WO2021226912A1 - Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations - Google Patents

Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations Download PDF

Info

Publication number
WO2021226912A1
WO2021226912A1 PCT/CN2020/090170 CN2020090170W WO2021226912A1 WO 2021226912 A1 WO2021226912 A1 WO 2021226912A1 CN 2020090170 W CN2020090170 W CN 2020090170W WO 2021226912 A1 WO2021226912 A1 WO 2021226912A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
parking space
memory
coordinate system
vehicle
Prior art date
Application number
PCT/CN2020/090170
Other languages
English (en)
Chinese (zh)
Inventor
苏林
Original Assignee
上海欧菲智能车联科技有限公司
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 上海欧菲智能车联科技有限公司 filed Critical 上海欧菲智能车联科技有限公司
Priority to PCT/CN2020/090170 priority Critical patent/WO2021226912A1/fr
Publication of WO2021226912A1 publication Critical patent/WO2021226912A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition

Definitions

  • This application relates to a parking space determination method, device, computer equipment and storage medium.
  • Autonomous driving is a vehicle that can move on its own without driver control.
  • the autopilot technology defined here is a technology that realizes the function of autopilot.
  • Autonomous driving can be decomposed into: 1) The driving of the vehicle on the road: The main driving mode is to preset the destination point, and the automatic driving technology realizes the movement of the vehicle from the current position to the preset destination point; 2) The parking of the vehicle after reaching the destination: After the vehicle reaches the destination point, automatic driving technology realizes that the vehicle will be parked in the parking space.
  • the self-driving parking task is to park the vehicle into the parking space by itself, and the technology applied at this time is the automatic parking technology.
  • parking spaces can be divided into random parking spaces and fixed parking spaces.
  • Fixed parking spaces Vehicles need to be parked in fixed parking spaces, such as residential parking spaces, etc.
  • Non-fixed parking spaces Vehicles can be parked in any parking space, such as commercial parking spaces.
  • the parking space memory and automatic matching and selection system memorize the parking space information of the first parking, and perform matching and selection when parking again, thereby completing repeated parking for the same parking space (target parking space).
  • a parking space determination method is provided.
  • a method for determining a parking space includes: collecting an initial image through a camera installed on a vehicle, and generating a mosaic to be processed based on the collected initial image; performing feature recognition on the mosaic to be processed to obtain image features; The obtained image features determine the preset type of useful information that characterizes the parking space to be determined; the useful information that characterizes the parking space to be determined is matched with the pre-stored memory parking space information; the useful information that is successfully matched with the memory parking space information is determined. The characterized parking space to be judged is used as the target parking space.
  • a parking space determining device includes:
  • the acquisition module is used to acquire an initial image through a camera installed on the vehicle, and generate a mosaic to be processed according to the acquired initial image;
  • the feature recognition module is used to perform feature recognition on the to-be-processed mosaic to obtain image features
  • the useful information determining module is used to determine a preset type of useful information that characterizes the parking space to be determined according to the recognized image characteristics;
  • the first matching module is used to match the useful information that characterizes the parking space to be judged with the pre-stored memory parking space information
  • the output module is used to take the parking space to be judged represented by the useful information successfully matched with the memory parking space information as the target parking space.
  • Computer-readable storage medium computer-readable storage medium The steps of the parking space determination method provided in any of the embodiments of the present application are implemented when the device is executed.
  • One or more non-volatile storage media storing computer-readable instructions.
  • the one or more processors realize the parking provided in any one of the embodiments of the present application. Steps of the parking space determination method.
  • Fig. 1 is an application environment diagram of a parking space determination method according to one or more embodiments.
  • Fig. 2 is a schematic flowchart of a method for determining a parking space according to one or more embodiments.
  • Fig. 3 is a flowchart of a process of initial parking of a vehicle according to one or more embodiments.
  • Fig. 4 is a flowchart of a method for determining a parking space according to another or more embodiments.
  • Fig. 5 is a schematic diagram of a vehicle motion trajectory according to one or more embodiments.
  • Fig. 6 is a schematic diagram of a mosaic in accordance with one or more embodiments.
  • Fig. 7 is a schematic diagram of a horizontal parking space line and a vertical parking space line and corner points according to one or more embodiments.
  • Fig. 8 is a schematic diagram of a two-dimensional coordinate space of a vehicle motion trajectory according to one or more embodiments.
  • Fig. 9 is a schematic diagram of a scene when there are multiple parking spaces according to one or more embodiments.
  • Fig. 10 is a schematic diagram of a scene when obstructions exist according to one or more embodiments.
  • Fig. 11 is a schematic diagram of a scene when the ambient light is poor according to one or more embodiments.
  • Fig. 12 is a schematic diagram of a system call according to one or more embodiments.
  • Fig. 13 is a block diagram of an apparatus for determining a parking space according to one or more embodiments.
  • Figure 14 is a block diagram of a computer device according to one or more embodiments.
  • the parking space determination method provided in this application can be applied to the application environment as shown in FIG. 1.
  • the vehicle terminal 102 can communicate with the camera 104 and the HUT installed on the vehicle.
  • IP refers to the Interface Processor (interface processor), which is mainly used for vehicle communication and control
  • CAN refers to the Controller Area Network (control Local area network), used for the system to communicate with other vehicle electronic and electrical systems
  • HUT106 refers to the vehicle multimedia host, used to interact with the driver.
  • the vehicle terminal 102 can obtain the initial image collected by the camera 104 installed on the vehicle, and generate a mosaic image to be processed based on the collected initial image, and then the vehicle terminal 102 performs feature recognition on the mosaic image to obtain the image feature, and then obtains the image feature according to the recognized image.
  • the image feature determines the preset type of useful information representing the parking space to be determined, etc., so that the vehicle terminal 102 matches the useful information representing the parking space to be determined with the pre-stored memory parking space information, so that the vehicle terminal can match the memory parking space information
  • the parking space to be judged represented by the useful information of successful matching is used as the target parking space, and the target parking space can be sent to the HUT 106 for display.
  • the vehicle terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers installed on the vehicle.
  • a method for determining a parking space is provided. Taking the method applied to the vehicle terminal in FIG. 1 as an example for description, the method includes the following steps:
  • S202 Collect an initial image through a camera installed on the vehicle, and generate a mosaic to be processed according to the collected initial image.
  • the initial image is collected by cameras installed around the vehicle.
  • multiple ( ⁇ 4) fisheye cameras can be installed around the vehicle, so that these fisheye cameras can be turned on and collected when the driver needs them.
  • the initial image around the vehicle For example, when the vehicle is stationary or when a parking instruction input by the driver is received while driving, the fisheye cameras start to collect initial images, the initial images carry a time stamp, and the time stamp is used to characterize the initial image Of the shooting time.
  • the stitching image is generated based on the initial image.
  • the vehicle terminal can use the on-board processor to compress and correct the obtained multi-channel video to stitch a single initial image of a single fisheye camera into a whole stitching image.
  • the vehicle terminal when the vehicle is at a standstill, only a certain frame of initial images of each fisheye camera may be collected, and then spliced.
  • the vehicle terminal will stitch together multiple initial images with the same time stamp according to the timestamps of the multiple environmental images collected by each fisheye camera to obtain a mosaic.
  • the vehicle terminal can obtain a mosaic from each fisheye camera Acquire multiple initial images with the same time stamp, and then determine whether the number of acquired initial images is greater than or equal to the preset number, for example, equal to the number of fisheye cameras.
  • the image generates a mosaic.
  • the vehicle terminal can directly read the corresponding mosaic image from the panoramic surround view system.
  • S204 Perform feature recognition on the stitched image to be processed to obtain image features.
  • feature recognition refers to the process of identifying and detecting feature information used in the parking process from the mosaic to be processed.
  • the identified image feature refers to the information that can characterize the parking space or the environment. Some unique markers (such as the support column of the garage) and other information, and even the characteristic points of the image that can be stably detected and tracked in the environment.
  • the vehicle terminal may use the pre-trained deep neural network model to perform feature recognition on the mosaic to be processed to obtain image features.
  • the deep neural network model may be trained based on historical images with pre-calibrated image features.
  • S206 Determine a preset type of useful information representing the parking space to be determined according to the recognized image feature.
  • the preset types include parking space types and environment types.
  • the useful information of the parking space types includes but is not limited to parking space parameters and the position of the parking space relative to the vehicle.
  • the useful information includes but not limited to geometric size information and relative position. Relationships and other measurement information.
  • the vehicle terminal can classify image features according to preset logic, and then process the classified image features to obtain parking space parameters and relative position relationships.
  • the useful information of the environment type includes, but is not limited to, some unique markers in the environment (such as the support column of the garage), and even the image feature points that can be stably detected and tracked in the environment.
  • S208 Match the useful information that characterizes the parking space to be determined with the pre-stored memory parking space information.
  • S210 Use the to-be-judged parking space represented by the useful information successfully matched with the memory parking space information as the target parking space.
  • matching the useful information that characterizes the parking space to be determined with the pre-stored memory parking space information includes matching the parking space to be determined in the useful information with the parking space in the memory parking space information, and matching the parking space in the useful information to the parking space.
  • the judgment environment information matches the memory environment information in the memory parking space information.
  • the terminal may first perform environmental matching between the parking space to be determined and the parking space in the memorized parking space information, if the matching is successful, output the corresponding target parking space, and if the matching fails, continue to match the parking space to be determined in the useful information The information is matched with the memory environment information in the memory parking space information to further determine the target parking space.
  • the vehicle terminal when the application scenario is that the vehicle is parked in a fixed parking space in the same scene again, after identifying multiple parking spaces to be determined from the useful information, the vehicle terminal performs real-time retrieval of the parking spaces to be determined and the memory parking space. Comparing to complete the automatic selection of the parking space to be judged, the parking space identification can be automatically displayed on the in-vehicle display screen, and the driver is prompted to park by voice or view, so as to realize the parking of the target parking space. In addition, when the application scenario is an automatic parking system, the vehicle terminal will give the correct parking space information to the control system, so as to complete the parking of the parking space to be judged without the participation of the driver.
  • image features are obtained by feature recognition of the mosaic to be processed, and a preset type of useful information representing the parking space to be determined is determined according to the recognized image features, which can be matched with the pre-stored memory parking space information This improves the accuracy of parking space determination, and does not require the driver to stare at the screen to determine whether there is a parking space, reducing the risk
  • the useful information includes the characteristic information of the parking space to be determined
  • the memorized parking space information includes the characteristic information of the memorized parking space
  • matching the useful information representing the parking space to be determined with the pre-stored memory parking space information includes: A vehicle coordinate system, and the characteristic information of the parking space to be judged is recorded through the first vehicle coordinate system.
  • the feature information of the parking space to be determined recorded by the first vehicle coordinate system is converted into the feature information of the parking space to be determined in the world coordinate system.
  • the characteristic information of the parking space to be judged is matched with the pre-stored memory parking space characteristic information, and when the characteristic information of the parking space to be judged matches the pre-stored memory parking space characteristic information successfully, the memorized parking space information matches the useful information successfully.
  • the first vehicle coordinate system is a vehicle global coordinate system established through a vehicle kinematics model, which may be located on the axle of the vehicle. According to the relative position relationship in the useful information, the vehicle terminal can use the first vehicle coordinate system to indicate and record the parking space in the useful information.
  • the world coordinate system is an absolute coordinate system, which can represent the absolute position of vehicles, parking spaces, and environmental elements. Since the first vehicle coordinate system is established on the vehicle, it moves with the movement of the vehicle, so it It is a relative coordinate system, which can only indicate the relative position of the vehicle, parking space, and environmental elements.
  • converting the characteristic information of the parking space to be determined recorded in the first vehicle coordinate system into the characteristic information of the parking space to be determined in the world coordinate system includes: obtaining the absolute position of the vehicle in the world coordinate system and in the first coordinate system Determine the conversion relationship between the first coordinate system and the world coordinate system according to the absolute position and the relative position; convert the feature information of the parking space to be determined into the feature information of the parking space to be determined in the world coordinate system according to the conversion relationship.
  • the vehicle terminal can obtain the absolute position of the vehicle in the world coordinate system according to GPS, etc., and then obtain the conversion relationship between the vehicle coordinate system and the world coordinate system according to the absolute position, so that the vehicle terminal can record the waiting information recorded in the first vehicle coordinate system.
  • the characteristic information of the parking space to be judged is converted into the characteristic information of the parking space to be judged in the world coordinate system. In this way, the absolute position of the parking space and environmental elements in the world coordinate system can be obtained.
  • Match the characteristic information of the parking space to be judged with the pre-stored characteristic information of the memorized parking space and when the characteristic information of the parking space to be judged matches the characteristic information of the pre-stored memorized parking space successfully, then the memorized parking space information matches the useful information successfully, if If the matching fails, it means that the memorized parking space information and the useful information have failed to match.
  • the terminal needs to continue to match the environment information to be judged. For details, please refer to the following.
  • the vehicle terminal has pre-stored memory parking space feature information, that is, the parking space feature information of the vehicle at the same location last time, so the vehicle terminal will recognize the parking space feature information to be judged and the pre-stored memory parking space feature information Matching includes the matching of vehicle location, and can sequentially match the identified parking space feature information to be determined with the pre-stored memory parking space feature information, so that the parking space feature information to be determined successfully matched with the memory parking space feature information
  • the target parking space corresponding to the characteristic information of the target parking space is obtained and output to the user, without the need for the user to stare at the screen to view it, thereby reducing the occurrence of danger.
  • the useful information further includes environmental information to be judged
  • the memorized parking space information includes memorized environmental information.
  • the useful information that characterizes the parking space to be judged is matched with the pre-stored memorized parking space information, including: when it does not exist and When memorizing the characteristic information of the parking space to be judged that matches the characteristic information of the parking space, match the environmental information to be judged with the pre-stored memory environment information.
  • the memory environment information is the surrounding environment information of the memorized parking space; If the stored memory environment information matches successfully, then the memory parking space information matches the useful information successfully, otherwise the memory parking space information fails to match the useful information.
  • the environmental information to be judged refers to some unique markers in the environment (such as a support column of a garage), or even image feature points that can be stably detected and tracked in the environment.
  • the vehicle terminal obtains and stores the environmental information around the parking space, so that when the vehicle is parked again, the vehicle terminal determines that there is no parking space to be determined that matches the memory parking space.
  • Match the environment information to be judged with the pre-stored memory environment information so that even if the parking space to be judged is not retrieved or the search fails due to environmental issues, the vehicle terminal can also match the environment information to be judged with the pre-stored memory Match the environmental information to determine the target parking space.
  • the vehicle terminal when the target parking space is not retrieved, but the vehicle terminal retrieves the information about the surrounding environment of the parking space and compares the stored information, when it is determined to be consistent, the vehicle terminal will display the stored parking space position on the in-vehicle display screen and pass The way of voice or view prompts the driver to stop, so as to realize the parking in the target parking space.
  • the application scenario is an automatic parking system
  • the vehicle terminal when the target parking space is not retrieved, but the vehicle terminal retrieves the surrounding environment information of the parking space, and compares the stored information, when it is determined to be consistent, the vehicle terminal will give the stored parking space location to Control the system to complete the dial-in of the parking space to be judged without the participation of the driver.
  • the parking scene is determined by matching the environmental information, and the target parking space is given to complete the goal.
  • the choice of parking space greatly improves the scope of support and driver experience.
  • the parking scene is determined by matching environmental information. The accuracy of the target parking space can be improved.
  • the above-mentioned embodiment gives the treatment plan when the vehicle is parked again.
  • the following will give the treatment method when the vehicle is parked for the first time.
  • Figure 3. 3 is a process flow chart of the initial parking of a vehicle in an embodiment.
  • the pre-stored memory parking space determination method includes:
  • S302 Collect a reference image through a camera installed on the vehicle, and generate a reference mosaic image according to the collected reference image.
  • the reference image is collected by cameras installed around the vehicle.
  • multiple ( ⁇ 4) fisheye cameras can be installed around the vehicle, so that these fisheye cameras can be turned on when the driver needs them and collected Reference image around the vehicle.
  • the fisheye cameras start to collect reference images, and the reference images carry time stamps, and the time stamps are used to characterize the reference images. Of the shooting time.
  • the reference mosaic is generated based on the reference image.
  • the vehicle terminal can use the on-board processor to compress and correct the obtained multi-channel videos to stitch multiple reference images of a single fisheye camera into a whole reference mosaic.
  • the vehicle terminal stitches multiple reference images with the same time stamp according to the time stamps of multiple reference images collected by each fisheye camera to obtain a reference mosaic.
  • the vehicle terminal can obtain a reference mosaic from each fisheye camera The camera acquires multiple reference images with the same time stamp, and then determines whether the number of acquired multiple reference images is greater than or equal to the preset number, for example, equal to the number of fisheye cameras. If so, based on the multiple acquired The reference image generates a reference mosaic.
  • the vehicle terminal can directly read the corresponding reference mosaic from the panoramic view system.
  • S304 Perform feature recognition on the reference mosaic to obtain a reference feature.
  • feature recognition refers to the process of identifying and detecting feature information used in the parking process from the reference mosaic, where the identified image feature refers to the information that can characterize the parking space of the line or is unique in the environment Some of the markers (such as the support column of the garage) and other information, and even the characteristic points of the image that can be stably detected and tracked in the environment.
  • the vehicle terminal can perform feature recognition on the reference mosaic to obtain image features through a pre-trained deep neural network model, and the deep neural network model can be trained based on historical images with pre-calibrated image features.
  • S306 Determine a preset type of reference information according to the identified reference feature.
  • the preset types include, but are not limited to, parking space parameters and the position of the parking space relative to the vehicle.
  • Reference information includes, but is not limited to, geometric size information, relative position relationships, and other measurement information.
  • the vehicle terminal can classify image features according to preset logic, and then process the classified image features to obtain parking space parameters and relative position relationships.
  • S308 Establish a second vehicle coordinate system, and record the reference information through the second vehicle coordinate system.
  • the second vehicle coordinate system is a vehicle global coordinate system established through a vehicle kinematics model, which may be located on the axle of the vehicle. According to the relative position relationship in the reference information, the vehicle terminal may use the second vehicle coordinate system to indicate and record the parking space in the reference information.
  • S310 Convert the reference information recorded in the second vehicle coordinate system into reference information in the world coordinate system.
  • the world coordinate system is an absolute coordinate system, which can represent the absolute position of vehicles, parking spaces, and environmental elements. Since the second vehicle coordinate system is established on the vehicle, it moves with the movement of the vehicle. It is a relative coordinate system, which can only indicate the relative position of the vehicle, parking space, and environmental elements.
  • the vehicle terminal can obtain the absolute position of the vehicle in the world coordinate system according to GPS, etc., and then obtain the conversion relationship between the vehicle coordinate system and the world coordinate system according to the absolute position, so that the vehicle terminal can convert the reference information recorded in the second vehicle coordinate system Converted to reference information in the world coordinate system. In this way, the absolute position of the parking space and environmental elements in the world coordinate system can be obtained.
  • S312 Acquire final parking space feature information.
  • S314 Store the final parking space feature information in the reference information in the world coordinate system as the memory parking space feature information.
  • the final parking space is the parking space that the user drove into when the user parked for the first time.
  • the vehicle terminal can obtain the final parking space of the vehicle, so that the characteristic information of the final parking space can be obtained and obtained
  • the characteristic information of the final parking space in the reference information is stored as the characteristic information of the memory parking space. In this way, it can be called directly the next time the car is parked.
  • the vehicle terminal can record the final parking space detected in a standard data format and store it in the controller's own memory. The stored information can be flashed and saved after the system is powered off. .
  • the memory parking spaces are stored in advance, so that when multiple effective parking spaces are retrieved, the accurate parking spaces can be determined by comparing with the multiple effective parking spaces stored in advance, and the accuracy of parking space determination can be improved.
  • the final parking space feature information in the reference information in the world coordinate system after storing the final parking space feature information in the reference information in the world coordinate system as the memorized parking space feature information, it further includes: obtaining the final and final parking space feature information in the reference information in the world coordinate system.
  • the memory environment information corresponding to the parking space feature information; the memory environment information and the memory parking space feature information are stored in association.
  • the vehicle terminal can record the detected final parking space feature information and the information in the surrounding environment in a standard data format, and store it in the controller's own memory, and the stored information can be flashed in. It can be saved after the system is powered off.
  • multiple final parking space feature information multiple final parking space feature information and surrounding environment information sets are established, so as to realize the memory of multiple final parking space feature information. In this way, when parking the vehicle again, if the matching with the memory parking space fails, the vehicle terminal can also match the memory environment information to determine the target parking space, avoiding the problem of matching failure caused by missed or wrong detection of the parking space.
  • the parking space not only the memory parking space is stored, but also the memory environment information.
  • the parking space is determined by matching the environment information.
  • By matching the environmental information to determine the parking scene which can improve the accuracy of the target parking space.
  • the method further includes: judging whether the memory parking space feature information and the memory environment information are valid according to a preset rule; when the parking space feature information and the memory environment are memorized When the information is valid, the driver's confirmation prompt will be output; when the memorized parking space characteristic information and the memorized environment information are invalid, the memorized parking space storage failure prompt will be output.
  • the vehicle terminal After the memorized parking space feature information and the memory environment check information are stored, the vehicle terminal performs a data check. If the memorized parking space feature information and the memory environment check information are valid, the validity check can be to determine whether the data is Complete, such as determining whether the location information of the memorized parking space feature information has data records, whether the environmental information has data records, etc., if it is valid, the memorized parking space will be displayed to the driver through HUT or mobile phone, and a pop-up box will prompt Let the driver determine the correctness of the target parking space; if memorizing the parking space and the memory environment check information is invalid, the pop-up window prompts the driver that the memory of the parking space has failed, and allows the driver to choose to give up the memory or start again. Only the memory parking space and memory environment check information after the data is valid and confirmed by the driver will be stored and numbered.
  • receiving the parking instruction input by the driver includes: receiving the parking instruction input by the driver through a button in the vehicle controller; or receiving the parking instruction input by the driver through a voice recognition device; or receiving The parking command sent by the terminal.
  • the trigger path for the first parking of the above parking method may include: the driver clicks a soft button in the HUT, or after the voice recognition module detects the driver’s voice command, the vehicle terminal sends the driver’s parking space memory requirements to Parking space memory and automatic matching and selection system to start the first parking for the target parking space.
  • the driver sends instructions to a wireless communication system, such as a Bluetooth system, an Ethernet system, etc., through a mobile phone Bluetooth or Ethernet module.
  • the wireless communication system sends the driver's needs to the parking space memory and automatic matching and selection system to turn on the target The first parking of the parking space.
  • the re-parking trigger method of the above parking method may include: the driver clicks the soft button in the HUT, or after the voice recognition module detects the driver’s voice command, the vehicle terminal sends the driver’s re-parking request to the parking space memory And automatic matching and selection, start parking again for the target parking space.
  • the driver sends instructions to a wireless communication system, such as a Bluetooth system, an Ethernet system, etc., through a mobile phone Bluetooth or Ethernet module.
  • the wireless communication system sends the driver's needs to the parking space memory and automatically matches and selects, and opens the target parking space Parked again.
  • the parking instruction is received in multiple ways, which can facilitate the operation of the user and improve the parking efficiency.
  • the method further includes: receiving a parking instruction input by the driver; when the parking instruction is the first parking instruction, executing the collection of reference images through a camera installed on the vehicle; when the parking instruction is not the first time When the parking command is executed, the initial image is collected through the camera installed on the vehicle.
  • the driver's instruction it is necessary to determine whether the first parking or not the first parking, which is convenient for reminding the driver to store and memorize the parking space and the memory environment information.
  • FIG. 4 is a flowchart of a method for determining a parking space in another embodiment.
  • the trajectory of the vehicle is from P1 to P2 and then to P3. Since the cruising distance of the vehicle is short, the trajectory of the vehicle can be simplified to a straight line.
  • a world coordinate system Oxy is established at the rear axle of the vehicle that is consistent with the direction of the P1 position coordinate system.
  • the driver inputs a parking instruction first, and the vehicle terminal needs to determine whether the parking instruction is the first parking instruction.
  • the judgment method can be specified by the driver or judged based on the historical driving records of the vehicle.
  • it is not the first parking instruction continue to execute the initial image collected by the camera installed on the vehicle to determine the target parking space by matching with the memory parking space.
  • it is determined as the first parking instruction continue to execute the pass
  • the camera installed on the vehicle collects reference images, that is, determines the memory parking space by determining the driver's last parking space, and stores it for subsequent processing.
  • the input mode of the parking command can include the driver clicking the soft button in the HUT, or the voice recognition module detects the driver's voice command, or the driver sends the command to the wireless communication system through the mobile phone Bluetooth or Ethernet module. To send parking instructions to the vehicle terminal.
  • FIG. 6 is a schematic diagram of a mosaic in an embodiment.
  • the mosaic may refer to the reference mosaic in the first parking, or the to-be-processed mosaic in the re-parking.
  • the vehicle terminal converts the fisheye view of the surrounding view into a horizontal real view through the stretching and correction of the view, in which each pixel refers to the real distance information.
  • each pixel refers to a specific distance ( Millimeter level).
  • the vehicle terminal when parking for the first time, the vehicle terminal performs feature recognition on the reference mosaic, and extracting image features is to classify and divide pixel point information to form different pixel point sets. Then the vehicle terminal intensively extracts the parking space line information from the picked-up feature points.
  • a horizontal parking space line composed of multiple A points
  • a vertical parking space line connected by points A and B and a horizontal parking space line and a vertical parking space line.
  • the image feature parameter extraction module extracts the picked-up feature point information, compares the existing feature point sets that characterize different features, so as to identify different features, realize the recognition of the parking space line and the parking space enclosed by the parking space line, that is, For the parking space to be determined in the reference information, the position relationship between the parking space to be determined and the vehicle can also be determined according to the pixel points occupied by the feature.
  • the vehicle terminal then performs the establishment and conversion of the coordinate system.
  • the characteristic point A (corner point) is given in the respective relative coordinate system O'x'y', and the characteristic point B (perpendicular to A Any point on the constituted line) and relative coordinates (A1', B1'), (A2', B2'), etc.
  • the cumulative amount of movement of the vehicle is obtained through the vehicle movement model.
  • the relative coordinates of points A and B in the relative coordinate system are converted to the coordinates in the absolute coordinate system (A1, B1), (A2, B2) etc.
  • the coordinates of the target parking space in the memory parking relative to the world coordinate system can be obtained (A5 ,B5), (A6,B6).
  • the angle range supported in the coordinate conversion is small and the cruising distance is short, so it can be considered that the vehicle is moving in a straight line during the cruising phase.
  • the vehicle terminal records the detected target parking space (that is, the end user's parking space) and the surrounding environment information in a standard data format, and stores it in the controller's own memory. When the target parking space and surrounding environment information is stored, the vehicle terminal will perform data inspection.
  • the target parking space and surrounding environment information will be displayed to the driver through HUT or mobile phone, and a pop-up box will prompt the driver to confirm Target parking space: If the target parking space and surrounding environment information is invalid, the pop-up window prompts the driver to fail, and allows the driver to choose to abandon the memory or start again. Only the parking spaces with valid data and confirmed by the driver will be stored and numbered.
  • the vehicle terminal When parking the vehicle again, the vehicle terminal performs feature recognition on the mosaic image to be processed, and extracting image features is to classify and divide pixel information to form different pixel point sets. Then the vehicle terminal intensively extracts the parking space line information from the picked-up feature points.
  • the image feature parameter extraction module extracts the picked-up feature point information, compares the existing feature point sets that characterize different features, so as to identify different features, realize the recognition of the parking space line and the parking space enclosed by the parking space line, that is, For the parking space to be determined in the useful information, the position relationship between the parking space to be determined and the vehicle can also be determined according to the pixel points occupied by the feature.
  • the vehicle terminal then performs the establishment and conversion of the coordinate system.
  • the characteristic point A (corner point) is given in the respective relative coordinate system O'x'y', and the characteristic point B (perpendicular to A Any point on the constituted line) and relative coordinates (A1', B1'), (A2', B2'), etc.
  • the cumulative amount of movement of the vehicle is obtained through the vehicle movement model.
  • the relative coordinates of points A and B in the relative coordinate system are converted to the coordinates in the absolute coordinate system (A1, B1), (A2, B2) etc.
  • the coordinates of the target parking space in the memory parking relative to the world coordinate system can be obtained (A5 ,B5), (A6,B6).
  • the angle range supported in the coordinate conversion is small and the cruising distance is short, so it can be considered that the vehicle is moving in a straight line during the cruising phase.
  • B B';
  • A A'+S (S is the cumulative travel distance of the vehicle during the driving process).
  • the vehicle terminal matches the to-be-determined parking space and surrounding environment information detected by re-parking with the multiple memory parking spaces and memory environment information recorded in the memory, thereby determining the target parking space.
  • the vehicle terminal When the vehicle terminal performs parking space detection and recognizes multiple parking spaces including the target parking space 5 in FIG. 9, the vehicle terminal determines that the target parking space is the No. 5 parking space through the comparison information. When the parking space line is blocked by obstacles, as shown in Figure 10, the ambient light is poor. As shown in Figure 11, when the vehicle terminal detects the parking space, the target parking space 5 is not detected, but the surrounding environment information of the parking space is matched, and the vehicle terminal will store the first parking The coordinate information (A5, B5), (A6, B6) of the target parking space 5 is used as the target parking space coordinates to complete the selection of the target parking space.
  • the above method when the above method is applied to the field of automatic driving, the above method can be integrated as a parking space memory and an automatic matching and selection system.
  • the automatic driving system enters the automatic parking software when there is a parking demand during the road driving phase.
  • the automatic parking software will automatically mobilize the parking space memory and the automatic matching and selection system to achieve complete functions.
  • the automatic driving system has parking during the road driving phase Carry out parking scheduling on demand; when the automatic parking system memorizes the parking scene, it turns on the parking space memory and the automatic matching and selection system; after the parking space memory and automatic matching and selection system are turned on, the result is returned to the automatic parking, so that the automatic parking The parking system completes the parking; after the automatic parking system completes the parking, the result is fed back to the automatic driving system.
  • the vehicle terminal determines the parking scene by matching the environmental information, and gives the target parking space information, thereby
  • the completion of the target parking space selection greatly improves the support range of the system and the driver experience; and due to its own technical constraints, the retrieval of the target parking space cannot be achieved 100%, and when the parking space is missed, the vehicle terminal determines by matching the environmental information
  • the parking scene and the target parking space information are given to complete the target parking space selection, which greatly improves the support range and driver experience; when the vehicle terminal retrieves multiple valid parking spaces, the target parking space cannot be determined without manual selection by the driver ,
  • the system will automatically determine the target parking space through matching and selection, complete the target parking space selection, greatly improving the scope of support and driver experience; when the vehicle terminal is retrieving parking spaces, even if the driver does not look at the screen, the vehicle terminal will match the target parking space Tell the driver through voice or image to avoid dangerous driving and improve the
  • the owner in the parking spaces on the ground, the owner has a fixed parking space, and the surrounding parking spaces are all empty, as shown in Figure 9.
  • the vehicle terminal turns on the parking space memory and automatic matching and selection system. Since there are empty parking spaces around the vehicle, the vehicle has retrieved three valid parking spaces. At this time, if there is no automatic parking space matching and selection system, the vehicle does not know where the target parking space is and may park in any parking space. In this scenario, the parking space automatic matching and selection system compares the target parking space information stored for the first parking, determines that the rightmost of the retrieved parking spaces is the target parking space, and then completes the parking.
  • the owner has a fixed parking space.
  • the target parking space parks a car behind the vehicle's forward direction.
  • the parking of the vehicle causes the parking space line of the target parking space to be blocked, as shown in Figure 10.
  • the vehicle terminal turns on the parking space memory and automatic matching and selection system. Because the parking space line is blocked, the vehicle does not retrieve the target parking space.
  • the parking space automatic matching and selection system matches the surrounding environment information. If the environmental information is matched, the parking space automatic matching and selection system will send the target parking space information stored in the initial parking to the visual parking system as the target parking space, and then complete the parking. vehicle.
  • the car owner In the underground parking space, the car owner has a fixed parking space, and the target parking space is not illuminated due to a light failure, as shown in Figure 11.
  • the vehicle terminal turns on the parking space memory and automatic matching and selection system. Due to insufficient light, the vehicle terminal does not retrieve the target parking space. At this time, if there is no automatic parking space matching and selection system, the vehicle cannot be parked. In this scenario, the parking space automatic matching and selection system will send the target parking space information stored in the first parking to the visual parking system as the target parking space, and then complete the parking.
  • a parking space determination device including: a collection module 100, a feature recognition module 200, a useful information determination module 300, a matching module 400, and an output module 500, where:
  • the module 100 is used to collect an initial image through a camera installed on a vehicle, and generate a mosaic to be processed according to the collected initial image.
  • the feature recognition module 200 is configured to perform feature recognition on the stitched image to be processed to obtain image features.
  • the useful information determining module 300 is configured to determine a preset type of useful information representing the parking space to be determined according to the recognized image characteristics.
  • the matching module 400 is used to match the useful information that characterizes the parking space to be determined with the pre-stored memory parking space information.
  • the output module 500 is used for taking the parking space to be judged represented by the useful information successfully matched with the memory parking space information as the target parking space.
  • the useful information includes the characteristic information of the parking space to be judged
  • the memorized parking space information includes the memorized parking space characteristic information
  • the matching module may include: a coordinate system establishing unit for establishing the first vehicle coordinate system and combining the The characteristic information of the parking space to be judged is recorded through the first vehicle coordinate system; the conversion module is used to convert the characteristic information of the parking space to be judged recorded through the first vehicle coordinate system into the characteristic information of the parking space to be judged in the world coordinate system;
  • the matching unit is configured to match the characteristic information of the parking space to be judged with the characteristic information of the pre-stored memory parking space, and when the characteristic information of the parking space to be judged matches the characteristic information of the pre-stored memory parking space successfully, the The memorized parking space information matches the useful information successfully.
  • the above-mentioned parking space determination device may further include: a stitching module for collecting reference images through a camera installed on the vehicle, and generating a reference stitching image based on the collected reference images; a reference feature acquiring module, It is used to perform feature recognition on the reference mosaic to obtain the reference feature; the reference information acquisition module is used to determine the preset type of reference information according to the recognized reference feature; the recording module is used to establish the second vehicle coordinate system and reference The information is recorded through the second vehicle coordinate system; the coordinate conversion module is used to convert the reference information recorded through the second vehicle coordinate system into reference information in the world coordinate system; the parking space acquisition module is used to obtain the final parking space Feature information; storage module, used to store the final parking space feature information in the reference information in the world coordinate system as a memory parking space.
  • a stitching module for collecting reference images through a camera installed on the vehicle, and generating a reference stitching image based on the collected reference images
  • a reference feature acquiring module It is used to perform feature recognition on the reference mosaic to obtain the
  • the above-mentioned matching module may further include: a second matching unit, for when there is no parking space feature information to be determined that matches the memory parking space feature information, then the environment information to be determined is stored in advance.
  • the memory environment information is matched with the memory environment information of the memory parking space; the result acquisition unit is used to match the memory parking space information with the useful information when the environmental information to be judged matches the pre-stored memory environment information successfully , Otherwise the memorized parking space information will fail to match the useful information.
  • the above-mentioned parking space determination device may further include: an environmental information acquisition module for acquiring memory environment information corresponding to the final parking space characteristic information in the reference information in the world coordinate system; and a storage module It is also used to store the memory environment information and the memory parking space feature information in association.
  • the above-mentioned parking space determining device may further include: a judging module for judging whether the memorized parking space feature information and the memorizing environment information are valid according to preset rules; the prompt module is used for memorizing parking space feature information And when the memory environment information is valid, the driver confirmation prompt is output; when the memorized parking space characteristic information and the memory environment information are invalid, the memory parking space storage failure prompt is output.
  • the above-mentioned conversion module includes: a position obtaining unit, configured to obtain the absolute position of the vehicle in the world coordinate system and the relative position in the first coordinate system; the conversion relationship obtaining unit, using For determining the conversion relationship between the first coordinate system and the world coordinate system according to the absolute position and the relative position; a conversion unit for converting the characteristic information of the parking space to be judged into world coordinates according to the conversion relationship The characteristic information of the parking space to be judged under the system.
  • the above-mentioned parking space determination device may further include: a receiving module for receiving a parking instruction input by the driver; a processing module for executing a parking instruction when the parking instruction is the first parking instruction
  • the camera installed on the vehicle collects the reference image; when the parking instruction is not the first parking instruction, the initial image is collected by the camera installed on the vehicle.
  • Each module in the above parking space determination device can be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above-mentioned modules may be embedded in the form of hardware or independent of the processor in the computer equipment, or may be stored in the memory of the computer equipment in the form of software, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
  • a computer device is provided.
  • the computer device may be a terminal, and its internal structure diagram may be as shown in FIG. 14.
  • the computer equipment includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus.
  • the processor of the computer device is used to provide calculation and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system and a computer-readable storage medium.
  • the internal memory provides an environment for the operation of the operating system in the non-volatile storage medium and the computer-readable storage medium.
  • the network interface of the computer device is used to communicate with an external terminal through a network connection.
  • the computer-readable storage medium is executed by the processor to realize a parking space determination method.
  • the display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen
  • the input device of the computer equipment can be a touch layer covered on the display screen, or it can be a button, a trackball or a touchpad set on the housing of the computer equipment , It can also be an external keyboard, touchpad, or mouse.
  • FIG. 14 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may Including more or fewer parts than shown in the figure, or combining some parts, or having a different arrangement of parts.
  • a computer device includes a memory and one or more processors.
  • the memory stores computer-readable instructions.
  • the steps of the parking space determination method provided in any embodiment of the present application are implemented.
  • One or more non-volatile storage media storing computer-readable instructions.
  • the one or more processors realize the parking provided in any one of the embodiments of the present application. Steps of the parking space determination method.
  • Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Channel (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Artificial Intelligence (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé de détermination de place de stationnement, consistant : à acquérir des images initiales au moyen de caméras montées sur un véhicule, et à générer, en fonction des images initiales acquises, des images de collage à traiter (S202) ; à procéder à une reconnaissance d'attributs sur lesdites images de collage, afin d'obtenir des attributs d'images (S204) ; à déterminer, en fonction des attributs d'images reconnus, un type prédéfini d'informations utiles caractérisant des places de stationnement à déterminer (S206) ; à apparier les informations utiles caractérisant les places de stationnement à déterminer à des informations de places de stationnement en mémoire présauvegardées (S208) ; et à prendre une place de stationnement à déterminer, laquelle est caractérisée par les informations utiles et s'apparie avec succès aux informations de places de stationnement en mémoire, en tant que place cible de stationnement (S210).
PCT/CN2020/090170 2020-05-14 2020-05-14 Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations WO2021226912A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/090170 WO2021226912A1 (fr) 2020-05-14 2020-05-14 Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/090170 WO2021226912A1 (fr) 2020-05-14 2020-05-14 Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations

Publications (1)

Publication Number Publication Date
WO2021226912A1 true WO2021226912A1 (fr) 2021-11-18

Family

ID=78526190

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/090170 WO2021226912A1 (fr) 2020-05-14 2020-05-14 Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations

Country Status (1)

Country Link
WO (1) WO2021226912A1 (fr)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114194180A (zh) * 2021-12-28 2022-03-18 阿波罗智联(北京)科技有限公司 一种辅助泊车信息的确定方法、装置、设备及介质
CN114220188A (zh) * 2021-12-27 2022-03-22 上海高德威智能交通系统有限公司 一种车位巡检方法、装置及设备
CN115223135A (zh) * 2022-04-12 2022-10-21 广州汽车集团股份有限公司 车位跟踪方法、装置、车辆及存储介质
CN115503694A (zh) * 2022-10-20 2022-12-23 北京易航远智科技有限公司 基于自主学习的记忆泊车路径生成方法、装置及电子设备
CN115527189A (zh) * 2022-11-01 2022-12-27 杭州枕石智能科技有限公司 车位状态的检测方法、终端设备及计算机可读存储介质
CN115565158A (zh) * 2022-11-17 2023-01-03 广汽埃安新能源汽车股份有限公司 车位检测方法、装置、电子设备和计算机可读介质
CN115743100A (zh) * 2023-01-10 2023-03-07 禾多科技（北京）有限公司 泊车路线信息生成方法、装置、设备和计算机可读介质
CN115817459A (zh) * 2023-02-23 2023-03-21 禾多科技（北京）有限公司 车辆控制方法、装置、电子设备和计算机可读介质
CN116061924A (zh) * 2023-03-31 2023-05-05 禾多科技（北京）有限公司 一种触碰点距离信息实时反馈的hpa记忆泊车系统
CN117576645A (zh) * 2024-01-16 2024-02-20 深圳市欧冶半导体有限公司 基于bev视角的车位检测方法、装置和计算机设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130021171A1 (en) * 2011-07-22 2013-01-24 Automotive Research & Test Center Parking space detection device and method thereof
EP2557020B1 (fr) * 2011-08-12 2014-10-01 Robert Bosch Gmbh Procédé destiné à assister un conducteur lors du parcage
CN109353334A (zh) * 2018-10-25 2019-02-19 广州小鹏汽车科技有限公司 车位检测方法及装置
CN110239524A (zh) * 2019-05-23 2019-09-17 浙江吉利控股集团有限公司 自动泊车方法、装置、系统及终端
CN111028534A (zh) * 2018-10-09 2020-04-17 杭州海康威视数字技术股份有限公司 一种泊车位检测方法及装置

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130021171A1 (en) * 2011-07-22 2013-01-24 Automotive Research & Test Center Parking space detection device and method thereof
EP2557020B1 (fr) * 2011-08-12 2014-10-01 Robert Bosch Gmbh Procédé destiné à assister un conducteur lors du parcage
CN111028534A (zh) * 2018-10-09 2020-04-17 杭州海康威视数字技术股份有限公司 一种泊车位检测方法及装置
CN109353334A (zh) * 2018-10-25 2019-02-19 广州小鹏汽车科技有限公司 车位检测方法及装置
CN110239524A (zh) * 2019-05-23 2019-09-17 浙江吉利控股集团有限公司 自动泊车方法、装置、系统及终端

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114220188A (zh) * 2021-12-27 2022-03-22 上海高德威智能交通系统有限公司 一种车位巡检方法、装置及设备
CN114194180A (zh) * 2021-12-28 2022-03-18 阿波罗智联(北京)科技有限公司 一种辅助泊车信息的确定方法、装置、设备及介质
CN115223135A (zh) * 2022-04-12 2022-10-21 广州汽车集团股份有限公司 车位跟踪方法、装置、车辆及存储介质
CN115223135B (zh) * 2022-04-12 2023-11-21 广州汽车集团股份有限公司 车位跟踪方法、装置、车辆及存储介质
CN115503694A (zh) * 2022-10-20 2022-12-23 北京易航远智科技有限公司 基于自主学习的记忆泊车路径生成方法、装置及电子设备
CN115527189A (zh) * 2022-11-01 2022-12-27 杭州枕石智能科技有限公司 车位状态的检测方法、终端设备及计算机可读存储介质
CN115565158B (zh) * 2022-11-17 2023-05-26 广汽埃安新能源汽车股份有限公司 车位检测方法、装置、电子设备和计算机可读介质
CN115565158A (zh) * 2022-11-17 2023-01-03 广汽埃安新能源汽车股份有限公司 车位检测方法、装置、电子设备和计算机可读介质
CN115743100A (zh) * 2023-01-10 2023-03-07 禾多科技（北京）有限公司 泊车路线信息生成方法、装置、设备和计算机可读介质
CN115817459A (zh) * 2023-02-23 2023-03-21 禾多科技（北京）有限公司 车辆控制方法、装置、电子设备和计算机可读介质
CN116061924A (zh) * 2023-03-31 2023-05-05 禾多科技（北京）有限公司 一种触碰点距离信息实时反馈的hpa记忆泊车系统
CN116061924B (zh) * 2023-03-31 2023-06-16 禾多科技（北京）有限公司 一种触碰点距离信息实时反馈的hpa记忆泊车系统
CN117576645A (zh) * 2024-01-16 2024-02-20 深圳市欧冶半导体有限公司 基于bev视角的车位检测方法、装置和计算机设备
CN117576645B (zh) * 2024-01-16 2024-03-22 深圳市欧冶半导体有限公司 基于bev视角的车位检测方法、装置和计算机设备

Similar Documents

Publication Publication Date Title
WO2021226912A1 (fr) Procédé et appareil de détermination de place de stationnement, dispositif informatique et support d'informations
CN111723659B (zh) 泊车位确定方法、装置、计算机设备和存储介质
JP7379682B2 (ja) インテリジェント駐車方法及び装置
CN110244738B (zh) 车辆的行驶控制方法、装置和车辆
US11541881B2 (en) Automatic parking method, device, system, and vehicle
CN111160172B (zh) 泊车位检测方法、装置、计算机设备和存储介质
JP6509361B2 (ja) 駐車支援装置及び駐車支援方法
US11900672B2 (en) Integrated internal and external camera system in vehicles
CN111860352B (zh) 一种多镜头车辆轨迹全跟踪系统及方法
US20160224974A1 (en) Method and system for wireless payment of public transport fare
CN103366601A (zh) 基于环视图像设置停车位置的装置和方法
US10937323B2 (en) System and method for guiding parking location of vehicle
CN111179162A (zh) 一种特殊环境下的定位初始化方法及车载终端
CN111783595B (zh) 一种车辆泊车方法、装置、车载设备及存储介质
WO2022088766A1 (fr) Procédé de traitement d'images, support, dispositif et système de traitement d'images
JP2011197728A (ja) 共用車両管理装置
CN112489112B (zh) 加油枪与车辆匹配方法、装置、电子设备及存储介质
CN112799391B (zh) 用于狭窄车位的泊车方法、装置、车辆及存储介质
KR102164702B1 (ko) 자동 주차 장치 및 자동 주차 방법
KR20160076114A (ko) 비디오 분석 기술을 활용한 주차장 관리 방법 및 그 장치
CN115407355B (zh) 库位地图的验证方法、装置及终端设备
WO2022073461A1 (fr) Procédé et dispositif d'affichage de processus de stationnement et véhicule
JP2009159241A (ja) 駐車時停止支援システム
US11069092B2 (en) Apparatus for providing top view image of parking space and method thereof
JP2019091230A (ja) 車両監視システム、監視装置および情報共有方法

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: 20935959

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20935959

Country of ref document: EP

Kind code of ref document: A1