WO2023273036A1 - 导航方法、装置、电子设备及可读存储介质 - Google Patents

导航方法、装置、电子设备及可读存储介质 Download PDF

Info

Publication number
WO2023273036A1
WO2023273036A1 PCT/CN2021/125858 CN2021125858W WO2023273036A1 WO 2023273036 A1 WO2023273036 A1 WO 2023273036A1 CN 2021125858 W CN2021125858 W CN 2021125858W WO 2023273036 A1 WO2023273036 A1 WO 2023273036A1
Authority
WO
WIPO (PCT)
Prior art keywords
real
image
navigation
scene image
vehicle
Prior art date
Application number
PCT/CN2021/125858
Other languages
English (en)
French (fr)
Inventor
邓苏南
Original Assignee
阿波罗智联(北京)科技有限公司
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 阿波罗智联(北京)科技有限公司 filed Critical 阿波罗智联(北京)科技有限公司
Publication of WO2023273036A1 publication Critical patent/WO2023273036A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
    • G01C21/3476—Special cost functions, i.e. other than distance or default speed limit of road segments using point of interest [POI] information, e.g. a route passing visible POIs
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3635—Guidance using 3D or perspective road maps
    • G01C21/3638—Guidance using 3D or perspective road maps including 3D objects and buildings
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34—Route searching; Route guidance
    • G01C21/36—Input/output arrangements for on-board computers
    • G01C21/3626—Details of the output of route guidance instructions
    • G01C21/3644—Landmark guidance, e.g. using POIs or conspicuous other objects

Definitions

  • the present disclosure relates to the technical field of Internet of Vehicles, and in particular to the technical field of navigation. Specifically, the present disclosure relates to a navigation method, device, electronic equipment, and readable storage medium.
  • AR Augmented Reality
  • the virtual 3D navigation guide model can be displayed on the real scene, giving users an augmented reality experience. How to ensure the combination effect of virtual scene and real scene in AR navigation is an important technical issue in the field of AR navigation.
  • the disclosure provides a navigation method, device, electronic equipment and readable storage medium.
  • a navigation method comprising:
  • Navigation content is generated based on the matching result.
  • a navigation device comprising:
  • the data acquisition module is configured to acquire real-scene images and navigation-related information
  • an object recognition module configured to recognize a target object in the real-scene image
  • a matching module configured to match the target object with the navigation-related information to obtain a matching result
  • a navigation content generation module configured to generate navigation content based on the matching result.
  • an electronic device includes:
  • a memory communicatively coupled to at least one of the processors; wherein,
  • the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the above navigation method.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions implement the above navigation method when executed by a computer.
  • a computer program product comprising a computer program which, when executed by a processor, implements the above navigation method.
  • FIG. 1 is a schematic flowchart of a navigation method provided by an embodiment of the present disclosure
  • Fig. 2 is a schematic flowchart of another navigation method provided by an embodiment of the present disclosure
  • FIG. 3 is a schematic structural diagram of a navigation system provided by an embodiment of the present disclosure.
  • Fig. 4 is a schematic structural diagram of a navigation device provided according to the present disclosure.
  • Fig. 5 is a schematic structural diagram of another navigation device provided according to the present disclosure.
  • FIG. 6 is a block diagram of an electronic device for implementing a navigation method of an embodiment of the present disclosure.
  • the existing AR navigation is generally projected on the car screen or the Augmented Reality Head Up Display (AR HUD). There are certain defects in the existing methods, which affect the user experience.
  • AR HUD Augmented Reality Head Up Display
  • the navigation information is not integrated with the real scene, but with the video, which is not a real real scene superposition in essence, and the driver needs to look down at the screen to obtain the navigation information.
  • AR HUD can achieve a small field of view (FOV), the contrast of the picture under strong light is seriously reduced, and the eyebox projected by the HUD is relatively fixed. Can't see the full picture.
  • FOV field of view
  • the AR navigation content can be projected on the MR glasses, the above-mentioned shortcomings of projecting the AR navigation on the car screen or the head-up display can be overcome.
  • MR Mediated Reality
  • the positioning chip and image generation unit are independently coupled to the glasses. But in the vehicle field, if you want to display relevant navigation information, superimposing positioning chips such as GPS/IMU on the glasses will increase the weight of the glasses and make the device look bloated.
  • the real-scene images are generally collected by the camera of the car, and then the navigation content is generated according to the real-scene images.
  • the content of the AR navigation is projected onto the car glasses, because the user's head may shake, making the projection
  • AR navigation is to display virtual navigation-related information on the real scene, giving users an augmented reality experience. How to ensure the combination effect of navigation-related information and real scenes is an important technical issue in the field of AR navigation.
  • the navigation method, device, electronic device, and computer-readable storage medium provided in the embodiments of the present application aim to solve at least one of the above technical problems in the prior art.
  • Fig. 1 shows a schematic flowchart of a navigation method provided by an embodiment of the present disclosure. As shown in Fig. 1, the method may mainly include:
  • Step S110 Acquiring real-scene images and navigation-related information
  • Step S120 Recognize the target object in the real-scene image
  • Step S130 matching the target object with navigation-related information to obtain a matching result
  • Step S140 Generate navigation content based on the matching result.
  • navigation-related information may include but not limited to Advanced Driving Assistance System (Advanced Driving Assistance System, ADAS) information, and high-precision map information, for example, it may be Point of Interest (POI) information, navigation information and Guidance signals, etc.
  • Advanced Driving Assistance System Advanced Driving Assistance System
  • POI Point of Interest
  • the real scene image is an image of the surrounding environment of the vehicle.
  • Scene recognition can be performed on real-scene images to identify target objects, such as lane lines, buildings, and turning intersections.
  • the navigation content can be rendered according to the matching result.
  • the rendered navigation content can be a virtual 3D navigation guidance model.
  • the navigation content is generated based on the matching result of the navigation-related information and the target object, the navigation content can be better combined with the real scene image to ensure the effect of AR navigation.
  • the method provided by the embodiments of the present disclosure acquires real-scene images and navigation-related information, identifies target objects in the real-scene images, matches the target objects with navigation-related information, obtains matching results, and generates navigation content based on the matching results. Since the navigation content is generated based on the matching result of the target object and the navigation-related information, the navigation content can be better combined with the real scene image, thereby ensuring the effect of AR navigation.
  • matching the target object with navigation-related information includes:
  • the navigation-related information corresponding to the target object is matched with the location information.
  • the location information of the target object in the real-scene image can be matched with navigation-related information, and correspondingly generated navigation content can also be matched with the location information, that is, the display location of the navigation content can be determined according to the location information.
  • the target object is a left turn at an intersection in the real scene image
  • the navigation content is a left turn arrow, which may be displayed above the left turn at the intersection.
  • the target object is a building in a Point of Information (POI)
  • the navigation content is the name of the building
  • the name of the building is displayed above the location of the building.
  • the navigation content can be closely combined with the corresponding entity object, ensuring the effect of AR navigation.
  • the above navigation method further includes:
  • Navigation-related information is generated based on the positioning information.
  • the sensors of the vehicle may include, but are not limited to, Global Positioning System (Global Positioning System, GPS), Inertial Measurement Unit (Inertial Measurement Unit, IMU), Radar (radar), lidar (lidar), and cameras.
  • the sensor data collected by these sensors can be sent to the data fusion module, and the data fusion is performed based on the preset data fusion algorithm to determine the current location information of the car.
  • the positioning information is input into the navigation module to obtain and generate navigation-related information.
  • the collected real-scene pictures and sensor data fusion results can be sent to the ADAS module for identifying obstacles and identifying environmental information.
  • the identified obstacle information and environment information can also be used to render and draw the navigation content.
  • Fig. 2 shows a schematic flowchart of another navigation method provided by an embodiment of the present disclosure. As shown in Fig. 2, the method may mainly include:
  • Step S210 Acquiring real-scene images and navigation-related information
  • Step S220 Recognize the target object in the real-scene image
  • Step S230 matching the target object with navigation-related information to obtain a matching result
  • Step S240 generating navigation content based on the matching result
  • Step S250 converting the real-scene image to obtain a projected image, the projected image matches the window of at least one vehicle-mounted glasses;
  • Step S260 Fusing the projected image with the navigation content to obtain a navigation image
  • Step S270 Sending the navigation image to the vehicle-mounted glasses, so that the vehicle-mounted glasses display the navigation image.
  • navigation-related information may include but not limited to Advanced Driving Assistance System (Advanced Driving Assistance System, ADAS) information, and high-precision map information, for example, it may be Point of Interest (POI) information, navigation information and Guidance signals, etc.
  • Advanced Driving Assistance System Advanced Driving Assistance System
  • POI Point of Interest
  • the real scene image is an image of the surrounding environment of the vehicle.
  • Scene recognition can be performed on real-scene images to identify target objects, such as lane lines, buildings, and turning intersections.
  • the navigation content can be rendered according to the matching result.
  • the rendered navigation content can be a virtual 3D navigation guidance model.
  • the navigation content is generated based on the matching result of the navigation-related information and the target object, the navigation content can be better combined with the real scene image to ensure the effect of AR navigation.
  • the target object in the real-scene image is identified, the target object is matched with the navigation-related information, the matching result is obtained, and the navigation content is generated based on the matching result. Since the navigation content is generated based on the matching result of the target object and the navigation-related information, the navigation content can be better combined with the real scene image, thereby ensuring the effect of AR navigation.
  • Vehicle-mounted glasses may include but are not limited to smart glasses such as MR glasses. Users can wear vehicle-mounted glasses while driving a vehicle and use the vehicle-mounted glasses to realize navigation.
  • a plurality of vehicle-mounted glasses may be equipped in the vehicle to meet the usage requirements of a large number of users.
  • the visible area of the user's eyes corresponds to the window (eyebox) of the vehicle-mounted glasses. Therefore, the real scene image is converted to obtain a projected image that matches the window of the vehicle-mounted glasses.
  • the projected image is consistent with the user's eyebox.
  • the visual area of the eyes is matched, and based on the fusion of the projected image and the navigation content, the AR navigation can ensure the AR navigation effect, give the user a sense of augmented reality, and avoid affecting the AR navigation effect due to the movement of the user's head.
  • an adjustment cycle is set to periodically convert the real scene image to ensure the AR navigation effect.
  • the adjustment cycle can be 2 seconds.
  • the navigation image may be sent to the vehicle-mounted glasses, and the navigation image is displayed through the vehicle-mounted glasses to realize AR navigation.
  • Projecting AR navigation on the car glasses can overcome the defects of the existing technology when AR navigation is projected on the car screen or AR HUD, and improve the user experience.
  • the method provided by the embodiments of the present disclosure acquires real-scene images and navigation-related information, identifies target objects in the real-scene images, matches the target objects with navigation-related information, obtains matching results, and generates navigation content based on the matching results.
  • Acquire the real-scene image and navigation content convert the real-scene image to obtain a projected image, match the projected image with the window of at least one vehicle-mounted glasses, fuse the projected image and navigation content to obtain a navigation image, and send the navigation image to the vehicle-mounted glasses, the vehicle-mounted The glasses display navigation images.
  • the navigation content can be better combined with the real scene image, and the AR navigation is realized based on the vehicle-mounted glasses, which can avoid the influence on the effect of the AR navigation caused by the change of the user's head position, ensure the effect of the AR navigation, and ensure the user use experience.
  • converting the real-scene image to obtain a projected image includes:
  • the first real-scene image is converted to obtain a projected image.
  • the real-scene image may be collected by the first image collection device of the vehicle, or may be collected by the second image collection device of the vehicle glasses.
  • Image capture devices may include, but are not limited to, cameras.
  • the real-scene image is the first real-scene image captured by the first image capture device of the car
  • the second image capture device of the vehicle-mounted glasses and the position of the window in the vehicle-mounted glasses are fixed, it can be based on the second image capture device and the position of the window in the vehicle-mounted glasses.
  • the actual positional relationship of the window in the vehicle-mounted glasses determines the first positional relationship between the second real-scene image and the window of the vehicle-mounted glasses.
  • the second positional relationship between the first real-scene image and the second real-scene image also changes in real time, so the second positional relationship may be acquired periodically according to the adjustment period.
  • the first real-scene image may be converted according to the first positional relationship and the second positional relationship to obtain a projected image.
  • [R1 T1] is a certain amount, where P(eyebox) represents the projected image, and P(camera2) represents the second real scene image.
  • determining a second positional relationship between the first real-scene image and the second real-scene image includes any of the following:
  • the second position relationship may be obtained by means of feature point tracking such as PNP solution.
  • the first real-scene image and the second real-scene image can be transmitted to the microcontroller unit (MCU) of the vehicle for processing.
  • MCU microcontroller unit
  • the generation of the navigation image can be completed in the vehicle, and the navigation image is sent to the vehicle glasses, so that the vehicle glasses do not need to be equipped with too many sensors, and the bloat of the vehicle glasses is avoided.
  • the designated position of the user in the car it is also possible to set the designated position of the user in the car, and use the designated position as a reference to calculate the third positional relationship between the third real-scene image collected when the vehicle-mounted glasses are at the designated position and the first real-scene image, Then, the vehicle-mounted glasses are positioned in real time, and the position change of the position of the vehicle-mounted glasses compared with the designated position is calculated, and the second positional relationship can be determined according to the positional change and the third positional relationship.
  • the third positional relationship can be obtained by tracking image feature points.
  • the position of the vehicle-mounted glasses when the driver is sitting upright and wearing the vehicle-mounted glasses may be used as the designated position.
  • Use the image feature point tracking to obtain the initial value of the relationship P(camera2) [R20 T20]P(camera1).
  • P(camera2) [Rx Tx][R20 T20]P(camera1)
  • the current location of the vehicle-mounted glasses is obtained based on a positioning system of the vehicle-mounted glasses.
  • the positioning system of the vehicle-mounted glasses may include positioning chips such as GPS/IMU.
  • converting the real-scene image to obtain a projected image includes:
  • the real-scene image is the second real-scene image collected by the second image acquisition device of the vehicle-mounted glasses
  • the positions of the second image-capture device of the vehicle-mounted glasses and the window in the vehicle-mounted glasses are fixed, it can be based on The actual positional relationship between the second image acquisition device and the window in the vehicle-mounted glasses determines the first positional relationship between the second real-scene image and the window of the vehicle-mounted glasses. Based on the first positional relationship, the second real-scene image can be converted into a projected image.
  • P(eyebox) [R1 T1]P(camera2), wherein, P(eyebox) represents the projected image, and P(camera2) represents the second real scene image.
  • the first positional relationship may be represented by [R1 T1].
  • the navigation image is sent to the car glasses, including:
  • the wireless communication method can be wireless fidelity (Wireless Fidelity, wifi), and the navigation image can also be sent through a wired method, such as through a Universal Serial Bus (Universal Serial Bus, USB) interface or a low-voltage differential signal interface (Low- Voltage Differential Signaling, lvdss) and other methods.
  • a wired method such as through a Universal Serial Bus (Universal Serial Bus, USB) interface or a low-voltage differential signal interface (Low- Voltage Differential Signaling, lvdss) and other methods.
  • FIG. 3 shows a schematic structural diagram of a navigation system provided by the implementation of the present disclosure.
  • Camera1 is the first image acquisition device of the vehicle.
  • Camera2 that is, the second image acquisition device of the vehicle-mounted glasses.
  • eyebox the window.
  • MCU is the MCU of the car;
  • AR creator is the augmented reality software suite, which includes ADAS (advanced driver assistance system), SD/HD MAP, street directory map or high-precision map, and ANP (Apollo Navigation Pilot) map.
  • ADAS advanced driver assistance system
  • SD/HD MAP street directory map or high-precision map
  • ANP Adpollo Navigation Pilot
  • the first real-scene image collected by Camera1 and the second real-scene image collected by Camera2 can be transmitted to the MCU.
  • the navigation image can be transmitted to the PGU of the vehicle glasses through wireless transmission (such as wifi), etc. (i.e. image generation unit), PGU displays the navigation image.
  • FIG. 4 shows a schematic structural diagram of a navigation device provided by an embodiment of the present disclosure.
  • the navigation device 40 may include:
  • the data acquisition module 410 is configured to acquire real-scene images and navigation-related information
  • the object identification module 420 is configured to identify the target object in the real-scene image
  • the matching module 430 is configured to match the target object with navigation-related information to obtain a matching result
  • the navigation content generation module 440 is configured to generate navigation content based on the matching result.
  • the device provided by the embodiments of the present disclosure acquires real-scene images and navigation-related information, identifies target objects in the real-scene images, matches the target objects with navigation-related information, obtains matching results, and generates navigation content based on the matching results. Since the navigation content is generated based on the matching result of the target object and the navigation-related information, the navigation content can be better combined with the real scene image, thereby ensuring the effect of AR navigation.
  • the matching module matches the target object with navigation-related information, it is configured to:
  • the navigation-related information corresponding to the target object is matched with the location information.
  • the above-mentioned navigation device further includes a navigation-related information generation module, and the navigation-related information generation module is configured to:
  • Navigation-related information is generated based on the positioning information.
  • the above-mentioned modules of the navigation device in the embodiment of the present disclosure have the function of implementing the corresponding steps of the navigation method in the embodiment shown in FIG. 1 .
  • This function may be implemented by hardware, or may be implemented by executing corresponding software on the hardware.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • the above-mentioned modules may be software and/or hardware, and each of the above-mentioned modules may be realized independently, or multiple modules may be integrated and realized.
  • For the functional description of each module of the above-mentioned navigation device please refer to the corresponding description of the navigation method in the embodiment shown in FIG. 1 , which will not be repeated here.
  • FIG. 5 shows a schematic structural diagram of another navigation device provided by an embodiment of the present disclosure.
  • the navigation device 50 may include:
  • the data acquisition module 510 is configured to acquire real-scene images and navigation-related information
  • the object identification module 520 is configured to identify the target object in the real-scene image
  • the matching module 530 is configured to match the target object with navigation-related information to obtain a matching result
  • the navigation content generation module 540 is configured to generate navigation content based on the matching result
  • the image conversion module 550 is configured to convert the real scene image to obtain a projected image, and the projected image matches the window of at least one vehicle-mounted glasses;
  • the image fusion module 560 is configured to fuse the projected image with the navigation content to obtain the navigation image
  • the navigation image sending module 570 is configured to send the navigation image to the vehicle glasses, so that the vehicle glasses display the navigation image.
  • the device acquires real-scene images and navigation-related information, identifies target objects in the real-scene images, matches the target objects with navigation-related information, obtains matching results, and generates navigation content based on the matching results.
  • Acquire the real-scene image and navigation content convert the real-scene image to obtain a projected image, match the projected image with the window of at least one vehicle-mounted glasses, fuse the projected image and navigation content to obtain a navigation image, and send the navigation image to the vehicle-mounted glasses, the vehicle-mounted The glasses display navigation images.
  • the navigation content can be better combined with the real scene image, and the AR navigation is realized based on the vehicle-mounted glasses, which can avoid the influence on the effect of the AR navigation caused by the change of the user's head position, ensure the effect of the AR navigation, and ensure the user experience.
  • the image conversion module is configured to: when converting the real-scene image to obtain the projection image:
  • the first real-scene image is converted to obtain a projected image.
  • the image conversion module acquires the first positional relationship between the second real scene image collected by the second image acquisition device of the vehicle-mounted glasses and the window of the vehicle-mounted glasses, it is configured to:
  • the first positional relationship is determined based on the position of the second image acquisition device and the position of the window on the vehicle-mounted glasses.
  • the image conversion module determines the second positional relationship between the first real-scene image and the second real-scene image, it is configured as any of the following:
  • the real-scene image is the second real-scene image collected by the second image acquisition device of the vehicle-mounted glasses
  • the image conversion module converts the real-scene image to obtain the projected image
  • the above modules of the navigation device in the embodiment of the present disclosure have the function of implementing the corresponding steps of the navigation method in the embodiment shown in FIG. 2 .
  • This function may be implemented by hardware, or may be implemented by executing corresponding software on the hardware.
  • the hardware or software includes one or more modules corresponding to the above functions.
  • the above-mentioned modules may be software and/or hardware, and each of the above-mentioned modules may be realized independently, or multiple modules may be integrated and realized.
  • For the functional description of each module of the above navigation device please refer to the corresponding description of the navigation method in the embodiment shown in FIG. 2 , which will not be repeated here.
  • the acquisition, storage and application of the user's personal information involved are in compliance with relevant laws and regulations, and do not violate public order and good customs.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • the electronic device includes: at least one processor; and a memory connected in communication with the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor
  • the navigation method provided by the embodiments of the present disclosure can be executed.
  • the electronic device acquires real-scene images and navigation-related information, recognizes target objects in the real-scene images, matches the target objects with navigation-related information, obtains matching results, and generates navigation content based on the matching results. Since the navigation content is generated based on the matching result of the target object and the navigation-related information, the navigation content can be better combined with the real scene image, thereby ensuring the effect of AR navigation.
  • the readable storage medium is a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions implement the navigation method provided by the embodiments of the present disclosure when executed by a computer.
  • the readable storage medium recognizes the target object in the real-scene image by acquiring the real-scene image and navigation-related information, matches the target object with the navigation-related information, obtains a matching result, and generates a navigation system based on the matching result. content. Since the navigation content is generated based on the matching result of the target object and the navigation-related information, the navigation content can be better combined with the real scene image, thereby ensuring the effect of AR navigation.
  • the computer program product includes a computer program, and when the computer program is executed by a processor, the navigation method provided by the embodiments of the present disclosure is implemented.
  • the computer program product recognizes the target object in the real-scene image by acquiring the real-scene image and navigation-related information, matches the target object with the navigation-related information, obtains a matching result, and generates navigation content based on the matching result . Since the navigation content is generated based on the matching result of the target object and the navigation-related information, the navigation content can be better combined with the real scene image, thereby ensuring the effect of AR navigation.
  • FIG. 6 shows a schematic block diagram of an example electronic device 2000 that may be used to implement embodiments of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 2000 includes a computing unit 2010 that can be executed according to a computer program stored in a read-only memory (ROM) 2020 or loaded from a storage unit 2080 into a random access memory (RAM) 2030. Various appropriate actions and treatments. In the RAM 2030, various programs and data necessary for the operation of the device 2000 can also be stored.
  • the calculation unit 2010, the ROM 2020 and the RAM 2030 are connected to each other through the bus 2040.
  • An input/output (I/O) interface 2050 is also connected to bus 2040 .
  • the I/O interface 2050 includes: an input unit 2060, such as a keyboard, a mouse, etc.; an output unit 2070, such as various types of displays, speakers, etc.; a storage unit 2080, such as a magnetic disk, an optical disk, etc. ; and a communication unit 2090, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 2090 allows the device 2000 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 2010 may be various general-purpose and/or special-purpose processing components having processing and computing capabilities. Some examples of computing units 2010 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc.
  • the computing unit 2010 executes the navigation method provided in the embodiments of the present disclosure.
  • the navigation method provided in the embodiments of the present disclosure may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as the storage unit 2080 .
  • part or all of the computer program may be loaded and/or installed on the device 2000 via the ROM 2020 and/or the communication unit 2090.
  • the computer program When the computer program is loaded into the RAM 2030 and executed by the computing unit 2010, one or more steps of the navigation method provided in the embodiments of the present disclosure can be executed.
  • the computing unit 2010 may be configured in any other appropriate way (for example, by means of firmware) to execute the navigation method provided in the embodiments of the present disclosure.
  • Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof.
  • FPGAs field programmable gate arrays
  • ASICs application specific integrated circuits
  • ASSPs application specific standard products
  • SOC system of systems
  • CPLD load programmable logic device
  • computer hardware firmware, software, and/or combinations thereof.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read only memory
  • CD-ROM compact disk read only memory
  • magnetic storage or any suitable combination of the foregoing.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user. ); and a keyboard and pointing device (eg, a mouse or a trackball) through which a user can provide input to the computer.
  • a display device e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor
  • a keyboard and pointing device eg, a mouse or a trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (WAN) and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.
  • steps may be reordered, added or deleted using the various forms of flow shown above.
  • each step described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Navigation (AREA)

Abstract

一种导航方法、装置(400,500)、电子设备(2000)及可读存储介质，涉及车联网技术领域，尤其涉及导航技术领域。导航方法包括：通过获取实景图像以及导航相关信息(S110)，对实景图像中的目标对象进行识别(S120)，将目标对象与导航相关信息进行匹配，得到匹配结果(S130)，基于匹配结果生成导航内容(S140)。

Description

导航方法、装置、电子设备及可读存储介质 技术领域
本公开涉及车联网技术领域，尤其涉及导航技术领域，具体而言，本公开涉及一种导航方法、装置、电子设备及可读存储介质。
背景技术
随着增强现实(Augmented Reality，AR)技术的应用越来越广泛，用户对AR应用的接受程度也越来越高。AR技术的重要应用场景之一在于实现AR导航。
AR导航时可以将虚拟的3D导航指引模型显示在实景之上，给用户以增强现实的使用感受。如何保证AR导航中虚景与实景的结合效果，是AR导航领域中的一个重要技术问题。
发明内容
本公开提供了一种导航方法、装置、电子设备及可读存储介质。
根据本公开的第一方面，提供了一种导航方法，该方法包括：
获取实景图像以及导航相关信息；
对所述实景图像中的目标对象进行识别；
将所述目标对象与所述导航相关信息进行匹配，得到匹配结果；
基于所述匹配结果生成导航内容。
根据本公开的第二方面，提供了一种导航装置，该装置包括：
数据获取模块，被配置为获取实景图像以及导航相关信息；
对象识别模块，被配置为对所述实景图像中的目标对象进行识别；
匹配模块，被配置为将所述目标对象与所述导航相关信息进行匹配，得到匹配结果；
导航内容生成模块，被配置为基于所述匹配结果生成导航内容。
根据本公开的第三方面，提供了一种电子设备，该电子设备包括：
至少一个处理器；以及
与上述至少一个处理器通信连接的存储器；其中，
存储器存储有可被上述至少一个处理器执行的指令，指令被上述至少一个处理器执行，以使上述至少一个处理器能够执行上述导航方法。
根据本公开的第四方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，该计算机指令在被计算机执行时实现上述导航方法。
根据本公开的第五方面，提供了一种计算机程序产品，包括计算机程序，该计算机程序在被处理器执行时实现上述导航方法。
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。
附图说明
附图用于更好地理解本方案，不构成对本公开的限定。其中：
图1是本公开实施例提供的一种导航方法的流程示意图；
图2是本公开实施例提供的另一种导航方法的流程示意图；
图3是本公开实施例提供的一种导航系统的结构示意图；
图4是根据本公开提供的一种导航装置的结构示意图；
图5是根据本公开提供的另一种导航装置的结构示意图；
图6是用来实现本公开实施例的导航方法的电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围和精神。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。
现有的AR导航一般投射在车机屏幕或者抬头显示器(Augmented Reality Head Up Display，AR HUD)上，现有方式中存在一定的缺陷，影响用户的使用体验。
对于投射车机屏幕上的AR导航：导航信息并没有与实景融合，而是与视频做融合，本质上不算真正的实景叠加，且驾驶人员需要低头看屏幕获取导航信息。
对于显示在AR HUD上的AR导航：AR HUD能够实现的视场角(FOV)较小，强光下画面的对比度严重下降，且HUD投射的视窗(eyebox)相对固定，脱离一定的视窗，就看不到完整的画面。
如果能够将AR导航内容投射在MR眼镜上，就能够克服上述将AR导航投射在车机屏幕或者抬头显示器时的缺陷。
在普通的介导现实(Mediated Reality，MR)眼镜上，定位的芯片和图像产生单元都是独立耦合在眼镜。但在车载领域，如果希望显示相关导航信息，把GPS/IMU等定位芯片叠加在眼镜上，会增加眼镜重量，也会让设备显得臃肿。
现有的AR导航中，一般由车机的摄像头采集实景图像，而后根据实景图像生成导航内容，如将AR导航的内容的投射至车载眼镜上，由于用户的头部可能会发生晃动，使得投射的AR导航内容与用户所看到的图像存在一定的位置偏移，这会影响AR导航的效果，影响用户的使用体验。
AR导航是将虚拟的导航相关信息显示在实景之上，给用户以增强现实的使用感受。如何保证使导航相关信息与实景的结合效果，是AR导航领域中的一个重要技术问题。
本申请实施例提供的导航方法、装置、电子设备和计算机可读存储介质，旨在解决现有技术的如上技术问题中的至少一个。
图1示出了本公开实施例提供的一种导航方法的流程示意图，如图1中所示，该方法主要可以包括：
步骤S110：获取实景图像以及导航相关信息；
步骤S120：对实景图像中的目标对象进行识别；
步骤S130：将目标对象与导航相关信息进行匹配，得到匹配结果；
步骤S140：基于匹配结果生成导航内容。
其中，导航相关信息可以为包括但是不限于高级驾驶辅助系统(Advanced Driving Assistance System，ADAS)信息，以及高精地图信息等，例如，可以为兴趣点(Point of Interest，POI)信息，导航信息以 及指引信号等。
实景图像为对车辆周围环境的图像。可以对实景图像进行场景识别，识别出目标对象，目标对象可以包括如车道线、建筑物以及转弯路口等。
在将目标对象与导航相关信息进行匹配后，可以根据匹配结果进行导航内容的渲染。渲染出的导航内容可以为虚拟的3D导航指引模型。
由于导航内容是基于导航相关信息与目标对象的匹配结果生成，因此导航内容能够与实景图像较好的结合，保证AR导航的效果。
本公开实施例提供的方法，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。由于是基于目标对象与导航相关信息的匹配结果生成导航内容，使得导航内容能够与实景图像较好的结合，从而保证AR导航的效果。
本公开的一种可选实施方式中，将目标对象与导航相关信息进行匹配，包括：
确定目标对象在实体图像中的位置信息；
将与目标对象对应的导航相关信息与位置信息匹配。
本公开实施例中，可以将目标对象在实景图像中的位置信息与导航相关信息匹配，相应的生成的导航内容也与该位置信息相匹配，即可以根据该位置信息确定导航内容的显示位置。
作为一个示例，目标对象为实景图像中的路口的左转弯，导航内容为左转箭头，可以将该左转箭头显示在的路口的左转弯处的上方。
作为另一个示例，目标对象为信息点(Point of Information，POI)中建筑物，导航内容为该建筑物的名称，将建筑物的名称显示在建筑物所处位置的上方。
通过将导航内容与目标对象在实景图中的位置相匹配，并将导航内容在该位置进行显示，能够使得导航内容与相应的实体对象结合紧密，保证AR导航的效果。
本公开的一种可选实施方式中，上述导航方法还包括：
对车机的传感器采集的传感器数据进行数据融合，确定当前的定位信息；
基于定位信息生成导航相关信息。
其中，车机的传感器可以包括但是不限于全球定位系统(Global Positioning System，GPS)、惯性测量单元(Inertial Measurement Unit，IMU)、Radar(雷达),lidar(激光雷达)以及相机等。这些传感器所采集到传感器数据可以被发送至数据融合模块，基于预设定的数据融合算法进行数据融合，能够确定出汽车当前的定位信息。
将定位信息输入导航模块，能够获取生成导航相关信息。
在实际使用中，可以将采集到的实景图片与传感器数据融合的结果一起传给ADAS模块用于识别障碍物，以及识别环境信息等。识别出的障碍物信息以及环境信息也可以用于对进行导航内容的渲染绘制。
图2示出了本公开实施例提供的另一种导航方法的流程示意图，如图2中所示，该方法主要可以包括：
步骤S210：获取实景图像以及导航相关信息；
步骤S220：对实景图像中的目标对象进行识别；
步骤S230：将目标对象与导航相关信息进行匹配，得到匹配结果；
步骤S240：基于匹配结果生成导航内容；
步骤S250：对实景图像进行转换得到投射图像，投射图像与至少一个车载眼镜的视窗相匹配；
步骤S260：将投射图像与导航内容进行融合，得到导航图像；
步骤S270：将导航图像发送至车载眼镜，以使车载眼镜显示导航图像。
其中，导航相关信息可以为包括但是不限于高级驾驶辅助系统(Advanced Driving Assistance System，ADAS)信息，以及高精地图信息等，例如，可以为兴趣点(Point of Interest，POI)信息，导航信息以及指引信号等。
实景图像为对车辆周围环境的图像。可以对实景图像进行场景识别，识别出目标对象，目标对象可以包括如车道线、建筑物以及转弯路口等。
在将目标对象与导航相关信息进行匹配后，可以根据匹配结果进行导航内容的渲染。渲染出的导航内容可以为虚拟的3D导航指引模型。
由于导航内容是基于导航相关信息与目标对象的匹配结果生成，因此导航内容能够与实景图像较好的结合，保证AR导航的效果。
通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。由于是基于目标对象与导航相关信息的匹配结果生成导航内容，使得导航内容能够与实景图像较好的结合，从而保证AR导航的效果。
车载眼镜可以包括但是不限于MR眼镜等智能眼镜，用户可以在驾驶车辆时佩戴车载眼镜，并借助车载眼镜实现导航。
本公开实施例中提供的导航系统中，可以在车辆内配备多个车载眼镜，以满足用户较多时的使用需求。
用户在佩戴车载眼镜时，用户眼睛的可视区域与车载眼镜的视窗(eyebox)相对应，因此，对实景图像进行转换，得到与车载眼镜的视窗相匹配的投射图像，该投射图像与用户的眼睛的可视区域相匹配，基于该投射图像与导航内容进行融合，进行AR导航，能够保证AR导航效果，给用户以增强现实的感觉，避免因用户的头部发生移动影响AR导航效果。
在实际使用中，由于用户的头部位置可能随时会发生变化，因此设定调整周期，周期性的对实景图像进行转换以保证AR导航效果，作为一个示例，调整周期可以为2秒。
本公开实施例中，在生成导航图像后，可以将导航图像发送给车载眼镜，通过车载眼镜显示导航图像，实现对AR导航。将AR导航投射在车载眼镜上，能够克服现有技术中将AR导航投射在车机屏幕或者AR HUD时的缺陷，提升用户的使用体验。
本公开实施例提供的方法，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。获取实景图像以及导航内容，对实景图像进行转换得到投射图像，投射图像与至少一个车载眼镜的视窗相匹配，将投射图像与导航内容进行融合，得到导航图像，将导航图像发送至车载眼镜，车载眼镜显示导航图像。本方案中，导航内容能够与实景 图像较好的结合，并且基于车载眼镜实现AR导航，能够避免因用户头部位置发生变化造成的对AR导航的效果的影响，保证AR导航的效果，保证用户的使用体验。
本公开的一种可选方式中，若实景图像为车机的第一图像采集设备所采集的第一实景图像，则对实景图像进行转换得到投射图像，包括：
获取车载眼镜的第二图像采集设备所采集的第二实景图像与车载眼镜的视窗的第一位置关系；
确定第一实景图像与第二实景图像的第二位置关系；
基于第一位置关系以及第二位置关系对第一实景图像进行转换得到投射图像。
本公开实施例中，实景图像可以由车机的第一图像采集设备所采集，也可以为由车载眼镜的第二图像采集设备所采集。
图像采集设备可以包括但是不限于摄像头。
在实景图像为车机的第一图像采集设备所采集的第一实景图像时，由于车载眼镜的第二图像采集设备与车载眼镜中视窗的位置是固定的，因此可以根据第二图像采集设备与车载眼镜中视窗的实际位置关系，确定出第二实景图像与车载眼镜的视窗的第一位置关系。
由于用户的头部的位置可能会实时变化，因此第一实景图像与第二实景图像的第二位置关系也是实时变化的，因此可以依照调整周期来周期性的获取第二位置关系。
在确定第一位置关系以及第二位置关系后，可以根据第一位置关系与第二位置关系对第一实景图像进行转换得到投射图像。
作为一个示例，第一位置关系可以通过[R1 T1]表示，其中，R为旋转矩阵，T为平移矩阵)，则有P(eyebox)＝[R1 T1]P(camera2)。此处[R1 T1]为确定的量，其中P(eyebox)表示投射图像，P(camera2)表示第二实景图像。
第二位置关系可以通过[R2 T2]表示，则有P(camera2)＝[R2 T2]P(camera1)，其中P(camera1)表示第一实景图像，P(camera2)表示第二实景图像。
由此可以推导出，P(eyebox)＝[R1 T1]P(camera2)＝[R1 T1][R2 T2] P(camera1)
本公开的一种可选方式中，确定第一实景图像与第二实景图像的第二位置关系，包括以下任一项：
将第一实景图像与第二实景图像进行特征点追踪，基于特征点追踪的第一结果确定第一实景图像与第二实景图像的第二位置关系；
将车载眼镜处于指定位置时采集的第三实景图像与第一实景图像进行特征点追踪，基于特征点追踪的第二结果确定第一实景图像与第三实景图像的第三位置关系；基于车载眼镜所处的当前位置与指定位置，并基于第三位置关系，确定第一实景图像与第二实景图像的第二位置关系。
本公开实施例中，可以通过PNP求解等特征点追踪等方式来获得第二位置关系。具体地，就是将第一实景图像的特征点，不断的与第二实景图像的特征点做对比追踪求解，求解的结果可以记做：P(camera2)＝[R2 T2]P(camera1)。
为了处理的实时性，需要控制此求解过程的时间延迟，可以将第一实景图像与第二实景图像传输至车机的微控制单元(Microcontroller Unit，MCU)中做处理。
本公开实施例中，导航图像的生成可以在车机完成，而将导航图像发送给车载眼镜，使得车载眼镜无需配置过多的传感器，避免了车载眼镜的臃肿。
本公开实施例中，也可以设定用户在车中的指定位置，将该指定位置作为基准，计算车载眼镜处于指定位置时采集的第三实景图与像第一实景图像的第三位置关系，而后实时对车载眼镜进行定位，并计算将车载眼镜位置相较于指定位置的位置变化，根据该位置变化以及第三位置关系能够确定出第二位置关系。
在实际使用中，第三位置关系可以通过图像特征点追踪的方式获取。
作为一示例，可以将司机端坐并佩戴车载眼镜时车载眼镜的位置作为指定位置。利用图片特征点追踪获取关系初始值P(camera2)＝[R20 T20]P(camera1)。在动态过程中，利用定位系统获得的相对位姿态变化[Rx Tx],则有P(camera2)＝[Rx Tx][R20 T20]P(camera1)
可选地，车载眼镜所处的当前位置是基于车载眼镜的定位系统得到的。
本公开实施例中，车载眼镜的定位系统可以包括GPS/IMU等定位芯片。
本公开实施例的一种可选实施方式中，若实景图像为车载眼镜的第二图像采集设备所采集的第二实景图像，则对实景图像进行转换得到投射图像，包括：
获取车载眼镜的第二图像采集设备所采集的第二实景图像与车载眼镜的视窗的第一位置关系；
基于第一位置关系对第一实景图像进行转换得到投射图像。
本公开实施例中，在实景图像为车载眼镜的第二图像采集设备所采集的第二实景图像时，由于车载眼镜的第二图像采集设备与车载眼镜中视窗的位置是固定的，因此可以根据第二图像采集设备与车载眼镜中视窗的实际位置关系，确定出第二实景图像与车载眼镜的视窗的第一位置关系。基于第一位置关系即能够将第二实景图像转换为投射图像。
示例性地，P(eyebox)＝[R1 T1]P(camera2)，其中，P(eyebox)表示投射图像，P(camera2)表示第二实景图像。第一位置关系可以通过[R1 T1]表示。
作为一可选示例，将导航图像发送至车载眼镜，包括：
通过无线通信的方式将导航图像发送至车载眼镜
其中，无线通讯方式可以为无线保真(Wireless Fidelity，wifi)，也可以通过有线方式进行导航图像的发送如通过通用串行总线(Universal Serial Bus，USB)接口或低电压差分信号接口(Low-Voltage Differential Signaling，lvdss)等方式。
图3中示出了本公开实施提供的一种导航系统的结构示意图。
如图3中所示，Camera1，即车机的第一图像采集设备。Camera2，即车载眼镜的第二图像采集设备。eyebox，即视窗。MCU即车机的MCU；AR creator，即增强现实感软件套装,其中包括ADAS(即高级驾驶辅助系统)，SD/HD MAP，即街道目录地图或高精地图，ANP(Apollo Navigation Pilot)地图。
Camera1采集的第一实景图像与Camera2采集的第二实景图像可以传输至MCU中，MCU中在生成导航图像后，可以通过无线传输的方式(如 wifi)等，将导航图像传至车载眼镜的PGU(即图像生成单元)，PGU对导航图像的展示。
基于与图1中所示的方法相同的原理，图4示出了本公开实施例提供的一种导航装置的结构示意图，如图4所示，该导航装置40可以包括：
数据获取模块410，被配置为获取实景图像以及导航相关信息；
对象识别模块420，被配置为对实景图像中的目标对象进行识别；
匹配模块430，被配置为将目标对象与导航相关信息进行匹配，得到匹配结果；
导航内容生成模块440，被配置为基于匹配结果生成导航内容。
本公开实施例提供的装置，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。由于是基于目标对象与导航相关信息的匹配结果生成导航内容，使得导航内容能够与实景图像较好的结合，从而保证AR导航的效果。
可选地，匹配模块在将目标对象与导航相关信息进行匹配时，被配置为：
确定目标对象在实体图像中的位置信息；
将与目标对象对应的导航相关信息与位置信息匹配。
可选地，上述导航装置还包括导航相关信息生成模块，导航相关信息生成模块被配置为：
对车机的传感器采集的传感器数据进行数据融合，确定当前的定位信息；
基于定位信息生成导航相关信息。
可以理解的是，本公开实施例中的导航装置的上述各模块具有实现图1中所示的实施例中的导航方法相应步骤的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。上述模块可以是软件和/或硬件，上述各模块可以单独实现，也可以多个模块集成实现。对于上述导航装置的各模块的功能描述具体可以参见图1中所示实施例中的导航方法的对应描述，在此不 再赘述。
基于与图2中所示的方法相同的原理，图5示出了本公开实施例提供的另一种导航装置的结构示意图，如图5所示，该导航装置50可以包括：
数据获取模块510，被配置为获取实景图像以及导航相关信息；
对象识别模块520，被配置为对实景图像中的目标对象进行识别；
匹配模块530，被配置为将目标对象与导航相关信息进行匹配，得到匹配结果；
导航内容生成模块540，被配置为基于匹配结果生成导航内容；
图像转换模块550，被配置为对实景图像进行转换得到投射图像，投射图像与至少一个车载眼镜的视窗相匹配；
图像融合模块560，被配置为将投射图像与导航内容进行融合，得到导航图像；
导航图像发送模块570，被配置为将导航图像发送至车载眼镜，以使车载眼镜显示导航图像。
本公开实施例提供的装置，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。获取实景图像以及导航内容，对实景图像进行转换得到投射图像，投射图像与至少一个车载眼镜的视窗相匹配，将投射图像与导航内容进行融合，得到导航图像，将导航图像发送至车载眼镜，车载眼镜显示导航图像。本方案中，导航内容能够与实景图像较好的结合，并且基于车载眼镜实现AR导航，能够避免因用户头部位置发生变化造成的对AR导航的效果的影响，保证AR导航的效果，保证用户的使用体验。
可选地，若实景图像为车机的第一图像采集设备所采集的第一实景图像，则图像转换模块在对实景图像进行转换得到投射图像时，被配置为：
获取车载眼镜的第二图像采集设备所采集的第二实景图像与车载眼镜的视窗的第一位置关系；
确定第一实景图像与第二实景图像的第二位置关系；
基于第一位置关系以及第二位置关系对第一实景图像进行转换得到投射图像。
可选地，图像转换模块在获取车载眼镜的第二图像采集设备所采集的第二实景图像与车载眼镜的视窗的第一位置关系时，被配置为：
基于车载眼镜上第二图像采集设备的位置与视窗的位置，确定第一位置关系。
可选地，图像转换模块在确定第一实景图像与第二实景图像的第二位置关系时，被配置为以下任一项：
将第一实景图像与第二实景图像进行特征点追踪，基于特征点追踪的第一结果确定第一实景图像与第二实景图像的第二位置关系；
将车载眼镜处于指定位置时采集的第三实景图像与第一实景图像进行特征点追踪，基于特征点追踪的第二结果确定第一实景图像与第三实景图像的第三位置关系；基于车载眼镜所处的当前位置与指定位置，并基于第三位置关系，确定第一实景图像与第二实景图像的第二位置关系。
可选地，若实景图像为车载眼镜的第二图像采集设备所采集的第二实景图像，则图像转换模块在对实景图像进行转换得到投射图像时，被配置为：
获取车载眼镜的第二图像采集设备所采集的第二实景图像与车载眼镜的视窗的第一位置关系；
基于第一位置关系对第一实景图像进行转换得到投射图像。
可以理解的是，本公开实施例中的导航装置的上述各模块具有实现图2中所示的实施例中的导航方法相应步骤的功能。该功能可以通过硬件实现，也可以通过硬件执行相应的软件实现。该硬件或软件包括一个或多个与上述功能相对应的模块。上述模块可以是软件和/或硬件，上述各模块可以单独实现，也可以多个模块集成实现。对于上述导航装置的各模块的功能描述具体可以参见图2中所示实施例中的导航方法的对应描述，在此不再赘述。
本公开的技术方案中，所涉及的用户个人信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
该电子设备包括：至少一个处理器；以及与至少一个处理器通信连接 的存储器；其中，存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行如本公开实施例提供的导航方法。
该电子设备与现有技术相比，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。由于是基于目标对象与导航相关信息的匹配结果生成导航内容，使得导航内容能够与实景图像较好的结合，从而保证AR导航的效果。
该可读存储介质为存储有计算机指令的非瞬时计算机可读存储介质，其中，计算机指令在被计算机执行时实现如本公开实施例提供的导航方法。
该可读存储介质与现有技术相比，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。由于是基于目标对象与导航相关信息的匹配结果生成导航内容，使得导航内容能够与实景图像较好的结合，从而保证AR导航的效果。
该计算机程序产品，包括计算机程序，计算机程序在被处理器执行时实现如本公开实施例提供的导航方法。
该计算机程序产品与现有技术相比，通过获取实景图像以及导航相关信息，对实景图像中的目标对象进行识别，将目标对象与导航相关信息进行匹配，得到匹配结果，基于匹配结果生成导航内容。由于是基于目标对象与导航相关信息的匹配结果生成导航内容，使得导航内容能够与实景图像较好的结合，从而保证AR导航的效果。
图6示出了可以用来实施本公开的实施例的示例电子设备2000的示意性框图。电子设备旨在表示各种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图6所示，设备2000包括计算单元2010，其可以根据存储在只读 存储器(ROM)2020中的计算机程序或者从存储单元2080加载到随机访问存储器(RAM)2030中的计算机程序，来执行各种适当的动作和处理。在RAM 2030中，还可存储设备2000操作所需的各种程序和数据。计算单元2010、ROM 2020以及RAM 2030通过总线2040彼此相连。输入/输出(I/O)接口2050也连接至总线2040。
设备2000中的多个部件连接至I/O接口2050，包括：输入单元2060，例如键盘、鼠标等；输出单元2070，例如各种类型的显示器、扬声器等；存储单元2080，例如磁盘、光盘等；以及通信单元2090，例如网卡、调制解调器、无线通信收发机等。通信单元2090允许设备2000通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
计算单元2010可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元2010的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元2010执行本公开实施例中所提供的导航方法。例如，在一些实施例中，行本公开实施例中所提供的导航方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元2080。在一些实施例中，计算机程序的部分或者全部可以经由ROM 2020和/或通信单元2090而被载入和/或安装到设备2000上。当计算机程序加载到RAM 2030并由计算单元2010执行时，可以执行本公开实施例中所提供的导航方法的一个或多个步骤。备选地，在其他实施例中，计算单元2010可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行本公开实施例中所提供的导航方法。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存 储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器 的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本公开中记载的各步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。
上述具体实施方式，并不构成对本公开保护范围的限制。本领域技术人员应该明白的是，根据设计要求和其他因素，可以进行各种修改、组合、子组合和替代。任何在本公开的精神和原则之内所作的修改、等同替换和改进等，均应包含在本公开保护范围之内。

Claims (19)

  1. 一种导航方法，包括：
    获取实景图像以及导航相关信息；
    对所述实景图像中的目标对象进行识别；
    将所述目标对象与所述导航相关信息进行匹配，得到匹配结果；
    基于所述匹配结果生成导航内容。
  2. 根据权利要求1所述的方法，所述将所述目标对象与所述导航相关信息进行匹配，包括：
    确定所述目标对象在所述实体图像中的位置信息；
    将与所述目标对象对应的所述导航相关信息与所述位置信息匹配。
  3. 根据权利要求1或2所述的方法，所述导航方法还包括：
    对车机的传感器采集的传感器数据进行数据融合，确定当前的定位信息；
    基于所述定位信息生成所述导航相关信息。
  4. 根据权利要求1-3中任一项所述的方法，所述导航方法还包括：
    对所述实景图像进行转换得到投射图像，所述投射图像与至少一个车载眼镜的视窗相匹配；
    将所述投射图像与所述导航内容进行融合，得到导航图像；
    将所述导航图像发送至所述车载眼镜，以使所述车载眼镜显示所述导航图像。
  5. 根据权利要求4所述的方法，其中，若所述实景图像为车机的第一图像采集设备所采集的第一实景图像，则所述对所述实景图像进行转换得到投射图像，包括：
    获取所述车载眼镜的第二图像采集设备所采集的第二实景图像与所述车载眼镜的视窗的第一位置关系；
    确定所述第一实景图像与所述第二实景图像的第二位置关系；
    基于所述第一位置关系以及所述第二位置关系对所述第一实景 图像进行转换得到投射图像。
  6. 根据权利要求5所述的方法，其中，所述获取所述车载眼镜的第二图像采集设备所采集的第二实景图像与所述车载眼镜的视窗的第一位置关系，包括：
    基于所述车载眼镜上所述第二图像采集设备的位置与所述视窗的位置，确定第一位置关系。
  7. 根据权利要求5或6所述的方法，其中，所述确定所述第一实景图像与所述第二实景图像的第二位置关系，包括以下任一项：
    将所述第一实景图像与所述第二实景图像进行特征点追踪，基于特征点追踪的第一结果确定所述第一实景图像与所述第二实景图像的第二位置关系；
    将所述车载眼镜处于指定位置时采集的第三实景图像与所述第一实景图像进行特征点追踪，基于特征点追踪的第二结果确定所述第一实景图像与所述第三实景图像的第三位置关系；基于所述车载眼镜所处的当前位置与所述指定位置，并基于所述第三位置关系，确定所述第一实景图像与所述第二实景图像的第二位置关系。
  8. 根据权利要求4-7中任一项所述的方法，其中，若所述实景图像为车载眼镜的第二图像采集设备所采集的第二实景图像，则所述对所述实景图像进行转换得到投射图像，包括：
    获取所述车载眼镜的第二图像采集设备所采集的第二实景图像与所述车载眼镜的视窗的第一位置关系；
    基于所述第一位置关系对所述第一实景图像进行转换得到投射图像。
  9. 一种导航装置，包括：
    数据获取模块，被配置为获取实景图像以及导航相关信息；
    对象识别模块，被配置为对所述实景图像中的目标对象进行识别；
    匹配模块，被配置为将所述目标对象与所述导航相关信息进行匹配，得到匹配结果；
    导航内容生成模块，被配置为基于所述匹配结果生成导航内容。
  10. 根据权利要求9所述的装置，其中，所述匹配模块在将目标对象与导航相关信息进行匹配时，被配置为：
    确定所述目标对象在所述实体图像中的位置信息；
    将与所述目标对象对应的所述导航相关信息与所述位置信息匹配。
  11. 根据权利要求9或10所述的装置，其中，所述导航装置还包括导航相关信息生成模块，所述导航相关信息生成模块被配置为：
    对车机的传感器采集的传感器数据进行数据融合，确定当前的定位信息；
    基于所述定位信息生成所述导航相关信息。
  12. 根据权利要求9-11中任一项所述的装置，所述导航装置还包括：
    图像转换模块，被配置为对所述实景图像进行转换得到投射图像，所述投射图像与至少一个车载眼镜的视窗相匹配；
    图像融合模块，被配置为将所述投射图像与所述导航内容进行融合，得到导航图像；
    导航图像发送模块，被配置为将所述导航图像发送至所述车载眼镜，以使所述车载眼镜显示所述导航图像
  13. 根据权利要求12所述的装置，若所述实景图像为车机的第一图像采集设备所采集的第一实景图像，则所述图像转换模块在对所述实景图像进行转换得到投射图像时，被配置为：
    获取所述车载眼镜的第二图像采集设备所采集的第二实景图像与所述车载眼镜的视窗的第一位置关系；
    确定所述第一实景图像与所述第二实景图像的第二位置关系；
    基于所述第一位置关系以及所述第二位置关系对所述第一实景图像进行转换得到投射图像。
  14. 根据权利要求13所述的装置，其中，所述图像转换模块在获取所述车载眼镜的第二图像采集设备所采集的第二实景图像与所述车载眼镜的视窗的第一位置关系时，被配置为：
    基于所述车载眼镜上所述第二图像采集设备的位置与所述视窗的位置，确定第一位置关系。
  15. 根据权利要求13或14所述的装置，其中，所述图像转换模块在确定所述第一实景图像与所述第二实景图像的第二位置关系时，被配置为以下任一项：
    将所述第一实景图像与所述第二实景图像进行特征点追踪，基于特征点追踪的第一结果确定所述第一实景图像与所述第二实景图像的第二位置关系；
    将所述车载眼镜处于指定位置时采集的第三实景图像与所述第一实景图像进行特征点追踪，基于特征点追踪的第二结果确定所述第一实景图像与所述第三实景图像的第三位置关系；基于所述车载眼镜所处的当前位置与所述指定位置，并基于所述第三位置关系，确定所述第一实景图像与所述第二实景图像的第二位置关系。
  16. 根据权利要求12-15中任一项所述的装置，其中，若所述实景图像为车载眼镜的第二图像采集设备所采集的第二实景图像，则所述图像转换模块在对所述实景图像进行转换得到投射图像时，被配置为：
    获取所述车载眼镜的第二图像采集设备所采集的第二实景图像与所述车载眼镜的视窗的第一位置关系；
    基于所述第一位置关系对所述第一实景图像进行转换得到投射图像。
  17. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-8中任一项所述的方法。
  18. 一种存储有计算机指令的非瞬时计算机可读存储介质，其 中，所述计算机指令在被所述计算机执行时实现如权利要求1-8中任一项所述的方法。
  19. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-8中任一项所述的方法。
PCT/CN2021/125858 2021-06-29 2021-10-22 导航方法、装置、电子设备及可读存储介质 WO2023273036A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110731641.4A CN113483774B (zh) 2021-06-29 2021-06-29 导航方法、装置、电子设备及可读存储介质
CN202110731641.4 2021-06-29

Publications (1)

Publication Number Publication Date
WO2023273036A1 true WO2023273036A1 (zh) 2023-01-05

Family

ID=77937833

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/125858 WO2023273036A1 (zh) 2021-06-29 2021-10-22 导航方法、装置、电子设备及可读存储介质

Country Status (2)

Country Link
CN (1) CN113483774B (zh)
WO (1) WO2023273036A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113483774B (zh) * 2021-06-29 2023-11-03 阿波罗智联(北京)科技有限公司 导航方法、装置、电子设备及可读存储介质
CN114187509B (zh) * 2021-11-30 2022-11-08 北京百度网讯科技有限公司 对象定位方法、装置、电子设备以及存储介质
CN114546120A (zh) * 2022-02-25 2022-05-27 北京百度网讯科技有限公司 导航标识显示方法、装置及电子设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170015260A1 (en) * 2015-07-13 2017-01-19 LAFORGE Optical, Inc. Apparatus And Method For Exchanging And Displaying Data Between Electronic Eyewear, Vehicles And Other Devices
US20170161958A1 (en) * 2015-12-02 2017-06-08 Superb Reality Ltd. Systems and methods for object-based augmented reality navigation guidance
CN110019580A (zh) * 2017-08-25 2019-07-16 腾讯科技（深圳）有限公司 地图显示方法、装置、存储介质及终端
CN111623795A (zh) * 2020-05-28 2020-09-04 北京百度网讯科技有限公司 实景导航图标显示方法、装置、设备和介质
US10871377B1 (en) * 2019-08-08 2020-12-22 Phiar Technologies, Inc. Computer-vision based positioning for augmented reality navigation
CN113237490A (zh) * 2021-02-08 2021-08-10 上海博泰悦臻网络技术服务有限公司 Ar导航方法、系统、电子设备和存储介质
CN113483774A (zh) * 2021-06-29 2021-10-08 阿波罗智联(北京)科技有限公司 导航方法、装置、电子设备及可读存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0784519A (ja) * 1993-09-17 1995-03-31 Sony Corp ナビゲーションシステム
KR20140145332A (ko) * 2013-06-13 2014-12-23 현대모비스 주식회사 차량용 hmd 시스템 및 그 작동 방법
CN110906949B (zh) * 2013-06-13 2024-01-09 移动眼视力科技有限公司 用于导航的计算机实施方法、导航系统和车辆
CN104090366A (zh) * 2014-07-23 2014-10-08 占舒婷 一种汽车驾驶眼镜
US10095034B1 (en) * 2015-07-23 2018-10-09 Snap Inc. Eyewear with integrated heads-up display
DE102016111783B4 (de) * 2016-06-28 2021-03-04 Hologram Industries Research Gmbh Anzeigevorrichtung zur Einblendung eines virtuellen Bildes in das Blickfeld eines Benutzers
US20190317328A1 (en) * 2018-04-17 2019-10-17 Faraday&Future Inc. System and method for providing augmented-reality assistance for vehicular navigation
CN110764264B (zh) * 2019-11-07 2022-02-15 中勍科技有限公司 一种ar智能眼镜
CN111595349A (zh) * 2020-06-28 2020-08-28 浙江商汤科技开发有限公司 导航方法及装置、电子设备和存储介质
CN112556685B (zh) * 2020-12-07 2022-03-25 腾讯科技（深圳）有限公司 导航路线的显示方法、装置和存储介质及电子设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170015260A1 (en) * 2015-07-13 2017-01-19 LAFORGE Optical, Inc. Apparatus And Method For Exchanging And Displaying Data Between Electronic Eyewear, Vehicles And Other Devices
US20170161958A1 (en) * 2015-12-02 2017-06-08 Superb Reality Ltd. Systems and methods for object-based augmented reality navigation guidance
CN110019580A (zh) * 2017-08-25 2019-07-16 腾讯科技（深圳）有限公司 地图显示方法、装置、存储介质及终端
US10871377B1 (en) * 2019-08-08 2020-12-22 Phiar Technologies, Inc. Computer-vision based positioning for augmented reality navigation
CN111623795A (zh) * 2020-05-28 2020-09-04 北京百度网讯科技有限公司 实景导航图标显示方法、装置、设备和介质
CN113237490A (zh) * 2021-02-08 2021-08-10 上海博泰悦臻网络技术服务有限公司 Ar导航方法、系统、电子设备和存储介质
CN113483774A (zh) * 2021-06-29 2021-10-08 阿波罗智联(北京)科技有限公司 导航方法、装置、电子设备及可读存储介质

Also Published As

Publication number Publication date
CN113483774B (zh) 2023-11-03
CN113483774A (zh) 2021-10-08

Similar Documents

Publication Publication Date Title
WO2023273036A1 (zh) 导航方法、装置、电子设备及可读存储介质
US10832084B2 (en) Dense three-dimensional correspondence estimation with multi-level metric learning and hierarchical matching
US20200090057A1 (en) Human-computer hybrid decision method and apparatus
EP4116462A2 (en) Method and apparatus of processing image, electronic device, storage medium and program product
EP3906527B1 (en) Image bounding shape using 3d environment representation
WO2017107537A1 (zh) 虚拟现实设备及避障方法
EP4050305A1 (en) Visual positioning method and device
WO2019095735A1 (zh) 用于车辆的信息输出方法和装置
CN112927363A (zh) 体素地图构建方法及装置、计算机可读介质和电子设备
CN115578433B (zh) 图像处理方法、装置、电子设备及存储介质
WO2023207522A1 (zh) 视频合成方法、装置、设备、介质及产品
JP2023530545A (ja) 空間幾何情報推定モデルの生成方法及び装置
CN112184914A (zh) 目标对象三维位置的确定方法、装置和路侧设备
CN113610702B (zh) 一种建图方法、装置、电子设备及存储介质
US10198843B1 (en) Conversion of 2D diagrams to 3D rich immersive content
CN113378605B (zh) 多源信息融合方法及装置、电子设备和存储介质
CN115082690B (zh) 目标识别方法、目标识别模型训练方法及装置
KR20220056834A (ko) 표시 방법, 장치, 단말 기기, 컴퓨터 판독 가능한 저장 매체 및 컴퓨터 프로그램
CN115790621A (zh) 高精地图更新方法、装置及电子设备
US11741671B2 (en) Three-dimensional scene recreation using depth fusion
JP7390436B2 (ja) ナビゲーション方法、装置、電子機器、コンピュータ読取可能な記憶媒体及びコンピュータプログラム
CN115578432B (zh) 图像处理方法、装置、电子设备及存储介质
CN115294234B (zh) 图像的生成方法、装置、电子设备和存储介质
KR102534449B1 (ko) 이미지 처리 방법, 장치, 전자 장치 및 컴퓨터 판독 가능 저장 매체
EP4134843A2 (en) Fusion and association method and apparatus for traffic objects in driving environment, and edge computing device

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: 21947963

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE