Control method of target vehicle, parking device, and target vehicle

Abstract

The application discloses a target vehicle control method, a parking device and a target vehicle. The method comprises the following steps: obtaining target parking space information in response to a received parking instruction, wherein the target parking space information is used to represent the positional relationship between multiple parking spaces; generating multiple parking space images corresponding to the multiple parking spaces based on the target parking space information, and displaying the multiple parking space images at a preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces; receiving a posture image of a target object, wherein the posture image is used to represent the parking intention of the target object; determining a target parking space image in the multiple parking space images based on the posture image of the target object; and controlling the target vehicle to move to a target parking space based on the target parking space image, wherein the target parking space is a parking space corresponding to the target parking space image. The application solves the technical problem of low efficiency in selecting a parking space when parking in the prior art.

Description

Technical Field

[0001] This invention relates to the field of driver assistance systems, and more specifically, to a control method for a target vehicle, a parking device, and a target vehicle. Background Technology

[0002] With economic development and the continuous improvement of people's living standards, cars are no longer just a means of transportation; their development has become more diversified, and parking systems are being used more widely. However, existing parking systems focus more on the realization of parking functions. When selecting a parking space, users need to get out of the car to check the specific parking space, which results in low efficiency when selecting a parking space.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This invention provides a method for controlling a target vehicle, a parking device, and a target vehicle, to at least solve the technical problem of low efficiency in selecting parking spaces when parking in the prior art.

[0005] According to one aspect of the present invention, a method for controlling a target vehicle is provided, comprising: in response to a received parking instruction, acquiring target parking space information, wherein the target parking space information is used to represent the positional relationship between multiple parking spaces; generating multiple parking space images corresponding to the multiple parking spaces based on the target parking space information, and displaying the multiple parking space images at a preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces; receiving a posture image of a target object, wherein the posture image is used to represent the parking intention of the target object; determining a target parking space image among the multiple parking space images based on the posture image of the target object; and controlling the target vehicle to move to the target parking space based on the target parking space image, wherein the target parking space is the parking space corresponding to the target parking space image.

[0006] Optionally, obtaining target parking space information includes: acquiring multiple video streams, wherein the multiple video streams contain initial parking space information, and the multiple video streams are acquired by multiple cameras set at different locations; and performing perceptual fusion on the initial parking space information in the multiple video streams to obtain target parking space information.

[0007] Optionally, determining the target parking space image among multiple parking space images based on the pose image of the target object includes: performing masking processing on the pose image to obtain a mask image; determining a first key point and a second key point of the target object based on the mask image, wherein the first key point is a key point corresponding to a first part of the target object, and the second key point is a key point corresponding to a second part of the target object; and determining the target parking space image among multiple parking space images based on the direction of the line connecting the first key point and the second key point.

[0008] Optionally, based on the direction of the line connecting the first key point and the second key point, the target parking space image among multiple parking space images is determined, including: determining the first coordinate of the first key point in the target coordinate system; determining the second coordinate of the second key point in the target coordinate system; determining the first line segment based on the first and second coordinates; determining the pointing coordinate of the extension line of the first line segment at a preset display position; determining multiple parking space coordinates of the multiple parking space images in the target coordinate system; determining the target parking space coordinate based on the distance information between the pointing coordinate and the multiple parking space coordinates, wherein the target parking space coordinate is the parking space coordinate with the shortest distance to the pointing coordinate among the multiple parking space coordinates; and determining the target parking space image corresponding to the target parking space coordinate among the multiple parking space images.

[0009] Optionally, before controlling the target vehicle to move to the target parking space based on the target parking space image, the method includes: sending a prompt message, wherein the prompt message is used to remind the target object whether the target parking space image is the parking space image corresponding to the parking space to be parked; and responding to the received confirmation instruction from the target object, controlling the target vehicle to move to the target parking space based on the target parking space image, wherein the confirmation instruction is used to confirm that the target parking space image is the parking space image corresponding to the parking space to be parked.

[0010] Optionally, the initial parking space information in multiple video streams is perceptually fused to obtain the target parking space information, including: acquiring the installation positions of multiple cameras on the target vehicle; and perceptually fusion of the initial parking space information in multiple video streams based on the installation positions to obtain the target parking space information.

[0011] Optionally, in response to a received parking instruction, obtaining target parking space information includes: obtaining voice information of the target object; and generating a parking instruction based on the voice information if the voice information contains target voice, wherein the target voice is voice related to the parking information of the target vehicle.

[0012] According to another aspect of the present invention, a parking device for a target vehicle is also provided, comprising: a first acquisition module, configured to acquire target parking space information in response to a received parking instruction, wherein the target parking space information is used to represent the positional relationship between multiple parking spaces; a generation module, configured to generate multiple parking space images corresponding to the multiple parking spaces based on the target parking space information, and display the multiple parking space images at a preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces; a receiving module, configured to receive a posture image of a target object, wherein the posture image is used to represent the parking intention of the target object; a determining module, configured to determine the target parking space image among the multiple parking space images based on the posture image of the target object; and a control module, configured to control the target vehicle to move to the target parking space based on the target parking space image, wherein the target parking space is the parking space corresponding to the target parking space image.

[0013] According to another aspect of the present invention, a computer-readable storage medium is also provided, characterized in that the computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the control method for the target vehicle described above.

[0014] According to another aspect of the present invention, a target vehicle is also provided, characterized in that it includes: one or more processors; a storage device for storing one or more programs; and a control method for the target vehicle that, when the one or more programs are executed by the one or more processors, causes the one or more processors to perform any of the above-described methods.

[0015] In this embodiment of the invention, in response to a received parking instruction, target parking space information is obtained, wherein the target parking space information represents the positional relationship between multiple parking spaces; multiple parking space images corresponding to the multiple parking spaces are generated based on the target parking space information, and the target parking space images are displayed at a preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces; a posture image of the target object is received, wherein the posture image represents the parking intention of the target object; the target parking space image is determined from the multiple parking space images based on the posture image of the target object; and the target vehicle is controlled to move to the target parking space based on the target parking space image, wherein the target parking space is the parking space corresponding to the target parking space image, thereby improving the efficiency of parking space selection during parking. It is noteworthy that multiple parking space images corresponding to multiple parking spaces can be displayed at a preset display position inside the vehicle, allowing the user to quickly select the target parking space image from the multiple parking space images using gestures. This simplifies the steps in the prior art where the user needs to get out of the car to check the actual parking space they want to park in, and then control the vehicle based on the actual confirmed situation so that the vehicle can park in the selected parking space. This technology achieves the goal of improving the efficiency of parking space selection, thereby solving the technical problem of low efficiency in selecting parking spaces when parking in existing technologies. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0017] Figure 1 This is a flowchart of a control method for a target vehicle according to an embodiment of the present invention;

[0018] Figure 2 A flowchart of an optional finger parking interaction system according to an embodiment of the present invention;

[0019] Figure 3This is a schematic diagram illustrating an optional user selection of a parking space according to an embodiment of the present invention;

[0020] Figure 4 This is a schematic diagram of an optional intelligent parking system according to an embodiment of the present invention;

[0021] Figure 5 This is a schematic diagram of the structure of a parking device for a target vehicle according to an embodiment of the present invention. Detailed Implementation

[0022] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0024] Example 1

[0025] According to an embodiment of the present invention, an embodiment of a control method for a target vehicle is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0026] Figure 1 This is a flowchart of a target vehicle control method according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0027] Step S102: In response to the received parking instruction, obtain target parking space information, wherein the target parking space information is used to represent the positional relationship between multiple parking spaces.

[0028] Optionally, the vehicle involved in the embodiments of the present invention may be an autonomous vehicle with an intelligent parking system, a vehicle driven by a user with an intelligent parking system, or an autonomous new energy vehicle with an intelligent parking system, but it is not limited thereto and is not specifically limited in the embodiments of the present invention.

[0029] The parking command mentioned above can be any command issued by the user that enables the vehicle to start the intelligent parking system. For example, it can be a voice command or a command input by the user. No specific limitation is made in this embodiment of the invention.

[0030] The target parking space mentioned above can be the parking space where the current vehicle wants to park; the target parking space information may include, but is not limited to, the distance between the target parking space and the current vehicle, the surrounding environment information of the target parking space, and the location information of the target parking space relative to other parking spaces.

[0031] The aforementioned acquisition of target parking space information can be obtained through a target recognition algorithm. The target recognition algorithm can be any kind of algorithm, such as a region-based convolutional neural network algorithm (R-CNN algorithm), a deep neural network-based object recognition and localization algorithm (YOLO algorithm), a single-order multi-layer target detection model algorithm (SSD algorithm), but it is not limited to these.

[0032] In one alternative embodiment, in response to a parking command issued by a user, the intelligent parking system obtains target parking space information through a target recognition algorithm.

[0033] Step S104: Generate multiple parking space images corresponding to multiple parking spaces based on the target parking space information, and display the multiple parking space images at the preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces.

[0034] The aforementioned multiple parking space images are obtained based on target recognition algorithms, cameras installed at different locations on the vehicle, and Head-Up Display (HUD) augmented reality (AR) technology, as well as the establishment of a target coordinate system.

[0035] The aforementioned multiple parking space images can be virtual parking space images displayed on the windshield by scanning multiple actual parking spaces using multiple cameras, HUD and AR technologies. These images can be any type of image, such as a rectangle or polygon. In this embodiment, a rectangle is used as an example for illustration. The virtual parking space images can also be displayed on the screen of the interactive interface.

[0036] The aforementioned method of generating multiple parking space images corresponding to multiple parking spaces based on target parking space information first involves acquiring the target parking space information through a target recognition algorithm. Then, it involves perceptual fusion of multiple parking space images captured by cameras installed at different locations on the vehicle, establishing a coordinate system so that the perceptually fused multiple parking space images are unified on a single coordinate system and correspond to the actual target parking space information. Perceptual fusion involves the alignment and fusion of data from different sensors in time and space. The final result will improve the perception capability of the autonomous driving system.

[0037] The aforementioned preset display position can be any location on the vehicle capable of displaying multiple parking space images. In this embodiment, the windshield of a car is used as an example for explanation.

[0038] The aforementioned display of multiple parking space images at preset display locations on the target vehicle can be achieved through HUD and AR technologies. HUD can project important information onto the glass, allowing the driver to see important information without looking down. AR technology overlays digital images onto the real world, making the information projected by HUD blend seamlessly with the real driving environment.

[0039] In one optional embodiment, after obtaining the target parking space information, the multiple parking space images captured by the camera are first perceptually fused and a coordinate system is established so that the multiple parking space images after perceptual fusion are unified on a coordinate system and correspond to the actual target parking space information. Then, the multiple parking space images are displayed on the windshield of the vehicle (i.e., the preset display position) through HUD and AR technology.

[0040] Step S106: Receive the pose image of the target object, wherein the pose image is used to represent the parking intention of the target object.

[0041] The target object mentioned above could be the user operating the current vehicle.

[0042] The aforementioned posture image can first be obtained by capturing the user's body posture image through an in-vehicle camera. This camera capture can be achieved by setting a Region of Interest (ROI) at the camera's location to ensure the captured user is the driver. Secondly, the initial human posture image is recognized using the holistic module of Mediapipe, an open-source framework designed for Graphics Processing Units (GPUs) or Central Processing Units (CPUs) based on convolutional neural networks. Mediapipe's holistic module includes optimized posture, facial, and hand components, each running in real-time. When all three components are included, over 540 key points can be identified (33 postures, 21 per hand, and 468 facial feature points). In this embodiment, gesture recognition is used as an example.

[0043] The aforementioned posture image is used to represent the parking intention of the target object. It can be based on the recognized posture image to establish a ray equation based on the wrist and fingers. The ray equation is located in the established coordinate system. The ray equation is an equation that can represent the extension direction of the target point. It has only one endpoint and the other end can extend infinitely. The parking intention can represent the user's choice to park the vehicle in a specific parking space.

[0044] In one optional embodiment, the user's initial posture image is first captured by an in-vehicle camera. Then, the captured initial posture image is identified by the holistic module in Mediapipe, which is based on a convolutional neural network, to obtain a posture image. Finally, a ray equation is established based on the wrist and fingers in the posture image. The direction of the extension line of the ray equation can represent the parking intention of the target object.

[0045] Step S108: Determine the target parking space image from multiple parking space images based on the pose image of the target object.

[0046] The pose image of the target object mentioned above was achieved using Mediapipe's holistic module and by establishing the corresponding ray equation.

[0047] In one optional embodiment, the parking space image corresponding to the parking space that the user wants to park in can be determined based on the acquired user's gesture (i.e., posture image), wherein the parking space image can be the target parking space image mentioned above.

[0048] Step S110: Control the target vehicle to move to the target parking space based on the target parking space image, wherein the target parking space is the parking space corresponding to the target parking space image.

[0049] The above-mentioned method of controlling the target vehicle to move to the target parking space based on the target parking space image can firstly confirm with the user via voice whether to park in the selected target parking space image. Specifically, if the user's gesture lingers on the target parking space image for more than 2 seconds, it indicates that the user has selected the target parking space image. Secondly, based on the user's confirmation, the parking target information is transmitted to the Highly Autonomous Driving (HAD) controller to execute the automatic parking procedure, enabling the vehicle to move to the target parking space.

[0050] In one alternative embodiment, once the user confirms the target parking space image, the parking target information can be passed to HAD to execute the automatic parking procedure, enabling the vehicle to move to the target parking space.

[0051] In this embodiment of the invention, in response to a received parking instruction, target parking space information is obtained, wherein the target parking space information represents the positional relationship between multiple parking spaces; multiple parking space images corresponding to the multiple parking spaces are generated based on the target parking space information, and the target parking space images are displayed at a preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces; a posture image of the target object is received, wherein the posture image represents the parking intention of the target object; the target parking space image is determined from the multiple parking space images based on the posture image of the target object; and the target vehicle is controlled to move to the target parking space based on the target parking space image, wherein the target parking space is the parking space corresponding to the target parking space image, thereby improving the efficiency of parking space selection during parking. It is noteworthy that multiple parking space images corresponding to multiple parking spaces can be displayed at a preset display position inside the vehicle, allowing the user to quickly select the target parking space image from the multiple parking space images using gestures. This simplifies the steps in the prior art where the user needs to get out of the car to check the actual parking space they want to park in, and then control the vehicle based on the actual confirmed situation so that the vehicle can park in the selected parking space. This technology achieves the goal of improving the efficiency of parking space selection, thereby solving the technical problem of low efficiency in selecting parking spaces when parking in existing technologies.

[0052] Optionally, obtaining target parking space information includes: acquiring multiple video streams, wherein the multiple video streams contain initial parking space information, and the multiple video streams are acquired by multiple cameras set at different locations; and performing perceptual fusion on the initial parking space information in the multiple video streams to obtain target parking space information.

[0053] The video stream mentioned above refers to the transmission of video data.

[0054] In one optional embodiment, initial parking space information is first collected by cameras installed at different locations on the vehicle to obtain a corresponding video stream. Then, the initial parking space information in the video stream is perceptually fused to obtain the target parking space information.

[0055] Optionally, determining the target parking space image among multiple parking space images based on the pose image of the target object includes: performing masking processing on the pose image to obtain a mask image; determining a first key point and a second key point of the target object based on the mask image, wherein the first key point is a key point corresponding to a first part of the target object, and the second key point is a key point corresponding to a second part of the target object; and determining the target parking space image among multiple parking space images based on the direction of the line connecting the first key point and the second key point.

[0056] The mask mentioned above is a string of binary code that performs a bitwise AND operation on the target field, masking the current input bits. The source code and the mask are then subjected to bitwise or logical operations to obtain new operands, which involve bitwise operations such as OR and AND.

[0057] The mask image described above can be obtained by modifying the pixels in the ROI region of an image to highlight them, while blurring the pixels in the non-ROI region to avoid affecting the ROI region.

[0058] The first part mentioned above can be the driver's wrist, and the first key point can be a specific point on the wrist, which is not specifically limited in this embodiment; the second part can be the driver's fingers, and the second key point can be the point where the fingertip is pointing, which is not specifically limited in this embodiment.

[0059] The aforementioned line direction based on the first and second key points can first be established in the target coordinate system based on the first and second key points, then the other end of the ray equation is extended, and finally the parking space image that intersects the extension line and is closest to the current vehicle is the target parking space image.

[0060] In one optional embodiment, the pose image is first masked to obtain a mask image. Then, the key points of the driver's (i.e. the target object) elbow and the points where the fingertips are pointing are determined based on the mask image. A ray equation is established based on the key points of the elbow and the points where the fingertips are pointing. Based on the extension of the equation and the distance to the current vehicle, the target parking space image among multiple parking space images can be determined.

[0061] Optionally, based on the direction of the line connecting the first key point and the second key point, the target parking space image among multiple parking space images is determined, including: determining the first coordinate of the first key point in the target coordinate system; determining the second coordinate of the second key point in the target coordinate system; determining the first line segment based on the first and second coordinates; determining the pointing coordinate of the extension line of the first line segment at a preset display position; determining multiple parking space coordinates of the multiple parking space images in the target coordinate system; determining the target parking space coordinate based on the distance information between the pointing coordinate and the multiple parking space coordinates, wherein the target parking space coordinate is the parking space coordinate with the shortest distance to the pointing coordinate among the multiple parking space coordinates; and determining the target parking space image corresponding to the target parking space coordinate among the multiple parking space images.

[0062] The first coordinate mentioned above can be the corresponding coordinate of the elbow key point in the target coordinate system; the second coordinate can be the corresponding coordinate of the fingertip pointing point in the target coordinate system; the first line segment can be a ray equation established based on the first and second coordinates.

[0063] In one optional embodiment, firstly, the first coordinates and second coordinates of the first key point and the second key point in the target coordinate system are determined. Based on the first coordinates and the second coordinates, the ray equation is determined. The pointing coordinates of the extension line of the ray equation at the preset display position are determined. Secondly, multiple parking space coordinates of multiple parking space images in the target coordinate system are determined. Based on the pointing coordinates and the parking space coordinates, the parking space coordinates with the shortest distance to the pointing coordinates can be determined. Finally, the corresponding parking space image can be determined based on the target parking space coordinates.

[0064] Optionally, before controlling the target vehicle to move to the target parking space based on the target parking space image, the method includes: sending a prompt message, wherein the prompt message is used to remind the target object whether the target parking space image is the parking space image corresponding to the parking space to be parked; and responding to the received confirmation instruction from the target object, controlling the target vehicle to move to the target parking space based on the target parking space image, wherein the confirmation instruction is used to confirm that the target parking space image is the parking space image corresponding to the parking space to be parked.

[0065] The aforementioned prompts can be any type of information that can prompt the driver, such as voice or text. In this embodiment, voice is used as an example. For example, it could be "Please confirm whether to park the vehicle in the target parking space corresponding to the selected parking space image." The confirmation command can be any confirmation command issued by the driver, such as voice or text. In this embodiment, voice is used as an example. For example, it could be "Confirm that the vehicle is parked in the target parking space corresponding to the selected parking space image."

[0066] In one optional embodiment, the system first confirms with the user via voice whether the target parking space image is the same as the parking space to be parked. After receiving the user's voice confirmation that the target parking space image is the same as the parking space to be parked, the system controls the vehicle to start the automatic parking system and move the vehicle to the target parking space.

[0067] Optionally, the initial parking space information in multiple video streams is perceptually fused to obtain the target parking space information, including: acquiring the installation positions of multiple cameras on the target vehicle; and perceptually fusion of the initial parking space information in multiple video streams based on the installation positions to obtain the target parking space information.

[0068] In one optional embodiment, the installation positions of multiple cameras in the current vehicle are first obtained, such as the driver's seat position, the passenger seat position, and the rearview mirror position. Then, based on the installation positions, the initial parking space information in the multiple video streams obtained by the multiple cameras is perceptually fused to obtain the target parking space information.

[0069] Optionally, in response to a received parking instruction, obtaining target parking space information includes: obtaining voice information of the target object; and generating a parking instruction based on the voice information if the voice information contains target voice, wherein the target voice is voice related to the parking information of the target vehicle.

[0070] The target voice mentioned above can be a voice issued by the driver that can confirm the current parking information of the vehicle, such as "Park the vehicle in the parking space I selected with my finger" or other voice information.

[0071] In one optional embodiment, the driver's voice information is first obtained, and when the voice information contains the current vehicle's parking information, a parking instruction is generated based on the parking information in the voice information.

[0072] The following is combined Figures 2 to 4 This embodiment will be further described.

[0073] The overall technical solution of this invention is as follows:

[0074] 1. Users can activate the intelligent parking program in the vehicle's infotainment system via voice commands.

[0075] 2. After the parking procedure is initiated, the system fuses the perception data from the in-vehicle camera and the site camera, unifying the parking spaces identified by both cameras onto a single coordinate system. Then, using a target recognition algorithm, the system detects the parking space information and enhances its display on the HUD screen. The approximate effect is as follows: Figure 3 As shown.

[0076] 3. Voice prompts allow users to select their target parking space using their fingers. The in-car camera detects the user's behavior. Detection consists of two main parts: first, gesture detection using Mediapipe based on a convolutional neural network estimates the user's posture. For example... Figure 3 The direction of the line connecting the wrist and fingertips is calculated, and then the orientation of the connection of key points is used to determine the user's target.

[0077] 4. The calculated target parking space for the user is enhanced and displayed on the HUD, such as... Figure 3 As shown in the image. After the user's gesture remains in place for 2 seconds, the system will confirm with the user, via voice, whether the gesture has stopped at the displayed target.

[0078] 5. Once the user confirms via voice, the entire interaction process is complete. The final parking goal is then transmitted to the HAD to execute subsequent automatic parking actions.

[0079] Figure 2 A flowchart of an optional finger parking interaction system according to an embodiment of the present invention is shown below. Figure 2 As shown, the flowchart includes the following steps:

[0080] Step S201: The user gives a voice command to stop the vehicle;

[0081] Step S202: The vehicle initiates the parking procedure;

[0082] Step S203: Fuse multi-sensor data, establish a coordinate system, and display the parking space image in the coordinate system;

[0083] Step S204: Enhance the display of parking spaces using a head-up display;

[0084] Step S205: The voice prompts the user to select the target parking space using the target finger;

[0085] Step S206: The user selects the target parking space using their finger;

[0086] Step S207: Confirm user intent through gesture judgment;

[0087] Step S208: Enhance the display of the parking space on the head-up display;

[0088] Step S209: Ask the user via voice whether they confirm selecting the parking space;

[0089] Step S210: The user confirms the selection of the parking space via voice.

[0090] Step S211: Transmit the parking target information to HAD to execute the automatic parking procedure so that the vehicle can move to the target parking space.

[0091] Figure 3 This is a schematic diagram of an optional user selection of parking spaces according to an embodiment of the present invention, such as... Figure 3 As shown, users can select parking spaces using wrist key points and fingertip pointing points. The HUD enhances the selected parking space with AR and displays it on the windshield of the current car. The rectangular area represents the windshield of the current car, and multiple small squares represent multiple parking space images.

[0092] Figure 4 The diagram shows an optional intelligent parking system according to an embodiment of the present invention. The system includes: a forward-facing camera 40, a panoramic camera 41, an Occupancy Monitoring System (OMS) 42, a Driver Monitoring System (DMS) 43, a Telematics Box (Tbox) 44, a Cockpit Space Center (CSC) 45, a HAD 46, a microphone 47, a speaker 48, and a Head-Up Display (HUD) 49.

[0093] The forward-facing camera 40, panoramic camera 41, OMS 42, and DMS 43 are connected to CSC 45 to transmit captured video streams to CSC 45. Tbox 44 is connected to CSC 45, enabling the vehicle to process the video streams via the network to obtain parking space information. CSC 45 is connected to HAD 46 and can transmit parking commands to HAD 46 to enable HAD 46 to control the vehicle to park automatically. CSC 45 is connected to microphone 47, speaker 48, and HUD 49. It can prompt the user to confirm the target parking space through microphone 47, obtain the user's parking command through speaker 48, and enhance the display of the target parking space image on the windshield through HUD 49.

[0094] This invention provides an in-vehicle finger-based parking system. Building upon the vehicle's existing automatic parking function, it utilizes voice recognition technology for simple user interaction, target detection algorithms for parking space identification, and AR-enhanced parking space display on the HUD. Human behavior detection determines the user's parking intention, and AR augmented reality is applied to the HUD system. This achieves dynamic recognition of the user's parking target. Compared to existing technologies, the overall interaction allows users to select parking spaces and complete the entire parking process in a completely natural state (voice and finger), significantly enhancing the technological sophistication and enjoyment of the interaction.

[0095] Example 2

[0096] According to another aspect of the present invention, a parking device for a target vehicle is also provided. This device can execute the target vehicle control method provided in Embodiment 1 above. The specific implementation and preferred application scenarios are the same as those in Embodiment 1 above, and will not be repeated here.

[0097] Figure 5 This is a schematic diagram of the structure of a parking device for a target vehicle according to an embodiment of the present invention, as shown below. Figure 5 As shown, the device includes: a first acquisition module 50, configured to acquire target parking space information in response to a received parking instruction, wherein the target parking space information represents the positional relationship between multiple parking spaces; a generation module 52, configured to generate multiple parking space images corresponding to the multiple parking spaces based on the target parking space information, and display the multiple parking space images at a preset display position of the target vehicle, wherein the positional relationship of the multiple parking space images corresponds to the positional relationship between the multiple parking spaces; a receiving module 54, configured to receive a posture image of the target object, wherein the posture image represents the parking intention of the target object; a determining module 56, configured to determine the target parking space image among the multiple parking space images based on the posture image of the target object; and a control module 58, configured to control the target vehicle to move to the target parking space based on the target parking space image, wherein the target parking space is the parking space corresponding to the target parking space image.

[0098] Optionally, the first acquisition module includes: an acquisition unit for acquiring multiple video streams, wherein the multiple video streams contain initial parking space information, and the multiple video streams are acquired by multiple cameras set at different locations; and a processing unit for perceptually fusing the initial parking space information in the multiple video streams to obtain target parking space information.

[0099] Optionally, the generation module includes: a processing unit for performing masking processing on the pose image to obtain a mask image; a first determining unit for determining a first key point and a second key point of the target object based on the mask image, wherein the first key point is a key point corresponding to a first part of the target object, and the second key point is a key point corresponding to a second part of the target object; and a second determining unit for determining a target parking space image among multiple parking space images based on the direction of the line connecting the first key point and the second key point.

[0100] Optionally, the second determining unit includes: a first determining subunit for determining the first coordinates of the first key point in the target coordinate system; a second determining subunit for determining the second coordinates of the second key point in the target coordinate system; a third determining subunit for determining a first line segment based on the first and second coordinates; a fourth determining subunit for determining the pointing coordinates of the extension line of the first line segment at a preset display position; a fifth determining subunit for determining multiple parking space coordinates of multiple parking space images in the target coordinate system; a sixth determining subunit for determining the target parking space coordinates based on the distance information between the pointing coordinates and the multiple parking space coordinates, wherein the target parking space coordinates are the parking space coordinates with the shortest distance to the pointing coordinates among the multiple parking space coordinates; and a seventh determining subunit for determining the target parking space image among the multiple parking space images that corresponds to the target parking space coordinates.

[0101] Optionally, the control module includes: a sending unit for sending a prompt message, wherein the prompt message is used to remind the target object whether the target parking space image is the parking space image corresponding to the parking space to be parked; and a control unit for responding to the received confirmation command from the target object and controlling the target vehicle to move to the target parking space based on the target parking space image, wherein the confirmation command is used to confirm that the target parking space image is the parking space image corresponding to the parking space to be parked.

[0102] Optionally, the processing unit in the first acquisition module includes: an acquisition subunit for acquiring the installation positions of multiple cameras on the target vehicle; and a processing subunit for performing perception fusion on the initial parking space information in multiple video streams based on the installation positions to obtain the target parking space information.

[0103] Optionally, the first acquisition module further includes: an acquisition unit for acquiring voice information of the target object; and a generation module for generating a parking instruction based on the voice information if the voice information contains the target voice, wherein the target voice is voice related to the parking information of the target vehicle.

[0104] Example 3

[0105] According to another aspect of the present invention, a computer-readable storage medium is also provided, characterized in that the computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to execute the control method for the target vehicle provided in the above embodiments.

[0106] Example 4

[0107] According to another aspect of the present invention, a target vehicle is also provided, characterized in that it includes: one or more processors; a storage device for storing one or more programs; and when the one or more programs are executed by the one or more processors, the one or more processors execute the control method of the target vehicle provided in the above embodiments.

[0108] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0109] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0110] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0111] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0113] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0114] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method of a target vehicle, characterized by, The method comprises the steps of: acquiring target parking space information in response to the received parking instruction, wherein the target parking space information is used to represent the positional relationship between a plurality of parking spaces, and the target parking space information is obtained by performing perception fusion on initial parking space information in a plurality of video streams acquired by a plurality of cameras at the mounting position of the target vehicle; generating a plurality of parking space images corresponding to the plurality of parking spaces based on the target parking space information, and displaying the plurality of parking space images at a preset display position of the target vehicle, wherein the positional relationship of the plurality of parking space images corresponds to the positional relationship between the plurality of parking spaces, the preset display position is the windshield of the target vehicle, and the plurality of parking space images are displayed at the preset display position by a head-up display and augmented reality technology; receiving a posture image of a target object, wherein the posture image is used to represent the parking intention of the target object; determining a target parking space image in the plurality of parking space images based on the posture image of the target object, wherein the target parking space image is determined by the direction of the line connecting a first key point and a second key point of the target object, the first key point and the second key point are determined by a mask image, the mask image is obtained by changing the pixels of a region of interest in the posture image, the target parking space image is a parking space image in the plurality of parking space images corresponding to a target parking space coordinate, the target parking space coordinate is determined by a pointing coordinate and distance information of a plurality of parking space coordinates, the target parking space coordinate is a parking space coordinate in the plurality of parking space coordinates with the shortest distance to the pointing coordinate, the plurality of parking space coordinates are coordinates of the plurality of parking space images in a target coordinate system, and the pointing coordinate is determined by the extension line of a first line segment, the first line segment is determined by a first coordinate and a second coordinate, the first coordinate is determined by the first key point, and the second coordinate is determined by the second key point; controlling the target vehicle to move to a target parking space based on the target parking space image, wherein the target parking space is a parking space corresponding to the target parking space image.

2. The method of claim 1, wherein, Acquiring target parking space information comprises: collecting a plurality of video streams, wherein the plurality of video streams contain initial parking space information, and the plurality of video streams are collected by a plurality of cameras arranged at different positions; performing perception fusion on the initial parking space information in the plurality of video streams to obtain the target parking space information.

3. The method of claim 1, wherein, Determining a target parking space image in the plurality of parking space images based on the posture image of the target object comprises: performing mask processing on the posture image to obtain a mask image; determining a first key point and a second key point of the target object based on the mask image, wherein the first key point is a key point corresponding to a first part of the target object, and the second key point is a key point corresponding to a second part of the target object; determining a target parking space image in the plurality of parking space images based on the direction of the line connecting the first key point and the second key point.

4. The method of claim 1, wherein, Before controlling the target vehicle to move to a target parking space based on the target parking space image, it comprises: sending prompt information, wherein the prompt information is used to remind the target object whether the target parking space image is a parking space image corresponding to a parking space to be parked; in response to the received confirmation instruction of the target object, controlling the target vehicle to move to the target parking space based on the target parking space image, wherein the confirmation instruction is used to confirm that the target parking space image is a parking space image corresponding to a parking space to be parked.

5. The method of claim 1, wherein, in response to the received parking instruction, obtaining target parking space information, including: obtaining voice information of the target object; in the case that the voice information contains target voice, generating the parking instruction based on the voice information, wherein the target voice is voice related to parking information of the target vehicle.

6. A parking device for a target vehicle, characterized by including: a first obtaining module, configured to obtain target parking space information in response to a received parking instruction, wherein the target parking space information is used to represent a positional relationship between a plurality of parking spaces, and the target parking space information is obtained by sensing and fusing initial parking space information in a plurality of video streams obtained by a plurality of cameras at an installation position of a target vehicle; a generating module, configured to generate a plurality of parking space images corresponding to the plurality of parking spaces based on the target parking space information, and display the plurality of parking space images at a preset display position of the target vehicle, wherein a positional relationship of the plurality of parking space images corresponds to the positional relationship between the plurality of parking spaces, the preset display position is a windshield of the target vehicle, and the plurality of parking space images are displayed at the preset display position by a head-up display instrument and augmented reality technology; a receiving module, configured to receive a posture image of a target object, wherein the posture image is used to represent a parking intention of the target object; a determining module, configured to determine a target parking space image in the plurality of parking space images based on the posture image of the target object, wherein the target parking space image is determined by a line direction of a first key point and a second key point of the target object, the first key point and the second key point are determined by a mask image, the mask image is obtained by changing pixels in a region of interest in the posture image, the target parking space image is a parking space image in the plurality of parking space images corresponding to a target parking space coordinate, the target parking space coordinate is determined by a pointing coordinate and distance information of a plurality of parking space coordinates, the target parking space coordinate is a parking space coordinate in the plurality of parking space coordinates having the shortest distance to the pointing coordinate, the plurality of parking space coordinates are coordinates of the plurality of parking space images in a target coordinate system, and the pointing coordinate is determined by an extension line of a first line segment, the first line segment is determined by a first coordinate and a second coordinate, the first coordinate is determined by the first key point, and the second coordinate is determined by the second key point; a control module, configured to control the target vehicle to move to a target parking space based on the target parking space image, wherein the target parking space is a parking space corresponding to the target parking space image.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, controls a device in which the computer-readable storage medium is placed to execute the control method of the target vehicle according to any one of claims 1 to 5.

8. A target vehicle characterized by comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors perform the control method of the target vehicle according to any one of claims 1 to 5.

Images