WO2022174750A1 - 一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品 - Google Patents

一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品 Download PDF

Info

Publication number
WO2022174750A1
WO2022174750A1 PCT/CN2022/075803 CN2022075803W WO2022174750A1 WO 2022174750 A1 WO2022174750 A1 WO 2022174750A1 CN 2022075803 W CN2022075803 W CN 2022075803W WO 2022174750 A1 WO2022174750 A1 WO 2022174750A1
Authority
WO
WIPO (PCT)
Prior art keywords
key
vehicle
multimedia
information
guidance
Prior art date
Application number
PCT/CN2022/075803
Other languages
English (en)
French (fr)
Inventor
孙中阳
张宇
Original Assignee
腾讯科技(深圳)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 腾讯科技(深圳)有限公司 filed Critical 腾讯科技(深圳)有限公司
Publication of WO2022174750A1 publication Critical patent/WO2022174750A1/zh
Priority to US17/968,550 priority Critical patent/US20230037777A1/en

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/005Traffic control systems for road vehicles including pedestrian guidance indicator
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/141Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
    • G08G1/144Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces on portable or mobile units, e.g. personal digital assistant [PDA]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/451Execution arrangements for user interfaces
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/94Hardware or software architectures specially adapted for image or video understanding
    • G06V10/95Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/20Scenes; Scene-specific elements in augmented reality scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/40Scenes; Scene-specific elements in video content
    • G06V20/46Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/146Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas where the parking area is a limited parking space, e.g. parking garage, restricted space
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/145Traffic control systems for road vehicles indicating individual free spaces in parking areas where the indication depends on the parking areas
    • G08G1/148Management of a network of parking areas
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/149Traffic control systems for road vehicles indicating individual free spaces in parking areas coupled to means for restricting the access to the parking space, e.g. authorization, access barriers, indicative lights
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/20Monitoring the location of vehicles belonging to a group, e.g. fleet of vehicles, countable or determined number of vehicles
    • G08G1/205Indicating the location of the monitored vehicles as destination, e.g. accidents, stolen, rental

Definitions

  • the present application relates to the field of Internet of Vehicles, and in particular, to a method, device, terminal device, electronic device, computer-readable storage medium, and program product for finding a car.
  • Embodiments of the present application provide a method, device, terminal device, electronic device, computer-readable storage medium, and program product for finding a vehicle, which can improve the efficiency of finding a vehicle.
  • An embodiment of the present application provides a car-finding guidance method, where the method is executed by a terminal device, including:
  • a car-finding guidance interface is displayed; wherein, the car-finding guidance interface is used to provide guidance information for car-finding;
  • the multimedia guidance content records the environmental information of the parking space where the vehicle is located;
  • the target object is instructed to find the vehicle.
  • An embodiment of the present application provides a method for searching for a car, and the method is executed by an electronic device, including:
  • the multimedia guidance content In response to the multimedia content acquisition request, acquire corresponding multimedia guidance content, wherein the multimedia guidance content records the environmental information of the parking space where the vehicle is located, and the multimedia guidance content is collected based on the vehicle-mounted collection device;
  • the embodiment of the present application provides a car-finding guidance device, including:
  • an information display module configured to display a car-searching guidance interface in response to a first trigger operation for the first control; wherein the car-searching guidance interface is used to provide guidance information for car-searching;
  • a first sending module configured to send a multimedia content acquisition request to the electronic device in response to a second trigger operation on the second control on the car-finding guidance interface
  • a first receiving module configured to receive multimedia guidance content returned by the electronic device for the multimedia content acquisition request, wherein the multimedia guidance content records environmental information of the parking space where the vehicle is located;
  • the information display module is further configured to guide the target object to find the vehicle by playing the multimedia guidance content.
  • the embodiment of the present application provides a car-finding guidance device, including:
  • a second receiving module configured to receive a multimedia content acquisition request sent by the terminal device
  • a video acquisition module configured to acquire corresponding multimedia guidance content in response to the multimedia content acquisition request, wherein the multimedia guidance content records the environmental information of the parking space where the vehicle is located, and the multimedia guidance content is collected based on the vehicle-mounted collection device get;
  • the second sending module is configured to send the multimedia guidance content to the terminal device, where the multimedia guidance content is used to guide the target object to find the vehicle.
  • An embodiment of the present application provides a terminal device for car-finding guidance, including:
  • a first memory for storing executable instructions
  • the first processor is configured to implement the terminal device-side vehicle search guidance method provided by the embodiment of the present application when executing the executable instructions stored in the first memory.
  • An electronic device for car-finding guidance is provided in the embodiments of the present application, including:
  • a second memory for storing executable instructions
  • the second processor is configured to implement the method for finding a car on the electronic device side provided by the embodiment of the present application when executing the executable instructions stored in the second memory.
  • the embodiments of the present application provide a computer-readable storage medium, which stores executable instructions, which are used to cause the first processor to execute the car-finding guidance method on the terminal device side provided by the embodiments of the present application; When executed by the second processor, the method for finding a car on the side of the electronic device provided by the embodiment of the present application is implemented.
  • An embodiment of the present application provides a computer program product, including a computer program or an instruction, where the computer program or instruction is used to implement the method for finding a car on the terminal device side provided by the embodiment of the present application when the computer program or instruction is executed by a first processor, or When the second processor is caused to execute, the electronic device-side processing method provided by the embodiment of the present application is implemented.
  • the embodiment of the present application has the following beneficial effects: when the terminal device detects the second trigger operation on the second control of the car-finding guidance interface, it determines that the target object has a need to guide the car-finding through multimedia guidance content, and sends a multimedia content acquisition request , and receive the returned multimedia guidance content that records the environmental information of the parking space, and display the multimedia guidance content, so as to provide the target object with the environmental details of the parking space through the multimedia guidance content, thereby increasing the information provided when searching for a car.
  • the amount of information provided by the target object reduces the time required for the target object to search for a parking space where its own vehicle is parked, and improves the efficiency of searching for a vehicle.
  • Fig. 1 is a schematic diagram of a vehicle-mounted collection device
  • Fig. 2 is another schematic diagram of the vehicle-mounted collection device
  • FIG. 3 is an optional schematic structural diagram of a car-finding guidance system provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of the terminal device in FIG. 3 provided by an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of implementing the electronic device in FIG. 3 as a server according to an embodiment of the present application;
  • FIG. 6 is an optional schematic flowchart of a car-finding guidance method provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a parking lot information interface provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of a car search guidance interface provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of playing multimedia guide content provided by an embodiment of the present application.
  • FIG. 10 is a schematic diagram of receiving a trigger operation for a third control provided by an embodiment of the present application.
  • 11A is a schematic diagram of a progress prompt indicator provided by an embodiment of the present application.
  • 11B is a schematic diagram of a key frame provided by an embodiment of the present application.
  • FIG. 12 is a schematic diagram of an enhancement effect of key guidance information provided by an embodiment of the present application.
  • FIG. 13 is another optional schematic flowchart of the car-finding guidance method provided by the embodiment of the present application.
  • FIG. 14 is a schematic diagram of a process of finding a vehicle by means of a mobile phone provided by an embodiment of the present application.
  • references to “some embodiments”, “one or more embodiments” describe a subset of all possible embodiments, but it is understood that “some embodiments”, “one or more implementations” Examples” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict.
  • first ⁇ second ⁇ third is only used to distinguish similar objects, and does not represent a specific ordering of objects. It is understood that “first ⁇ second ⁇ third” is used in Where permitted, the specific order or sequence may be interchanged to enable the embodiments of the application described herein to be practiced in sequences other than those illustrated or described herein.
  • AI Artificial Intelligence
  • a comprehensive technique of computer science that attempts to understand the essence of intelligence and generate a new kind of intelligent machine that can respond in a similar way to human intelligence.
  • Artificial intelligence is to study the design principles and implementation methods of various intelligent machines, so that the machines have the functions of perception, reasoning and decision-making.
  • Artificial intelligence technology is a comprehensive discipline with a wide range of design fields, including both hardware-level technology and software-level technology.
  • the basic technologies of artificial intelligence generally include technologies such as sensors, special artificial intelligence chips, cloud computing, distributed storage, big data processing technology, operation/interaction systems, and mechatronics.
  • Artificial intelligence software technology mainly includes computer vision technology, speech processing technology, natural language processing technology, and machine learning/deep learning.
  • Computer Vision is a science that studies how to make machines "see”. Further, it refers to the use of cameras and computers instead of human eyes to identify, track and measure targets. And further image processing, so that computer processing becomes more suitable for human eye observation or transmission to the instrument detection image.
  • Computer vision technology usually includes image processing, image recognition, image semantic understanding, image retrieval, OCR, video processing, video semantic understanding, video content/behavior recognition, 3D object reconstruction, 3D technology, virtual reality, augmented reality, simultaneous localization and mapping It also includes common biometric identification technologies such as face recognition and fingerprint recognition.
  • Machine Learning is a multi-field interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in how computers simulate or realize human learning behaviors to acquire new knowledge or skills, and to reorganize existing knowledge structures to continuously improve their performance.
  • Machine learning is the core of artificial intelligence and the fundamental way to make computers intelligent, and its applications are in all fields of artificial intelligence.
  • Machine learning and deep learning usually include artificial neural networks, belief networks, reinforcement learning, transfer learning, inductive learning and other techniques.
  • Searching for a car refers to the process of a user searching for a parking space where his own vehicle is parked. For example, the user parks the vehicle in the parking space, such as the parking space of a shopping mall and then enters the shopping mall for shopping. After completing the shopping and leaving the shopping mall, he needs to return to the parking lot to find out which parking space his vehicle is parked in. This process, Also sometimes called reverse car hunt.
  • Vehicle-mounted acquisition device refers to a camera mounted on a vehicle and capable of photographing the surrounding environment of the vehicle.
  • the vehicle-mounted collection device includes cameras such as a camera on a driving recorder installed in the vehicle, a surround-view camera, and a 360-degree panoramic camera around the vehicle.
  • FIG. 1 is a schematic diagram of a vehicle-mounted acquisition device.
  • a driving recorder 1-1 is installed in the center of the windshield of the vehicle.
  • the vehicle-mounted acquisition device may be a camera installed on the driving recorder.
  • Fig. 2 is another schematic diagram of the vehicle-mounted acquisition device. As shown in Fig.
  • the vehicle-mounted acquisition device may include a front-view camera mounted on the head of the vehicle body for photographing the road conditions 2-1 directly in front of the vehicle; the vehicle-mounted acquisition device may include The rear-view camera installed at the rear of the vehicle body is used to photograph the road conditions directly behind the vehicle 2-2; the vehicle-mounted acquisition device may include a left-view camera installed on the left side of the vehicle body to photograph the road conditions on the left side of the vehicle 2-3; The collection device may also include a right-view camera installed on the right side of the vehicle body to capture road conditions 2-4 on the right side of the vehicle. Since the front-view camera, rear-view camera, left-view camera and right-view camera can respectively capture the surrounding situation of the vehicle from different perspectives, the front-view camera, rear-view camera, left-view camera and right-view camera are all surround view cameras. Camera.
  • one or more of the executed operations may be real-time or may have a set delay; Unless otherwise specified, there is no restriction on the order of execution of multiple operations to be executed.
  • Embodiments of the present application provide a method, device, terminal device, electronic device, computer-readable storage medium, and program product for finding a vehicle, which can improve the efficiency of finding a vehicle.
  • the terminal device for car-finding guidance provided by the embodiments of the present application may be implemented as a notebook computer, a tablet computer, a desktop computer, a set-top box, a mobile device (for example, a mobile phone, a portable music player, a personal digital assistant, a dedicated message device, a portable Various types of user terminals such as game equipment), the electronic device for car-finding guidance provided in this embodiment of the present application may be implemented as a vehicle-mounted terminal, or may be implemented as a server.
  • FIG. 3 is an optional schematic diagram of the architecture of a car-finding guidance system provided by an embodiment of the present application.
  • the terminal device 400 connects to the server through the network 300 200 or the in-vehicle terminal 500 (respectively, an implementation manner of an electronic device), and the network 300 may be a wide area network or a local area network, or a combination of the two.
  • the terminal device 400 In response to the first trigger operation for the first control displayed on the graphical interface 410, the terminal device 400 displays a car-finding guidance interface on the graphical interface 410, wherein the car-finding guidance interface is used to provide guidance information for car-finding.
  • the terminal device 400 detects the second trigger operation on the second control on the car search guidance interface, in response to the second trigger operation for the second control, it sends a multimedia content acquisition request to the server 200 or the vehicle-mounted terminal 500 through the network 300 , and receive the multimedia guidance content returned by the server 200 or the vehicle terminal 500 for the multimedia content acquisition request, wherein the multimedia guidance content records the environmental information of the parking space where the vehicle is located, and the multimedia guidance content can be obtained by the vehicle collection device.
  • the terminal device 400 will guide the target object to find the vehicle by playing the multimedia guidance content.
  • the terminal device 400 can be connected to the vehicle terminal through Bluetooth, Wi-Fi, mobile network (such as 5G network, 4G network, etc.), near field communication technology (Near Field Communication, NFC), etc. 500 or the server 200 , and then acquire the multimedia guidance content from the in-vehicle terminal 500 or the server 200 .
  • mobile network such as 5G network, 4G network, etc.
  • NFC Near Field Communication
  • the terminal device 400 can determine whether to acquire the multimedia guidance content from the vehicle-mounted terminal 500 or the server 200 according to whether a connection is established with the vehicle-mounted terminal 500 . For example, when the terminal device 400 establishes a connection with the vehicle terminal 500 through Bluetooth and NFC, the terminal device 400 can directly send a multimedia content acquisition request to the vehicle terminal 500; when the terminal device 400 does not establish a connection with the vehicle terminal 500, it can A multimedia content acquisition request is sent to the server 200 through Wi-Fi or a mobile network.
  • the environmental information of the parking route can include the image information of the floor where the parking space is located, the image information of the route from the entrance of the parking lot to the parking space, the image information of the landmarks passed by the vehicle during the driving process, and the information of the passing signs. Image information, image information of the numbers of other parking spaces passed by, etc.
  • the environmental information of the parking space corresponding to the vehicle may include image information of the number of the parking space, image information of other cars parked around the parking space, and the like.
  • the server 200 may be an independent physical server, or may be a server cluster or distributed system composed of multiple physical servers, or may provide cloud services, cloud databases, cloud computing, cloud functions, Cloud servers for cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and basic cloud computing services such as big data and artificial intelligence platforms.
  • the terminal device 400 may be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto.
  • the terminal device and the server may be directly or indirectly connected through wired or wireless communication, which is not limited in this embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of the terminal device in FIG. 3 provided by an embodiment of the present application.
  • the terminal device 400 shown in FIG. 4 includes: at least one first processor 410, a first memory 450, at least one first A network interface 420 and a first user interface 430.
  • the various components in the terminal device 400 are coupled together by a first bus system 440 .
  • the first bus system 440 is used to realize the connection and communication between these components.
  • the first bus system 440 also includes a power bus, a control bus and a status signal bus.
  • the various buses are labeled as the first bus system 440 in FIG. 4 .
  • the first processor 410 may be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, Discrete hardware components, etc., where a general purpose processor may be a microprocessor or any conventional processor or the like.
  • DSP Digital Signal Processor
  • the first user interface 430 includes one or more first output devices 431 that enable presentation of media content, including one or more speakers and/or one or more visual display screens.
  • the first user interface 430 also includes one or more first input devices 432, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, and other input buttons and controls.
  • the first memory 450 may be removable, non-removable, or a combination thereof.
  • Exemplary hardware devices include solid state memory, hard drives, optical drives, and the like.
  • the first memory 450 optionally includes one or more storage devices that are physically remote from the first processor 410 .
  • the first memory 450 includes volatile memory or nonvolatile memory, and may also include both volatile and nonvolatile memory.
  • the non-volatile memory may be a read-only memory (ROM, Read Only Memory), and the volatile memory may be a random access memory (RAM, Random Access Memory).
  • ROM read-only memory
  • RAM random access memory
  • the first memory 450 described in the embodiments of the present application is intended to include any suitable type of memory.
  • the first memory 450 can store data to support various operations, and examples of the data include programs (for example, executable instructions for implementing the method for finding a car on the terminal device side in this embodiment of the present application), modules and data structures, or a subset or superset thereof, exemplified below.
  • programs for example, executable instructions for implementing the method for finding a car on the terminal device side in this embodiment of the present application
  • modules and data structures or a subset or superset thereof, exemplified below.
  • the first operating system 451 includes system programs for processing various basic system services and performing hardware-related tasks, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks;
  • the first network communication module 452 is used to reach other computing devices via one or more (wired or wireless) first network interfaces 420.
  • Exemplary first network interfaces 420 include: Bluetooth, wireless compatibility certification (Wi-Fi ), and Universal Serial Bus (USB, Universal Serial Bus), etc.;
  • a first presentation module 453 for enabling presentation of information (eg, for operating peripherals and displays) via one or more first output devices 431 (eg, a display screen, speakers, etc.) associated with the first user interface 430 user interface for content and information);
  • first output devices 431 eg, a display screen, speakers, etc.
  • a first input processing module 454 for detecting one or more user inputs or interactions from one of the one or more first input devices 432 and translating the detected inputs or interactions.
  • the car-finding and guiding device 455 may be implemented in software.
  • FIG. 4 shows the car-finding and guiding device 455 stored in the first memory 450, which may be software in the form of programs and plug-ins, including the following software Modules: an information display module 4551, a first sending module 4552 and a first receiving module 4553, these modules are logical, and therefore can be arbitrarily combined or further split according to the functions implemented. The function of each module will be explained below.
  • FIG. 5 is a schematic structural diagram of implementing the electronic device in FIG. 3 as a server according to an embodiment of the present application.
  • the server 200 shown in FIG. 5 includes: at least one second processor 210, a second memory 250, at least one The second network interface 220 and the second user interface 230 .
  • the various components in server 200 are coupled together by second bus system 240 .
  • the second bus system 240 is used to realize the connection and communication between these components.
  • the second bus system 240 also includes a power bus, a control bus and a status signal bus.
  • the various buses are labeled as the second bus system 240 in FIG. 5 .
  • the second processor 210 may be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gate or transistor logic devices, Discrete hardware components, etc., where a general purpose processor may be a microprocessor or any conventional processor or the like.
  • DSP Digital Signal Processor
  • the implementation of the second user interface 230 is similar to that of the first user interface 430, and the description is not repeated.
  • the second memory 250 can store data to support various operations, and examples of such data include programs (for example, executable instructions for implementing the method for finding a car on the electronic device side provided by the embodiments of the present application), modules, and A data structure, or a subset or superset thereof, is exemplified below.
  • the embodiment of the second operating system 251 is similar to that of the first operating system 451, and the description will not be repeated;
  • the implementation of the second network communication module 252 is similar to that of the first network communication module 452, and the description is not repeated;
  • the implementation of the second presentation module 253 is similar to that of the first presentation module 453, and the description is not repeated;
  • the implementation of the second input processing module 254 is similar to that of the first input processing module 454, and the description is not repeated.
  • the car-finding and guiding device 255 may be implemented in software.
  • FIG. 5 shows the car-finding guiding device 255 stored in the second memory 250 , which may be in the form of programs and plug-ins.
  • software including the following software modules: the second receiving module 2551, the video acquisition module 2552, the second sending module 2553, the video recording module 2554, these modules are logical, so according to the realized functions can be combined arbitrarily or further split. The function of each module will be explained below.
  • the electronic device may be implemented as the vehicle-mounted terminal 500 in FIG. 3 or the server 200 in FIG. 3 , and the structure of the vehicle-mounted terminal 500 in FIG. 3 may be similar to the structure of the server 200 in FIG. Repeat instructions.
  • FIG. 6 is an optional schematic flowchart of the car-finding guidance method provided by the embodiment of the present application, which will be described with reference to the steps shown in FIG. 6 .
  • the terminal device displays a car-searching guidance interface in response to a first trigger operation for the first control.
  • the car-finding guidance method in the embodiment of the present application is implemented in a scenario where the target object needs to drive away from the parking lot after the target object parks his vehicle in the parking lot.
  • the target object parks the vehicle in the underground parking lot of a shopping center, and After shopping, you need to find a parking space with your own vehicle and drive out of the shopping center, or the target object drives into the above-ground parking lot in the express service area and needs to leave the service area.
  • the terminal device will detect whether the target object has performed the first triggering operation on the first control, so as to distinguish whether the target object has the requirement of obtaining the guidance information of car-finding.
  • the terminal device When the terminal device detects that the target object has performed the first trigger operation on the first control, it will confirm that the target object has the need to obtain the guidance information for car-finding, so that in response to the first trigger operation acting on the first control, Create a car-finding guidance interface, and display the car-finding guidance interface on the display interface of the terminal device, so that the target object can obtain guidance information when searching for a car. That is to say, the car-finding guidance interface is used to provide guidance information for car-finding.
  • the target object may be a user who is currently looking for a vehicle, or an intelligent robot that helps the user to find the vehicle.
  • the first control can be set in the parking lot information interface, so that the target object can trigger the first control in the parking lot information interface after the terminal device enters the parking lot information interface.
  • the parking lot information interface can be entered by the target object scanning the parking lot information QR code, parking lot information barcode, etc. What is searched for and entered by the name of the field may also be matched and entered by the terminal device according to the current geographic location of the target object, etc., which is not limited here.
  • the basic information of the parking lot may be provided in the parking lot information interface, for example, the name of the parking lot, the geographic location of the parking lot, the opening time of the parking lot, and the charging standard of the parking lot.
  • the parking lot information interface may also include information related to the target object (in this case, the parking lot information interface can be bound with the identity information of the target object), for example, the parking time of the target object, the time the target object enters the parking lot, the payment costs, etc.
  • the first control may be set in the first area of the parking lot information interface, wherein the size and location of the first area may be set according to actual conditions.
  • the first area is set at the bottom of the parking lot information interface, and the size is set to 100 ⁇ 50, or the first area is set at the upper right corner of the parking lot information interface, and the size is set to 50 ⁇ 50. This is not limited.
  • FIG. 7 is a schematic diagram of a parking lot information interface provided by an embodiment of the present application.
  • a basic information display area 7-11 and a target object information display area 7-12 are set in the parking lot information interface 7-1.
  • the basic information display area 7-11 the basic information of the parking lot is displayed, that is, the name of the parking lot: service area parking lot 7-111, the opening time of the parking lot: open all day 7-112, the charging standard of the parking lot : 2 yuan/hour 7-113.
  • the target object information display area 7-12 the duration of the parking of the target object is displayed: 2 hours has been parked 7-121, and the time when the vehicle enters the parking lot: 14:00 into 7-122.
  • there is a first control that is, a car search guide mark 7-13.
  • the target object can click on the car search guide mark 7-13 to enter the car search guide interface.
  • the first trigger operation may be an operation such as a click, a double-click, or an operation such as a long press, a slide, etc., which is not limited herein.
  • the car search guidance interface may include a text information display area and a video playback area.
  • the graphic information display area is used to provide the target object with guidance information in the form of graphic and text, for example, the number of the parking space of the vehicle where the target object is parked, the orientation of the parking space in the parking lot, pictures of the surrounding environment of the parking space, etc.
  • the video play area can provide guidance information in the form of video to the target object.
  • the graphic information display area may be set in the second area of the car-finding guidance interface, and the video playing area may be set in the third area of the car-finding guidance interface.
  • the sizes and positions of the second area and the third area can be set according to actual conditions, which are not limited here.
  • set the second area on the upper half of the car-finding guidance interface set the third area on the lower half of the car-finding guidance interface, and set the width of both the second area and the third area to the width of the car-finding guidance interface.
  • Width set the height of the second area and the third area to be half of the height of the car-finding guidance interface.
  • set the second area on the left half of the car search guidance interface set the third area on the right half of the car search guidance interface, and set the width of the second area and the third area to the width of the car search guidance interface.
  • Half of the width set the height of the second area and the third area to the height of the car-finding guidance interface.
  • FIG. 8 is a schematic diagram of a car search guidance interface provided by an embodiment of the present application.
  • a video playback area 8-11 and a graphic information display area 8-12 are provided in the car search guidance interface 8-1.
  • the video playback area 8-11 is used to play the video that guides the target object to search for the car in reverse
  • the graphic information display area 8-12 displays the guidance information with graphic and text: parking space number: B2-11 8-121, parking space orientation: 8-122 directly in front of the elevator, photo 8-123 of the surroundings of the parking space.
  • the terminal device sends a multimedia content acquisition request to the electronic device in response to a second trigger operation on the second control on the car-finding guidance interface.
  • a second control is provided on the car-finding guidance interface.
  • the triggering operation is the second triggering operation, so that the terminal device will determine that the target object has the ability to search for a parking space by means of multimedia guidance content. requirements, and in response to the second trigger operation, a multimedia content acquisition request is generated, and the multimedia content acquisition request is sent to the electronic device.
  • the electronic device receives the multimedia content acquisition request sent by the terminal device.
  • the second control may be a button in the car-finding guidance interface for triggering acquisition of guidance content, for example, a "get guidance content” button, a “get route when parking” button, and the like. It can also be a link that triggers getting the guide content.
  • the electronic device may be implemented as a vehicle-mounted terminal; in other embodiments, the electronic device may be implemented as a server.
  • the terminal device can send the multimedia content acquisition request to the vehicle terminal device or server through Bluetooth, Near Field Communication (NFC), Wi-Fi, etc.
  • the terminal device can use the mobile network, for example, 5G, 4G network and so on, sending the multimedia content acquisition request to the server.
  • the electronic device acquires the corresponding multimedia guide content in response to the multimedia content acquisition request.
  • the electronic device After receiving the multimedia content acquisition request, the electronic device will respond to the received multimedia content acquisition request, and acquire the multimedia guidance content collected when the vehicle is parked, so as to provide the multimedia guidance content to the target object subsequently.
  • the multimedia guidance content records the environmental information of the parking space where the vehicle is located, and the multimedia guidance content is collected based on the vehicle-mounted collection device.
  • the multimedia guidance content may include not only rich environmental information, but also timing information, and the environmental information can be formed into a sequence in the time dimension, so that the target object can determine the sequence of various events, so that the The road multimedia guidance content can better record the situation around the parking space, so that the target object can find his vehicle according to these situations.
  • the multimedia guidance content may be a continuous image including environmental information around the parking space, or may be a video including environmental information around the parking space, which is not limited herein.
  • the electronic device may directly use continuous images or videos containing environmental information around the parking space as multimedia guidance content, or may first perform redundant information on the continuous images or videos containing environmental information around the parking space culling, and updating the obtained key route video or key route image set to multimedia guidance content.
  • the redundant information may include repeated landmark images, repeated environmental information of parking spaces, and the like.
  • the electronic device sends the multimedia guidance content to the terminal device, where the multimedia guidance content is used to guide the target object to find the vehicle.
  • the electronic device delivers the multimedia guidance content to the terminal device, so that the terminal device can display the multimedia guidance content.
  • the terminal device receives the multimedia guidance content after sending the multimedia content acquisition request. Therefore, the terminal device receives the multimedia guidance content returned by the electronic device for the multimedia content acquisition request.
  • the electronic device when an electronic device is required to collect multimedia guidance content, the electronic device may be implemented as a vehicle-mounted terminal, that is, the vehicle-mounted terminal invokes the vehicle-mounted acquisition device to collect the multimedia guidance content, and the multimedia guidance content is collected. The content is sent to the end device.
  • the electronic device when the electronic device is required to generate a key route video or key image set and update the generated key route video or key image set to multimedia guidance content, the electronic device can be implemented as a vehicle-mounted terminal or a server, that is, through the vehicle-mounted terminal or It is the server that de-redundantly updates the multimedia guidance content, and then the vehicle-mounted terminal or the server sends the updated multimedia guidance content to the terminal device.
  • the multimedia guidance content of the server when the electronic device is implemented as a server, the multimedia guidance content of the server can be received from the vehicle-mounted terminal.
  • the terminal device guides the target object to find the vehicle by playing the multimedia guidance content.
  • the terminal device plays the multimedia guidance content in the form of video in the video playback area of the car search guidance interface, or displays it in the graphic information display area of the car search guidance interface, that is, statically plays the multimedia guidance content in the form of graphics and text, so as to enrich the
  • the image information of the parking space is displayed to the target object, so that the target object can move to the parking space with its own vehicle by walking or other means, so as to realize the guidance process of the target object to find the vehicle, thereby saving the time for the target object to find the vehicle.
  • an adjustment mark is also set in the video playback area.
  • the terminal device can enlarge the size of the video playback area to a full screen, so as to realize full screen playback of the parking route video, so as to facilitate the target Object gets details.
  • the terminal device can also continue to receive the zoom operation of the target object, so as to adjust the size of the video play area by the zoom ratio, so that the target object can adjust the video play area.
  • FIG. 9 is a schematic diagram of playing multimedia guidance content provided by an embodiment of the present application.
  • the terminal device plays the multimedia guidance content in the video playing area 9-1, but because the area of the video playing area 9-1 is small, This makes it inconvenient for the target object to watch.
  • the video playback area 9-1 occupies the entire display interface of the terminal device.
  • the terminal device when the terminal device detects the second trigger operation on the second control on the car-finding guidance interface, it will determine that the target object has the need to guide the reverse car-finding through multimedia content, and send a multimedia content acquisition request, And receive the returned multimedia guidance content that records the environmental information of the parking space, and display the multimedia guidance content, so as to provide the target object with the environmental details of the parking space through the multimedia guidance content, thereby increasing the information provided to the target when searching for a car.
  • the amount of information provided by the object reduces the time required for the target object to find a parking space with its own vehicle, and improves the efficiency of finding the vehicle.
  • the vehicle-mounted collection device collects the environmental information of the parking route, it is very likely to capture the payment code pasted on the wall of the parking lot or on the pillar, so that the multimedia guidance content includes the payment code.
  • Video frame the payment code in the payment code video frame is recorded as the third control, then after the terminal device plays the multimedia guidance content in the play area, that is, after S105, the method may further include: S106, as follows:
  • the terminal displays a payment page in response to the triggering operation for the third control. Among them, the payment page is used for the target object to complete the parking payment.
  • the parking lot does not have charging staff, but charges the parking fee through a payment code, that is, a third control.
  • the parking space of the vehicle where the target object is parked may be far away from the payment code, which causes inconvenience for the target object to pay the parking fee. Therefore, in one or more embodiments, when the multimedia guidance content includes the payment code video frame, the terminal device may detect the target object for the payment code in the payment code video frame, that is, after the triggering operation of the third control, In response to the triggering operation, a payment page is generated and displayed, so that the target object can complete parking payment through the payment page.
  • the triggering operation for the third control may only be a double-click operation of the target object, or may be a long-press operation of the target object, or may be other operations that can achieve the same goal, which is implemented in this application.
  • the example is not limited here.
  • the payment code may be a two-dimensional code, a barcode, or a graphic code in other forms, which is not specifically limited in this embodiment of the present application.
  • FIG. 10 is a schematic diagram of receiving a trigger operation for a third control provided by an embodiment of the present application.
  • the payment code is a two-dimensional code pasted on the post, and the terminal device can first receive the target object's long-press operation on the area where the two-dimensional code 10-2 (third control) in the payment code video frame 10-1 is located , and then a pop-up window 10-3 pops up around the two-dimensional code 10-2.
  • the pop-up window is set with the identification button 10-31 for the two-dimensional code.
  • the terminal device receives the trigger operation of the target object for the identification button , it will jump to the payment interface.
  • the multimedia guidance content includes a payment code video frame
  • the terminal device can display the payment page when detecting a triggering operation of the target object on the third control in the payment code video frame, so as to realize the multimedia guidance-based
  • the content helps the target object to complete the parking fee payment process, reduces the time for the target object to find the payment code, and improves the convenience of the target object to pay the parking fee.
  • the multimedia guidance content further records the environmental information of the parking route, wherein the parking route represents the route traveled by the vehicle from the entrance of the parking lot to the stop of driving.
  • the multimedia guidance content corresponds to a progress bar, and the progress bar corresponding to the multimedia guidance content displays a progress prompt sign.
  • the terminal device guides the target object to find the vehicle by playing the multimedia guidance content, that is, the specific implementation process of S105 may include: S1051, as follows:
  • the terminal device jumps to the key frame corresponding to the progress indication sign in response to the triggering operation for the progress indication sign, and plays multimedia guidance content from the key frame corresponding to the progress indication sign to guide the target object to find the vehicle.
  • the terminal device detects the triggering operation of the target object on the progress bar of the multimedia guidance content, so as to determine whether the target object adjusts the playback progress of the multimedia guidance content through the triggering operation.
  • the terminal device detects the triggering operation of the target object for the progress indicator of the progress bar, it determines that the target object needs to skip some less important guidance content, and directly obtain the key guidance information from the multimedia guidance content.
  • the device In response to the trigger operation, the device will directly jump from the current video frame played by the multimedia guidance content to the key frame corresponding to the progress indicator to start playing.
  • the key frame records key guidance information, and the key guidance information starts from The environmental information of the parking route and the environmental information of the parking space are extracted.
  • the terminal device After the terminal device jumps from the current video frame to the key frame, it will continue to play the multimedia guidance content from the key frame until the multimedia guidance content is played.
  • the terminal device When the multimedia guidance content is in the form of video, the terminal device starts to play the video from the key frame, so as to realize the playback of the multimedia guidance content; when the multimedia guidance content is in the form of images or graphics, the terminal device can display the multimedia content through static display. Directs the playback of content.
  • the key guidance information may include: number information of the parking space, landmark information passed by the parking route, floor information of the parking space, payment code, appearance information of other vehicles adjacent to the vehicle, At least one of environmental information directly in front of the parking space and a look-around image of the parking space.
  • the surround-view image of the parking space may be captured by a surround-view camera of the vehicle body.
  • the electronic device may further synthesize an overhead image of the parking space according to the image captured by the surround-view camera, and use the overhead image of the parking space as key guidance information.
  • the key frame may also include one or more images or video frames, because the key guidance information is likely to be scattered in different video frames or images, in this case, each of the key frames
  • the video frames or images may have corresponding progress indication signs, so that the target object can quickly jump the playback progress to these video frames or images.
  • FIG. 11A is a schematic diagram of a progress indication indicator provided by an embodiment of the present application. As shown in FIG. 11A , there is a progress bar corresponding to the multimedia guidance content, and at 04:01 of the progress bar, the key guidance information is set in the form of solid dots. A progress indication mark, when the target object clicks the mark, the terminal device will continue to play the multimedia guidance content from 04:01.
  • FIG. 11B is a schematic diagram of a key frame provided by an embodiment of the present application.
  • the key frame includes video frames of appearance information of other vehicles adjacent to the vehicle of the target object, that is, video frames 11-11, including the positive image of the parking space.
  • the terminal device in order to make the key guidance information in the key frame more conspicuous, the terminal device adds some enhancement effects to the key guidance information in the key frame, thereby making the key guidance information more conspicuous and prominent. That is to say, the method for finding a car on the terminal device side provided by the embodiment of the present application may further include:
  • the terminal device When playing the multimedia guidance content by starting from the key frame corresponding to the progress indication identifier, the terminal device displays an enhancement effect for the key guidance information, and the enhancement effect can include all effects that can make the key guidance information more conspicuous.
  • the enhancement effects include: at least one of arrows, callout boxes, star effects, and flicker effects.
  • FIG. 12 is a schematic diagram of the enhancement effect of the key guidance information provided by the embodiment of the present application.
  • the key guidance information is the number of the parking space, and the terminal device can mark the number of the parking space with a frame Mark it out to make the number more eye-catching;
  • the key guidance information is the landmark, that is, the indication mark of the elevator in Building B, and the terminal device can add a star effect to the indication mark, so that the indication mark is in the key It is more prominent in the video frame;
  • the key guidance information is the floor information where the parking space is located, that is, the second underground floor, so the terminal device will add an arrow pointing to the floor information around the floor information to show Highlight the floor information.
  • the terminal device when the terminal device detects that the target object triggers the progress indication indicator in the progress bar of the multimedia guidance content containing the environmental information of the parking route, it will directly jump from the currently playing video frame to the video frame containing the key guidance information. From the key frame, the multimedia guidance content continues to be played, thereby reducing the time for the target object to obtain key guidance information, and continuing to improve the efficiency of finding vehicles.
  • FIG. 13 is another optional schematic flowchart of the method for finding a car provided by an embodiment of the present application.
  • the multimedia guidance content also records the environmental information of the parking route
  • the electronic device can call the vehicle-mounted collection device to collect the video or image of the environmental information of the parking route, so that when the terminal device responds to the first control for the first control
  • the method may further include: S201-S202, as follows:
  • the electronic device analyzes the real-time driving environment of the vehicle to obtain an analysis result.
  • the electronic device when the vehicle is in a driving state, continuously analyzes the real-time driving environment of the vehicle to confirm whether the target object has entered the parking lot, thereby obtaining the analysis result. That is to say, in the embodiment of the present application, the analysis result represents whether the vehicle has entered the parking lot.
  • the electronic device may capture image information or video of the real-time driving environment of the vehicle through the vehicle-mounted acquisition device, and then identify the captured image or video to determine whether the vehicle has entered a parking lot. In other embodiments, the electronic device may obtain the real-time location information of the vehicle through the positioning device, and then combine the real-time location information of the vehicle and the location information of the geo-fence of the parking lot on the digital map to determine whether the vehicle has entered the parking lot field.
  • the electronic device may further determine whether the vehicle has entered the parking lot through information such as the target object's voice, gesture, and the like. For example, the electronic device can determine that the vehicle has entered the parking lot after receiving the sentence "entering the parking lot, start recording" spoken by the target object, or detect obvious changes in light intensity, such as light suddenly darkened, it was judged that the vehicle had entered the parking lot.
  • the electronic device collects the environmental information of the parking route and the parking space from the time the vehicle enters the parking lot to the stop of driving through the vehicle-mounted collection device, and obtains multimedia guidance content.
  • the electronic device When the electronic device determines that the vehicle has entered the parking lot, it will call the on-board acquisition device, and use the on-board acquisition device to collect the environmental information of the route from the time the vehicle enters the parking lot to the time when the vehicle completely stops, and for The environmental information of the parking space where the vehicle is parked is collected until it is determined that the collection ends when the vehicle is parked according to the sensor data of the vehicle, and the multimedia guidance content is obtained.
  • These environmental information intuitively show the location where the vehicle traveled when parking and the real situation of the parking space. Look for the vehicle that has parked itself in the follow-up target object.
  • the electronic device may determine the angular velocity collected by the angular velocity sensor in the vehicle's relational measurement unit (Inertial Measurement Unit, IMU) in combination with the acceleration collected by the acceleration sensor. Whether the vehicle has completely stopped running; the electronic device can also judge whether the vehicle has completely stopped running through the wheel speed measured by the wheel speed sensor of the vehicle; the electronic device can also detect the stillness of the picture captured by the vehicle-mounted collection device through the detection network. The electronic device can also judge whether the vehicle has completely stopped running through whether the vehicle's flameout signal is received or not.
  • IMU Inertial Measurement Unit
  • the vehicle-mounted acquisition device includes a front-facing camera mounted on the driving recorder, and may also include a surround-view camera mounted on the vehicle body.
  • the electronic device can call the front camera and the surround view camera at the same time to collect the multimedia guidance content, and can also collect the multimedia guidance content only through any one of the front camera and the surround view camera, which is not limited here.
  • the surround-view camera may start to collect multimedia guidance content after the target object is manually turned on, which is not limited in this embodiment of the present application.
  • the electronic device when collecting the environmental information of the parking route and the environmental information of the parking space through the vehicle-mounted collection device, the electronic device may also adjust the shooting parameters of the vehicle-mounted collection device according to the environment of the parking lot, so that the The quality of multimedia guidance content has been improved.
  • the shooting parameters such as the aperture and sensitivity of the vehicle-mounted acquisition device can be increased, and the shutter can be adjusted.
  • the aperture, sensitivity and other shooting parameters are adjusted above the numerical threshold, and the shutter is adjusted below the numerical threshold, so as to ensure the quality of the multimedia guidance content.
  • the aperture, sensitivity and shutter of the vehicle-mounted acquisition device may not be adjusted.
  • the electronic device may also adjust the shooting parameters of the vehicle-mounted collection device according to weather conditions. For example, when the electronic device learns through the network that the current weather is rainy and snowy weather with insufficient light, or foggy weather, the aperture and sensitivity of the vehicle-mounted acquisition device can be adjusted to above the numerical threshold to ensure the quality of the multimedia guidance content. .
  • the electronic device in order to include as much important information as possible in the multimedia guidance content, can keep the frame rate of the on-board capture device above the frame rate threshold, for example, the frame rate of the on-board capture device is not less than every 5 frames per second. In other embodiments, in order to minimize the storage space occupied by the multimedia guidance content and the data consumption during transmission, the electronic device may keep the frame rate of the vehicle capture device below the frame rate threshold.
  • the frame rate of the acquisition device was set to 2 frames per second.
  • the electronic device when the electronic device collects the multimedia guidance content through the vehicle-mounted collection device, it may also preprocess the images captured by the vehicle-mounted collection device, such as scaling, cropping, and image quality enhancement, and then The preprocessed images are used to form the multimedia guidance content, thereby improving the quality of the multimedia guidance content.
  • preprocessed images are used to form the multimedia guidance content, thereby improving the quality of the multimedia guidance content.
  • the multimedia guidance content collected by the electronic device through the vehicle-mounted collection device can be stored in the local storage space of the electronic device, or uploaded to a cloud device such as a server through a network, as long as the content can be completely The multimedia guide content can be saved.
  • the multimedia guidance content may be the parking route video or the parking route image collection collected by the vehicle-mounted collection device, that is, the electronic device may directly record the parking route video or the parking route image collection without any processing.
  • the video or parking route image set is determined as multimedia guidance content, so that the unprocessed parking route video or parking route image set is sent to the terminal device in response to a multimedia content acquisition request sent by the terminal device subsequently.
  • the electronic device may also remove redundant information in the parking route video or the parking route image set, for example, select and retain a plurality of video frames or images whose similarity exceeds a certain threshold, and reserve the more blurred video frames or images. The video frames or images are removed, etc., so that the parking route video or the parking route image set after the redundant information is removed is determined as the multimedia guidance content.
  • the electronic device can also identify and extract key information in the parking route video or parking route image collection, and then add enhancement effects to the key information, and use the enhanced parking route video or parking route image collection as multimedia guidance content .
  • the electronic device can perform a series of processing processes such as extracting key frames, cropping, and extracting important instruction information on the collected parking route video or parking route image set, and then process the processed parking route video or parking route image. Collection, updated with multimedia guide content.
  • the electronic devices in S201-S202 may be implemented as vehicle-mounted terminals.
  • the electronic device continuously analyzes the real-time driving environment during the driving process of the vehicle, and only when the analysis result indicates that the vehicle has entered the parking lot will the vehicle-mounted acquisition device be called to capture the environmental information and information of the parking route.
  • the environmental information of the parking space can obtain the multimedia guidance content, which realizes the effect of automatically starting the collection of the multimedia guidance content according to the driving scene of the vehicle, and improves the intelligence level of collecting the multimedia guidance content.
  • the multimedia guidance content is captured by the vehicle-mounted acquisition device, there is no need to set up additional cameras in the parking lot, so that the cost of the car-finding guidance system is lower.
  • the electronic device analyzes the real-time driving environment of the vehicle, and obtains the analysis result, that is, the specific implementation process of S201 may include: S2011-S2012, as follows:
  • the electronic device collects images or videos of the real-time driving environment of the vehicle through the vehicle-mounted collection device.
  • the electronic device uses the classification model to classify and process the images or videos of the real-time driving environment to obtain an analysis result.
  • the electronic device analyzes the real-time driving environment of the vehicle, it can collect the image or video of the real-time driving environment of the vehicle through the on-board acquisition device, and then input the image or video of the real-time driving environment into the classification model, so as to analyze the real-time driving environment through the classification model. Images or videos of the environment are classified to determine whether the real-time driving environment is the entrance to the parking lot. That is, the analysis result indicates whether the image or video of the real-time driving environment is the entrance scene of the parking lot. When the analysis result indicates that the image or video of the real-time driving environment is indeed the entrance scene of the parking lot, the electronic device determines the analysis result as the vehicle entering the parking lot. Correspondingly, when the analysis result indicates that the image or video of the real-time driving environment is not the entrance scene of the parking lot, the electronic device will determine the analysis result as the vehicle has not entered the parking lot. In this way, the electronic device will get the analysis result.
  • the image of the entrance scene of the parking lot may include the image of the parking lot entrance barrier, the image of the entrance of the underground parking lot, the image of the entrance of the surface parking lot, etc., and may also include the image of the entrance of the underground parking lot.
  • the indication signs, the name signs of the surface parking lot, etc., are not limited here.
  • the classification model may be a model trained using labeled entrance scene images of various parking lots.
  • the classification model may be a deep model such as a convolutional neural network (Convolutional Neural Networks, CNN) model, or a shallow machine learning model such as a support vector machine (Support Vector Machine, SVM), which is not limited in this embodiment of the present application.
  • CNN convolutional neural network
  • SVM Support Vector Machine
  • the electronics may further preprocess the images or videos of the real-time driving environment, such as scaling, cropping, and enhancing the images of the real-time driving environment.
  • the video of the real-time driving environment is compressed, framed, etc., to make the classification speed faster.
  • the electronic device can classify the images or videos of the real-time driving environment captured by the vehicle-mounted collection device, so as to determine whether the vehicle has entered the parking lot from the image dimension, which improves the collection and parking performance. How smart the route video is.
  • the electronic device analyzes the real-time driving environment of the vehicle, and obtains the analysis result, that is, the specific implementation process of S201 may also include: S2013, as follows:
  • the electronic device obtains the real-time geographic location of the vehicle through the positioning device, and determines the location relationship between the real-time geographic location and the geo-fence of the parking lot as an analysis result.
  • the electronic device can also continuously obtain the real-time geographic location of the vehicle through the positioning device on the vehicle. Next, the electronic device compares the real-time geographic location with the geo-fence of the parking lot provided by the digital map, and determines whether the real-time geographic location of the vehicle is inside the geo-fence, thereby obtaining an analysis result. That is, the analysis results are based on whether or not the real-time geographic location is inside the geofence.
  • the positioning device on the vehicle may be a Global Positioning System (Global Positioning System, GPS) locator, or a Beidou locator, which is not limited in this embodiment of the present application.
  • GPS Global Positioning System
  • Beidou locator which is not limited in this embodiment of the present application.
  • the electronic device compares the real-time geographic location with the geo-fence and finds that the real-time geographic location of the vehicle is inside the geo-fence, it will determine that the vehicle has entered the parking lot, and the analysis result will determine that the vehicle has entered the parking lot. Correspondingly, when the real-time geographic location is outside the geo-fence, the electronic device will determine the analysis result that the vehicle has not entered the parking lot.
  • S2011-S2012 and S2013 are two side-by-side implementations of S201, and the electronic device may choose one of these two implementations to implement according to the actual situation.
  • the electronic device can also compare the real-time geographic location of the vehicle with the geo-fence of the parking lot, so as to determine whether the vehicle has entered the parking lot according to the positioning information, which improves the intelligence of collecting parking route videos. degree.
  • the electronic device may also combine the real-time geographic location and light intensity of the vehicle to determine whether the vehicle has entered the parking lot. For example, when the distance between the real-time geographic location and the geofence is less than the distance threshold, and the light intensity suddenly falls below the intensity threshold, the vehicle is considered to have entered an underground parking lot; when the real-time geographic location is inside the geofence and the light intensity does not change, The vehicle is believed to have pulled into the surface parking lot.
  • the method may further include: S203-S204, as follows:
  • the electronic device extracts key frames from the multimedia guidance content.
  • key guidance information is recorded in the key frame, and the key guidance information is extracted based on the environmental information of the parking route and the environmental information of the parking space.
  • a key frame is a plurality of consecutive video frames in the multimedia guidance content. In other embodiments of the present application, the key frame is a plurality of independent video frames in the multimedia guidance content.
  • the electronic device constructs a key route video or a key route image set by using the key frame, and updates the key route video or the key route image set to multimedia guidance content.
  • the electronic device After the electronic device obtains the key frame, it will connect the key frame to the video in time sequence, and the obtained video is the key route video, or the key frame is directly formed into the key route image set, and then the key route video or key route video is formed.
  • the route image set is updated to the multimedia guidance content, so as to realize the de-redundancy of the multimedia guidance content, so that the multimedia guidance content received by the terminal device is more streamlined.
  • the key route video or the key route image set includes the payment information video or the payment information image set, the payment information video or the payment information image set is recorded with the payment code, and the key route video or the key route image set has a corresponding progress bar, the progress bar There is a progress indicator on the display, and the progress indicator corresponds to the key frame.
  • the electronic device can also remove the motion blur part in the key frame, and then use the key frame from which the motion blur has been removed to construct a key route video or a set of key route images, that is, the electronic device guides from the multimedia
  • the method may further include: S205, as follows:
  • the electronic device may input the key frame into the deep learning model for deblurring, and determine the output of the deblurring deep learning model as the optimization key frame.
  • the electronic device may also crop a map for removing the blurred part for the key frame from the adjacent frames of the key frame, and use the map to replace the blurred part in the key frame to obtain the optimized key frame.
  • the key frame is used to construct a key route video or a key route image set, that is, the specific implementation process of S204 can be changed to: S204A, as follows:
  • the key route video is spliced out by using the optimized key frame, or the key route image set is combined by using the optimized key frame, so that the quality of the key route video or the key route image set is better.
  • the electronic device in S203 may be implemented as a vehicle-mounted terminal, and the electronic device in S204 may be implemented as a server, so that the vehicle-mounted terminal may send the key frame to the server after extracting the key frame from the multimedia guidance content , the server uses the key frame to generate a key route video or a set of key route images, and updates the key route video frame or the set of key route images to multimedia guidance content to provide to the terminal device.
  • the electronic devices in S203-S204 can all be implemented as servers.
  • the server first receives the multimedia guidance content (such as parking route videos or parking route image sets) sent by the vehicle terminal without removing redundancy. , and then the server performs key frame extraction, key route video or key route image collection generation, and updating multimedia guidance content.
  • the multimedia guidance content such as parking route videos or parking route image sets
  • the electronic devices in S203-S204 can also be implemented as vehicle-mounted terminals, that is, after the vehicle-mounted terminal collects the multimedia guidance content (parking route video or parking route image set), the vehicle-mounted terminal can also It extracts key frames, generates key route videos or key route image sets, and updates multimedia guidance content.
  • the vehicle-mounted terminal collects the multimedia guidance content (parking route video or parking route image set)
  • the vehicle-mounted terminal can also It extracts key frames, generates key route videos or key route image sets, and updates multimedia guidance content.
  • the electronic device can extract key frames from the multimedia guidance content, generate a key route video or a set of key route images, and update the multimedia guidance content based on the key route video or key route image combination, thereby reducing the need for multimedia Redundancy of guidelines.
  • the electronic device extracts key frames from the multimedia guidance content, that is, the specific implementation process of S203 may include: performing one of the following processes on the multimedia guidance content, as follows:
  • the electronic device extracts key frames from the multimedia guidance content by taking the threshold of the distance traveled by the vehicle as the extraction interval.
  • the electronic device will detect the driving distance of the vehicle. Whenever the vehicle travels over the distance threshold, the electronic device will extract some video frames from each video frame of the multimedia guidance content. When the frame extraction is completed, the key frame can be obtained. .
  • the distance threshold may be set to 5 meters, may also be set to 10 meters, and may also be set to other values according to actual conditions, which are not limited in this embodiment of the present application.
  • the number of extracted video frames may be set to 1, may also be set to 3, or may be set to other values according to actual conditions, which is not limited in this embodiment of the present application.
  • the distance traveled by the vehicle is proportional to the speed of the vehicle, that is, the greater the distance traveled by the vehicle in the same time period, the greater the travel speed of the vehicle.
  • the distance traveled by the vehicle is the threshold value. Extracting the interval and extracting some video frames can ensure that the frame sampling interval changes with the speed of the vehicle, that is, the faster the vehicle travels, the smaller the frame sampling interval, and the slower the vehicle travels. The frame interval will be larger. In this way, it will be ensured that sufficient environmental information can be collected even when the vehicle is traveling at a high speed.
  • the electronic device selects a target frame interval corresponding to the real-time driving environment from a plurality of frame intervals according to the real-time driving environment of the vehicle, and extracts key frames from the multimedia guidance content according to the target frame interval.
  • the electronic device can also find out the target frame sampling interval corresponding to the real-time driving environment from multiple frame sampling intervals according to the environment of the location where the vehicle is driven, and then follow the target frame sampling interval.
  • the frame extraction interval is used to extract the frame of the multimedia guidance content to obtain the key frame.
  • the frame sampling interval may be set according to actual requirements, for example, the frame sampling interval is set to 10, or set to 8, etc., which is not limited in this embodiment of the present application.
  • the electronic device when the electronic device selects the corresponding target frame sampling interval from multiple frame sampling intervals according to the real-time driving environment, it can be in some places that do not require retaining more environmental information, according to the larger frame sampling interval. In some places where it is required to retain enough environmental information, the frame sampling is carried out according to a smaller frame sampling interval, so as to realize the effect of adaptively adjusting the frame sampling interval according to the location where the vehicle travels.
  • the frame sampling interval corresponding to the parking lot entrance can be set to 10 frames; when the vehicle approaches the parking space, it is often necessary to retain more Therefore, the corresponding frame sampling interval can be set to 3 to retain enough environmental information.
  • the electronic device extracts the video frames in which the key guidance information is identified in the multimedia guidance content to obtain the key frames.
  • the electronic device can also identify whether the location where the vehicle travels contains key guidance information. When it is identified that the location where the vehicle is driving contains key guidance information, it will extract the video frame containing the key guidance information, and extract the extracted video frame. Video frames as keyframes.
  • the electronic device can determine the frame sampling interval and extract key frames based on the driving distance of the vehicle, or determine the frame sampling interval and extract key frames based on the real-time driving environment of the vehicle, or based on key guidance information. According to the identification result, the key target is extracted, so that the key frame can be adaptively extracted from the multimedia guidance content according to the driving situation of the vehicle, and the intelligence of the key frame extraction is improved.
  • the electronic device may also select some video frames from the video frames that have not been extracted to be added to the key frames. That is to say, after the electronic device extracts the key frame from the multimedia guidance content, and before constructing the key route video or the key route image set by using the key frame, that is, after S203 and before S204, the method may further include: S206, as follows:
  • the remaining content is the content other than the key frame in the multimedia guidance content, and the candidate video frames at least include: video frames containing text information, video frames when reversing, and video frames when containing two-dimensional codes.
  • the electronic device uses key frames to construct a key route video or a key route image set, that is, the specific implementation process of S204 can be changed to S204B, as follows:
  • the electronic device will select video frames containing text information, video frames when reversing, and video frames containing QR codes from other video frames except key frames, and add them to the key frames to re-create
  • a key route video or a key route image set is constructed by using the key frames supplemented with the video frame, so that the key route video or the key route image set contains more useful information.
  • the electronic device extracts the video frames in which the key guidance information is identified in the multimedia guidance content to obtain the key frames, that is, the specific implementation process of S2033 may include: S2033a-S2033b, as follows:
  • the electronic device recognizes the text of the video frame in the multimedia guidance content to obtain key guidance information.
  • Electronic devices can use deep learning, optical character recognition (Optical Character Recognition, OCR) and other technologies to perform text recognition on video frames in multimedia guidance content to obtain text information in these video frames, and then carry out the meaning of these text information. Analysis, and extract the key guidance information corresponding to the key frame from the text information.
  • OCR Optical Character Recognition
  • the electronic device can identify the number in the video frame, the number is the key guidance information, and the video frame is the key frame.
  • the electronic device extracts the video frames containing key guidance information to obtain key video frames.
  • the electronic device After identifying the key guidance information, the electronic device will extract the video frame containing the key guidance information from the multimedia guidance content, thereby obtaining the key frame. In some embodiments, the electronic device further determines the corresponding position of the key frame on the progress bar, so as to add a progress prompt sign on the position.
  • the electronic device will extract key guidance information from each video frame of the multimedia guidance content by means of text recognition, and then use the video frame containing the key guidance information as the key frame, thereby completing the process of extracting the key frame , which provides the intelligence of keyframe extraction.
  • the electronic device uses key frames to construct a specific implementation process of a key route video or a key route image set, that is, the specific implementation process of S204, which may include: S2041-S2042, and any of S2043 and S2044 One, as follows:
  • the electronic device selects the scan code video frame containing the scan code from the key frames.
  • the electronic device When constructing a key route video or a set of key route images, the electronic device also performs image recognition on the key frames one by one, extracts video frames containing scan codes from the key frames, and records these extracted video frames as scanned video frames.
  • the scan code includes a two-dimensional code and a barcode.
  • the electronic device determines the usage of the scan code in the scan code video frame, and obtains usage information of the scan code.
  • the electronic device identifies and parses the scan code in the scanned video frame, thereby judging the use of the scan code and obtaining the use information of the scan code. That is to say, in the embodiment of the present application, in order to prevent the target object from confusing the scan code for other purposes with the payment code for paying parking fees, the electronic device will first determine the purpose of the scan code in advance, so that it can be used in the key route video or the key route. Scancodes excluded from other uses in the route image collection.
  • the electronic device constructs a key route video or a key route image set by using the key frame including the scan code video frame.
  • the electronic device when the usage information of the scan code is not payment, the electronic device removes the scan code video frame from the key frame, and uses the key frame after the scan code video frame is removed to construct a key route video or a key route image set.
  • the electronic device when the electronic device determines that the scan code is not a payment code, it will remove the scan code video frame containing the scan code from the key frame, so as to exclude the scan code for other purposes from the key frame. After that, the electronic device will splicing the key frames after the scanning video frame is removed in time sequence to obtain the key route video frame, or directly form a set of the key frames after the scanning video frame is proposed to obtain the key route image. gather.
  • the electronic device can identify the scan code in the scan code video frame, and when determining that the scan code is not a payment code, delete the scan code video frame from the key video frame, thereby realizing the optimization of the key frame .
  • the vehicle-mounted collection device includes a front camera and a surround-view camera.
  • the electronic device through the vehicle-mounted collection device, obtains the environmental information of the parking route from the vehicle entering the parking lot to the time when the vehicle stops driving, And the environmental information of the parking space is collected to obtain the multimedia guidance content, that is, the specific implementation process of S202 may include: S2021, and one of S2022 and S2023, as follows:
  • the electronic device acquires the historical parking times of the vehicle in the parking lot.
  • the electronic device collects the environmental information of the parking route and the environmental information of the parking space, it can first distinguish whether the target object frequently visits the parking lot. At this time, the electronic device can count the time when the target object visited the parking lot in the historical time from the Internet or its own storage space, so as to obtain the historical parking times.
  • the electronic device uses the front camera and the surround-view camera as vehicle-mounted collection devices to collect the environmental information of the parking route and the environmental information of the parking space.
  • the electronic device will call the front camera and the surround view camera at the same time, and then use the front camera and the surround view camera as the vehicle collection device, and collect the environmental information of the parking route and the environmental information of the parking space at the same time, so as to obtain more abundant information.
  • the parking times threshold may be set according to actual requirements.
  • the parking times threshold may be set to 5 or 3, which is not limited in this embodiment of the present application.
  • the electronic device uses the front camera as a vehicle-mounted collection device to collect the environmental information of the parking route and the environmental information of the parking space.
  • the number of historical parking times is greater than or equal to the preset number of parking times, it means that the target object has visited the parking lot many times and is already familiar with the parking lot.
  • the environmental information and the environmental information of the parking space are collected to save the storage resources occupied by the multimedia guidance content.
  • the electronic device may not collect the multimedia guidance content, that is, neither the front camera nor the surround view camera is turned on.
  • the electronic device can obtain the historical parking times of the vehicle in the parking lot, and then determine whether the target object often visits the parking lot through the magnitude relationship between the historical parking times and the parking times threshold, so as to determine whether the target object should visit the parking lot frequently.
  • Which cameras are called to collect the environmental information of the parking route and the environmental information of the parking space, which improves the intelligence of the multimedia guidance content collection.
  • the surround-view camera may also start recording after the target object manually turns on the surround-view function, so that the surround-view camera can meet the needs of the target object.
  • the car-finding guidance method is implemented in a scenario where a user searches for a vehicle in a parking lot by means of a mobile phone.
  • the user can view the video from the mobile phone (terminal device) from the time the vehicle enters the parking lot to the time when the vehicle stops in the parking space (including the environmental information of the parking route and the environmental information of the parking space) ), this video was recorded by a vehicle-mounted capture device.
  • the video there may also be a payment QR code (payment code) of the parking lot, and the user can pay the parking fee through the payment QR code in the video.
  • useful information for the user includes, but is not limited to: the location of the landmark (the bottom information of the parking route), the parking floor (the floor information of the parking space), the QR code information of the parking payment (payment fee) code), the environment near the parking space, the number information of the vehicle and the parking space (the number information of the parking space, the appearance information of other vehicles adjacent to the vehicle), the information directly in front of the parking position (the environment information directly in front of the parking space) , a look around image (a look around image of a parking space).
  • FIG. 14 is a schematic diagram of a process of searching for a vehicle by means of a mobile phone provided in this embodiment. Referring to Figure 14, the process includes:
  • the vehicle-mounted terminal determines whether the vehicle enters the parking lot.
  • the in-vehicle terminal calls the in-vehicle acquisition device to collect the image of the environment near the vehicle (image or video of the real-time driving environment) at a certain frame rate, and judges that the vehicle has entered the low parking lot through the model or in combination with other information.
  • the vehicle-mounted terminal After judging that the vehicle has entered the underground parking lot, the vehicle-mounted terminal records images with a frame rate higher than the threshold, otherwise, records images with an array lower than the threshold.
  • the in-vehicle terminal determines whether the vehicle stops running.
  • the in-vehicle terminal combines data such as body sensors to determine whether to park or not. If yes, go to S305, if no, go to S303.
  • the in-vehicle terminal selects frames from the recorded images and uploads them to the cloud.
  • the in-vehicle terminal extracts some image frames (key frames) and uploads them to the cloud (server, an embodiment of an electronic device) or the user's mobile phone in combination with the speed of the vehicle and the text in the video during the recording process.
  • the cloud server, an embodiment of an electronic device
  • the user's mobile phone in combination with the speed of the vehicle and the text in the video during the recording process.
  • the cloud performs data analysis on the frames uploaded by the vehicle terminal, and generates a video for delivery to the mobile phone.
  • the cloud analyzes the received video frames, obtains useful information (key guidance information), and generates a video (updated to the multimedia guidance content of the key route video) distributed to the user.
  • the mobile phone receives the video and plays the video.
  • the phone plays a video on the display interface so that the user can view useful information.
  • the vehicle-mounted collecting device needs to capture a color image (image or video of the real-time driving environment) with sufficient clarity of environmental information near the vehicle, and the vehicle-mounted collecting device needs to be able to collect the road surface of the parking lot. In some cases, the viewing angle cannot be too inclined downwards or upwards.
  • the in-vehicle terminal can perform preprocessing corresponding to the image, such as scaling, cropping, and enhancement.
  • the in-vehicle terminal can identify the image of the environment near the vehicle through a classification model whose output is a discrete quantity, and a model (classification model) whose output content is a subdivided scene (classification result).
  • the subdivision scenarios can be: underground parking lot, above-ground parking lot, parking lot entrance bar, etc.
  • the output of the classification model can also be only a binary result, such as whether to start recording, etc.
  • the in-vehicle terminal can also combine GPS signals (real-time geographic location), the light intensity output by the light sensor, the geo-fence provided by the map information, etc., to determine whether it has entered the parking lot.
  • the vehicle-mounted terminal calls the vehicle-mounted acquisition device to start recording, and tries to maintain a larger aperture, higher sensitivity and smaller shutter during the recording process to ensure the recording quality.
  • the recording frame rate of the vehicle-mounted capture device cannot be too low to miss important information.
  • the frame rate is required to be no less than 5 frames per second, and the recording should be kept locally after the recording is completed.
  • the front camera keeps recording, and the surround-view camera can start recording after the user manually turns on the surround-view function.
  • the frame rate and other requirements are the same as above.
  • the vehicle-mounted terminal may determine whether the vehicle is stationary according to the angular velocity sensor in the inertial measurement unit combined with the acceleration sensor, may determine whether the vehicle is stationary according to the wheel speed measured by the wheel speed sensor, and may determine whether the vehicle is stationary according to the image captured by the vehicle-mounted acquisition device. still.
  • the vehicle terminal can extract some key frames (key frames) for upload.
  • the vehicle terminal can extract every x frames, and x changes dynamically with the vehicle speed. For example, when the vehicle speed is fast, x is small, and when the vehicle speed is slow, x increases, that is, try to ensure that the same distance is traveled every time.
  • the cloud detects and records key text information (key guidance information) for the key frame, so that it can be highlighted in the video playback progress bar later (prompted by a progress prompt indicator).
  • the cloud detects the QR code information (scanning code), parses the QR code and determines whether it is a parking payment QR code (payment code), and deletes it if it is not a payment QR code.
  • the cloud uses digital image processing technology or deep learning technology, such as the deblurgan2 model, to remove the dynamically blurred part of the image.
  • the cloud generates videos and distributes them to users.
  • the S307 runs on the user's mobile phone, which may be software, small programs, etc. on the mobile phone.
  • the mobile phone receives the user's download video operation, and then downloads the video for the user, or receives the user's click to identify the payment QR code (for the trigger operation of the third control), and pops up the payment interface for the user.
  • a video recording the period from entering the parking lot to the time when the car stops in the parking space can be provided to the user, so that the user can search for the car in reverse according to the video, and improve the reverse search process. efficiency of the car.
  • the video only needs to be collected through the vehicle terminal and uploaded to the cloud, no additional infrastructure investment is required, and the system complexity and cost will be lower.
  • the embodiments of the present application involves the real-time geographic location of the vehicle such as user information, the video or image of the environmental information of the parking lot where the user parks, and the video or image of the route when the user parks.
  • the embodiments of this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data need to comply with relevant laws and standards of relevant countries and regions.
  • the software stored in the car-finding guiding device 455 of the first memory 450 Modules can include:
  • the information display module 4551 is configured to display a car search guidance interface in response to a first trigger operation for the first control; wherein, the car search guidance interface is used to provide guidance information for car search;
  • the first sending module 4552 is configured to send a multimedia content acquisition request to the electronic device in response to a second trigger operation on the second control on the car-finding guidance interface;
  • the first receiving module 4553 is configured to receive the multimedia guidance content returned by the electronic device for the multimedia content acquisition request, wherein the multimedia guidance content records the environmental information of the parking space where the vehicle is located;
  • the information display module 4551 is further configured to guide the target object to find the vehicle by playing the multimedia guidance content.
  • the information display module 4551 is further configured to display a payment page in response to a triggering operation on the third control, wherein the payment page is used for the target object to complete parking payment.
  • the multimedia guidance content further records the environmental information of the parking route, and the progress bar corresponding to the multimedia guidance content displays a progress prompt sign;
  • the information display module 4551 is further configured to jump to the key frame corresponding to the progress prompt sign in response to the triggering operation for the progress prompt sign, and start playing from the key frame corresponding to the progress prompt sign.
  • the multimedia guidance content guides the target object to find the vehicle; wherein, key guidance information is recorded in the key frame, and the key guidance information is obtained from the environmental information of the parking route and the environmental information of the parking space extracted.
  • the information display module 4551 is further configured to display the enhancement for the key guidance information when the multimedia guidance content is played by starting from the key frame corresponding to the progress indication identifier
  • the enhancement effect includes at least one of arrows, callout boxes, star-shaped effects, and flickering effects.
  • the software stored in the car-finding and guiding device 255 of the second memory 250 Modules can include:
  • the second receiving module 2551 is configured to receive a multimedia content acquisition request sent by the terminal device
  • the video acquisition module 2552 is configured to acquire corresponding multimedia guidance content in response to the multimedia content acquisition request, wherein the multimedia guidance content records the environmental information of the parking space where the vehicle is located, and the multimedia guidance content is based on the vehicle-mounted collection device collected;
  • the second sending module 2553 is configured to send the multimedia guidance content to the terminal device, where the multimedia guidance content is used to guide the target object to find the vehicle.
  • the multimedia guidance content further records the environmental information of the parking route
  • the vehicle search guidance device 255 further includes: a video recording module 2554;
  • the video recording module 2554 is configured to analyze the real-time driving environment of the vehicle to obtain an analysis result; when the analysis result indicates that the vehicle has entered a parking lot, the vehicle is collected through the vehicle-mounted collection device.
  • the environment information of the parking route and the environment information of the parking space from entering the parking lot to stopping driving are collected to obtain the multimedia guidance content.
  • the video recording module 2554 is further configured to collect images or videos of the real-time driving environment of the vehicle through the vehicle-mounted collection device; The image or video of the environment is classified and processed to obtain the analysis result; or, through the positioning device, the real-time geographical position of the vehicle is obtained, and the positional relationship between the real-time geographical position and the geo-fence of the parking lot is determined as the results of the analysis.
  • the video recording module 2554 is further configured to extract key frames from the multimedia guide content, where key guide information is recorded in the key frames, and the key guide information is based on the The environmental information of the parking route and the environmental information of the parking space are extracted; using the key frame, a key route video or a set of key route images is constructed, and the video of the key route or the set of key route images is updated to the Multimedia guide content.
  • the video recording module 2554 is further configured to perform one of the following processes for the multimedia guidance content: taking the vehicle traveled distance threshold as an extraction interval, extracting data from the multimedia guidance content Extract the key frame; according to the real-time driving environment of the vehicle, from a plurality of frame extraction intervals, select the target frame extraction interval corresponding to the real-time driving environment, and according to the target frame extraction interval, from the multimedia Extracting the key frame from the guidance content; extracting the video frame in which the key guidance information is identified in the multimedia guidance content to obtain the key frame.
  • the video recording module 2554 is further configured to obtain the historical parking times of the vehicle in the parking lot; when the historical parking times is less than the parking times threshold, the front camera and the The surround-view camera is used as the vehicle-mounted collection device to collect the environmental information of the parking route and the environmental information of the parking space; when the historical parking times is greater than or equal to the parking times threshold, the front camera is used as the The in-vehicle collection device performs collection of the environmental information of the parking route and the environmental information of the parking space.
  • the video recording module 2554 is further configured to obtain candidate video frames from the remaining contents of the multimedia guidance content; Content other than the key frame, the candidate video frame at least includes: a video frame containing text information, a video frame when reversing, and a video frame when a two-dimensional code is included; using the key frame and the candidate video frame , and construct the key route video or the key route image set.
  • the video recording module 2554 is further configured to perform blurring removal on the key frames to obtain optimized key frames; and use the optimized key frames to construct the key route video or the key Route image collection.
  • the video recording module 2554 is further configured to select a scan code video frame containing a scan code from the key frames; the scan code includes a two-dimensional code and a barcode; The use of the scan code in the scan code video frame is determined, and the use information of the scan code is obtained; when the use information of the scan code is payment, the key frame including the code scan video frame is used to construct The key route video or the key route image collection is obtained; when the usage information of the scan code is not payment, the scan code video frame is removed from the key frame, and the scan code video frame is eliminated by using After the key frame, the key route video or the key route image set is constructed.
  • Embodiments of the present application provide a computer program product or computer program, where the computer program product or computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium.
  • the processor of the computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method for finding a car and guiding the vehicle described above in the embodiment of the present application.
  • Embodiments of the present application provide a computer-readable storage medium storing executable instructions, wherein executable instructions are stored, and when the executable instructions are executed by a first processor, the first processor will be caused to execute the instructions provided by the embodiments of the present application.
  • the car-finding and guiding method on the terminal device side of the electronic device, or when executed by the second processor, will cause the second processor to execute the car-finding and guiding method on the electronic device side provided by the embodiment of the present application.
  • the computer-readable storage medium may be memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; it may also include one or any combination of the foregoing memories Various equipment.
  • executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language, including compiled or interpreted languages, or declarative or procedural languages, and which Deployment may be in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.
  • executable instructions may, but do not necessarily correspond to files in a file system, may be stored as part of a file that holds other programs or data, for example, stored in Hypertext Markup Language (HTML, One or more scripts in a Hyper Text Markup Language) document, in a single file dedicated to the program in question, or in multiple cooperating files (for example, storing one or more modules, subroutines, or code part of the document).
  • HTML Hypertext Markup Language
  • executable instructions may be deployed to execute on one computing device (electronic device or terminal device), or on multiple computing devices located at one location, or alternatively, distributed across multiple computing devices. Executed on multiple computing devices at multiple locations and interconnected by a communication network.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Multimedia (AREA)
  • Computer Security & Cryptography (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Navigation (AREA)

Abstract

一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品;寻车指引方法包括:响应于针对第一控件的第一触发操作,展示寻车指引界面;其中,寻车指引界面用于提供寻车的指引信息;响应于针对寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求;接收电子设备针对多媒体内容获取请求返回的多媒体指引内容;其中,多媒体指引内容记录有车辆所在的停车位的环境信息;通过播放多媒体指引内容,指引目标对象寻找车辆。

Description

一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品
相关申请的交叉引用
本申请基于申请号为202110193653.6、申请日为2021年2月20日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及车联网领域,尤其涉及一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品。
背景技术
驾车是常见的出行方式,为此,城市或乡镇中也配备了许多的停车场,以满足人们的停车需求。在实际生活中,当目标对象返回停车场时,会发生找不到停有自己车辆的车位的情况,给目标对象的出行带来困扰。例如:大型商场的停车场、大型停车场、立体式停车场,等等,由于对目标对象的指引信息较少,使得目标对象找到停放自己车辆的效率较低。
发明内容
本申请实施例提供一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品,能够提高寻找车辆的效率。
本申请实施例提供一种寻车指引方法,所述方法由终端设备执行,包括:
响应于针对第一控件的第一触发操作,展示寻车指引界面;其中,所述寻车指引界面用于提供寻车的指引信息;
响应于针对所述寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求;
接收所述电子设备针对所述多媒体内容获取请求返回的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息;
通过播放所述多媒体指引内容,指引目标对象寻找所述车辆。
本申请实施例提供一种寻车指引方法,所述方法由电子设备执行,包括:
接收终端设备发送的多媒体内容获取请求;
响应于所述多媒体内容获取请求,获取对应的多媒体指引内容,其中, 所述多媒体指引内容记录有车辆所在的停车位的环境信息,所述多媒体指引内容基于车载采集装置采集得到;
将所述多媒体指引内容发送给所述终端设备,所述多媒体指引内容用于指引目标对象寻找所述车辆。
本申请实施例提供一种寻车指引装置,包括:
信息展示模块,配置为响应于针对第一控件的第一触发操作,展示寻车指引界面;其中,所述寻车指引界面用于提供寻车的指引信息;
第一发送模块,配置为响应于针对所述寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求;
第一接收模块,配置为接收所述电子设备针对所述多媒体内容获取请求返回的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息;
所述信息展示模块,还配置为通过播放所述多媒体指引内容,指引目标对象寻找所述车辆。
本申请实施例提供一种寻车指引装置,包括:
第二接收模块,配置为接收终端设备发送的多媒体内容获取请求;
视频获取模块,配置为响应于所述多媒体内容获取请求,获取对应的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息,所述多媒体指引内容基于车载采集装置采集得到;
第二发送模块,配置为将所述多媒体指引内容发送给所述终端设备,所述多媒体指引内容用于指引目标对象寻找所述车辆。
本申请实施例提供一种用于寻车指引的终端设备,包括:
第一存储器,用于存储可执行指令;
第一处理器,用于执行所述第一存储器中存储的可执行指令时,实现本申请实施例提供的终端设备侧的寻车指引方法。
本申请实施例中提供一种用于寻车指引的电子设备,包括:
第二存储器,用于存储可执行指令;
第二处理器,用于执行所述第二存储器中存储的可执行指令时,实现本申请实施例提供的电子设备侧的寻车指引方法。
本申请实施例提供一种计算机可读存储介质,存储有可执行指令,用于引起第一处理器执行时,实现本申请实施例提供的终端设备侧的寻车指引方法;或者用于引起第二处理器执行时,实现本申请实施例提供的电子设备侧的寻车指引方法。
本申请实施例提供一种计算机程序产品,包括计算机程序或指令,所述计算机程序或指令用于被第一处理器执行时,实现本申请实施例提供的终端设备侧的寻车指引方法,或者用于引起第二处理器执行时,实现本申请实施例提供的电子设备侧的处理方法。
本申请实施例中具有以下有益效果:终端设备在寻车指引界面的第二 控件上检测到第二触发操作时,确定目标对象有通过多媒体指引内容来指引寻车的需求,发送多媒体内容获取请求,并接收所返回的记录了停车位的环境信息的多媒体指引内容,将多媒体指引内容进行展示,以通过多媒体指引内容,将停车位的环境详情提供给目标对象,从而增加了寻车指引时给目标对象提供的信息量,减少目标对象寻找停放有自己的车辆的停车位所需要的时间,提高了寻找车辆的效率。
附图说明
图1是车载采集装置的一个示意图;
图2是车载采集装置的另一个示意图;
图3是本申请实施例提供的寻车指引系统的一个可选的架构示意图;
图4是本申请实施例提供的图3中的终端设备的结构示意图;
图5是本申请实施例提供的图3中的电子设备实施为服务器的结构示意图;
图6是本申请实施例提供的寻车指引方法的一个可选的流程示意图;
图7是本申请实施例提供的停车场信息界面的示意图;
图8是本申请实施例提供的寻车指引界面的示意图;
图9是本申请实施例提供的播放多媒体指引内容的示意图;
图10是本申请实施例提供的接收针对第三控件的触发操作的示意图;
图11A是本申请实施例提供的进度提示标识的示意图;
图11B是本申请实施例提供的关键帧的示意图;
图12是本申请实施例提供的关键指引信息的增强效果的示意图;
图13是本申请实施例提供的寻车指引方法的另一个可选的流程示意图;
图14是本申请实施例提供的借助于手机进行寻找车辆的过程示意图。
具体实施方式
为了使本申请的目的、技术方案和优点更加清楚,下面将结合附图对本申请作进一步地详细描述,所描述的实施例不应视为对本申请的限制,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例,都属于本申请保护的范围。
在以下的描述中,涉及到“一些实施例”、“一个或多个实施例”,其描述了所有可能实施例的子集,但是可以理解,“一些实施例”、“一个或多个实施例”可以是所有可能实施例的相同子集或不同子集,并且可以在不冲突的情况下相互结合。
在以下的描述中,所涉及的术语“第一\第二\第三”仅仅是区别类似的对象,不代表针对对象的特定排序,可以理解地,“第一\第二\第三”在允许的情况下可以互换特定的顺序或先后次序,以使这里描述的本申请实施 例能够以除了在这里图示或描述的以外的顺序实施。
除非另有定义,本文所使用的所有的技术和科学术语与属于本申请的技术领域的技术人员通常理解的含义相同。本文中所使用的术语只是为了描述本申请实施例的目的,不是旨在限制本申请。
对本申请实施例进行进一步详细说明之前,对本申请实施例中涉及的名词和术语进行说明,本申请实施例中涉及的名词和术语适用于如下的解释。
1)人工智能(Artificial Intelligence,AI)是利用数字计算机或者数字计算机控制的机器模拟、延伸和扩展人的智能,感知环境、获取知识并使用知识获得最佳结果的理论、方法、技术及应用系统。换句话说,人工智能是计算机科学的一个综合技术,它企图了解智能的实质,并生成出一种新的能以人类智能相似的方式做出反应的智能机器。人工智能也就是研究各种智能机器的设计原理与实现方法,使机器具有感知、推理与决策的功能。
人工智能技术是一门综合学科,设计领域广泛,既有硬件层面的技术也有软件层面的技术。人工智能基础技术一般包括如传感器、专用人工智能芯片、云计算、分布式存储、大数据处理技术、操作/交互系统、机电一体化等技术。人工智能软件技术主要包括计算机视觉技术、语音处理技术、自然语言处理技术以及机器学习/深度学习等几大方向。
2)计算机视觉技术(Computer Vision,CV)是一门研究如何使机器“看”的科学,更进一步的说,就是指用摄影机和电脑代替人眼对目标进行识别、跟踪和测量等机器视觉,并进一步做图像处理,使电脑处理成为更适合人眼观察或传送给仪器检测的图像。作为一个科学学科,计算机视觉研究相关的理论和技术,试图建立能够从图像或者多维数据中获取信息的人工智能系统。计算机视觉技术通常包括图像处理、图像识别、图像语义理解、图像检索、OCR、视频处理、视频语义理解、视频内容/行为识别、三维物体重建、3D技术、虚拟现实、增强现实、同步定位与地图构建等技术,还包括常见的人脸识别、指纹识别等生物特征识别技术。
3)机器学习(Machine Learning,ML)是一门多领域交叉学科,涉及概率论、统计学、逼近论、凸分析、算法复杂度理论等多门学科。专门研究计算机怎样模拟或实现人类的学习行为,以获取新的知识或技能,重新组织已有的知识结构使之不断改善自身的性能。机器学习是人工智能的核心,是使计算机具有智能的根本途径,其应用遍及人工智能的各个领域。机器学习和深度学习通常包括人工神经网络、置信网络、强化学习、迁移学习、归纳学习等技术。
4)寻车,是指用户寻找停有自己的车辆的车位过程。例如,用户将车辆停在停车位上,如某个商场的停车位之后进入商场购物,在完成购物要离开商场时,需要返回停车场来寻找自己的车辆停放在哪个车位的过程, 这个过程,有时也被称作反向寻车。
5)车载采集装置,是指搭载在车辆上,能够拍摄到车辆周围环境的摄像头。车载采集装置包括在车辆所安装的行车记录仪上摄像头、环视摄像头、车辆四周的360度全景摄像头等摄像头。
示例性的,图1是车载采集装置的一个示意图,参见图1,在车辆的挡风玻璃正中央安装有行车记录仪1-1,车载采集装置可以是安装在行车记录仪上的摄像头。图2是车载采集装置的另一个示意图,如图2所示,车载采集装置可以包括车身的头部安装的前视摄像头,用于拍摄车辆正前方的道路情况2-1;车载采集装置可以包括车身的尾部安装的后视摄像头,用于拍摄车辆正后方的道路情况2-2;车载采集装置可以包括安装在车身左侧的左视摄像头,以拍摄车辆左侧的道路情况2-3;车载采集装置还可以包括安装在车身右侧的右视摄像头,以拍摄车辆右侧的道路情况2-4。由于前视摄像头、后视摄像头、左视摄像头和右视摄像头分别能够以不同的视角对车辆的周围情况进行拍摄,因而,前视摄像头、后视摄像头、左视摄像头和右视摄像头都属于环视摄像头。
6)响应于,用于表示所执行的操作所依赖的条件或者状态,当满足所依赖的条件或状态时,所执行的一个或多个操作可以是实时的,也可以具有设定的延迟;在没有特别说明的情况下,所执行的多个操作不存在执行先后顺序的限制。
本申请实施例提供一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品,能够提高寻找车辆的效率。本申请实施例提供的用于寻车指引的终端设备可以实施为笔记本电脑,平板电脑,台式计算机,机顶盒,移动设备(例如,移动电话,便携式音乐播放器,个人数字助理,专用消息设备,便携式游戏设备)等各种类型的用户终端,本申请实施例提供的用于寻车指引的电子设备可以实施为车载终端,也可以实施为服务器。
参见图3,图3是本申请实施例提供的寻车指引系统的一个可选的架构示意图,为实现支撑一个寻车指引应用,在寻车指引系统100中,终端设备400通过网络300连接服务器200或者车载终端500(分别为电子设备一种实施方式),网络300可以是广域网或者局域网,又或者是二者的组合。
终端设备400响应于针对在图形界面410上所显示的第一控件的第一触发操作,在图形界面410展示寻车指引界面,其中,寻车指引界面用于提供寻车的指引信息。当终端设备400在寻车指引界面上的第二控件上检测到第二触发操作时,响应于针对第二控件的第二触发操作,通过网络300向服务器200或车载终端500发送多媒体内容获取请求,并接收服务器200或车载终端500针对多媒体内容获取请求返回的多媒体指引内容,其中,多媒体指引内容记录有车辆的所在停车位的环境信息,多媒体指引内容可由车辆采集装置得到。最后,终端设备400会通过播放多媒体指引内容, 指引目标对象寻找车辆。
在一个或多个实施例中,终端设备400可以通过蓝牙、Wi-Fi、移动网络(如5G网络、4G网络等)、近距离无线通讯技术(Near Field Commun ication,NFC)等连接到车载终端500或服务器200,然后从车载终端500或服务器200获取到多媒体指引内容。
可以理解的是,终端设备400可以通过与车载终端500之间是否建立了连接,确定是从车载终端500还是服务器200获取多媒体指引内容。例如,在终端设备400与车载终端500通过蓝牙、NFC建立了连接时,终端设备400可以直接向车载终端500发送多媒体内容获取请求;而在终端设备400未与车载终端500建立连接时,则可以通过Wi-Fi或移动网络向服务器200发送多媒体内容获取请求。
停车路线的环境信息,可以包括停车位所在的楼层的图像信息、从停车场入口到达停车位所经过的路线的图像信息、车辆行驶过程中所经过的地标的图像信息、所经过的指示牌的图像信息、所经过的其他车位的编号的图像信息等。车辆对应的停车位的环境信息可以包括停车位的编号的图像信息、停车位周围所停放的其他汽车的图像信息等。
在一个或多个实施例中,服务器200可以是独立的物理服务器,也可以是多个物理服务器构成的服务器集群或者分布式系统,还可以是提供云服务、云数据库、云计算、云函数、云存储、网络服务、云通信、中间件服务、域名服务、安全服务、CDN、以及大数据和人工智能平台等基础云计算服务的云服务器。终端设备400可以是智能手机、平板电脑、笔记本电脑、台式计算机、智能音箱、智能手表等,但并不局限于此。终端设备以及服务器可以通过有线或无线通信方式进行直接或间接地连接,本申请实施例中不做限制。
参见图4,图4是本申请实施例提供的图3中的终端设备的结构示意图,图4所示的终端设备400包括:至少一个第一处理器410、第一存储器450、至少一个第一网络接口420和第一用户接口430。终端设备400中的各个组件通过第一总线系统440耦合在一起。可理解,第一总线系统440用于实现这些组件之间的连接通信。第一总线系统440除包括数据总线之外,还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见,在图4中将各种总线都标为第一总线系统440。
第一处理器410可以是一种集成电路芯片,具有信号的处理能力,例如通用处理器、数字信号处理器(DSP,Digital Signal Processor),或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等,其中,通用处理器可以是微处理器或者任何常规的处理器等。
第一用户接口430包括使得能够呈现媒体内容的一个或多个第一输出装置431,包括一个或多个扬声器和/或一个或多个视觉显示屏。第一用户接口430还包括一个或多个第一输入装置432,包括有助于用户输入的用户 接口部件,比如键盘、鼠标、麦克风、触屏显示屏、摄像头、其他输入按钮和控件。
第一存储器450可以是可移除的,不可移除的或其组合。示例性的硬件设备包括固态存储器,硬盘驱动器,光盘驱动器等。第一存储器450可选地包括在物理位置上远离第一处理器410的一个或多个存储设备。
第一存储器450包括易失性存储器或非易失性存储器,也可包括易失性和非易失性存储器两者。非易失性存储器可以是只读存储器(ROM,Re ad Only Memory),易失性存储器可以是随机存取存储器(RAM,Random Access Memory)。本申请实施例描述的第一存储器450旨在包括任意适合类型的存储器。
在一个或多个实施例中,第一存储器450能够存储数据以支持各种操作,这些数据的示例包括程序(例如实现本申请实施例终端设备侧的寻车指引方法的可执行指令)、模块和数据结构或者其子集或超集,下面示例性说明。
第一操作系统451,包括用于处理各种基本系统服务和执行硬件相关任务的系统程序,例如框架层、核心库层、驱动层等,用于实现各种基础业务以及处理基于硬件的任务;
第一网络通信模块452,用于经由一个或多个(有线或无线)第一网络接口420到达其他计算设备,示例性的第一网络接口420包括:蓝牙、无线相容性认证(Wi-Fi)、和通用串行总线(USB,Universal Serial Bus)等;
第一呈现模块453,用于经由一个或多个与第一用户接口430相关联的第一输出装置431(例如,显示屏、扬声器等)使得能够呈现信息(例如,用于操作外围设备和显示内容和信息的用户接口);
第一输入处理模块454,用于对一个或多个来自一个或多个第一输入装置432之一的一个或多个用户输入或互动进行检测以及翻译所检测的输入或互动。
在一些实施例中,寻车指引装置455可以采用软件方式实现,图4示出了存储在第一存储器450中的寻车指引装置455,其可以是程序和插件等形式的软件,包括以下软件模块:信息展示模块4551、第一发送模块4552和第一接收模块4553,这些模块是逻辑上的,因此根据所实现的功能可以进行任意的组合或进一步拆分。将在下文中说明各个模块的功能。
参见图5,图5是本申请实施例提供的图3中的电子设备实施为服务器的结构示意图,图5所示的服务器200包括:至少一个第二处理器210、第二存储器250、至少一个第二网络接口220和第二用户接口230。服务器200中的各个组件通过第二总线系统240耦合在一起。可理解,第二总线系统240用于实现这些组件之间的连接通信。第二总线系统240除包括数据总线之外,还包括电源总线、控制总线和状态信号总线。但是为了清楚说明起见,在图5中将各种总线都标为第二总线系统240。
第二处理器210可以是一种集成电路芯片,具有信号的处理能力,例如通用处理器、数字信号处理器(DSP,Digital Signal Processor),或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等,其中,通用处理器可以是微处理器或者任何常规的处理器等。
第二用户接口230的实施与第一用户接口430类似,不再重复说明。
在一些实施例中,第二存储器250能够存储数据以支持各种操作,这些数据的示例包括程序(例如实现本申请实施例提供的电子设备侧的寻车指引方法的可执行指令)、模块和数据结构或者其子集或超集,下面示例性说明。
第二操作系统251的实施例与第一操作系统451类似,不再重复说明;
第二网络通信模块252的实施与第一网络通信模块452类似,不再重复说明;
第二呈现模块253的实施与第一呈现模块453类似,不再重复说明;
第二输入处理模块254的实施与第一输入处理模块454类似,不再重复说明。
在一些实施例中,本申请实施例提供的寻车指引装置255可以采用软件方式实现,图5示出了存储在第二存储器250中的寻车指引装置255,其可以是程序和插件等形式的软件,包括以下软件模块:第二接收模块2551、视频获取模块2552、第二发送模块2553、视频录制模块2554,这些模块是逻辑上的,因此根据所实现的功能可以进行任意的组合或进一步拆分。将在下文中说明各个模块的功能。
可以理解的是,电子设备可以实施为图3中的车载终端500或者图3中的服务器200,图3中的车载终端500的结构可以与图3中的服务器200的结构类似,在此不再重复说明。
下面,将结合本申请实施例提供的终端设备和电子设备的示例性应用和实施,说明本申请实施例提供的寻车指引方法。
参见图6,图6是本申请实施例提供的寻车指引方法的一个可选的流程示意图,将结合图6示出的步骤进行说明。
S101、终端设备响应于针对第一控件的第一触发操作,展示寻车指引界面。
本申请实施例的寻车指引方法是在目标对象将自己的车辆停放停车场之后,需要驾车从停车场离开的场景下实现的,例如,目标对象将车辆停放在购物中心的地下停车场,并在结束购物之后,需要寻找到停有自己的车辆的停车位,并要驾车离开购物中心的场景下实现的,或者是目标对象开车驶入高速服务区的地上停车场,在需要从服务区离开时寻找停放有自己的车辆的停车位的场景下实现的。终端设备会通过检测目标对象是否在第一控件上进行了第一触发操作,以分辨出目标对象是否具有获取寻车的指引信息的需求。当终端设备检测到目标对象在第一控件上进行了第一触 发操作时,就会确认目标对象有获取寻车的指引信息的需求,从而响应于作用在第一控件上的第一触发操作,创建寻车指引界面,并在终端设备的显示界面上展示寻车指引界面,以便于目标对象获取寻车时的指引信息。也就是说,寻车指引界面用于提供寻车的指引信息。其中,目标对象可以是当前正在寻找车辆的用户,还可以是帮助用户寻找车辆的智能机器人等。
在一个或多个实施例中,第一控件可以设置在停车场信息界面中,从而,目标对象可以在终端设备进入停车场信息界面之后,在停车场信息界面中触发第一控件。其中,停车场信息界面可以是目标对象在寻找车辆时,扫描停车场内停车场信息二维码、停车场信息条形码等进入的,也可以是目标对象在终端设备的搜索引擎上,直接根据停车场的名称所搜索并进入的,还可以是终端设备根据目标对象当前的地理位置所匹配到并进入的等等,在此不作限定。
在一个或多个实施例中,停车场信息界面中可以提供停车场的基本信息,例如,停车场的名称、停车场的地理位置、停车场的开放时间以及停车场的收费标准等。停车场信息界面中还可以包括与目标对象相关的信息(此时停车场信息界面可与目标对象的身份信息绑定),例如,目标对象停车的时长、目标对象进入停车场的时间、应缴纳的费用等。
在一个或多个实施例中,第一控件可以设置在停车场信息界面的第一区域,其中,第一区域的大小和位置等均可以根据实际情况进行设置。例如,将第一区域设置在停车场信息界面的底部,大小设置为100×50,或者是将第一区域设置在停车场信息界面的右上角,大小设置为50×50,本申请实施例在此不作限定。
示例性的,图7是本申请实施例提供的停车场信息界面的示意图。参见图7,在停车场信息界面7-1中设置有基本信息展示区域7-11和目标对象信息展示区域7-12。在基本信息展示区域7-11中,显示有停车场的基本信息,即停车场的名称:服务区停车场7-111、停车场的开放时间:全天开放7-112、停车场的收费标准:2元/时7-113。在目标对象信息展示区域7-12中,显示有目标对象停车的时长:已停车2小时7-121、车辆驶入停车场的时间:14:00驶入7-122。在停车场信息界面7-1的底部中央,设置有第一控件,即寻车指引标识7-13,目标对象可以通过点击寻车指引标识7-13,进入到寻车指引界面中。
在一个或多个实施例中,第一触发操作可以是点击、双击等操作,还可以是长按、滑动等操作,在此不作限定。
在一个或多个实施例中,寻车指引界面中可以包括文字信息展示区域和视频播放区域。其中,图文信息展示区域用于向目标对象提供图文形式的指引信息,例如,停放有目标对象的车辆的停车位的编号、停车位在停车场的方位、停车位周围环境的图片等信息;视频播放区域则可以向目标对象提供视频形式的指引信息。
在一个或多个实施例中,图文信息展示区域可以设置在寻车指引界面的第二区域中,视频播放区域可以设置在寻车指引界面的第三区域中。其中,第二区域和第三区域的大小和位置均是可以根据实际情况设置的,在此不作限定。
例如,将第二区域设置在寻车指引界面的上半部分,将第三区域设置在寻车指引界面的下半部分,将第二区域和第三区域的宽度均设置为寻车指引界面的宽度,将第二区域和第三区域的高度均设置为寻车指引界面的高度的一半。或者,将第二区域设置在寻车指引界面的左半部分,将第三区域设置在寻车指引界面的右半部分,将第二区域和第三区域的宽度均设置为寻车指引界面的宽度的一半,将第二区域和第三区域的高度均设置为寻车指引界面的高度。
图8是本申请实施例提供的寻车指引界面的示意图。参见图8,在寻车指引界面8-1中,设置有视频播放区域8-11和图文信息展示区域8-12。视频播放区域8-11用来播放指引目标对象进行反向寻车的视频,图文信息展示区域8-12则显示有图文的指引信息:车位编号:B2-11 8-121、车位方位:电梯正前方8-122,车位周围环境的照片8-123。
S102、终端设备响应于针对寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求。
寻车指引界面上设置有第二控件,当目标对象在第二控件上进行触发操作时,该触发操作就是第二触发操作,从而终端设备会确定目标对象有借助于多媒体指引内容来寻找车位的需求,并响应于该第二触发操作,生成多媒体内容获取请求,将多媒体内容获取请求发送给电子设备。电子设备接收终端设备发送的多媒体内容获取请求。
在一个或多个实施例中,第二控件可以是寻车指引界面中的用于触发获取指引内容的按键,例如,“获取指引内容”按键,“获得停车时的路线”按键等。也可以是用于触发获取指引内容的链接。
在一些实施例中,电子设备可以实施为车载终端;在另一些实施例中,电子设备可以实施为服务器。终端设备可以通过蓝牙、近距离无线通信技术(Near Field Communication,NFC)、Wi-Fi等,将多媒体内容获取请求发送给车载终端设备或服务器,终端设备可以通过移动网络,例如,5G、4G网络等,将多媒体内容获取请求发送给服务器。
S103、电子设备响应于多媒体内容获取请求,获取对应的多媒体指引内容。
电子设备在接收到多媒体内容获取请求之后,就会响应所接收到的多媒体内容获取请求,获取车辆在停车时所采集好的多媒体指引内容,以便于后续将多媒体指引内容提供给目标对象。
多媒体指引内容记录有车辆所在的停车位的环境信息,多媒体指引内容基于车载采集装置采集得到。在一些实施例中,多媒体指引内容中不仅 可以包含着丰富的环境信息,还可以包含时序信息,能够将环境信息在时间维度上组成序列,以便于目标对象明确各种事件的先后顺序,从而依据路多媒体指引内容能够更好地记录停车位周边的情况,以便于目标对象依据这些情况来找到自己的车辆。
在一个或多个实施例中,多媒体指引内容可以为包含有停车位周围的环境信息的连续图像,也可以为包含停车位周围的环境信息的视频,在此不作限定。
在一些实施例中,电子设备可以是对包含停车位周围的环境信息的连续图像或视频直接作为多媒体指引内容,还可以是先对包含停车位周围的环境信息的连续图像或视频进行冗余信息的剔除,将所得到的关键路线视频或者关键路线图像集合更新为多媒体指引内容。其中,冗余信息可以包括重复的地标图像、重复的停车位的环境信息等。
S104、电子设备将多媒体指引内容发送给终端设备,多媒体指引内容用于指引目标对象寻找车辆。
电子设备将多媒体指引内容下发给终端设备,以使得终端设备能够展示多媒体指引内容。对于终端设备而言,其是在发送了多媒体内容获取请求之后才接收到多媒体指引内容的,因而,终端设备接收电子设备针对多媒体内容获取请求返回的多媒体指引内容。
需要说明的是,在一个或多个实施例中,当需要电子设备采集多媒体指引内容时,电子设备可以实施为车载终端,即由车载终端调用车载采集装置采集得到多媒体指引内容,并将多媒体指引内容发送给终端设备。当需要电子设备生成关键路线视频或关键图像集合,并将生成关键路线视频或关键图像集合更新为多媒体指引内容时,电子设备可以实施为车载终端,也可以实施为服务器,即可以通过车载终端或者是服务器来对多媒体指引内容进行去冗余的更新,再由车载终端或者是服务器将更新后的多媒体指引内容发送给终端设备。在一个或多个实施例中,当电子设备实施为服务器时,服务器的多媒体指引内容可以接收自车载终端。
S105、终端设备通过播放多媒体指引内容,指引目标对象寻找车辆。
终端设备在寻车指引界面的视频播放区域中播放视频形式的多媒体指引内容,或者是在寻车指引界面的图文信息展示区域中显示,即静态播放图文形式的多媒体指引内容,从而通过丰富的图像信息,将停车位周边的情况展示给目标对象,便于目标对象通过步行或者是其他方式,前进到停放有自己的车辆的停车位上,以实现对目标对象寻找车辆的指引过程,从而节省了目标对象寻找车辆的时间。
在另一些实施例中,视频播放区域中还设置有调整标识,当目标对象触发调整标识时,终端设备可以将视频播放区域的大小放大至全屏,从而实现停车路线视频的全屏播放,以便于目标对象获取细节信息。当目标对象触发调整标识时,终端设备也可以继续接收目标对象的缩放操作,从而 通过缩放的比例来调整视频播放区域的大小,以便于目标对象调整视频播放区域。
图9是本申请实施例提供的播放多媒体指引内容的示意图,如图9所示,终端设备在视频播放区域9-1中播放多媒体指引内容,但是由于视频播放区域9-1的面积较小,从而使得目标对象观看不便。在视频播放区域9-1的右下角,设置有全屏播放按键9-2(调整标识),当目标对象点击该按键之后,就会进入到全屏播放模式,此时,视频播放区域9-1占据了终端设备的整个显示界面。
本申请实施例中,终端设备在寻车指引界面的第二控件上检测到第二触发操作时,就会确定目标对象有通过多媒体内容来指引反向寻车的需求,发送多媒体内容获取请求,并接收所返回的记录了停车位的环境信息的多媒体指引内容,将多媒体指引内容进行展示,以通过多媒体指引内容,将停车位的环境详情提供给目标对象,从而增加了寻车指引时给目标对象提供的信息量,减少目标对象寻找停放有自己的车辆的停车位所需要的时间,提高了寻找车辆的效率。
在一些实施例中,车载采集装置在采集停车路线的环境信息时,极有可能会将停车场的墙面上,或者是柱子上所粘贴的缴费码拍摄进去,从而,多媒体指引内容包括缴费码视频帧,将缴费码视频帧中的缴费码记为第三控件,则终端设备在播放区域播放多媒体指引内容之后,即在S105之后,该方法还可以包括:S106,如下:
S106、终端响应于针对第三控件的触发操作时,展示缴费页面。其中,缴费页面用于供目标对象完成停车缴费。
在一个或多个实施例中,停车场并没有设置收费工作人员,而是通过缴费码,即第三控件来收取停车费的。停有目标对象的车辆的停车位,有可能离缴费码较远,给目标对象缴纳停车费用造成了不便。因此,在一个或多个实施例中,当多媒体指引内容中包括了缴费码视频帧时,终端设备可以在检测目标对象针对缴费码视频帧中的缴费码,即第三控件的触发操作之后,响应于该触发操作,生成并展示缴费页面,以使得目标对象能够通过缴费页面完成停车缴费。
在一个或多个实施例中,针对第三控件的触发操作,可以仅是目标对象的双击操作,也可以是目标对象的长按操作,还可以是其他能够达到相同目标的操作,本申请实施例在此不作限定。
在一个或多个实施例中,缴费码可以是二维码,也可以是条形码,还可以是其他形式的图形码,本申请实施例在此不作具体限定。
图10是本申请实施例提供的接收针对第三控件的触发操作的示意图。参见图10,缴费码是粘贴在柱子上的二维码,终端设备可以先接收目标对象针对缴费码视频帧10-1中二维码10-2(第三控件)所在的区域的长按操作,然后在二维码10-2的周围弹出弹窗10-3,该弹窗上设置了针对该二维 码的识别10-31按键,当终端设备接收到目标对象针对该识别按键的触发操作时,就会跳转至缴费界面。
本申请实施例中,多媒体指引内容中包含了缴费码视频帧,终端设备当检测到目标对象针对缴费码视频帧中的第三控件的触发操作时,可以展示缴费页面,从而能够实现基于多媒体指引内容就帮助目标对象完成停车缴费的过程,减少了目标对象寻找缴费码的时间,提高了目标对象缴纳停车费用的便利性。
在一些实施例中,多媒体指引内容还记录有停车路线的环境信息,其中,停车路线表征从车辆从停车场入口开始至停止行驶时所行驶过的路线。多媒体指引内容对应有进度条,多媒体指引内容所对应的进度条上展示有进度提示标识。在此情况下,终端设备通过播放多媒体指引内容,指引目标对象寻找车辆,即S105的具体实现过程,可以包括:S1051,如下:
S1051、终端设备响应于针对进度提示标识的触发操作,跳转到进度提示标识对应的关键帧,并通过从进度提示标识对应的关键帧开始,播放多媒体指引内容,指引目标对象寻找车辆。
目标对象的时间是有限的,同时,能够为目标对象的提供寻找车辆线索的关键指引信息也是有限的,从而关键指引信息的进度提示标识,能够提醒目标对象可以重点关注多媒体指引内容中的哪些内容,节省目标对象寻找车辆的时间。在一些实施例中,终端设备会检测目标对象对多媒体指引内容的进度条的触发操作,以通过该触发操作,来判断目标对象是否调整多媒体指引内容的播放进度。在终端设备检测到目标对象针对进度条的进度提示标识的触发操作时,就确定目标对象需要跳过一些不太重要的指引内容,而直接从多媒体指引内容中获得关键指引信息,此时,终端设备会响应该触发操作,直接从多媒体指引内容所播放到的当前视频帧,跳转到进度提示标识所对应的关键帧开始播放,其中,关键帧中记录有关键指引信息,而关键指引信息从停车路线的环境信息和停车位的环境信息提取得到。终端设备在从当前视频帧跳转到关键帧之后,就会继续从关键帧处,继续播放多媒体指引内容,直至将多媒体指引内容播放完成。
当多媒体指引内容为视频形式时,终端设备即为从关键帧开始进行视频播放,以实现多媒体指引内容的播放;当多媒体指引内容为图像或图文形式时,终端设备可以通过静态显示,实现多媒体指引内容的播放。
在一个或多个实施例中,关键指引信息可以包括:停车位的编号信息、停车路线所经过的地标信息、停车位所在的楼层信息、缴费码、与车辆相邻的其他车辆的外观信息、停车位的正前方的环境信息、以及停车位的环视图像中的至少一个。
停车位的环视图像,可以是车身的环视摄像头所拍摄到的。在一些实施例中,电子设备还可以根据环视摄像头所拍摄到的图像,来合成停车位的俯视图像,并将停车位的俯视图像作为关键指引信息。
在一些实施例中,关键帧也可以包括一个或多个图像或视频帧,这是由于关键指引信息很可能是分散在不同的视频帧或者是图像中的,此时,关键帧中的每个视频帧或者是图像都可以有其所对对应的进度提示标识,以使得目标对象可以快速将播放进度跳转到这些视频帧或者是图像。
图11A是本申请实施例提供的进度提示标识的示意图,如图11A所示,在多媒体指引内容对应有进度条,在进度条的04:01处,以实心点的形式设置了关键指引信息的进度提示标识,当目标对象点击该标识时,终端设备就会从04:01处继续播放多媒体指引内容。
图11B是本申请实施例提供的关键帧的示意图,参见图11B,关键帧包含与目标对象的车辆相邻的其他车辆的外观信息的视频帧,即视频帧11-11,包含停车位的正前方的环境信息的视频帧,即视频帧11-12,以及同时包含停车位的环视图像和停车位的俯视图像的视频帧,即视频帧11-13,共同组成了关键帧11-1。
在一些实施例中,为了使得关键帧中的关键指引信息更加醒目,终端设备会在关键帧中针对关键指引信息添加上一些增强效果,从而使得关键指引信息更加醒目、突出。也就是说,本申请实施例提供的终端设备侧的寻车指引方法,还可以包括:
S1051A、当通过从进度提示标识对应的关键帧开始,播放多媒体指引内容时,终端设备展示针对关键指引信息的增强效果,该增强效果可以囊括一切能够使关键指引信息更加醒目的效果。增强效果包括:箭头、标注框、星型效果、闪烁效果中的至少一种。
图12是本申请实施例提供的关键指引信息的增强效果的示意图,如图12所示,在视频帧12-1中,关键指引信息是车位的编号,终端设备可以将车位的编号用标注框标注出来,从而使得编号更加醒目;在视频帧12-2中,关键指引信息是地标,即B栋电梯的指示标识,终端设备可以对该指示标识添加星型效果,从而使得该指示标识在关键视频帧中更加突出;在视频帧12-3中,关键指引信息是停车位所在的楼层信息,即地下二层,从而,终端设备会将在楼层信息周围添加一个指向该楼层信息的箭头,以突出该楼层信息。
本申请实施例中,终端设备检测到目标对象对包含停车路线的环境信息的多媒体指引内容的进度条中的进度提示标识的触发操作时,会直接从当前播放视频帧跳转到包含关键指引信息的关键帧,从关键帧处,开始继续播放多媒体指引内容,从而减少目标对象获取关键指引信息的时间,继续提高寻找车辆的效率。
参见图13,图13是本申请实施例提供的寻车指引方法的另一个可选的流程示意图。在一些实施例中,多媒体指引内容还记录有停车路线的环境信息,电子设备能够调用车载采集装置来采集停车路线的环境信息的视频或图像,从而,当终端设备响应于针对第一控件的第一触发操作,展示寻 车指引界面之前,也即在电子设备接收终端设备发送的多媒体内容获取请求之前,该方法还可以包括:S201-S202,如下:
S201、电子设备对车辆的实时行驶环境进行分析,得到分析结果。
在一个或多个实施例中,在车辆处于行驶状态中时,电子设备不断地分析车辆的实时行驶环境,以确认目标对象是否驶进了停车场,从而得到分析结果。也就是说,本申请实施例中,分析结果表征车辆是否驶入停车场。
在一些实施例中,电子设备可以通过车载采集装置拍摄车辆的实时行驶环境的图像信息或视频,然后对拍摄到的图像或视频进行识别,从而判断出车辆是否驶入了停车场。在另一些实施例中,电子设备可以通过定位设备获取车辆的实时位置信息,然后结合车辆的实时位置信息和数字地图上的停车场的地理围栏的位置信息,来判断出车辆是否驶入了停车场。
除此之外,在一些实施例中,电子设备还可以通过目标对象的语音、手势等信息,来明确出车辆是否驶入停车场。例如,电子设备可以在接收到目标对象所说出的“进入停车场了,开始录像吧”的语句,来判断出车辆已经驶入停车场了,或者是检测到光照强度的明显变化,例如光照突然变暗,判断出车辆已经驶入停车场。
S202、当分析结果表征车辆驶入停车场时,电子设备通过车载采集装置,对车辆从驶入停车场至停止行驶时的停车路线的环境信息,以及停车位的环境信息进行采集,得到多媒体指引内容。
当电子设备判断出车辆已经驶入停车场之后,就会调用车载采集装置,通过车载采集装置,来对车辆从驶入停车场开始,至车辆完全停止时的路线的环境信息进行采集,以及对车辆所停放的停车位的环境信息进行采集,直至依据车辆的传感器数据判断出车辆停车时采集结束,得到多媒体指引内容。这些环境信息直观地表现出了车辆在停车时所行驶过的地点、以及停车位的真实情形,目标对象无疑是能够从环境信息中了解停车路线途径的途径地点,以及停车位周围的情况,以便于后续目标对象寻找停有自己的车辆。
在一个或多个实施例中,电子设备可以通过车辆的关系测量单元(Iner tial Measurement Unit,IMU)中的角速度传感器所采集到的角速度,和加速度传感器所采集到的加速度相结合,来判断出车辆是否完全停止行驶;电子设备还可以通过车辆的轮速传感器所测得的轮速,来判断出车辆是否完全停止行驶;电子设备也可以通过检测网络,对车载采集装置拍摄到的画面的静止情况进行判断,判断出车辆是否完全停止行驶;电子设备还可以通过车辆的熄火信号的接收与否,来判断出车辆是否完全停止行驶。
在一些实施例中,车载采集装置包括安装在行车记录仪上的前置摄像头,还可以包括安装在车身上的环视摄像头。电子设备可以同时调用前置摄像头和环视摄像头,来采集多媒体指引内容,还可以仅通过前置摄像头 和环视摄像头中的任意一个摄像头,来采集多媒体指引内容,在此不作限定。可以理解的是,环视摄像头可以是在目标对象手动开启之后才开始采集多媒体指引内容,本申请实施例在此不做限定。
在一个或多个实施例中,电子设备在通过车载采集装置在采集停车路线的环境信息和停车位的环境信息时,还可以根据停车场的环境对车载采集装置的拍摄参数进行调整,以使得多媒体指引内容的质量得到提升。
例如,当电子设备判断出车辆驶入的是地下停车场时(可以通过光线的变化、车身行驶时道路的坡度变化),可以将车载采集装置的光圈、感光度等拍摄参数调高,将快门调低,例如,将光圈、感光度等拍摄参数调整到数值阈值之上,将快门调整到数值阈值之下,以保证多媒体指引内容的质量。又例如,当电子设备判断出车辆驶入的是地面停车场时,则可以不对车载采集装置的光圈、感光度和快门进行调整。
当然,在一些实施例中,电子设备还可以依据天气情况来对车载采集装置的拍摄参数进行调整。例如,当电子设备通过网络得知当前天气是光线不足的雨雪天气,或者是大雾天气时,可以将车载采集装置的光圈、感光度调整到数值阈值之上,以保证多媒体指引内容的质量。
在一些实施例中,为了多媒体指引内容中尽可能多地包含重要信息,电子设备可以使得车载采集装置的帧率保持在帧率阈值之上,例如,将车载采集装置的帧率不少于每秒5帧。在另一些实施例中,为了尽量减少多媒体指引内容所占用的存储空间以及在传输时所消耗的流量费用,电子设备可以将车载采集装置的帧率保持在帧率阈值之下,例如,将车载采集装置的帧率设置为每秒2帧。
在一些实施例中,电子设备在通过车载采集装置采集多媒体指引内容时,还可以是先对车载采集装置所拍摄的图像进行预处理,例如,进行缩放、裁剪、图像质量增强的处理,然后再利用预处理之后的图像构成多媒体指引内容,从而提升多媒体指引内容的质量。
在一个或多个实施例中,电子设备通过车载采集装置所采集到的多媒体指引内容,可以存储在电子设备本地的存储空间中,也可以通过网络上传给服务器等云端设备,只要是能够使得完整的多媒体指引内容得以保存即可。
在一些实施例中,多媒体指引内容可以是车载采集设备所采集到的停车路线视频或者是停车路线图像集合,即电子设备可以对停车路线视频或停车路线图像集合不进行任何处理,直接将停车路线视频或停车路线图像集合确定为多媒体指引内容,以便于后续响应于终端设备所发送的多媒体内容获取请求时,将未经过处理的停车路线视频或停车路线图像集合发送给终端设备。
在一些实施例中,电子设备还可以将停车路线视频或停车路线图像集合中的冗余信息进行去除,例如,对相似程度超过一定阈值的多个视频帧 或图像择一保留,对较为模糊的视频帧或图像进行去除等,从而将去除冗余信息之后的停车路线视频或停车路线图像集合确定为多媒体指引内容。当然,电子设备也可以对停车路线视频或停车路线图像集合中的关键信息进行识别、提取,然后为关键信息添加增强效果,将添加了增强效果的停车路线视频或停车路线图像集合作为多媒体指引内容。也就是说,电子设备可以对采集到的停车路线视频或停车路线图像集合进行抽取关键帧、裁剪、重要指示信息的提取等一系列处理过程,并将进行处理过的停车路线视频或停车路线图像集合,更新为多媒体指引内容。
在一个或多个实施例中,S201-S202中的电子设备,可以实施为车载终端。
在一个或多个实施例中,电子设备在车辆行驶过程中,不断对实时行驶环境进行分析,在分析结果表征车辆驶入停车场时,才会调用车载采集装置,拍摄停车路线的环境信息和停车位的环境信息,得到多媒体指引内容,实现了根据车辆的行驶场景,自动开启多媒体指引内容的采集的效果,提高了采集多媒体指引内容的智能程度。同时,由于多媒体指引内容是通过车载采集装置拍摄的,并不需要在停车场内额外设置摄像头,从而使得寻车指引系统的成本更低。
在一些实施例中,电子设备对车辆的实时行驶环境进行分析,得到分析结果,即S201的具体实现过程,可以包括:S2011-S2012,如下:
S2011、电子设备通过车载采集装置,采集车辆的实时行驶环境的图像或视频。
S2012、电子设备利用分类模型,对实时行驶环境的图像或视频进行分类处理,得到分析结果。
电子设备在分析车辆的实时行驶环境时,可以通过车载采集装置,采集车辆的实时行驶环境的图像或视频,然后将实时行驶环境的图像或视频输入到分类模型中,以通过分类模型对实时行驶环境的图像或视频进行分类,从而确定出实时行驶环境是不是停车场的入口。也就是说,分析结果表征实时行驶环境的图像或视频是否为停车场的入口场景。当分析结果表明实时行驶环境的图像或视频确实是停车场的入口场景时,电子设备就会将分析结果确定为车辆驶入了停车场。相应的,当分析结果表明实时行驶环境的图像或视频不是停车场的入口场景时,电子设备就会将分析结果确定为车辆没有驶入停车场。这样,电子设备就会得到分析结果了。
在一个或多个实施例中,停车场的入口场景图像,可以包括停车场入口档杆的图像、地下停车场的入口的图像、地面停车场的入口的图像等,还可以包括地下停车场的指示标识、地面停车场的名称标识等,在此不作限定。
分类模型可以是利用经过标注的各种停车场的入口场景图像所训练出来的模型。分类模型可以是卷积神经网络(Convolutional Neural Networks, CNN)模型等深层模型,还可以是支持向量机(Support Vector Machine,SVM)等浅层机器学习模型,本申请实施例在此不作限定。
在一些实施例中,对实时行驶环境的图像或视频进行分类之前,电子还可以先对实时行驶环境的图像或视频进行预处理,例如对实时行驶环境的图像进行缩放、裁剪、增强等处理,以使得分析结果更加准确;对实时行驶环境的视频进行压缩、抽帧等处理,以使得分类速度更快。
在一个或多个实施例中,电子设备能够对车载采集装置所拍摄的实时行驶环境的图像或视频进行分类,从而实现了从图像维度上判断出车辆是否驶入了停车场,提高了采集停车路线视频的智能程度。
在一些实施例中,电子设备对车辆的实时行驶环境进行分析,得到分析结果,即S201的具体实现过程,还可以包括:S2013,如下:
S2013、电子设备通过定位装置,获取车辆的实时地理位置,将实时地理位置与停车场的地理围栏的位置关系,确定为分析结果。
电子设备在对车辆的实时行驶环境进行判断时,还可以通过车辆上的定位装置,来不断获取车辆的实时地理位置。接着,电子设备将实时地理位置与数字地图所提供的停车场的地理围栏进行比对,判断出车辆的实时地理位置是否在地理围栏的内部,从而得到分析结果。也就是说,分析结果基于实时地理位置是否在地理围栏内部得到。
车辆上的定位装置,可以是全球定位系统(Global Positioning System,GPS)定位器,还可以是北斗定位器,本申请实施例在此不作限定。
当电子设备将实时地理位置与地理围栏比对,发现车辆的实时地理位置处于地理围栏内部时,就会确定车辆已经驶入了停车场,从而将分析结果确定为车辆驶入停车场。相应的,实时地理位置处于地理围栏外部时,电子设备就会将分析结果确定为车辆未驶入停车场。
可以理解的是,S2011-S2012与S2013为S201的两种并列实现方式,电子设备可以根据实际情况从这两种实现方式中择一实现。
本申请实施例中,电子设备还能够将车辆的实时地理位置与停车场的地理围栏进行比对,从而实现根据定位信息来判断出车辆是否驶入了停车场,提高了采集停车路线视频的智能程度。
在一个或多个实施例中,电子设备还可以同时结合车辆的实时地理位置和光照强度,来判断出车辆是否驶入了停车场。例如,当实时地理位置与地理围栏的距离小于距离阈值,并且光照强度突然低于强度阈值时,则认为车辆驶入了地下停车场;当实时地理位置位于地理围栏内部,光照强度没有变化时,认为车辆驶入了地面停车场。
在一些实施例中,电子设备在得到多媒体指引内容之后,即在S202之后,该方法还可以包括:S203-S204,如下:
S203、电子设备从多媒体指引内容中抽取出关键帧。
其中,关键帧中记录有关键指引信息,关键指引信息是基于停车路线 的环境信息和停车位的环境信息提取得到。
在本申请的一些实施例中,关键帧是多媒体指引内容中连续的多个视频帧。在本申请的另一些实施例中,关键帧是多媒体指引内容中独立的多个视频帧。
S204、电子设备利用关键帧,构建关键路线视频或关键路线图像集合,以及将关键路线视频或关键路线图像集合更新为多媒体指引内容。
电子设备在得到关键帧之后,就会将关键帧在时序上连接成视频,所得到的视频,就是关键路线视频,或者是将关键帧直接组成关键路线图像集合,然后将关键路线视频或者是关键路线图像集合,更新为多媒体指引内容,从而实现对多媒体指引内容的去冗余,从而使得终端设备所接收到的多媒体指引内容为更为精简。
其中,关键路线视频或关键路线图像集合包括缴费信息视频或缴费信息图像集合,缴费信息视频或缴费信息图像集合记录有缴费码,以及关键路线视频或关键路线图像集合具有对应的进度条,进度条上展示有进度提示标识,进度提示标识与关键帧相对应。
在一些实施例中,电子设备还能够对关键帧中的动态模糊部分进行去除,然后用去除了动态模糊的关键帧,构建出关键路线视频或者关键路线图像集合,也即,电子设备从多媒体指引内容中抽取出关键帧之后,利用所述关键帧,构建关键路线视频或关键路线图像集合之前,即在S203之后,S204之前,该方法还可以包括:S205,如下:
S205、对关键帧进行模糊去除,得到优化关键帧。
电子设备可以将关键帧输入至用于去除模糊的深度学习模型中,并将去除模糊的深度学习模型的输出,确定为优化关键帧。电子设备还可以从关键帧的相邻帧中,为关键帧裁剪出用于去除模糊部分的贴图,并利用该贴图对关键帧中的模糊部分进行替换,得到优化关键帧。
在此情况下,利用关键帧,构建关键路线视频或关键路线图像集合,即S204的具体实现过程可以变为:S204A,如下:
S204A、利用优化关键帧,构建关键路线视频或关键路线图像集合。
即利用优化关键帧拼接出关键路线视频,或者是利用优化关键帧组合为关键路线图像集合,以使得关键路线视频或关键路线图像集合的质量更好。
在一些实施例中,S203中的电子设备可以实施为车载终端,S204中的电子设备可以实施为服务器,从而,车载终端在从多媒体指引内容中抽取出关键帧之后,可以将关键帧发送给服务器,服务器利用关键帧生成关键路线视频或是关键路线图像集合,并将关键路线视频帧或关键路线图像集合更新为多媒体指引内容获,以提供给终端设备。
在另一些实施例中,S203-S204中的电子设备均可以实施为服务器,此时,服务器是先接收车载终端发送的未去除冗余的多媒体指引内容(例如 停车路线视频或停车路线图像集合),然后由服务器进行关键帧的抽取、关键路线视频或关键路线图像集合的生成,以及更新多媒体指引内容。
在一个或多个实施例中,S203-S204中的电子设备还可以均实施为车载终端,即车载终端在采集得到多媒体指引内容(停车路线视频或停车路线图像集合)之后,还可以由车载终端本身进行关键帧的抽取、生成关键路线视频或关键路线图像集合,以及更新多媒体指引内容。
本申请实施例中,电子设备能够从多媒体指引内容中抽取出关键帧,并生成关键路线视频或关键路线图像集合,基于关键路线视频或关键路线图像结合对多媒体指引内容进行更新,从而减少了多媒体指引内容的冗余。
在本申请的一些实施例中,电子设备从多媒体指引内容中抽取出关键帧,即S203的具体实现过程,可以包括:针对多媒体指引内容执行以下处理之一,如下:
S2031、电子设备以车辆行驶过距离阈值为抽取间隔,从多媒体指引内容中抽取关键帧。
电子设备会对车辆的行驶距离进行检测,每当车辆行驶过距离阈值,电子设备就会从多媒体指引内容的各个视频帧中,抽取出一些视频帧,在完成抽帧时,就可以得到关键帧了。
在一个或多个实施例中,距离阈值可以设置为5米,也可以设置为10米,还可以根据实际情况设置成其他数值,本申请实施例在此不作限定。抽取的视频帧的数量可以设置为1,也可以设置为3,还可以根据实际情况设置成其他数值,本申请实施例在此不作限定。
可以理解的是,由于车辆行驶过的距离和车辆的速度是成正比的,即相同时间内车辆行驶过的距离越大,车辆的行驶速度就越大,此时,以车辆行驶过距离阈值为抽取间隔,抽取一些视频帧,能够保证抽帧间隔是随着车辆的行驶速度的变化而变化的,即在车辆行驶速度越快时,抽帧间隔就会越小,车辆行驶速度越慢时,抽帧间隔就会越大。这样,就会保证车辆的行驶速度较快时,也能够采集到足够的环境信息。
S2032、电子设备依据车辆的实时行驶环境,从多个抽帧间隔中,选择出实时行驶环境对应的目标抽帧间隔,并依据目标抽帧间隔,从多媒体指引内容中抽取出关键帧。
电子设备除了依据车辆的行驶距离来控制抽帧之外,还可以依据车辆所行驶到的地点的环境,从多个抽帧间隔中查找出实时行驶环境对应的目标抽帧间隔,然后按照该目标抽帧间隔,来对多媒体指引内容进行抽帧,得到关键帧。
抽帧间隔可以根据实际需求进行设定,例如,将抽帧间隔设定为10,或者是设定为8等,本申请实施例在此不作限定。
可以理解的是,电子设备依据实时行驶环境,从多个抽帧间隔中挑选出对应的目标抽帧间隔时,可以在一些不要求保留较多的环境信息的地点, 按照较大的抽帧间隔来进行抽帧,而在一些要求保留足够多的环境信息的地点,按照较小的抽帧间隔来进行抽帧,从而实现根据车辆所行驶到的地点,自适应调整抽帧间隔的效果。
例如,当车辆刚刚驶入停车场时,并不需要保留大量的环境信息,因而,可以将停车场入口对应的抽帧间隔,设置为10帧;当车辆临近停车位时,往往需要保留较多的环境信息,因而,可以将对应的抽帧间隔设置为3,以保留足够多的环境信息。
S2033、电子设备对多媒体指引内容中识别出关键指引信息的视频帧进行抽取,得到关键帧。
电子设备还可以对车辆行驶时所经过的地点是否包含关键指引信息进行识别,当识别出车辆行驶的地点包含关键指引信息时,就会将包含关键指引信息的视频帧抽取出来,将抽取出的视频帧作为关键帧。
本申请实施例中,电子设备能够基于车辆的行驶距离,确定抽帧间隔并抽取关键帧,或者是基于车辆的实时行驶环境,确定出抽帧间隔并抽取关键帧,亦或是基于关键指引信息的识别结果,进行关键针对的抽取,从而实现能够根据车辆的行驶情况自适应的从多媒体指引内容中抽取出关键帧,提高了关键帧抽取的智能程度。
在本申请的一些实施例中,电子设备在对多媒体指引内容完成抽帧之后,还可以从未被抽取的视频帧中,选择一些视频帧补入到关键帧中。也就是说,电子设备从多媒体指引内容中抽取出关键帧之后,利用关键帧,构建关键路线视频或关键路线图像集合之前,即在S203之后,S204之前,该方法还可以包括:S206,如下:
S206、从多媒体指引内容的剩余内容中,筛选得到候补视频帧。
其中,剩余内容是多媒体指引内容中除关键帧之外的内容,候补视频帧至少包括:包含文字信息的视频帧、倒车时的视频帧和包含二维码时的视频帧。
在此情况下,电子设备利用关键帧,构建关键路线视频或关键路线图像集合,即S204的具体实现过程,可以变为S204B,如下:
S204B、利用关键帧和候补视频帧,构建关键路线视频或关键路线图像集合。
也就是说,电子设备会从除关键帧之外其他的视频帧中,选择包含文字信息的视频帧、倒车时的视频帧以及包含二维码的视频帧,补入到关键帧中,以重新利用补入了视频帧的关键帧构建出关键路线视频或者关键路线图像集合,以使得关键路线视频或关键路线图像集合中包含更多的有用信息。
在本申请的一些实施例中,电子设备对多媒体指引内容中识别出关键指引信息的视频帧进行抽取,得到关键帧,即S2033的具体实现过程,可以包括:S2033a-S2033b,如下:
S2033a、电子设备对多媒体指引内容中的视频帧的文字进行识别,得到关键指引信息。
电子设备可以利用深度学习、光学字符识别(Optical Character Recog nition,OCR)等技术,对多媒体指引内容中的视频帧进行文字识别,得到这些视频帧中的文字信息,然后对这些文字信息的含义进行分析,从这些文字信息中提取出关键帧所对应的关键指引信息。
示例性的,当视频帧包含有停车位的编号的图像时,电子设备就可以将该视频帧中的编号识别出来,该编号就是关键指引信息,该视频帧就是关键帧。
S2033b、电子设备对包含关键指引信息的视频帧进行提取,得到关键视频帧。
电子设备在识别出关键指引信息之后,就会将包含关键指引信息的视频帧从多媒体指引内容中提取出来,从而得到关键帧。在一些实施例中,电子设备还会确定关键帧在进度条上的对应位置,从而在该位置上添加进度提示标识。
本申请实施例中,电子设备会从多媒体指引内容的各个视频帧中,通过文字识别的方式提取出关键指引信息,然后将包含关键指引信息的视频帧作为关键帧,从而完成关键帧的抽取过程,提供关键帧抽取的智能程度。
在本申请的一些实施例中,电子设备利用关键帧,构建关键路线视频或关键路线图像集合的具体实现过程,即S204的具体实现过程,可以包括:S2041-S2042,以及S2043和S2044中的任意一个,如下:
S2041、电子设备从关键帧中挑选出包含扫描码的扫码视频帧。
电子设备在构建关键路线视频或关键路线图像集合时,还会对关键帧逐一进行图像识别,从关键帧中提取出包含扫描码的视频帧,将这些提取出的视频帧记为扫描视频帧。其中,扫描码包括二维码和条形码。
S2042、电子设备对扫码视频帧中的扫描码进行用途确定,得到扫描码的用途信息。
电子设备对扫描视频帧中的扫描码进行识别、解析,从而判断出扫描码的用途,得到扫描码的用途信息。也就是说,在本申请实施例中,为了避免目标对象将其他用途的扫描码与缴纳停车费用的缴费码混淆,电子设备会先预先对扫描码的用途进行判断,以在关键路线视频或关键路线图像集合中排除其他用途的扫描码。
S2043、当扫描码的用途信息是缴费时,电子设备利用包含扫描码视频帧的关键帧,构建出关键路线视频或关键路线图像集合。
S2044、当扫描码的用途信息不是缴费时,电子设备将扫码视频帧从关键帧中剔除,并利用剔除所述扫码视频帧之后的关键帧,构建出关键路线视频或关键路线图像集合。
也就是说,当电子设备判断出扫描码不是缴费码时,就会将包含扫描 码的扫码视频帧从关键帧中剔除,以从关键帧中排除其他用途的扫描码。之后,电子设备将剔除了扫码视频帧之后的关键帧在时序上拼接取来,得到关键路线视频帧,或者是直接将提出了扫码视频帧之后的关键帧组成一个集合,得到关键路线图像集合。
本申请实施例中,电子设备能够对扫码视频帧中的扫描码进行识别,在判断出扫描码不是缴费码时,将扫码视频帧从关键视频帧中删除,从而实现对关键帧的优化。
在本申请的一些实施例中,车载采集装置包括前置摄像头和环视摄像头,此时,电子设备通过车载采集装置,对车辆从车辆驶入停车场至车辆停止行驶时的停车路线的环境信息,以及停车位的环境信息进行采集,得到多媒体指引内容,即S202的具体实现过程,可以包括:S2021,以及S2022和S2023中的一个,如下:
S2021、电子设备获取车辆在停车场的历史停放次数。
电子设备在对停车路线的环境信息和停车位的环境信息采集时,可以先分辨出目标对象是否经常到访停车场。此时,电子设备可以从互联网,或者是自身的存储空间中,统计出目标对象在历史时间到访该停车场的此时,从而得到历史停放次数。
S2022、当历史停放次数小于停放次数阈值时,电子设备将前置摄像头和环视摄像头作为车载采集装置,执行停车路线的环境信息以及停车位的环境信息的采集。
当历史停放次数小于停放次数阈值时,说明该停车场是很有可能是目标对象所不熟悉的停车场,需要尽可能多的采集环境信息。因而,电子设备会同时调用前置摄像头和环视摄像头,然后利用前置摄像头和环视摄像头作为车载采集装置,同时对停车路线的环境信息,以及停车位的环境信息进行采集,从而能够得到更丰富的环境信息,以便于目标对象在不熟悉的停车场内寻找车辆。
在一个或多个实施例中,停放次数阈值是可以根据实际需求进行设置的,例如,可以将停放次数阈值设置为5,或者设置为3,本申请实施例在此不作限定。
S2023、当历史停放次数大于等于停放次数阈值时,电子设备将前置摄像头作为车载采集装置,执行停车路线的环境信息以及停车位的环境信息的采集。
当历史停放次数大于或者等于预设停放次数时,说明目标对象已经多次到访该停车场,对该停车场已经比较熟悉了,此时,电子设备可以仅通过前置摄像头,对停车路线的环境信息和停车位的环境信息进行采集,以节省多媒体指引内容所要占用的存储资源。
当然,在一些实施例中,当历史停放次数大于停放次数阈值时,电子设备也可以不采集多媒体指引内容,即前置摄像头和环视摄像头都不开启。
本申请实施例中,电子设备能够获取车辆在停车场的历史停放次数,然后通过历史停放次数与停放次数阈值之间的大小关系,来判断出目标对象是否经常到访停车场,从而确定出应当调用哪些摄像头来采集停车路线的环境信息和停车位的环境信息,提高了多媒体指引内容采集的智能程度。
在一些实施例中,环视摄像头还可以是目标对象手动开启环视功能之后,才开始录制,以使得环视摄像头能够能将符合目标对象的需求。
下面,将说明寻车指引方法在一个实际的应用场景中的示例性应用。
该寻车指引方法是在用户借助于手机在停车场中寻找车辆的场景下实现的。本实施例中,用户(目标对象)可以从手机(终端设备)上查看车辆从进入停车场到车辆在停车位停稳这段时间的视频(包括了停车路线的环境信息和停车位的环境信息),这段视频是由车载采集装置录制的。在该视频中,还可以有停车场的缴费二维码(缴费码),用户可以通过视频中的缴费二维码缴停车费。
在视频中,对于用户而言有用的信息包括但不限于:地标的位置(停车路线所经过的底部信息)、停车的楼层(停车位所在的楼层信息)、停车支付的二维码信息(缴费码)、停车位附近的环境、车辆和停车位的编号信息(停车位的编号信息、车辆相邻的其他车辆的外观信息)、停车位置正前方的信息(停车位的正前方的环境信息)、环视图像(停车位的环视图像)。
下面,从视频录制开始,对用户借助于手机进行寻找车辆的过程进行介绍。图14是本实施例提供的借助于手机进行寻找车辆的过程示意图。参见图14,该过程包括:
S301、开始。
S302、车载终端判断车辆是否进入停车场。
车载终端(电子设备)调用车载采集装置,以一定帧率采集车辆附近环境图像(实时行驶环境的图像或视频),通过模型或结合其他信息,判断车辆进入了低下停车场。
S303、车载终端判断车辆进入停车场时,开始录制图像。
在判断出车辆进入了地下停车场之后,车载终端以高于阈值的帧率录制图像,否则,则以低于阈值的阵列录制图像。
S304、车载终端判断车辆是否停止行驶。
车载终端结合车身传感器等数据判断是否停车。在是时,进入S305,在否时,进入S303。
S305、车载终端从录制的图像中选帧上传至云端。
车载终端结合录制过程中的车速、视频中的文字情况,抽取部分图像帧(关键帧)上传到云端(服务器,电子设备的一种实施方式)或用户的手机。
S306、云端对车载终端上传的帧进行数据分析,并生成视频下发手机。
云端分析接收到的视频帧,获得有用信息(关键指引信息),生成下发 给用户的视频(更新为关键路线视频的多媒体指引内容)。
S307、手机接收视频并播放视频。
手机在显示界面上播放视频,以使用户可以查看有用信息。
在一个或多个实施例中,在S302,车载采集装置需要拍摄到车辆附近环境信息的清晰度足够的彩色图像(实时行驶环境的图像或视频),车载采集装置需要能够采集到停车场路面的情况,视角不能过于倾向向下或向上。车载终端可以对应图像进行预处理,例如缩放、裁剪、增强等。车载终端可以通过一个输出为离散量的分类模型,输出内容为细分场景(分类结果)的模型(分类模型),来对车辆附近环境图像进行识别。细分场景可以为:地下停车场、地上停车场、停车场入口档杆等。分类模型的输出也可以仅为一个二分结果,例如是否开始录像等。车载终端还可以结合GPS信号(实时地理位置)、光照传感器输出的光照强度、地图信息提供的地理围栏等,来判断出是否驶入了停车场。
在S303中,车载终端调用车载采集装置开始录像,录像过程中尽量保持较大光圈、较高感光度和较小的快门,以保证录制质量。并且,车载采集装置的录制帧率不能过低,以致错过重要信息,例如要求帧率不低于每秒5帧,录制完成后保持在本地。前置摄像头一直录制,环视摄像头可以在用户手工开启环视功能后在开始录制,帧率等要求同上。
在S304中,车载终端可以根据惯性测量单元中的角速度传感器结合加速度传感器判断车辆是否静止,可以通过轮速传感器测量的轮速判断车辆是否静止,可以通过车载采集装置所拍摄到的图像判断车辆是否静止。
在S305中,若是车载终端通过蓝牙、Wi-Fi等方式连接到手机,则可以将完整的视频(未经过去冗余的多媒体指引内容)发送给手机,否则,为了节省上传视频时的流量资费,可以抽取部分关键帧(关键帧)上传。在抽帧过程中,车载终端可以按照每隔x帧抽取的方式进行,x随车速动态变化,如车速较快时,x较小,车速较慢时x加大,即尽量保证每行驶相同距离上传(以车辆行驶过距离阈值为抽取间隔,从多媒体指引内容中抽取关键帧),或者是刚刚驶入车库(实时行驶环境)时x较大,临近停车位(实时行驶环境)时x较小(依据实时行驶环境,从多个抽帧间隔中选择出对应的目标抽帧间隔),即保证解决停车位时有足够多的信息。在抽帧完成后,在未被选中的视频帧中继续选择部分补入关键帧中,如将检测到有文字存在的帧、倒车时的帧、包含二维码的帧等补入关键帧中。
在S306中,云端对关键帧检测关键文字信息(关键指引信息)并记录,以便于后续在视频播放进度条中着重提示(通过进度提示标识来提示)。云端检测二维码信息(扫描码),解析二维码并判断是否是停车缴费二维码(缴费码),在不是缴费二维码时删除。云端通过数字图像处理技术或深度学习技术,例如deblurgan2模型,去除图像中动态模糊的部分。云端生成下发给用户的视频。
S307运行于用户的手机,其可以为手机上的软件、小程序等。手机接收用户的下载视频操作,然后为用户下载视频,或者是接收用户点击识别缴费二维码(针对第三控件的触发操作),为用户弹出缴费界面。
在一个或多个实施例中,能够将记录了从进入停车场到汽车在停车位停稳的这段时间的视频提供给用户,以使用户根据这个视频来反向寻车,提高反向寻车的效率。并且,本申请实施例只需要通过车载终端采集视频,并上传到云端,不需要额外的基础设施投入,系统复杂度、成本都会较低。
需要说明的是,在本申请实施例中,涉及到用户信息等车辆的实时地理位置,用户停车的停车场的环境信息的视频或图像,以及用户停车时的路线的视频或图像等相关的数据,当本申请实施例运用到具体产品或技术中时,需要获得用户许可或者同意,且相关数据的收集、使用和处理需要遵守相关国家和地区的相关法律和标准。
下面继续说明本申请实施例提供的寻车指引装置455实施为软件模块的示例性结构,在一些实施例中,如图4所示,存储在第一存储器450的寻车指引装置455中的软件模块可以包括:
信息展示模块4551,配置为响应于针对第一控件的第一触发操作,展示寻车指引界面;其中,所述寻车指引界面用于提供寻车的指引信息;
第一发送模块4552,配置为响应于针对所述寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求;
第一接收模块4553,配置为接收所述电子设备针对所述多媒体内容获取请求返回的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息;
所述信息展示模块4551,还配置为通过播放所述多媒体指引内容,指引目标对象寻找所述车辆。
在本申请的一些实施例中,所述信息展示模块4551,还配置为响应于针对第三控件的触发操作,展示缴费页面,其中,所述缴费页面用于供所述目标对象完成停车缴费。
在本申请的一些实施例中,所述多媒体指引内容还记录有停车路线的环境信息,以及所述多媒体指引内容所对应的进度条上展示有进度提示标识;
所述信息展示模块4551,还配置为响应于针对所述进度提示标识的触发操作,跳转到所述进度提示标识对应的关键帧,并通过从所述进度提示标识对应的关键帧开始,播放所述多媒体指引内容,指引所述目标对象寻找所述车辆;其中,所述关键帧中记录有关键指引信息,所述关键指引信息从所述停车路线的环境信息和所述停车位的环境信息提取得到。
在本申请的一些实施例中,所述信息展示模块4551,还配置为当通过从所述进度提示标识对应的关键帧开始,播放所述多媒体指引内容时,展示针对所述关键指引信息的增强效果,所述增强效果包括:箭头、标注框、 星型效果、闪烁效果中的至少一种。
下面继续说明本申请实施例提供的寻车指引装置255实施为软件模块的示例性结构,在一些实施例中,如图5所示,存储在第二存储器250的寻车指引装置255中的软件模块可以包括:
第二接收模块2551,配置为接收终端设备发送的多媒体内容获取请求;
视频获取模块2552,配置为响应于所述多媒体内容获取请求,获取对应的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息,所述多媒体指引内容基于车载采集装置采集得到;
第二发送模块2553,配置为将所述多媒体指引内容发送给所述终端设备,所述多媒体指引内容用于指引目标对象寻找所述车辆。
在本申请的一些实施例中,所述多媒体指引内容还记录有停车路线的环境信息,所述寻车指引装置255还包括:视频录制模块2554;
所述视频录制模块2554,配置为对所述车辆的实时行驶环境进行分析,得到分析结果;当所述分析结果表征所述车辆驶入停车场时,通过所述车载采集装置,对所述车辆从驶入所述停车场至停止行驶时的停车路线的环境信息,以及所述停车位的环境信息进行采集,得到所述多媒体指引内容。
在本申请的一些实施例中,所述视频录制模块2554,还配置为通过所述车载采集装置,采集所述车辆的所述实时行驶环境的图像或视频;利用分类模型,对所述实时行驶环境的图像或视频进行分类处理,得到所述分析结果;或者,通过定位装置,获取所述车辆的实时地理位置,将所述实时地理位置与所述停车场的地理围栏的位置关系,确定为所述分析结果。
在本申请的一些实施例中,所述视频录制模块2554,还配置为从所述多媒体指引内容中抽取出关键帧,所述关键帧中记录有关键指引信息,所述关键指引信息基于所述停车路线的环境信息和所述停车位的环境信息提取得到;利用所述关键帧,构建关键路线视频或关键路线图像集合,以及将所述关键路线视频或所述关键路线图像集合更新为所述多媒体指引内容。
在本申请的一些实施例中,所述视频录制模块2554,还配置为针对所述多媒体指引内容执行以下处理之一:以所述车辆行驶过距离阈值为抽取间隔,从所述多媒体指引内容中抽取所述关键帧;依据所述车辆的实时行驶环境,从多个抽帧间隔中,选择出所述实时行驶环境对应的目标抽帧间隔,并依据所述目标抽帧间隔,从所述多媒体指引内容中抽取出所述关键帧;对所述多媒体指引内容中识别出所述关键指引信息的视频帧进行抽取,得到所述关键帧。
在本申请的一些实施例中,所述视频录制模块2554,还配置为获取所述车辆在所述停车场的历史停放次数;当所述历史停放次数小于停放次数阈值时,将前置摄像头和环视摄像头作为所述车载采集装置,执行所述停车路线的环境信息以及所述停车位的环境信息的采集;当所述历史停放次数大于等于所述停放次数阈值时,将所述前置摄像头作为所述车载采集装 置,执行所述停车路线的环境信息以及所述停车位的环境信息的采集。
在本申请的一些实施例中,所述视频录制模块2554,还配置为从所述多媒体指引内容的剩余内容中,筛选得到候补视频帧;其中,所述剩余内容是所述多媒体指引内容中除所述关键帧之外的内容,所述候补视频帧至少包括:包含文字信息的视频帧、倒车时的视频帧和包含二维码时的视频帧;利用所述关键帧和所述候补视频帧,构建所述关键路线视频或所述关键路线图像集合。
在本申请的一些实施例中,所述视频录制模块2554,还配置为对所述关键帧进行模糊去除,得到优化关键帧;利用所述优化关键帧,构建所述关键路线视频或所述关键路线图像集合。
在本申请的一些实施例中,所述视频录制模块2554,还配置为从所述关键帧中挑选得到包含扫描码的扫码视频帧;所述扫描码包括二维码和条形码;对所述扫码视频帧中的所述扫描码进行用途确定,得到所述扫描码的用途信息;当所述扫描码的用途信息是缴费时,利用包含所述扫码视频帧的所述关键帧,构建出所述关键路线视频或所述关键路线图像集合;当所述扫描码的用途信息不是缴费时,将所述扫码视频帧从所述关键帧中剔除,并利用剔除所述扫码视频帧之后的关键帧,构建出所述关键路线视频或所述关键路线图像集合。
本申请实施例提供了一种计算机程序产品或计算机程序,该计算机程序产品或计算机程序包括计算机指令,该计算机指令存储在计算机可读存储介质中。计算机设备的处理器从计算机可读存储介质读取该计算机指令,处理器执行该计算机指令,使得该计算机设备执行本申请实施例上述的寻车指引方法。
本申请实施例提供一种存储有可执行指令的计算机可读存储介质,其中存储有可执行指令,当可执行指令被第一处理器执行时,将引起第一处理器执行本申请实施例提供的终端设备侧的寻车指引方法,或者被第二处理器执行时,将引起第二处理器执行本申请实施例提供的电子设备侧的寻车指引方法。
在一些实施例中,计算机可读存储介质可以是FRAM、ROM、PROM、EPROM、EEPROM、闪存、磁表面存储器、光盘、或CD-ROM等存储器;也可以是包括上述存储器之一或任意组合的各种设备。
在一些实施例中,可执行指令可以采用程序、软件、软件模块、脚本或代码的形式,按任意形式的编程语言(包括编译或解释语言,或者声明性或过程性语言)来编写,并且其可按任意形式部署,包括被部署为独立的程序或者被部署为模块、组件、子例程或者适合在计算环境中使用的其它单元。
在一个或多个实施例中,可执行指令可以但不一定对应于文件系统中的文件,可以可被存储在保存其它程序或数据的文件的一部分,例如,存 储在超文本标记语言(HTML,Hyper Text Markup Language)文档中的一个或多个脚本中,存储在专用于所讨论的程序的单个文件中,或者,存储在多个协同文件(例如,存储一个或多个模块、子程序或代码部分的文件)中。
在一个或多个实施例中,可执行指令可被部署为在一个计算设备(电子设备或终端设备)上执行,或者在位于一个地点的多个计算设备上执行,又或者,在分布在多个地点且通过通信网络互连的多个计算设备上执行。
以上所述,仅为本申请的实施例而已,并非用于限定本申请的保护范围。凡在本申请的精神和范围之内所作的任何修改、等同替换和改进等,均包含在本申请的保护范围之内。

Claims (22)

  1. 一种寻车指引方法,所述方法由终端设备执行,包括:
    响应于针对第一控件的第一触发操作,展示寻车指引界面;其中,所述寻车指引界面用于提供寻车的指引信息;
    响应于针对所述寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求;
    接收所述电子设备针对所述多媒体内容获取请求返回的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息;
    通过播放所述多媒体指引内容,指引目标对象寻找所述车辆。
  2. 根据权利要求1所述的方法,其中,所述方法还包括:
    响应于针对第三控件的触发操作,展示缴费页面,其中,所述缴费页面用于供所述目标对象完成停车缴费。
  3. 根据权利要求1或2所述的方法,其中,所述多媒体指引内容还记录有停车路线的环境信息,以及所述多媒体指引内容所对应的进度条上展示有进度提示标识;
    所述通过播放所述多媒体指引内容,指引目标对象寻找所述车辆,包括:
    响应于针对所述进度提示标识的触发操作,跳转到所述进度提示标识对应的关键帧,并通过从所述进度提示标识对应的关键帧开始,播放所述多媒体指引内容,指引所述目标对象寻找所述车辆;
    其中,所述关键帧中记录有关键指引信息,所述关键指引信息从所述停车路线的环境信息和所述停车位的环境信息提取得到。
  4. 根据权利要求3所述的方法,其中,所述关键指引信息包括:所述停车位的编号信息、所述停车路线所经过的地标信息、所述停车位所在的楼层信息、缴费码、与所述车辆相邻的其他车辆的外观信息、所述停车位的正前方的环境信息、以及所述停车位的环视图像中的至少一个。
  5. 根据权利要求4所述的方法,其中,当通过从所述进度提示标识对应的关键帧开始,播放所述多媒体指引内容时,展示针对所述关键指引信息的增强效果,所述增强效果包括:箭头、标注框、星型效果、闪烁效果中的至少一种。
  6. 一种寻车指引方法,所述方法由电子设备执行,包括:
    接收终端设备发送的多媒体内容获取请求;
    响应于所述多媒体内容获取请求,获取对应的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息,所述多媒体指引内容基于车载采集装置采集得到;
    将所述多媒体指引内容发送给所述终端设备,所述多媒体指引内容用于指引目标对象寻找所述车辆。
  7. 根据权利要求6所述的方法,其中,所述多媒体指引内容还记录有停车路线的环境信息,以及,在所述接收终端设备发送的多媒体内容获取请求之前,所述方法还包括:
    对所述车辆的实时行驶环境进行分析,得到分析结果;
    当所述分析结果表征所述车辆驶入停车场时,通过所述车载采集装置,对所述车辆从驶入所述停车场至停止行驶时的停车路线的环境信息,以及所述停车位的环境信息进行采集,得到所述多媒体指引内容。
  8. 根据权利要求7所述的方法,其中,所述对所述车辆的实时行驶环境进行分析,得到分析结果,包括:
    通过所述车载采集装置,采集所述车辆的所述实时行驶环境的图像或视频;
    利用分类模型,对所述实时行驶环境的图像或视频进行分类处理,得到所述分析结果;或者,
    通过定位装置,获取所述车辆的实时地理位置,将所述实时地理位置与所述停车场的地理围栏的位置关系,确定为所述分析结果。
  9. 根据权利要求7或8所述的方法,其中,所述方法还包括:
    从所述多媒体指引内容中抽取出关键帧,所述关键帧中记录有关键指引信息,所述关键指引信息基于所述停车路线的环境信息和所述停车位的环境信息提取得到;
    利用所述关键帧,构建关键路线视频或关键路线图像集合,以及将所述关键路线视频或所述关键路线图像集合更新为所述多媒体指引内容。
  10. 根据权利要求9所述的方法,其中,所述从所述多媒体指引内容中抽取出关键帧,包括:针对所述多媒体指引内容执行以下处理之一:
    以所述车辆行驶过距离阈值为抽取间隔,从所述多媒体指引内容中抽取所述关键帧;
    依据所述车辆的实时行驶环境,从多个抽帧间隔中,选择出所述实时行驶环境对应的目标抽帧间隔,并依据所述目标抽帧间隔,从所述多媒体指引内容中抽取出所述关键帧;
    对所述多媒体指引内容中识别出所述关键指引信息的视频帧进行抽取,得到所述关键帧。
  11. 根据权利要求10所述的方法,其中,所述关键路线视频或所述关键路线图像集合包括缴费信息视频或缴费信息图像集合,所述缴费信息视频或所述缴费信息图像集合记录有缴费码,以及所述关键路线视频或所述关键路线图像集合具有对应的进度条,所述进度条上展示有进度提示标识,所述进度提示标识与所述关键帧相对应。
  12. 根据权利要求7所述的方法,其中,所述方法还包括:
    获取所述车辆在所述停车场的历史停放次数;
    当所述历史停放次数小于停放次数阈值时,将前置摄像头和环视摄像 头作为所述车载采集装置,执行所述停车路线的环境信息以及所述停车位的环境信息的采集;
    当所述历史停放次数大于等于所述停放次数阈值时,将所述前置摄像头作为所述车载采集装置,执行所述停车路线的环境信息以及所述停车位的环境信息的采集。
  13. 根据权利要求9所述的方法,其中,所述关键帧是所述多媒体指引内容中连续的多个视频帧。
  14. 根据权利要求9所述的方法,其中,所述从所述多媒体指引内容中抽取出关键帧之后,所述利用所述关键帧,构建关键路线视频或关键路线图像集合之前,所述方法还包括:
    从所述多媒体指引内容的剩余内容中,筛选得到候补视频帧;其中,所述剩余内容是所述多媒体指引内容中除所述关键帧之外的内容,所述候补视频帧至少包括:包含文字信息的视频帧、倒车时的视频帧和包含二维码时的视频帧;
    所述利用所述关键帧,构建关键路线视频或关键路线图像集合,包括:
    利用所述关键帧和所述候补视频帧,构建所述关键路线视频或所述关键路线图像集合。
  15. 根据权利要求9所述的方法,其中,所述从所述多媒体指引内容中抽取出关键帧之后,所述利用所述关键帧,构建关键路线视频或关键路线图像集合之前,所述方法还包括:
    对所述关键帧进行模糊去除,得到优化关键帧;
    所述利用所述关键帧,构建关键路线视频或关键路线图像集合,包括:
    利用所述优化关键帧,构建所述关键路线视频或所述关键路线图像集合。
  16. 根据权利要求11所述的方法,其中,所述利用所述关键帧,构建关键路线视频或关键路线图像集合,包括:
    从所述关键帧中挑选得到包含扫描码的扫码视频帧;所述扫描码包括二维码和条形码;
    对所述扫码视频帧中的所述扫描码进行用途确定,得到所述扫描码的用途信息;
    当所述扫描码的用途信息是缴费时,利用包含所述扫码视频帧的所述关键帧,构建出所述关键路线视频或所述关键路线图像集合;
    当所述扫描码的用途信息不是缴费时,将所述扫码视频帧从所述关键帧中剔除,并利用剔除所述扫码视频帧之后的关键帧,构建出所述关键路线视频或所述关键路线图像集合。
  17. 一种寻车指引装置,包括:
    信息展示模块,配置为响应于针对第一控件的第一触发操作,展示寻车指引界面;其中,所述寻车指引界面用于提供寻车的指引信息;
    第一发送模块,配置为响应于针对所述寻车指引界面上的第二控件的第二触发操作,向电子设备发送多媒体内容获取请求;
    第一接收模块,配置为接收所述电子设备针对所述多媒体内容获取请求返回的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息;
    所述信息展示模块,还配置为通过播放所述多媒体指引内容,指引目标对象寻找所述车辆。
  18. 一种寻车指引装置,包括:
    第二接收模块,配置为接收终端设备发送的多媒体内容获取请求;
    视频获取模块,配置为响应于所述多媒体内容获取请求,获取对应的多媒体指引内容,其中,所述多媒体指引内容记录有车辆所在的停车位的环境信息,所述多媒体指引内容基于车载采集装置采集得到;
    第二发送模块,配置为将所述多媒体指引内容发送给所述终端设备,所述多媒体指引内容用于指引目标对象寻找所述车辆。
  19. 一种用于寻车指引的终端设备,包括:
    第一存储器,用于存储可执行指令;
    第一处理器,用于执行所述第一存储器中存储的可执行指令时,实现权利要求1至5任一项所述的寻车指引方法。
  20. 一种用于寻车指引的电子设备,包括:
    第二存储器,用于存储可执行指令;
    第二处理器,用于执行所述第二存储器中存储的可执行指令时,实现权利要求6至16任一项所述的寻车指引方法。
  21. 一种计算机可读存储介质,存储有可执行指令,用于被第一处理器执行时,实现权利要求1至5任一项所述的寻车指引方法,或者用于被第二处理器执行时,实现权利要求6至16任一项所述的寻车指引方法。
  22. 一种计算机程序产品,包括计算机程序或指令,所述计算机程序或指令用于被第一处理器执行时,实现权利要求1至5任一项所述的寻车指引方法,或者用于被第二处理器执行时,实现权利要求6至16任一项所述的寻车指引方法。
PCT/CN2022/075803 2021-02-20 2022-02-10 一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品 WO2022174750A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/968,550 US20230037777A1 (en) 2021-02-20 2022-10-18 Vehicle-searching guidance method and apparatus, terminal device, electronic device, and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110193653.6 2021-02-20
CN202110193653.6A CN113012464B (zh) 2021-02-20 2021-02-20 一种寻车指引方法、装置、设备及计算机可读存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/968,550 Continuation US20230037777A1 (en) 2021-02-20 2022-10-18 Vehicle-searching guidance method and apparatus, terminal device, electronic device, and computer-readable storage medium

Publications (1)

Publication Number Publication Date
WO2022174750A1 true WO2022174750A1 (zh) 2022-08-25

Family

ID=76404487

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/075803 WO2022174750A1 (zh) 2021-02-20 2022-02-10 一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品

Country Status (3)

Country Link
US (1) US20230037777A1 (zh)
CN (1) CN113012464B (zh)
WO (1) WO2022174750A1 (zh)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113012464B (zh) * 2021-02-20 2022-03-22 腾讯科技(深圳)有限公司 一种寻车指引方法、装置、设备及计算机可读存储介质
CN116229753A (zh) * 2021-12-03 2023-06-06 北京罗克维尔斯科技有限公司 寻车的导航方法及其装置
CN114333400A (zh) * 2021-12-21 2022-04-12 上汽通用汽车有限公司 一种寻车指引方法、系统及存储介质
CN114333404A (zh) * 2021-12-29 2022-04-12 阿维塔科技(重庆)有限公司 一种停车场寻车方法、装置、车辆及存储介质
CN114202956A (zh) * 2022-01-26 2022-03-18 深圳市元征科技股份有限公司 取车方法、车载终端、用户终端及电子设备
CN114173287A (zh) * 2022-02-14 2022-03-11 荣耀终端有限公司 定位方法及装置、设备、定位系统以及存储介质
CN115050206B (zh) * 2022-06-09 2023-06-27 陕西工业职业技术学院 一种基于智能手机的智能停车场停车寻车导航系统
CN115063721A (zh) * 2022-06-20 2022-09-16 广州小鹏汽车科技有限公司 寻车方法、车辆及移动终端
CN115410401A (zh) * 2022-08-30 2022-11-29 深圳市神州路路通网络科技有限公司 基于停车场内车辆数据共享的车位展示与推荐方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104023181A (zh) * 2014-06-23 2014-09-03 联想(北京)有限公司 信息处理方法及装置
US20140266803A1 (en) * 2013-03-15 2014-09-18 Xerox Corporation Two-dimensional and three-dimensional sliding window-based methods and systems for detecting vehicles
CN104809771A (zh) * 2015-04-30 2015-07-29 上海天奕达电子科技有限公司 寻车方法及系统
CN110223528A (zh) * 2019-06-10 2019-09-10 三星电子(中国)研发中心 寻车方法、停车方法及使用该方法的装置
CN110599794A (zh) * 2019-07-31 2019-12-20 广东翼卡车联网服务有限公司 一种基于车联网的智能找车方法及系统
CN111524381A (zh) * 2020-03-23 2020-08-11 深圳市大拿科技有限公司 一种停车位置的推送方法、装置、系统及电子设备
CN113012464A (zh) * 2021-02-20 2021-06-22 腾讯科技(深圳)有限公司 一种寻车指引方法、装置、设备及计算机可读存储介质

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040128317A1 (en) * 2000-07-24 2004-07-01 Sanghoon Sull Methods and apparatuses for viewing, browsing, navigating and bookmarking videos and displaying images
CN103024561B (zh) * 2011-09-28 2016-05-25 深圳市快播科技有限公司 一种拖拽进度条的显示方法及装置
CA3041176C (en) * 2016-10-13 2020-07-21 Nissan Motor Co., Ltd. Parking assistance method and parking assistance device
CN106776890B (zh) * 2016-11-29 2021-06-29 北京小米移动软件有限公司 视频播放进度的调整方法及装置
CN107862899A (zh) * 2017-11-16 2018-03-30 深圳市小猫信息技术有限公司 反向寻车方法、装置、计算机装置及计算机可读存储介质
CN108510786A (zh) * 2018-04-18 2018-09-07 西安艾润物联网技术服务有限责任公司 停车场寻车方法、装置及计算机可读存储介质
CN208655049U (zh) * 2018-08-17 2019-03-26 郑州丰嘉科技有限公司 一种停车场摄像监控系统
CN109377779A (zh) * 2018-09-27 2019-02-22 盯盯拍(深圳)云技术有限公司 停车场寻车方法以及停车场寻车装置
CN109166344A (zh) * 2018-09-27 2019-01-08 盯盯拍(深圳)云技术有限公司 停车场寻车方法以及停车场寻车装置
CN110232826A (zh) * 2018-10-23 2019-09-13 蔚来汽车有限公司 停车场入口寻找方法和装置以及控制器和介质
CN109466546B (zh) * 2018-11-20 2020-09-18 广州小鹏汽车科技有限公司 自动泊车方法及系统
CN110234069A (zh) * 2019-05-29 2019-09-13 深圳市轱辘汽车维修技术有限公司 一种寻车方法、装置及终端设备
CN110491166A (zh) * 2019-08-22 2019-11-22 宇龙计算机通信科技(深圳)有限公司 一种寻找车辆的方法、装置、系统、存储介质及用户终端
CN110556022A (zh) * 2019-09-29 2019-12-10 深圳市大拿科技有限公司 基于人工智能的停车场车位指示方法、装置及电子设备
CN110751854B (zh) * 2019-10-28 2021-08-31 芜湖雄狮汽车科技有限公司 汽车的停车指引方法、装置及存储介质
CN110889971B (zh) * 2019-11-08 2021-11-30 深圳市国佳智能软件有限公司 停车场智能找车方法和装置
CN110958470A (zh) * 2019-12-09 2020-04-03 北京字节跳动网络技术有限公司 一种多媒体内容处理方法、装置、介质和电子设备
US10846534B1 (en) * 2020-03-17 2020-11-24 Capital Once Services, LLC Systems and methods for augmented reality navigation

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140266803A1 (en) * 2013-03-15 2014-09-18 Xerox Corporation Two-dimensional and three-dimensional sliding window-based methods and systems for detecting vehicles
CN104023181A (zh) * 2014-06-23 2014-09-03 联想(北京)有限公司 信息处理方法及装置
CN104809771A (zh) * 2015-04-30 2015-07-29 上海天奕达电子科技有限公司 寻车方法及系统
CN110223528A (zh) * 2019-06-10 2019-09-10 三星电子(中国)研发中心 寻车方法、停车方法及使用该方法的装置
CN110599794A (zh) * 2019-07-31 2019-12-20 广东翼卡车联网服务有限公司 一种基于车联网的智能找车方法及系统
CN111524381A (zh) * 2020-03-23 2020-08-11 深圳市大拿科技有限公司 一种停车位置的推送方法、装置、系统及电子设备
CN113012464A (zh) * 2021-02-20 2021-06-22 腾讯科技(深圳)有限公司 一种寻车指引方法、装置、设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN113012464B (zh) 2022-03-22
CN113012464A (zh) 2021-06-22
US20230037777A1 (en) 2023-02-09

Similar Documents

Publication Publication Date Title
WO2022174750A1 (zh) 一种寻车指引方法、装置、终端设备、电子设备及计算机可读存储介质、程序产品
US11443555B2 (en) Scenario recreation through object detection and 3D visualization in a multi-sensor environment
KR102043588B1 (ko) 자율 주행 차량 내에서 미디어 콘텐츠를 표시하기 위한 시스템 및 방법
US11115646B2 (en) Exposure coordination for multiple cameras
Rasouli et al. Are they going to cross? a benchmark dataset and baseline for pedestrian crosswalk behavior
US20190078905A1 (en) Systems and methods for using real-time imagery in navigation
KR102652023B1 (ko) 실시간 교통 정보 제공 방법 및 장치
JP6503218B2 (ja) 運転支援システム、運転支援装置及び運転支援方法
CN107436153A (zh) 基于实时交通信息在无人驾驶车辆中提供内容的系统和方法
WO2020024457A1 (zh) 交通事故的定责方法、装置及计算机可读存储介质
CN107563267A (zh) 在无人驾驶车辆中提供内容的系统和方法
CN107369207A (zh) 在无人驾驶车辆中提供增强虚拟现实内容的系统和方法
JP7450287B2 (ja) 再生装置および再生方法ならびにそのプログラムならびに記録装置および記録装置の制御方法等
Jiang et al. Anti-uav: a large-scale benchmark for vision-based uav tracking
CN104537837B (zh) 确定交通路线的方法、装置及系统
US20210357662A1 (en) Ground truth based metrics for evaluation of machine learning based models for predicting attributes of traffic entities for navigating autonomous vehicles
CN105814532A (zh) 用于三维对象显示的方法
CN112650772B (zh) 数据处理方法、装置、存储介质及计算机设备
CN110782653A (zh) 一种道路信息采集方法和系统
CN109544981B (zh) 图像处理方法、装置、设备和介质
CN112686998B (zh) 一种信息展示方法、装置、设备及计算机可读存储介质
CN108881846A (zh) 信息融合方法、装置及计算机可读存储介质
Gao et al. Detecting and learning city intersection traffic contexts for autonomous vehicles
CN114332798A (zh) 网约车环境信息的处理方法及相关装置
Shukla et al. Real-Time Parking Space Detection and Management with Artificial Intelligence and Deep Learning System

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: 22755523

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 17/01/2024)