Projection-based automatic parking method and device

Abstract

The application relates to a projection-based automatic parking method and device, and relates to the technical field of automatic parking. The method comprises the following steps: acquiring the distance between a target user and a current vehicle, and detecting at least one physical feature or physiological feature when the distance is less than a preset distance threshold; acquiring current vehicle environment information and extracting environment features corresponding to the environment information when the physical feature or physiological feature is detected, inputting the environment features into a domain controller, identifying the parking-out direction of the vehicle and obstacle information, and projecting the parking-out direction to the open ground in the form of a projection point; and when the target user selects a target parking-out direction projected on the open ground in at least one preset mode, controlling the current vehicle to perform a parking operation in the target parking-out direction. Thus, the existing automatic parking start technology cannot control the vehicle to perform an automatic parking operation in a scene where the user is inconvenient to manually send an automatic parking command.

Description

Technical Field

[0001] This application relates to the field of automatic parking technology, and in particular to an automatic parking method and apparatus based on projection. Background Technology

[0002] Most existing automatic parking activation methods require the driver to manually activate the automatic parking function, such as clicking the "Start Automatic Parking" button on the car's infotainment app, clicking the "Activate Automatic Parking" button on a mobile app when using remote parking, or clicking the automatic parking button on a key or other medium.

[0003] However, in scenarios where users are carrying heavy objects or other items with both hands, or holding children, it is inconvenient for users to manually send automatic parking commands to the intelligent driving assistance system to activate automatic parking, which urgently needs to be addressed. Summary of the Invention

[0004] This application provides a projection-based automatic parking method and apparatus to solve the problem that existing automatic parking activation technologies are difficult to control the vehicle to perform automatic parking operations in scenarios where it is inconvenient for the user to manually send automatic parking commands.

[0005] The first aspect of this application provides a projection-based automatic parking method, comprising the following steps: acquiring the distance between a target user and a current vehicle, and determining whether the distance is less than a preset distance threshold; in response to the distance being less than the preset distance threshold, detecting at least one physical feature or at least one physiological feature of the target user; when the at least one physical feature or the at least one physiological feature is detected, acquiring the current vehicle's environmental information, extracting the environmental features corresponding to the environmental information, and inputting the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and projecting the parking direction onto an open ground in the form of projection points; when it is detected that the target user selects a target parking direction projected onto the open ground in at least one preset manner, controlling the current vehicle to perform a parking operation in the target parking direction.

[0006] Optionally, in one embodiment of this application, the step of obtaining the distance between the target user and the current vehicle, and determining whether the distance is less than a preset distance threshold, and detecting at least one physical feature or at least one physiological feature of the target user in response to the distance being less than the preset distance threshold, includes: obtaining the location perception information of the current vehicle in the target area, so as to determine the relative distance state between the target user and the vehicle body of the current vehicle based on the location perception information; comparing the relative distance state with a preset distance condition to obtain a corresponding distance matching result, and performing a preset multimodal feature recognition operation based on the distance matching result when the preset distance condition is met, to collect at least one physical feature or at least one physiological feature corresponding to the target user.

[0007] Optionally, in one embodiment of this application, the step of acquiring the current vehicle environment information, extracting the environmental features corresponding to the environment information, and inputting the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and projecting the parking direction onto an open ground in the form of projection points, includes: activating the vehicle's surrounding environment perception sensor to collect the current vehicle environment information, and parsing the environment information to extract corresponding environmental features, wherein the environmental features include vehicle spatial distribution information, obstacle location information, and ground projection area information; inputting the environmental features into the domain controller for fusion calculation to obtain the corresponding fusion calculation result, and dividing the vehicle's passable space and obstacle space through the fusion calculation result to generate a corresponding division result, and determining the parking direction and obstacle information of the current vehicle that meet preset safety requirements based on the division result; generating projection point instructions in the corresponding direction based on the parking direction and obstacle information, and controlling a preset projection device to project the parking direction onto a ground area that meets preset open requirements in the form of projection points through the projection point instructions.

[0008] Optionally, in one embodiment of this application, the step of controlling the current vehicle to perform a parking operation in the target parking direction when the target user selects a target parking direction projected onto an open ground using at least one preset method includes: determining whether the target user is a target vehicle owner or a target authorized user based on at least one physiological characteristic, and obtaining the target user's action information if the target user is a target vehicle owner or a target authorized user; determining whether the target user selects a target parking direction projected onto an open ground using at least one preset method based on the action information, wherein the at least one preset method includes the target user tapping a corresponding projection point on the open ground with their foot, or the target user's gaze lingering on the projection point in the corresponding direction for a duration greater than a preset time threshold, and issuing a parking command simultaneously; responding to the target user selecting a target parking direction projected onto an open ground using the at least one preset method, determining the target user's parking intention through the domain controller, and controlling the current vehicle to perform a parking operation in the target parking direction based on the parking intention.

[0009] A second aspect of this application provides a projection-based automatic parking device, comprising: a feature detection module, configured to acquire the distance between a target user and a current vehicle, and determine whether the distance is less than a preset distance threshold; in response to the distance being less than the preset distance threshold, detecting at least one physical feature or at least one physiological feature of the target user; an extraction module, configured to acquire the current vehicle's environmental information when the at least one physical feature or the at least one physiological feature is detected, extract the environmental features corresponding to the environmental information, and input the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and project the parking direction onto an open ground in the form of projection points; and a parking module, configured to control the current vehicle to perform a parking operation in the target parking direction when it is detected that the target user selects a target parking direction projected onto an open ground in at least one preset manner.

[0010] Optionally, in one embodiment of this application, the feature detection module includes: an acquisition unit, configured to acquire the location perception information of the current vehicle within the target area, so as to determine the relative distance state between the target user and the vehicle body of the current vehicle based on the location perception information; and a matching unit, configured to compare the relative distance state with preset distance conditions to obtain a corresponding distance matching result, and, based on the distance matching result, perform a preset multimodal feature recognition operation when the preset distance conditions are met, to collect at least one physical feature or at least one physiological feature corresponding to the target user.

[0011] Optionally, in one embodiment of this application, the extraction module includes: a parsing unit, configured to activate the vehicle's surrounding environment perception sensor to collect the current vehicle's environmental information and parse the environmental information to extract corresponding environmental features, wherein the environmental features include vehicle spatial distribution information, obstacle location information, and ground projectable area information; a fusion unit, configured to input the environmental features to the domain controller for fusion calculation to obtain corresponding fusion calculation results, and divide the vehicle's passable space and obstacle space according to the fusion calculation results to generate corresponding division results, and determine the parking direction of the current vehicle that meets preset safety requirements and the obstacle information according to the division results; and a projection unit, configured to generate projection point instructions in the corresponding direction based on the parking direction and the obstacle information, and control a preset projection device to project the parking direction as projection points onto a ground area that meets preset open space requirements through the projection point instructions.

[0012] Optionally, in one embodiment of this application, the parking module includes: a first judgment unit, configured to determine whether the target user is a target vehicle owner or a target authorized user based on the at least one physiological characteristic, and to acquire the target user's action information if the target user is a target vehicle owner or a target authorized user; a second judgment unit, configured to determine, based on the action information, whether the target user selects a target parking direction projected onto an open ground through at least one preset method, wherein the at least one preset method includes the target user clicking a corresponding projection point on the open ground with their foot, or the target user's gaze lingering on the projection point in the corresponding direction for a duration greater than a preset time threshold, and simultaneously issuing a parking command; and an execution unit, configured to, in response to the target user selecting a target parking direction projected onto an open ground through the at least one preset method, determine the target user's parking intention through the domain controller, and control the current vehicle to perform a parking operation in the target parking direction according to the parking intention.

[0013] A third aspect of this application provides a vehicle including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the projection-based automatic parking method as described in the above embodiments.

[0014] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the projection-based automatic parking method described above.

[0015] A fifth aspect of this application provides a computer program product, including a computer program that is executed to implement the above-described projection-based automatic parking method.

[0016] Therefore, the embodiments of this application have the following beneficial effects: The embodiments of this application can obtain the distance between the target user and the current vehicle, and determine whether the distance is less than a preset distance threshold. In response to a distance less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected. When at least one physical feature or at least one physiological feature is detected, the current vehicle environment information is obtained, and the corresponding environmental features are extracted and input into a preset domain controller to identify the parking direction and obstacle information of the current vehicle. The parking direction is then projected onto an open ground in the form of projection points. When it is detected that the target user selects the target parking direction projected onto the open ground using at least one preset method, the current vehicle is controlled to perform a parking operation in the target parking direction. This application, by identifying user information in advance and activating the automatic parking program, identifies the vehicle's surrounding environment and projects the projection direction onto the ground in the form of projection points. This facilitates automatic parking when the user is carrying items outside the vehicle and it is inconvenient to operate the vehicle, allowing the vehicle to park directly in front of the user so that the user can get into the car directly, thus improving user convenience and comfort. This solves the problem that existing automatic parking activation technologies struggle to control the vehicle for automatic parking in scenarios where it is inconvenient for users to manually send automatic parking commands.

[0017] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0018] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a flowchart of a projection-based automatic parking method provided according to an embodiment of this application; Figure 2 A schematic diagram of the logical architecture of a projection-based automatic parking method provided for one embodiment of this application; Figure 3 This is an example diagram of a projection-based automatic parking device according to an embodiment of this application; Figure 4 This is a structural schematic diagram of the vehicle provided in an embodiment of this application.

[0019] Among them, 10-projection-based automatic parking device, 100-feature detection module, 200-extraction module, 300-parking module, 401-memory, 402-processor, and 403-communication interface. Detailed Implementation

[0020] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0021] The following describes a projection-based automatic parking method and apparatus according to embodiments of this application with reference to the accompanying drawings. Addressing the problems mentioned in the background section, this application provides a projection-based automatic parking method. In this method, the distance between a target user and the current vehicle is obtained, and it is determined whether the distance is less than a preset distance threshold. If the distance is less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected. When at least one physical feature or at least one physiological feature is detected, current vehicle environmental information is obtained, and environmental features corresponding to the environmental information are extracted and input into a preset domain controller to identify the parking direction and obstacle information of the current vehicle. The parking direction is then projected onto an open ground in the form of projection points. When it is detected that the target user selects a target parking direction projected onto the open ground using at least one preset method, the current vehicle is controlled to perform a parking operation in the target parking direction. This application activates the automatic parking program by pre-identifying user information. It then identifies the vehicle's surroundings and projects the surrounding environment onto the ground as projection points. This facilitates automatic parking in situations where the user's hands are occupied and manual operation is inconvenient, allowing the vehicle to park itself directly in front of the user for immediate entry. This significantly improves user convenience and comfort. Therefore, it solves the problem of existing automatic parking technologies struggling to control the vehicle in scenarios where the user cannot manually send parking commands.

[0022] Specifically, Figure 1 This is a flowchart of a projection-based automatic parking method provided in an embodiment of this application.

[0023] like Figure 1 As shown, the projection-based automatic parking method includes the following steps: In step S101, the distance between the target user and the current vehicle is obtained, and it is determined whether the distance is less than a preset distance threshold. In response to the case that the distance is less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected.

[0024] In actual operation, when a user is carrying items in both hands or holding a child and walks to a distance of 3m or less from the vehicle (i.e., the preset distance threshold, which can be calibrated), the vehicle will detect the key through the corresponding configuration or recognize the user's facial features through the sensor, thus identifying the user as the owner or authorized user and activating the vehicle's automatic parking program.

[0025] Optionally, in one embodiment of this application, the distance between the target user and the current vehicle is obtained, and it is determined whether the distance is less than a preset distance threshold. In response to the distance being less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected, including: obtaining the location perception information of the current vehicle in the target area to determine the relative distance state between the target user and the vehicle body of the current vehicle based on the location perception information; comparing the relative distance state with a preset distance condition to obtain a corresponding distance matching result; and performing a preset multimodal feature recognition operation based on the distance matching result when the preset distance condition is met, collecting at least one physical feature or at least one physiological feature corresponding to the target user.

[0026] It should be noted that the embodiments of this application can obtain real-time location perception information of the vehicle's surroundings within the target area through the panoramic perception unit mounted on the vehicle, and dynamically track and locate the target user based on the location perception information to determine the real-time relative distance between the target user and the vehicle itself.

[0027] Secondly, in this embodiment, the relative distance state can be compared with the preset distance conditions to obtain the distance matching result. Based on the distance matching result, when the preset distance conditions are met, the fusion multimodal feature recognition operation is started to collect the authorized physical identification features or physiological features such as face and body shape carried by the target user.

[0028] Therefore, the embodiments of this application can realize user proximity recognition and multi-dimensional identity feature collection without manual triggering, which can be adapted to scenarios such as inconvenient hands, and improve the convenience and safety of automatic parking start.

[0029] In step S102, when at least one physical feature or at least one physiological feature is detected, the current vehicle environment information is acquired, the environmental features corresponding to the environmental information are extracted, and the environmental features are input into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and the parking direction is projected onto the open ground in the form of projection points.

[0030] Furthermore, embodiments of this application can use vehicle-configured sensors to sense and identify surrounding environmental features and transmit them to a domain controller. The domain controller analyzes the environmental features sensed by the sensors to identify parking spaces and surrounding obstacles, analyzes the parking direction, and issues corresponding instructions to the corresponding projection to project the parking direction onto the open ground in the form of projection points.

[0031] Therefore, the embodiments of this application are based on sensor recognition of user information, such as recognizing that the key is 3m away from the vehicle (TBD), or recognizing physiological features such as facial features, the vehicle can activate the automatic parking program and project the direction in which the vehicle can park onto the open ground in the corresponding direction of the vehicle as a projection point, thereby providing reliable technical support for the vehicle to achieve automatic parking.

[0032] Optionally, in one embodiment of this application, acquiring current vehicle environment information, extracting environmental features corresponding to the environment information, and inputting the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and projecting the parking direction onto an open ground in the form of projection points, includes: activating the vehicle's surrounding environment perception sensor to collect current vehicle environment information, and parsing the environment information to extract corresponding environmental features, wherein the environmental features include vehicle spatial distribution information, obstacle location information, and ground projection area information; inputting the environmental features into the domain controller for fusion calculation to obtain the corresponding fusion calculation result, and dividing the vehicle's passable space and obstacle space through the fusion calculation result to generate the corresponding division result, and determining the parking direction and obstacle information of the current vehicle that meet preset safety requirements based on the division result; generating projection point instructions in the corresponding direction based on the parking direction and obstacle information, and controlling a preset projection device to project the parking direction onto a ground area that meets preset open requirements in the form of projection points through the projection point instructions.

[0033] In the specific implementation process, the embodiments of this application can activate the panoramic vision, millimeter wave and ultrasonic fusion perception sensors deployed around the current vehicle, collect the environmental information of the entire surrounding area of ​​the current vehicle, perform multi-dimensional analysis of the environmental information, and extract environmental features including the spatial distribution around the vehicle, the location and outline of obstacles, and the ground projection area.

[0034] Secondly, the embodiments of this application can perform multi-source data fusion calculation on the environmental feature input domain controller to obtain fusion calculation results, and distinguish and mark the passable space and obstacle space around the vehicle through the fusion calculation results to generate space division results, and filter out the parking direction and corresponding obstacle constraint information that meet the preset safety requirements based on the space division results.

[0035] Subsequently, based on the parking direction and obstacle constraint information, this application embodiment can generate a projection point command matching the corresponding direction, and control the vehicle-mounted projection device through the projection point command to project the parking direction as a projection point onto an open ground area without obstructions or obstacles.

[0036] Therefore, the embodiments of this application can accurately identify the safe parking direction and visualize it, eliminating the need for users to manually judge the environment, making the operation more intuitive, and effectively improving the safety and smoothness of automatic parking.

[0037] In step S103, when it is detected that the target user selects a target parking direction projected onto an open ground in at least one preset method, the current vehicle is controlled to perform a parking operation in the target parking direction.

[0038] Subsequently, in this embodiment, after the user sees the projection point of the parking direction, the user can click the corresponding projection point of the parking direction projected onto the ground with their foot or other means. After the vehicle recognizes the user's intention to select the parking direction through the sensor, it sends the information to the domain controller to control the vehicle to perform automatic parking. After parking is completed, the user can enter the vehicle, thereby greatly improving the vehicle's intelligence and reliability, and improving the user's parking function experience.

[0039] Optionally, in one embodiment of this application, when it is detected that a target user selects a target parking direction projected onto an open ground using at least one preset method, the current vehicle is controlled to perform a parking operation in the target parking direction. This includes: determining whether the target user is the target vehicle owner or the target authorized user based on at least one physiological characteristic, and if the target user is the target vehicle owner or the target authorized user, obtaining the target user's action information; based on the action information, determining whether the target user selects a target parking direction projected onto an open ground using at least one preset method, wherein the at least one preset method includes the target user clicking the corresponding projection point on the open ground with their foot, or the target user's gaze lingering on the projection point in the corresponding direction for a duration exceeding a preset time threshold, and simultaneously issuing a parking command; in response to the target user selecting a target parking direction projected onto an open ground using at least one preset method, determining the target user's parking intention through a domain controller, and controlling the current vehicle to perform a parking operation in the target parking direction according to the parking intention.

[0040] As one possible approach, embodiments of this application can activate the automatic parking program by recognizing user information in advance, identifying the surrounding environment, and projecting the projection direction onto the ground in the form of projection points. This allows the user to activate the parking function from outside the vehicle using the following preset methods: 1. The user taps the corresponding projection point on the open ground with their foot; 2. The user's gaze is directed to the corresponding projection point on the ground and remains there for a certain period of time, i.e., a preset time threshold (such as 3 seconds, which can be calibrated), and a parking command is issued.

[0041] Therefore, in this embodiment, the vehicle sensor can perceive the surrounding environment and the user's action information in real time, and transmit the action information and instruction information to the domain controller. The domain controller can analyze the action information to obtain the user's parking intention, and then control the current vehicle to perform the corresponding parking operation in the direction that the target can be parked, according to the parking intention.

[0042] As one possible approach, during the detection of a vehicle's foot touching the ground projection point, this embodiment of the application can control the vehicle to work collaboratively with the ground near-field visual sensor and ultrasonic touch detection unit mounted on the vehicle body. First, the coordinate area of ​​the ground projection point is locked, and then high-frequency motion capture is performed on the area. When a vertically downward limb contact action is detected and the contact position coincides with the coordinates of the projection point, it is determined to be a valid foot touch operation. The detection result is used by the domain controller to confirm the user's intention to select the parking direction.

[0043] Secondly, during the detection of the vehicle's gaze projection point and voice commands, this embodiment can control the vehicle to locate the user's eye gaze direction through the onboard gaze tracking sensor, continuously determine whether the user's gaze is stably focused on the area where the ground projection point is located and maintain a continuous lock state; at the same time, the onboard voice pickup unit collects the parking-related commands issued by the user, performs joint verification of the gaze lock signal and the voice command signal, and determines that the double matching is valid. The joint verification result is used by the domain controller to confirm the user's intention to select the parking direction.

[0044] Therefore, the embodiments of this application can trigger automatic parking without manual operation, which can be well adapted to scenarios where both hands are holding objects, improving the convenience of parking operation and the safety of use.

[0045] In summary, this application embodiment identifies the driver's identity through vehicle body sensors, initiates the automatic parking program in advance, identifies surrounding obstacles, and analyzes the parking direction through the domain controller. The parking direction is then projected onto an open ground as a projection point. This allows users to initiate parking by tapping the projection point on the ground with their foot or by the domain controller recognizing the driver's intention to start parking through the vehicle body sensors, even when their hands are not fully engaged. This solves the user pain point of difficulty in initiating automatic parking when their hands are not fully engaged, and improves the convenience and functionality of vehicle parking.

[0046] The execution logic of the projection-based automatic parking method of this application will be described below with reference to the accompanying drawings.

[0047] Figure 2This is a schematic diagram illustrating the execution logic of the projection-based automatic parking method of this application. Figure 2 As shown, the execution process of the projection-based automatic parking method of this application is as follows: S201: When the user walks to a certain distance of 3m (calibrable) from the vehicle and physical features such as a key or physiological features such as the user's face are detected, the vehicle is activated and the automatic parking program is started. S202: Identify surrounding environmental features through vehicle perimeter sensors and transmit them to the domain controller; S203: After analysis, the domain controller identifies the direction in which the vehicle can park and surrounding obstacles, and projects the direction in which the vehicle can park onto the open ground in the form of projection points. S204: The user can click the projection point in the corresponding parking direction with their foot, or point to the projection point in the corresponding direction with their eyes and fingers, and issue a parking command. The relevant command information and action information are transmitted to the domain controller through the sensor, and the parking action in the corresponding direction can be executed.

[0048] According to the projection-based automatic parking method proposed in this application, the distance between the target user and the current vehicle is obtained, and it is determined whether the distance is less than a preset distance threshold. In response to the distance being less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected. When at least one physical feature or at least one physiological feature is detected, the current vehicle environment information is obtained, and the corresponding environmental features are extracted and input into a preset domain controller to identify the parking direction and obstacle information of the current vehicle. The parking direction is then projected onto an open ground in the form of projection points. When it is detected that the target user selects a target parking direction projected onto an open ground using at least one preset method, the current vehicle is controlled to perform a parking operation in the target parking direction. This application, by identifying user information in advance and activating the automatic parking program to identify the vehicle's surrounding environment and projecting the direction onto the ground in the form of projection points, facilitates automatic parking when the user is carrying items outside the vehicle and it is inconvenient to operate the vehicle. The vehicle parks itself in front of the user, allowing the user to directly enter the vehicle, thus improving user convenience and comfort.

[0049] Secondly, a projection-based automatic parking device according to an embodiment of this application will be described with reference to the accompanying drawings.

[0050] Figure 3 This is a block diagram of a projection-based automatic parking device according to an embodiment of this application.

[0051] like Figure 3 As shown, the projection-based automatic parking device 10 includes a feature detection module 100, an extraction module 200, and a parking module 300.

[0052] The feature detection module 100 is used to obtain the distance between the target user and the current vehicle, and to determine whether the distance is less than a preset distance threshold. In response to the distance being less than the preset distance threshold, it detects at least one physical feature or at least one physiological feature of the target user.

[0053] The extraction module 200 is used to acquire current vehicle environment information when at least one physical feature or at least one physiological feature is detected, extract the environmental features corresponding to the environmental information, and input the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and project the parking direction onto the open ground in the form of projection points.

[0054] The parking module 300 is used to control the current vehicle to perform a parking operation in the target parking direction when it detects that the target user has selected a target parking direction projected onto an open ground in at least one preset method.

[0055] Optionally, in one embodiment of this application, the feature detection module 100 includes an acquisition unit and a matching unit.

[0056] The acquisition unit is used to acquire the location perception information of the current vehicle within the target area, so as to determine the relative distance between the target user and the vehicle body of the current vehicle based on the location perception information.

[0057] The matching unit is used to compare the relative distance state with the preset distance conditions to obtain the corresponding distance matching result, and to perform a preset multimodal feature recognition operation based on the distance matching result when the preset distance conditions are met, and to collect at least one physical feature or at least one physiological feature corresponding to the target user.

[0058] Optionally, in one embodiment of this application, the extraction module 200 includes: a parsing unit, a fusion unit, and a projection unit.

[0059] The parsing unit is used to activate the vehicle's surrounding environment perception sensors to collect current vehicle environment information and parse the environment information to extract corresponding environmental features, including vehicle spatial distribution information, obstacle location information, and ground projection area information.

[0060] The fusion unit is used to input environmental features into the domain controller for fusion calculation, obtain the corresponding fusion calculation results, divide the vehicle passable space and obstacle space based on the fusion calculation results to generate corresponding division results, and determine the parking direction and obstacle information of the current vehicle that meet the preset safety requirements based on the division results.

[0061] The projection unit is used to generate projection point commands in the corresponding direction based on the parking direction and obstacle information, and to control the preset projection device to project the parking direction as projection points onto the ground area that meets the preset open space requirements through the projection point commands.

[0062] Optionally, in one embodiment of this application, the parking module 300 includes: a first judgment unit, a second judgment unit, and an execution unit.

[0063] The first judgment unit is used to determine whether the target user is the target vehicle owner or the target authorized user based on at least one physiological characteristic, and to obtain the target user's action information if the target user is the target vehicle owner or the target authorized user.

[0064] The second judgment unit is used to determine, based on action information, whether the target user has selected a parking direction projected onto an open ground through at least one preset method. The at least one preset method includes the target user clicking the corresponding projection point on the open ground with their foot, or the target user's gaze lingering on the projection point in the corresponding direction for a duration exceeding a preset time threshold, and simultaneously issuing a parking command.

[0065] The execution unit is used to respond to a target user selecting a target parking direction projected onto an open ground through at least one preset method, and to determine the target user's parking intention through the domain controller, so as to control the current vehicle to perform a parking operation in the target parking direction according to the parking intention.

[0066] It should be noted that the foregoing explanation of the projection-based automatic parking method embodiment also applies to the projection-based automatic parking device of this embodiment, and will not be repeated here.

[0067] The projection-based automatic parking device proposed in this application includes a feature detection module 100, used to acquire the distance between the target user and the current vehicle, and determine whether the distance is less than a preset distance threshold. In response to the distance being less than the preset distance threshold, it detects at least one physical feature or at least one physiological feature of the target user. An extraction module 200 is used to acquire the current vehicle environment information when at least one physical feature or at least one physiological feature is detected, extract the environmental features corresponding to the environmental information, and input the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and project the parking direction onto an open ground in the form of projection points. A parking module 300 is used to control the current vehicle to perform a parking operation in the target parking direction when it is detected that the target user selects the target parking direction projected onto the open ground in at least one preset method. This application enables the automatic parking program by recognizing user information in advance, identifying the surrounding environment of the vehicle, and projecting the direction of the parking onto the ground in the form of projection points. This makes it convenient for users to activate automatic parking when they are carrying items outside the vehicle and it is inconvenient to operate the vehicle. The vehicle then parks itself in front of the user, who can then get into the car directly, thus improving the user's convenience and comfort.

[0068] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include: The memory 401, the processor 402, and the computer program stored on the memory 401 and capable of running on the processor 402.

[0069] When the processor 402 executes the program, it implements the projection-based automatic parking method provided in the above embodiments.

[0070] Furthermore, the vehicle also includes: Communication interface 403 is used for communication between memory 401 and processor 402.

[0071] The memory 401 is used to store computer programs that can run on the processor 402.

[0072] Memory 401 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0073] If the memory 401, processor 402, and communication interface 403 are implemented independently, then the communication interface 403, memory 401, and processor 402 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of representation, Figure 4 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0074] Optionally, in a specific implementation, if the memory 401, processor 402, and communication interface 403 are integrated on a single chip, then the memory 401, processor 402, and communication interface 403 can communicate with each other through an internal interface.

[0075] Processor 402 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0076] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described projection-based automatic parking method.

[0077] This application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-described projection-based automatic parking method.

[0078] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0079] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0080] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0081] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0082] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0083] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0084] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0085] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A projection-based automatic parking method, characterized in that, Includes the following steps: The distance between the target user and the current vehicle is obtained, and it is determined whether the distance is less than a preset distance threshold. In response to the distance being less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected. When the at least one physical feature or the at least one physiological feature is detected, the current vehicle environment information is obtained, and the environmental features corresponding to the environmental information are extracted. The environmental features are then input into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and the parking direction is projected onto an open ground in the form of projection points. When it is detected that the target user selects a target parking direction projected onto an open ground in at least one preset method, the current vehicle is controlled to perform a parking operation in the target parking direction.

2. The method according to claim 1, characterized in that, The step of obtaining the distance between the target user and the current vehicle, and determining whether the distance is less than a preset distance threshold, and in response to the case that the distance is less than the preset distance threshold, detecting at least one physical feature or at least one physiological feature of the target user, includes: The location perception information of the current vehicle within the target area is obtained, so as to determine the relative distance between the target user and the vehicle body of the current vehicle based on the location perception information; The relative distance state is compared with the preset distance conditions to obtain the corresponding distance matching result. Based on the distance matching result, when the preset distance conditions are met, a preset multimodal feature recognition operation is performed to collect at least one physical feature or at least one physiological feature corresponding to the target user.

3. The method according to claim 2, characterized in that, The process of acquiring the current vehicle environment information, extracting the corresponding environmental features, and inputting the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and projecting the parking direction onto an open ground in the form of projection points, includes: The vehicle's surrounding environment perception sensor is activated to collect the vehicle's environmental information, and the environmental information is analyzed to extract corresponding environmental features, including vehicle spatial distribution information, obstacle location information, and ground projection area information. The environmental features are input to the domain controller for fusion calculation to obtain the corresponding fusion calculation result. The vehicle passable space and obstacle space are divided according to the fusion calculation result to generate the corresponding division result. The parking direction of the current vehicle that meets the preset safety requirements and the obstacle information are determined according to the division result. Based on the parking direction and the obstacle information, a projection point instruction is generated in the corresponding direction, and the preset projection device is controlled by the projection point instruction to project the parking direction as a projection point onto a ground area that meets the preset open space requirements.

4. The method according to claim 3, characterized in that, When the system detects that the target user has selected a target parking direction projected onto an open ground using at least one preset method, it controls the current vehicle to perform a parking operation in the target parking direction, including: Based on the at least one physiological characteristic, determine whether the target user is the target vehicle owner or the target authorized user, and if the target user is the target vehicle owner or the target authorized user, obtain the target user's action information; Based on the action information, it is determined whether the target user selects a parking direction projected onto an open ground through at least one preset method. The at least one preset method includes the target user clicking the corresponding projection point on the open ground with their foot, or the target user's gaze lingering on the projection point in the corresponding direction for a duration exceeding a preset time threshold, while issuing a parking command. In response to the target user selecting a target parking direction projected onto an open ground through at least one preset method, the domain controller determines the target user's parking intention and controls the current vehicle to perform a parking operation in the target parking direction according to the parking intention.

5. An automatic parking device based on projection, characterized in that, include: The feature detection module is used to obtain the distance between the target user and the current vehicle, and determine whether the distance is less than a preset distance threshold. In response to the distance being less than the preset distance threshold, at least one physical feature or at least one physiological feature of the target user is detected. An extraction module is used to acquire the current vehicle environment information when the at least one physical feature or the at least one physiological feature is detected, extract the environmental features corresponding to the environmental information, and input the environmental features into a preset domain controller to identify the parking direction and obstacle information of the current vehicle, and project the parking direction onto an open ground in the form of projection points. The parking module is used to control the current vehicle to perform a parking operation in the target parking direction when it detects that the target user has selected a target parking direction projected onto an open ground in at least one preset method.

6. The apparatus according to claim 5, characterized in that, The feature detection module includes: The acquisition unit is used to acquire the location perception information of the current vehicle in the target area, so as to determine the relative distance state between the target user and the vehicle body of the current vehicle based on the location perception information; The matching unit is used to compare the relative distance state with the preset distance conditions to obtain the corresponding distance matching result, and according to the distance matching result, when the preset distance conditions are met, to perform a preset multimodal feature recognition operation to collect at least one physical feature or at least one physiological feature corresponding to the target user.

7. The apparatus according to claim 6, characterized in that, The extraction module includes: The parsing unit is used to activate the vehicle's surrounding environment perception sensor to collect the current vehicle's environmental information and parse the environmental information to extract corresponding environmental features, wherein the environmental features include vehicle spatial distribution information, obstacle location information and ground projection area information. The fusion unit is used to input the environmental features into the domain controller for fusion calculation, obtain the corresponding fusion calculation result, divide the vehicle passable space and obstacle space through the fusion calculation result to generate the corresponding division result, and determine the parking direction of the current vehicle that meets the preset safety requirements and the obstacle information based on the division result. The projection unit is used to generate projection point instructions in the corresponding direction based on the parking direction and the obstacle information, and to control a preset projection device to project the parking direction as projection points onto a ground area that meets preset open space requirements through the projection point instructions.

8. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the projection-based automatic parking method as described in any one of claims 1-4.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the projection-based automatic parking method as described in any one of claims 1-4.

10. A computer program product, comprising a computer program, characterized in that, The computer program is executed to implement the projection-based automatic parking method as described in any one of claims 1-4.

Images