CN114872545A - Target vehicle control method, parking device, and target vehicle - Google Patents

Abstract

The invention discloses a control method of a target vehicle, a parking device and the target vehicle. Wherein, the method comprises the following steps: responding to the received parking instruction, and acquiring target parking space information, wherein the target parking space information is used for representing the position relation among a plurality of parking spaces; 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 position relationship of the plurality of parking space images corresponds to the position relationship among the plurality of parking spaces; receiving a posture image of the target object, wherein the posture image is used for representing the parking intention of the target object; determining a target parking space image in the plurality of parking space images based on the attitude 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 a parking space corresponding to the target parking space image. The invention solves the technical problem of low efficiency of selecting the parking space when parking in the prior art.

Description

Target vehicle control method, parking device, and target vehicle

technical field

The present invention relates to the field of assisted driving, in particular, to a control method of a target vehicle, a parking device and a target vehicle.

Background technique

With economic development and the continuous improvement of people's living standards, cars are no longer just means of transportation, their development is more diversified, and the application of parking systems is also more extensive, but the parking systems in the existing technology focus more on the functions of parking Realization, when selecting a parking space, the user needs to get off the car to check the specific parking space situation, resulting in low efficiency when selecting a parking space.

For the above problems, no effective solution has been proposed yet.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a control method, a parking device and a target vehicle for a target vehicle, so as to at least solve the technical problem of low efficiency in selecting a parking space when parking in the prior art.

According to an aspect of the embodiments of the present invention, a method for controlling a target vehicle is provided, including: in response to a received parking instruction, acquiring target parking space information, where the target parking space information is used to represent a positional relationship between multiple parking spaces ; 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 the preset display position of the target vehicle, wherein the positional relationship between the plurality of parking space images and the positional relationship between the plurality of parking spaces Corresponding; receiving the gesture image of the target object, wherein the gesture image is used to represent the parking intention of the target object; determining the target parking space image in the plurality of parking space images based on the gesture image of the target object; controlling the target vehicle to move to the target parking space based on the target parking space image , where the target parking space is the parking space corresponding to the target parking space image.

Optionally, acquiring the target parking space information includes: collecting multiple video streams, wherein the multiple video streams include initial parking space information, and the multiple video streams are collected by multiple cameras set at different positions; The initial parking space information in the sensor is perceptually fused to obtain the target parking space information.

Optionally, determining the target parking space image in the plurality of parking space images based on the posture image of the target object includes: performing mask processing on the posture image to obtain a mask image; determining the first key point and the first key point of the target object based on the mask image. Two key points, wherein the first key point is the key point corresponding to the first part of the target object, and the second key point is the key point corresponding to the second part of the target object; based on the connection between the first key point and the second key point The line direction is used to determine the target parking space image in the multiple parking space images.

Optionally, based on the connection direction of the first key point and the second key point, determining the target parking space image in the plurality of parking space images includes: determining the first coordinate of the first key point in the target coordinate system; determining the second The second coordinate of the key point in the target coordinate system; the first line segment is determined based on the first coordinate and the second coordinate; the pointing coordinates of the extension line of the first line segment at the preset display position are determined; Multiple parking space coordinates in the target coordinate system; determine the target parking space coordinates based on the pointing coordinates and the distance information of the multiple parking space coordinates, wherein the target parking space coordinates are the parking space coordinates with the shortest distance from the pointing coordinates among the multiple parking space coordinates; determine Among the multiple parking space images, the target parking space image corresponding to the coordinates of the target parking space.

Optionally, before controlling the target vehicle to move to the target parking space based on the target parking space image, it includes: 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 the parking space to be parked; The confirmation instruction of the target object controls 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.

Optionally, perceptual fusion is performed on the initial parking space information in the multiple video streams to obtain the target parking space information, including: acquiring the installation positions of multiple cameras on the target vehicle; Perceptual fusion to obtain target parking space information.

Optionally, in response to the received parking instruction, acquiring the target parking space information includes: acquiring the voice information of the target object; when the voice information includes the target voice, generating a parking instruction based on the voice information, wherein the target voice is a Speech related to the parking information of the target vehicle.

According to another aspect of the embodiments of the present invention, a parking device for a target vehicle is also provided, including: a first acquisition module, configured to acquire target parking space information in response to the received parking instruction, wherein the target parking space information is used for Represents the positional relationship between multiple parking spaces; the generating module is used 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 in the preset display position of the target vehicle, wherein multiple parking space images are displayed. The positional relationship of the parking space image corresponds to the positional relationship between multiple parking spaces; the receiving module is used to receive the gesture image of the target object, wherein the gesture image is used to represent the parking intention of the target object; the determination module is used for the target object-based The gesture image determines a target parking space image in the plurality of parking space images; the control module is 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 a parking space corresponding to the target parking space image.

According to another aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute The control method of the target vehicle according to any one of the above.

According to another aspect of the embodiments of the present invention, a target vehicle is also provided, which is characterized by comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are The one or more processors execute such that the one or more processors execute any one of the above-mentioned control methods for the target vehicle.

In the embodiment of the present invention, the target parking space information is obtained in response to the received parking instruction, wherein the target parking space information is used to represent the positional relationship between multiple parking spaces; and display the target parking space image 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; receive the attitude image of the target object, wherein the attitude image uses to express the parking intention of the target object; determine the target parking space image in the multiple parking space images based on the gesture image of the target object; 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. In this way, the purpose of improving the efficiency of parking space selection when parking is achieved. It is easy to notice that multiple parking space images corresponding to multiple parking spaces can be displayed in the preset display positions in the car, so that the user can quickly select the target parking space image from the multiple parking space images through gestures, thereby simplifying the current situation. In the prior art, users need to get off the car to check the actual parking space they want to park, and then control the vehicle according to the actual confirmed situation, so that the vehicle can park in the parking space of their choice. The technical effect of improving the efficiency of parking space selection is achieved, thereby solving the technical problem of low efficiency in selecting a parking space when parking in the prior art.

Description of drawings

The accompanying drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

1 is a flowchart of a control method for a target vehicle according to an embodiment of the present invention;

2 is a flowchart of an optional finger parking interaction system according to an embodiment of the present invention;

3 is a schematic diagram of an optional user-selected parking space according to an embodiment of the present invention;

4 is a schematic diagram of an optional intelligent parking system according to an embodiment of the present invention;

FIG. 5 is a schematic structural diagram of a parking device for a target vehicle according to an embodiment of the present invention.

Detailed ways

In order to make those skilled in the art better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Embodiments are part of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

It should be noted that the terms "first", "second" and the like in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific sequence or sequence. It is to be understood that the data so used may be interchanged under appropriate circumstances such that the embodiments of the invention described herein can be practiced in sequences other than those illustrated or described herein. Furthermore, the terms "comprising" and "having" and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those expressly listed Rather, those steps or units may include other steps or units not expressly listed or inherent to these processes, methods, products or devices.

Example 1

According to an embodiment of the present invention, an embodiment of a method for controlling a target vehicle is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and , although a logical order is shown in the flowcharts, in some cases steps shown or described may be performed in an order different from that herein.

FIG. 1 is a flowchart of a control method for a target vehicle according to an embodiment of the present invention. As shown in FIG. 1 , the method includes the following steps:

Step S102 , in response to the received parking instruction, obtain target parking space information, where the target parking space information is used to represent the positional relationship between multiple parking spaces.

Optionally, the vehicle involved in the embodiment of the present invention may be an automatic driving vehicle with an intelligent parking system, a vehicle driven by a user with an intelligent parking system, or a vehicle with an intelligent parking system The self-driving new energy vehicle is not limited to this, and is not specifically limited in the embodiment of the present invention.

The above parking instruction may be any instruction issued by the user to enable the vehicle to activate the intelligent parking system, for example, it may be a voice or an instruction input by the user, which is not specifically limited in this embodiment of the present invention.

The above-mentioned target parking space may be the parking space where the current vehicle is to be parked; 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 position information between the target parking space and other parking spaces.

The above-mentioned acquisition of target parking space information can be obtained through a target recognition algorithm, wherein the target recognition algorithm can be any algorithm, such as a region-based convolutional neural network algorithm, (Region with Convolutional Neural Networks Features, R-CNN). algorithm), object recognition and localization algorithm based on deep neural network, (You Only Look Once, YOLO algorithm), single-order multi-layer target detection model algorithm, (SingleShort Multibox Detector, SSD algorithm), but not limited to this.

In an optional embodiment, in response to a parking instruction issued by the user, the intelligent parking system acquires target parking space information through a target recognition algorithm.

Step S104: 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 the preset display position of the target vehicle, wherein the positional relationship between the multiple parking space images and the multiple parking spaces positional relationship.

The above-mentioned multiple parking space images are obtained based on a target recognition algorithm, cameras installed at different positions of the vehicle, and Augmented Reality (AR) technology of a head-up digital display (HUD), and the establishment of a target coordinate system.

The above-mentioned multiple parking space images can be scanned by multiple cameras, HUD and AR technology to scan actual multiple parking spaces, and the virtual parking space images displayed on the windshield can be any kind of images such as boxes, polygons, etc. , In this embodiment, a block is used as an example for description, wherein the virtual parking space image can also be displayed on the display screen of the interactive interface.

The above-mentioned generation of multiple parking space images corresponding to multiple parking spaces based on the target parking space information can firstly obtain the target parking space information through a target recognition algorithm, and secondly, perform multiple parking space images captured by cameras installed at different positions on the vehicle. Perceptual fusion, and establish a coordinate system, so that the multiple parking space images after perceptual fusion are unified in one coordinate system and correspond to the actual target parking space information. Among them, perceptual fusion is the alignment and fusion of different sensor data in time and space, The end result will improve the perception capabilities of autonomous driving systems

The above-mentioned preset display position may be any position on the vehicle that can display multiple parking space images. In this embodiment, a windshield of a car is used as an example for description.

The above-mentioned display of multiple parking space images at the preset display position of the target vehicle can be realized through HUD and AR technology, wherein the HUD can map important information on the glass, so that the driver can see the important information without lowering his head. , AR technology is to overlay digital images in the real world, so that the information projected by the HUD is integrated with the real driving environment.

In an optional embodiment, after acquiring the target parking space information, first perform perceptual fusion of multiple parking space image information captured by the camera and establish a coordinate system, so that the multiple parking space images after perceptual fusion are unified in one coordinate It corresponds to the actual target parking space information, and secondly, multiple parking space images are displayed on the windshield of the vehicle (ie, the preset display position) through HUD and AR technology.

Step S106, receiving a gesture image of the target object, wherein the gesture image is used to represent the parking intention of the target object.

The aforementioned target object may be a user operating the current vehicle.

The above-mentioned posture image can firstly be captured by the in-vehicle camera of the user's limb posture image, wherein, the capture by the camera can be to set the region of interest (ROI) by the position of the camera, so as to ensure that the user captured by the camera is The driver, followed by the Holistic module in the open source framework (Mediapipe) designed for Graphics Processing Unit (GraphicProcess Unit, GPU) or Central Processing Unit (Central Process Unit, CPU) based on convolutional neural network pairs the captured data. The initial posture image of the human body is recognized to obtain the posture image. Among them, the Holistic module of Mediapipe contains optimized posture, face and hand components, each of which runs in real time. When all three components are included, more than 540 key points can be identified. (33 gestures, 21 for each hand, 468 facial feature points). In this embodiment, gesture recognition is used as an example for description.

The above attitude image is used to represent the parking intention of the target object, which can be based on the recognized attitude image, and a ray equation based on the wrist and fingers is established, wherein the ray equation is located in the established coordinate system, and the ray equation is a kind that can represent the extension of the target point. The equation of direction has only one end point and the other end can be extended indefinitely, wherein the parking intention can indicate that the user chooses to park the vehicle in a specific parking space.

In an optional embodiment, the initial posture image of the user is first captured by the in-vehicle camera, and then the captured initial posture image of the human body is recognized by the Holistic module in the Mediapipe based on the convolutional neural network to obtain the posture image, Finally, a ray equation is established based on the wrist and finger in the pose image, and the direction of the extension line of the ray equation can represent the parking intention of the target object.

Step S108, determining a target parking space image among the plurality of parking space images based on the pose image of the target object.

The pose image of the above-mentioned target object is realized by the Holistic module of Mediapipe and the establishment of the corresponding ray equation.

In an optional embodiment, a parking space image corresponding to a parking space where the user wants to park may be determined according to the acquired gesture action (ie, a gesture image) of the user, wherein the parking space image may be the above-mentioned target parking space image.

Step S110 , controlling the target vehicle to move to the 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 above-mentioned control of the target vehicle to move to the target parking space based on the target parking space image may firstly confirm to the user whether to park at the selected target parking space image through voice. The target parking space image, secondly, based on the user's confirmation information, transmits the parking target information to the Advanced Autonomous Driving Controller (Highly Autonomous Driving, HAD) to execute the automatic parking procedure, so that the vehicle can move to the target parking space.

In an optional embodiment, after the user confirms the target parking space image, the parking target information can be transmitted to the HAD to execute the automatic parking procedure, so that the vehicle can move to the target parking space.

In the embodiment of the present invention, the target parking space information is obtained in response to the received parking instruction, wherein the target parking space information is used to represent the positional relationship between multiple parking spaces; and display the target parking space image 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; receive the attitude image of the target object, wherein the attitude image uses to express the parking intention of the target object; determine the target parking space image in the multiple parking space images based on the gesture image of the target object; 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. In this way, the purpose of improving the efficiency of parking space selection when parking is achieved. It is easy to notice that multiple parking space images corresponding to multiple parking spaces can be displayed in the preset display positions in the car, so that the user can quickly select the target parking space image from the multiple parking space images through gestures, thereby simplifying the current situation. In the prior art, users need to get off the car to check the actual parking space they want to park, and then control the vehicle according to the actual confirmed situation, so that the vehicle can park in the parking space of their choice. The technical effect of improving the efficiency of parking space selection is achieved, thereby solving the technical problem of low efficiency in selecting a parking space when parking in the prior art.

Optionally, acquiring the target parking space information includes: collecting multiple video streams, wherein the multiple video streams include initial parking space information, and the multiple video streams are collected by multiple cameras set at different positions; The initial parking space information in the sensor is perceptually fused to obtain the target parking space information.

The above-mentioned video stream refers to the transmission of video data.

In an optional embodiment, firstly, the initial parking space information is collected by cameras installed at different positions on the vehicle to obtain a corresponding video stream, and secondly, the initial parking space information in the video stream is perceptually fused to obtain the target parking space information .

Optionally, determining the target parking space image in the plurality of parking space images based on the posture image of the target object includes: performing mask processing on the posture image to obtain a mask image; determining the first key point and the first key point of the target object based on the mask image. Two key points, wherein the first key point is the key point corresponding to the first part of the target object, and the second key point is the key point corresponding to the second part of the target object; based on the connection between the first key point and the second key point The line direction is used to determine the target parking space image in the multiple parking space images.

The above mask is a string of binary codes that perform a bitwise AND operation on the target field, mask the current input bits, and obtain a new operand by bitwise operation or logical operation between the source code and the mask. OR (OR) operation and AND (AND) operation.

The above-mentioned mask image can be an image obtained by changing the pixels of the ROI area in the image to focus on display, and blurring the pixels of the non-ROI area to avoid affecting the ROI area.

The above-mentioned first part can be the driver's wrist, and the first key point can be to select a specific point on the wrist, which is not specifically limited in this embodiment; the second part can be the driver's finger, and the second key point can be selected. The point may be a point toward which the fingertip is directed, which is not specifically limited in this embodiment.

The above-mentioned connection direction based on the first key point and the second key point may firstly establish a ray equation in the target coordinate system based on the first key point and the second key point, then extend the other end of the ray equation, and finally. The parking space image that intersects the extension line and has the closest distance to the current vehicle is the target parking space image.

In an optional embodiment, mask processing is performed on the gesture image to obtain a mask image, and then the key points of the elbow of the driver (that is, the target object) and the points facing the fingertips of the driver are determined based on the mask image, A ray equation is established based on the key points of the elbow and the points toward which the fingertips are directed. Based on the extension line of the equation and the distance to the current vehicle, the target parking space image in the multiple parking space images can be determined.

Optionally, based on the connection direction of the first key point and the second key point, determining the target parking space image in the plurality of parking space images includes: determining the first coordinate of the first key point in the target coordinate system; determining the second The second coordinate of the key point in the target coordinate system; the first line segment is determined based on the first coordinate and the second coordinate; the pointing coordinates of the extension line of the first line segment at the preset display position are determined; Multiple parking space coordinates in the target coordinate system; determine the target parking space coordinates based on the pointing coordinates and the distance information of the multiple parking space coordinates, wherein the target parking space coordinates are the parking space coordinates with the shortest distance from the pointing coordinates among the multiple parking space coordinates; determine Among the multiple parking space images, the target parking space image corresponding to the coordinates of the target parking space.

The above-mentioned first coordinate 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 facing point in the target coordinate system; the first line segment can be based on the first coordinate and the ray equation established by the second coordinate.

In an optional embodiment, firstly determine the first coordinate and the second coordinate of the first key point and the second key point in the target coordinate system, determine the ray equation based on the first coordinate and the second coordinate, and determine the ray equation The pointing coordinates of the extension line of the extension line in the preset display position, and then determine the multiple parking space coordinates of the multiple parking space images in the target coordinate system. Based on the pointing coordinates and the parking space coordinates, the parking space coordinates with the shortest distance from the pointing coordinates can be determined. Based on the target parking space coordinates, the corresponding parking space image is determined.

Optionally, before controlling the target vehicle to move to the target parking space based on the target parking space image, it includes: 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 the parking space to be parked; The confirmation instruction of the target object controls 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.

The above-mentioned prompt information can be any kind of information that can prompt the driver, and can be information such as voice, text, etc. In this embodiment, voice is used as an example for description, for example, it can be “Please confirm whether to drive the vehicle. Park at the target parking space corresponding to the selected parking space image"; the confirmation command can be any kind of confirmation command issued by the driver, which can be commands such as voice, text, etc. In this embodiment, the voice is used as an example for description, for example, It can be "Confirm to park the vehicle in the target parking space corresponding to the selected parking space image".

In an optional embodiment, first confirm to the user by voice whether the target parking space image is the parking space image corresponding to the parking space to be parked, and after receiving the user's voice to confirm that the target parking space image is the parking space image corresponding to the parking space to be parked, control the The vehicle activates the automatic parking system to move the vehicle to the target parking space.

Optionally, perceptual fusion is performed on the initial parking space information in the multiple video streams to obtain the target parking space information, including: acquiring the installation positions of multiple cameras on the target vehicle; Perceptual fusion to obtain target parking space information.

In an optional embodiment, the installation positions of the multiple cameras in the current vehicle are obtained first, for example, the position of the driver's seat in the car, the position of the co-pilot in the car, the position of the outside rearview mirror, etc., and then based on the installation position, Perceptual fusion of initial parking space information in multiple video streams obtained by multiple cameras is performed to obtain target parking space information.

Optionally, in response to the received parking instruction, acquiring the target parking space information includes: acquiring the voice information of the target object; when the voice information includes the target voice, generating a parking instruction based on the voice information, wherein the target voice is a Speech related to the parking information of the target vehicle.

The above-mentioned target voice may be a voice issued by the driver that can confirm the parking information of the current vehicle, for example, may be other voice information such as "park the vehicle in the parking space selected by my finger".

In an optional embodiment, the driver's voice information is obtained first, and when the voice information includes the parking information of the current vehicle, a parking instruction is generated based on the parking information in the voice information.

The present embodiment will be further described below with reference to FIGS. 2 to 4 .

The overall technical scheme of the present invention is as follows:

1. The user interacts with the voice command to start the smart parking program in the car machine.

2. After the parking program is started, the parking spaces identified by the outside and inside cameras are unified on a single coordinate system through the perception fusion of the in-vehicle camera and the field-end camera. And through the target recognition algorithm, the information of the parking space is detected, and the HUD is used to enhance the display on the screen. The general effect is shown in Figure 3.

3. The voice prompts the user to select the target parking space by finger. The user's behavior is detected through the in-vehicle camera. The detection is mainly divided into two parts. First, the user pose is estimated through the gesture detection of Mediapipe based on convolutional neural network. As shown in Figure 3, the direction of the connection between the wrist and the fingertip is calculated, and then the user's goal is determined by using the direction of the connection of the key points.

4. The user's target parking space is calculated and displayed on the HUD, as shown in Figure 3. After the user's gesture stays for 2s, confirm through voice and whether the user really stops to the displayed target.

5. After the user confirms by voice, the overall interaction process is completed. And transmit the final parking target to HAD to perform subsequent automatic parking behavior.

FIG. 2 is a flowchart of an optional finger parking interaction system according to an embodiment of the present invention. As shown in FIG. 2 , the flowchart includes the following steps:

Step S201: the user voice commands to park;

Step S202: the vehicle starts a parking procedure;

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

Step S204: enhancing the display of the parking space through the head-up digital display;

Step S205: voice prompting the user to use the target finger to select the target parking space;

Step S206: the user selects the target parking space with a finger;

Step S207: Confirm the user's intention through gesture judgment;

Step S208: enhancing the display of the parking space on the head-up digital display;

Step S209: Voice asking the user whether to confirm the selection of the parking space;

Step S210: the user confirms the selection of the parking space by voice;

Step S211: Transfer the parking target information to the HAD to execute the automatic parking procedure, so that the vehicle can move to the target parking space.

FIG. 3 is a schematic diagram of an optional user selecting a parking space according to an embodiment of the present invention. As shown in FIG. 3 , the user can select a parking space through the key point of the wrist and the pointing point of the fingertip, and the HUD selects the parking space through AR Enhanced display is performed and displayed on the windshield of the current car, wherein the rectangular area represents the windshield of the current car, and multiple small boxes represent multiple images of parking spaces.

4 is a schematic diagram of an optional intelligent parking system according to an embodiment of the present invention, the system includes: a front-view camera 40, a peripheral-view camera 41, an occupant monitoring system (Occupancy Monitoring System, OMS) 42, a driver Monitoring system (Drive Monitoring System, DMS) 43, telematics box (Telematics box, Tbox) 44, cockpit domain control unit (Cockpit Space Center, CSC) 45, HAD 46, microphone 47, speaker 48, HUD 49.

The front view camera 40, the surrounding view camera 41, the OMS 42 and the DMS 43 are connected with the CSC 45 for sending the captured video stream to the CSC 45, and the Tbox 44 is connected with the CSC 45, so that the vehicle can process the video stream through the network After getting the parking space information, the CSC 45 is connected with the HAD 46 and can transmit the parking instruction to the HAD 46 to make the HAD 46 control the vehicle to park automatically. The CSC 45 is connected with the microphone 47, the speaker 48, and the HUD 49, and the user can be prompted to confirm the target parking space through the microphone 47 , the user's parking instruction can be acquired through the speaker 48 , and the target parking space image can be enhanced and displayed on the windshield through the HUD 49 .

The invention provides a vehicle-mounted finger parking system. On the basis of the original automatic parking function of the vehicle, simple user purpose interaction is realized through speech recognition technology, parking space recognition is realized through target detection algorithm, and AR-enhanced parking space is provided on the HUD. show. Through human behavior detection, the user's parking intention is judged, and AR augmented reality is implemented on the HUD system. The dynamic recognition of the user's parking target is realized. Compared with the prior art, in the overall interaction mode, the user can select a parking space in a natural state (voice, finger), and realize the overall parking process, which greatly enhances the sense of technology and interest of the interaction.

Example 2

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

FIG. 5 is a schematic structural diagram of a parking device for a target vehicle according to an embodiment of the present invention. As shown in FIG. 5 , the device includes: a first acquisition module 50 for acquiring 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; the generating module 52 is used to generate a plurality of parking space images corresponding to the multiple parking spaces based on the target parking space information, and display them at the preset display position of the target vehicle a plurality of parking space images, wherein the positional relationship of the plurality of parking space images corresponds to the positional relationship between the plurality of parking spaces; the receiving module 54 is used to receive the gesture image of the target object, wherein the gesture image is used to represent the parking intention of the target object The determination module 56 is used to determine the target parking space image in the plurality of parking space images based on the gesture image of the target object; the control module 58 is used 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 same as the target parking space. The parking space corresponding to the image.

Optionally, the first acquisition module includes: a collection unit configured to collect multiple video streams, wherein the multiple video streams include initial parking space information, and the multiple video streams are acquired by collecting multiple cameras arranged at different positions; processing The unit is used for perceptual fusion of initial parking space information in multiple video streams to obtain target parking space information.

Optionally, the generation module includes: a processing unit for performing mask processing on the pose image to obtain a mask image; a first determination unit for determining the first key point and the second key point of the target object based on the mask image , where the first key point is the key point corresponding to the first part of the target object, and the second key point is the key point corresponding to the second part of the target object; The connection direction of key points determines the target parking space image in multiple parking space images.

Optionally, the second determination unit includes: a first determination subunit for determining the first coordinate of the first key point in the target coordinate system; a second determination subunit for determining the second key point in the target coordinate system the second coordinate in The fifth determination subunit is used to determine multiple parking space coordinates of multiple parking space images in the target coordinate system; the sixth determination subunit is used to determine the target based on the pointing coordinates and the distance information of the multiple parking space coordinates Parking space coordinates, wherein the target parking space coordinate is the parking space coordinate with the shortest distance from the pointing coordinate among the plurality of parking space coordinates; the seventh determination subunit is used to determine the target parking space image corresponding to the target parking space coordinate among the plurality of parking space images.

Optionally, the control module includes: a sending unit for 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 the parking space to be parked; the control unit is used for responding to the received target The confirmation instruction of the object controls 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.

Optionally, the processing unit in the first obtaining module includes: an obtaining subunit, used to obtain the installation positions of multiple cameras in the target vehicle; Perform perceptual fusion to obtain the target parking space information.

Optionally, the first obtaining module further includes: an obtaining unit for obtaining the voice information of the target object; a generating module for generating a parking instruction based on the voice information when the voice information includes the target voice, wherein the target voice is It is the speech related to the parking information of the target vehicle.

Example 3

According to another aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is run, the device where the computer-readable storage medium is located is controlled to execute The control method of the target vehicle provided by the above embodiments.

Example 4

According to another aspect of the embodiments of the present invention, a target vehicle is also provided, which is characterized by comprising: one or more processors; a storage device for storing one or more programs; when the one or more programs are One or more processors execute, so that the one or more processors execute the control method of the target vehicle provided by the above embodiments.

The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages or disadvantages of the embodiments.

In the above-mentioned embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

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 only illustrative, for example, the division of the units may be a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components may be combined or Integration into another system, or some features can be ignored, or not implemented. On the other hand, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of units or modules, and may be in electrical or other forms.

The units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated units may be implemented in the form of hardware, or may be implemented in the form of software functional units.

The integrated unit, if implemented in the form of a software functional unit and sold or used as an independent product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially 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, and the computer software product is stored in a storage medium , including several instructions for causing a computer device (which may be a personal computer, a server, or a 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: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes .

The above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principles of the present invention, several improvements and modifications can be made. It should be regarded as the protection scope of the present invention.

Claims (10)

1. a control method of a target vehicle, is characterized in that, comprises: Acquiring target parking space information in response to the received parking instruction, wherein the target parking space information is used to represent a positional relationship between multiple parking spaces; A plurality of parking space images corresponding to the plurality of parking spaces are generated based on the target parking space information, and the plurality of parking space images are displayed in a preset display position of the target vehicle, wherein the positional relationship of the plurality of parking space images is the same as that of the plurality of parking space images. The positional relationship between the multiple parking spaces corresponds to; receiving a gesture image of the target object, wherein the gesture 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 pose image of the target object; The target vehicle is controlled 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 according to claim 1, wherein acquiring target parking space information comprises: collecting multiple video streams, wherein the multiple video streams include initial parking space information, and the multiple video streams are collected by multiple cameras arranged at different positions; Perceptual fusion is performed on the initial parking space information in the multiple video streams to obtain the target parking space information. 3. The method according to claim 1, wherein determining the target parking space image in the plurality of parking space images based on the gesture image of the target object, comprising: performing mask processing on the gesture image to obtain a mask image; Determine the first key point and the second key point of the target object based on the mask image, wherein the first key point is the key point corresponding to the first part of the target object, and the second key point is the key point corresponding to the second part of the target object; Based on the connection direction of the first key point and the second key point, a target parking space image in the plurality of parking space images is determined. 4. The method according to claim 3, wherein determining a target parking space image in the plurality of parking space images based on the connection direction of the first key point and the second key point, comprising: 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 a first line segment based on the first coordinate and the second coordinate; determining the pointing coordinates of the extension line of the first line segment at the preset display position; determining a plurality of parking space coordinates of the plurality of parking space images in the target coordinate system; Determine the target parking space coordinates based on the pointing coordinates and the distance information of the plurality of parking space coordinates, wherein the target parking space coordinates are the parking space coordinates with the shortest distance from the pointing coordinates among the plurality of parking space coordinates; A target parking space image corresponding to the coordinates of the target parking space among the plurality of parking space images is determined. 5. The method according to claim 1, wherein before controlling the target vehicle to move to a target parking space based on the target parking space image, the method 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 the parking space to be parked; In response to the received confirmation instruction of the target object, the target vehicle is controlled 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 corresponds to the parking space to be parked image of parking spaces. 6. The method according to claim 2, wherein the initial parking space information in the multiple video streams is perceptually fused to obtain the target parking space information, comprising: obtaining the installation positions of the plurality of cameras on the target vehicle; Based on the installation position, the initial parking space information in the multiple video streams is perceptually fused to obtain the target parking space information. 7. The method according to claim 1, wherein, in response to the received parking instruction, acquiring target parking space information, comprising: Obtain the voice information of the target object; When the voice information includes a target voice, the parking instruction is generated based on the voice information, wherein the target voice is a voice related to the parking information of the target vehicle. 8. A parking device for a target vehicle, comprising: a first obtaining module, configured to obtain 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 multiple parking spaces; 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 the plurality of parking space images The positional relationship of is corresponding to the positional relationship between the plurality of parking spaces; a receiving module, configured to receive a gesture image of the target object, wherein the gesture image is used to represent the parking intention of the target object; a determination 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; The control module is 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. 9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored program, wherein, when the program is run, a device where the computer-readable storage medium is located is controlled to execute claims 1 to 7 The control method of the target vehicle described in any one of. 10. A target vehicle, 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 are caused to execute the control method of the target vehicle described in any one of claims 1 to 7 .

Images