩余部分通过硬件电路的形式实现。
可选地,若该装置1900位于车辆中,上述处理单元1930可以是图1所示的处理器131。
可选地,上述处理单元1930可以是图20中的处理器2020,上述存储单元可以是图20中的存储器2010,上述获取单元1920可以是图20中的通信接口2030。
图20是本申请实施例提供的支付装置2000示意图。该装置2000可应用于图1的车辆100中。
该支付装置2000包括:存储器2010、处理器2020、以及通信接口2030。其中,存储器2010、处理器2020,通信接口2030通过内部连接通路相连,该存储器2010用于存储指令,该处理器2020用于执行该存储器2020存储的指令,以控制输入/输出接口2030接收/发送第二信道模型的至少部分参数。可选地,存储器2010既可以和处理器2020通过接口耦合,也可以和处理器2020集成在一起。
需要说明的是,上述通信接口2030使用例如但不限于收发器一类的收发装置,来实现通信设备1000与其他设备或通信网络之间的通信。上述通信接口2030还可以包括输入/输出接口(input/output interface)。
处理器2020存储有一个或多个计算机程序,该一个或多个计算机程序包括指令。当该指令被所述处理器2020运行时,使得该支付装置2000执行上述各实施例中支付方法技术方案。
可选地,该装置1900或装置2000可以位于图1中的车辆100中。
可选地,该装置1900或装置2000可以为图1中车辆中的计算平台130。
在实现过程中,上述方法的各步骤可以通过处理器2020中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法可以直接体现为硬件处理器执行完成,或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器2010,处理器2020读取存储器2010中的信息,结合其硬件完成上述方法的步骤。为避免重复,这里不再详细描述。
本申请实施例还提供一种计算机可读介质,所述计算机可读介质存储有程序代码,当所述计算机程序代码在计算机上运行时,使得所述计算机执行上述图9至图18中的任一种方法。
本申请实施例还提供一种芯片,包括:至少一个处理器和存储器,所述至少一个处理 器与所述存储器耦合,用于读取并执行所述存储器中的指令,以执行上述图9至图18中的任一种方法。
本申请实施例还提供一种智能车辆,包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,以执行上述图9至图18中的任一种方法。
本申请实施例还提供一种智能车辆,包括图19或图20任一种支付装置。
在本申请实施例中,处理器是一种具有信号的处理能力的电路,在一种实现中,处理器可以是具有指令读取与运行能力的电路,例如CPU、微处理器、GPU、或数字信号处理器(digital signal processor,DSP)等;在另一种实现中,处理器可以通过硬件电路的逻辑关系实现一定功能,该硬件电路的逻辑关系是固定的或可以重构的,例如处理器为ASIC或PLD实现的硬件电路,例如FPGA。在可重构的硬件电路中,处理器加载配置文档,实现硬件电路配置的过程,可以理解为处理器加载指令,以实现以上部分或全部单元的功能的过程。此外,还可以是针对人工智能设计的硬件电路,其可以理解为一种ASIC,例如,神经网络处理单元(neural network processing unit,NPU)、张量处理单元(tensor processing unit,TPU)、深度学习处理单元(deep learning processing unit,DPU)等。
在实现过程中,上述方法的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法可以直接体现为硬件处理器执行完成,或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器,闪存、只读存储器,可编程只读存储器或者上电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器,处理器读取存储器中的信息,结合其硬件完成上述方法的步骤。为避免重复,这里不再详细描述。
应理解,本申请实施例中,该存储器可以包括只读存储器和随机存取存储器,并向处理器提供指令和数据。
还应理解,本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系。
还应理解,在本申请的各种实施例中,上述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请实施例的实施过程构成任何限定。
在本说明书中使用的术语“部件”、“模块”等用于表示计算机相关的实体、硬件、固件、硬件和软件的组合、软件、或执行中的软件。例如,部件可以是但不限于,在处理器上运行的进程、处理器、对象、可执行文件、执行线程、程序和/或计算机。通过图示,在计算设备上运行的应用和计算设备都可以是部件。一个或多个部件可驻留在进程和/或执行线程中,部件可位于一个计算机上和/或分布在2个或更多个计算机之间。此外,这些部件可从在上面存储有各种数据结构的各种计算机可读介质执行。部件可例如根据具有一个或多个数据分组(例如来自与本地系统、分布式系统和/或网络间的另一部件交互的二个部件的数据,例如通过信号与其它系统交互的互联网)的信号通过本地和/或远程进程来通信。
本领域普通技术人员可以意识到,结合本文中所公开的实施例描述的各示例的单元及 算法步骤,能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行,取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能,但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统、装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统、装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。
所述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(Read-Only Memory,ROM)、随机存取存储器(Random Access Memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (22)

  1. 一种支付方法,其特征在于,所述方法包括:
    检测到车辆进入或驶离停车场;
    通过第一摄像装置获取第一图像信息,所述第一图像信息为所述车辆外部的图像信息,所述第一图像信息包括第一支付码;
    识别所述第一支付码,得到所述车辆待缴纳的停车费用;
    通过第二摄像装置获取用户的第一生物特征信息,所述第二摄像装置为获取所述车辆内部图像的摄像装置;
    在所述第一生物特征信息与第二生物特征信息匹配的情况下,使用第一用户的账户支付所述待缴纳的停车费用,所述第二生物特征信息为所述第一用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户。
  2. 如权利要求1所述的方法,其特征在于,所述方法还包括:
    在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,使用第二用户的账户支付所述待缴纳的停车费用,所述第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第二用户。
  3. 如权利要求1或2所述的方法,其特征在于,在所述通过所述第一摄像装置获取第一图像信息之前,所述方法还包括:
    通过所述第一摄像装置获取第二图像信息;
    在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用的情况下,通过所述第一摄像装置获取所述第一图像信息。
  4. 如权利要求3所述的方法,其特征在于,所述第二图像信息包括所述第一支付码,所述在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用时,通过所述第一摄像装置获取所述第一图像信息,包括:
    根据所述第一支付码在所述第二图像中的位置坐标与所述第二图像信息的中心位置坐标,确定所述第一摄像装置的控制参数;
    根据所述控制参数控制所述第一摄像装置获取所述第一图像信息,所述第一支付码在所述第一图像信息的中心位置。
  5. 如权利要求1至4任一项所述的方法,其特征在于,在所述使用第一用户的账户支付所述待缴纳的停车费用之前,所述方法还包括:
    获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;
    其中,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:
    在所述第一车牌信息与第二车牌信息一致的情况下,使用所述第一用户的账户支付所述待缴纳的停车费用,所述第二车牌信息为与所述第一用户账户绑定的车牌信息。
  6. 如权利要求1至4任一项所述的方法,其特征在于,在所述使用第一用户的账户支付所述待缴纳的停车费用之前,所述方法还包括:
    获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;
    在所述第一车牌信息与第二车牌信息不一致的情况下,向所述第一用户提示所述第一车牌信息未与所述第一用户账户绑定,所述第二车牌信息为与所述第一用户账户绑定的车牌信息;
    其中,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:
    在检测到所述第一用户将所述第一车牌信息与所述第一用户的账号绑定时,支付所述待缴纳的停车费用。
  7. 如权利要求1至6任一项所述的方法,其特征在于,所述第一图像信息还包括第二支付码,所述第一支付码对应第一支付平台,所述第二支付码对应第二支付平台,所述使用第一用户的账户支付所述待缴纳的停车费用,包括:
    在所述第一用户使用所述第一支付平台支付的频率大于使用所述第二支付平台支付的频率情况下,使用所述第一支付平台支付所述待缴纳的停车费用。
  8. 如权利要求1至7任一项所述的方法,其特征在于,在通过所述第一摄像装置获取第一图像信息之前,所述方法还包括:
    通过所述第一摄像装置获取第三图像信息,所述第三图像信息中的第一像素占比大于第一阈值;
    根据所述第一像素占比,将所述车灯的亮度调整为第一亮度;
    所述通过所述第一摄像装置获取第一图像信息包括:在所述第一亮度下通过所述第一摄像装置获取所述第一图像信息。
  9. 如权利要求1至8任一项所述的方法,其特征在于,所述第一摄像装置为行车记录仪或环视摄像头,所述第二摄像装置为深度摄像头。
  10. 一种支付装置,其特征在于,所述装置包括:
    检测单元,用于检测到车辆进入或驶离停车场;
    获取单元,用于通过第一摄像装置获取第一图像信息,所述第一图像信息为所述车辆外部的图像信息,所述第一图像信息包括第一支付码;
    处理单元,用于识别所述第一支付码,得到所述车辆待缴纳的停车费用;
    所述获取单元,还用于通过第二摄像装置获取用户的第一生物特征信息,所述第二摄像装置为获取所述车辆内部图像的摄像装置;
    在所述第一生物特征信息与第二生物特征信息匹配的情况下,所述处理单元,还用于使用第一用户的账户支付所述待缴纳的停车费用,所述第二生物特征信息为所述第一用户在所述车辆中预设的生物特征信息,所述用户包括所述第一用户。
  11. 如权利要求10所述的支付装置,其特征在于,
    在所述第一生物特征信息与所述第二生物特征信息不匹配,且所述第一生物特征信息与第三生物特征信息相匹配的情况下,所述处理单元,还用于使用第二用户的账户支付所述待缴纳的停车费用,所述第三生物特征信息为所述第二用户在所述车辆中预设的生物特征信息,所述用户包括所述第二用户。
  12. 如权利要求10或11所述的支付装置,其特征在于,
    所述获取单元,还用于通过所述第一摄像装置获取第二图像信息;
    所述获取单元,具体用于在通过所述第二图像信息识别不出所述车辆待缴纳的停车费用的情况下,通过所述第一摄像装置获取所述第一图像信息。
  13. 如权利要求12所述的支付装置,其特征在于,所述第二图像信息包括所述第一支付码,
    所述处理单元,还用于根据所述第一支付码在所述第二图像中的位置坐标与所述第二图像信息的中心位置坐标,确定所述第一摄像装置的控制参数;
    所述处理单元,还用于根据所述控制参数控制所述第一摄像装置获取所述第一图像信息,所述第一支付码在所述第一图像信息的中心位置。
  14. 如权利要求10至13任一项所述的支付装置,其特征在于,
    所述获取单元,还用于获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;
    所述处理单元,具体用于在所述第一车牌信息与第二车牌信息一致的情况下,使用所述第一用户的账户支付所述待缴纳的停车费用,所述第二车牌信息为与所述第一用户账户绑定的车牌信息。
  15. 如权利要求10至13任一项所述的支付装置,其特征在于,
    所述获取单元,还用于获取第一车牌信息,所述第一车牌信息为所述车辆的车牌信息;
    所述处理单元,还用于在所述第一车牌信息与第二车牌信息不一致的情况下,向所述第一用户提示所述第一车牌信息未与所述第一用户账户绑定,所述第二车牌信息为与所述第一用户账户绑定的车牌信息;
    所述处理单元,具体用于在检测到所述第一用户将所述第一车牌信息与所述第一用户的账号绑定时,支付所述待缴纳的停车费用。
  16. 如权利要求10至15任一项所述的支付装置,其特征在于,所述第一图像信息还包括第二支付码,所述第一支付码对应第一支付平台,所述第二支付码对应第二支付平台,
    所述处理单元,具体用于在所述第一用户使用所述第一支付平台支付的频率大于使用所述第二支付平台支付的频率情况下,使用所述第一支付平台支付所述待缴纳的停车费用。
  17. 如权利要求10至16任一项所述的支付装置,其特征在于,
    所述获取单元,还用于通过所述第一摄像装置获取第三图像信息,所述第三图像信息中的第一像素占比大于第一阈值;
    所述处理单元,还用于根据所述第一像素占比,将所述车灯的亮度调整为第一亮度;
    所述处理单元,具体用于在所述第一亮度下通过所述第一摄像装置获取所述第一图像信息。
  18. 如权利要求10至17任一项所述的支付装置,其特征在于,所述第一摄像装置为行车记录仪或环视摄像头,所述第二摄像装置为深度摄像头。
  19. 一种支付装置,其特征在于,包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,以执行如权利要求1至9中任一项所述的方法。
  20. 一种计算机可读介质,其特征在于,所述计算机可读介质存储有程序代码,当所述计算机程序代码在计算机上运行时,使得所述计算机执行如权利要求1至9中任一项所述的方法。
  21. 一种芯片,其特征在于,包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,以执行如权利要求1至9中任一项所述的方法。
  22. 一种车辆,其特征在于,包括:至少一个处理器和存储器,所述至少一个处理器与所述存储器耦合,用于读取并执行所述存储器中的指令,以执行如权利要求1至9中任一项所述的方法。
PCT/CN2022/137558 2022-05-30 2022-12-08 支付方法、装置以及车辆 WO2023231360A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210600490.3 2022-05-30
CN202210600490.3A CN117236944A (zh) 2022-05-30 2022-05-30 支付方法、装置以及车辆

Publications (1)

Publication Number Publication Date
WO2023231360A1 true WO2023231360A1 (zh) 2023-12-07

Family

ID=89026876

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/137558 WO2023231360A1 (zh) 2022-05-30 2022-12-08 支付方法、装置以及车辆

Country Status (2)

Country Link
CN (1) CN117236944A (zh)
WO (1) WO2023231360A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108573533A (zh) * 2018-05-09 2018-09-25 西安艾润物联网技术服务有限责任公司 费用支付方法、装置、系统及存储介质
CN110766814A (zh) * 2018-07-27 2020-02-07 比亚迪股份有限公司 车辆支付方法、装置及车辆钥匙
CN112419516A (zh) * 2020-10-26 2021-02-26 腾讯科技(深圳)有限公司 一种信息处理方法、系统、装置及存储介质
CN112541980A (zh) * 2020-12-18 2021-03-23 支付宝(杭州)信息技术有限公司 车载装置、车载终端系统、支付方法及非暂态计算机可读存储介质
CN114373233A (zh) * 2022-01-04 2022-04-19 中国银联股份有限公司 支付方法、装置、设备及计算机可读存储介质
CN114511315A (zh) * 2020-11-17 2022-05-17 博泰车联网科技(上海)股份有限公司 车载摄像移动支付的方法及计算机存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108573533A (zh) * 2018-05-09 2018-09-25 西安艾润物联网技术服务有限责任公司 费用支付方法、装置、系统及存储介质
CN110766814A (zh) * 2018-07-27 2020-02-07 比亚迪股份有限公司 车辆支付方法、装置及车辆钥匙
CN112419516A (zh) * 2020-10-26 2021-02-26 腾讯科技(深圳)有限公司 一种信息处理方法、系统、装置及存储介质
CN114511315A (zh) * 2020-11-17 2022-05-17 博泰车联网科技(上海)股份有限公司 车载摄像移动支付的方法及计算机存储介质
CN112541980A (zh) * 2020-12-18 2021-03-23 支付宝(杭州)信息技术有限公司 车载装置、车载终端系统、支付方法及非暂态计算机可读存储介质
CN114373233A (zh) * 2022-01-04 2022-04-19 中国银联股份有限公司 支付方法、装置、设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN117236944A (zh) 2023-12-15

Similar Documents

Publication Publication Date Title
US11115646B2 (en) Exposure coordination for multiple cameras
TWI706342B (zh) 業務執行方法及裝置
US10877485B1 (en) Handling intersection navigation without traffic lights using computer vision
US11785183B2 (en) Sensor device and signal processing method
KR20220016184A (ko) 차량의 도어 잠금 해제 방법 및 장치, 시스템, 차량, 전자 기기 및 기억 매체
US11173838B2 (en) Switchable display during parking maneuvers
US20230037777A1 (en) Vehicle-searching guidance method and apparatus, terminal device, electronic device, and computer-readable storage medium
CN110435670A (zh) 车辆控制装置以及计算机可读存储介质
US11470268B2 (en) Sensor device and signal processing method
CN112581641A (zh) 车辆收费方法、存储介质和电子设备
US20200074060A1 (en) User authentication device and method for triggering user-specific target operation
KR20180125858A (ko) 차량의 동작을 제어하는 전자 장치 및 방법
WO2023069250A1 (en) Vehicle door interface interactions
US11199854B2 (en) Vehicle control system, apparatus for classifying markings, and method thereof
WO2023231360A1 (zh) 支付方法、装置以及车辆
KR102433345B1 (ko) 차량 카메라를 이용한 정보 제공 서비스 방법 및 장치
KR102414984B1 (ko) 영상 인식 기술을 이용한 주차 관리 시스템 및 장치
US11351963B2 (en) User authentication device and method using authentication score
KR102174863B1 (ko) 자율주행 차량의 외장 디스플레이 인터랙션 장치 및 방법
CN114639260A (zh) 用于车辆之间的智能交互方法、交互系统和计算机可读的介质
CN115223143A (zh) 用于自动驾驶车辆的图像处理方法、装置、设备及介质
KR20210035360A (ko) 교행 다차로를 위한 차량번호 인식방법 및 장치
CN112215748A (zh) 图像处理方法和装置
RU2793737C1 (ru) Способ интеллектуальной парковки и устройства для его реализации
CN112477886B (zh) 无人驾驶车辆的控制方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22944661

Country of ref document: EP

Kind code of ref document: A1