CN112835350A - Automatic parking method, device and system - Google Patents

Automatic parking method, device and system Download PDF

Info

Publication number
CN112835350A
CN112835350A CN201911155478.0A CN201911155478A CN112835350A CN 112835350 A CN112835350 A CN 112835350A CN 201911155478 A CN201911155478 A CN 201911155478A CN 112835350 A CN112835350 A CN 112835350A
Authority
CN
China
Prior art keywords
parking space
vehicle
available
parking
available parking
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911155478.0A
Other languages
Chinese (zh)
Inventor
袁少波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Hikvision Digital Technology Co Ltd
Original Assignee
Hangzhou Hikvision Digital Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Hikvision Digital Technology Co Ltd filed Critical Hangzhou Hikvision Digital Technology Co Ltd
Priority to CN201911155478.0A priority Critical patent/CN112835350A/en
Publication of CN112835350A publication Critical patent/CN112835350A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/582Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of traffic signs
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/586Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096805Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route
    • G08G1/096827Systems involving transmission of navigation instructions to the vehicle where the transmitted instructions are used to compute a route where the route is computed onboard
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/141Traffic control systems for road vehicles indicating individual free spaces in parking areas with means giving the indication of available parking spaces
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/14Traffic control systems for road vehicles indicating individual free spaces in parking areas
    • G08G1/149Traffic control systems for road vehicles indicating individual free spaces in parking areas coupled to means for restricting the access to the parking space, e.g. authorization, access barriers, indicative lights

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Theoretical Computer Science (AREA)
  • Remote Sensing (AREA)
  • Computer Security & Cryptography (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Electromagnetism (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

The application provides an automatic parking method, a device and a system, wherein the method comprises the following steps: controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera arranged on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image; if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space; and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy. Through the technical scheme of this application, improve automatic parking efficiency, improve user's use and experience.

Description

Automatic parking method, device and system
Technical Field
The application relates to the technical field of auxiliary driving, in particular to an automatic parking method, device and system.
Background
With the continuous development of the vehicle auxiliary driving technology, many vehicles have an automatic parking function (automatic parking can also be called automatic parking), and automatic parking refers to automatic parking of the vehicles without manual control of users, so that the vehicles can be helped to park automatically by the users, manual parking of the users is avoided, and the use experience of the users can be improved. At present, in the automatic parking process, a user needs to drive a vehicle to a position near an available parking space and then input an automatic parking instruction to a vehicle-mounted control system. After receiving the automatic parking instruction, the vehicle-mounted control system controls the vehicle to automatically park in place without manually parking in place by a user.
In the above manner, the user is required to drive the vehicle to a position near the available parking space, and if the user does not know the condition of the available parking space in the parking lot, the user needs to continuously search for the available parking space, so that the efficiency of automatic parking is low.
Disclosure of Invention
The application provides an automatic parking method, which comprises the following steps:
controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera deployed on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image;
if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space;
and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
The application provides an on-vehicle control system, on-vehicle control system deploys on the vehicle, on-vehicle control system includes on-vehicle camera and on-vehicle treater, wherein:
the vehicle-mounted camera is used for acquiring a first image in the running process of a vehicle and outputting the first image to the vehicle-mounted processor;
the vehicle-mounted processor is used for controlling the vehicle to run according to a specified path; acquiring guide sign information according to the first image in the running process of the vehicle; if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space; and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
The application provides an on-vehicle control system, includes: an onboard processor and a machine-readable storage medium storing machine-executable instructions executable by the onboard processor; the onboard processor is configured to execute machine executable instructions to perform the steps of:
controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera deployed on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image;
if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space;
and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
The application provides an automatic parking device, the device includes:
the control module is used for controlling the vehicle to run according to the specified path;
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a first image through a vehicle-mounted camera arranged on a vehicle in the driving process of the vehicle and acquiring guide sign information according to the first image;
the selection module is used for selecting one available parking space from the at least one available parking space as a target available parking space if the situation that the at least one available parking space exists around the vehicle is determined according to the guiding mark information;
and the processing module is used for acquiring a parking control strategy of the vehicle if the target available parking space is determined to be capable of parking the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
According to the technical scheme, in the embodiment of the application, the vehicle-mounted control system can acquire the guide mark information and determine the available parking spaces around the vehicle according to the guide mark information in the driving process of the vehicle, so that the available parking spaces around the vehicle can be automatically determined, a user does not need to drive the vehicle to the position near the available parking spaces, and the user does not need to continuously search for the available parking spaces. According to the mode, the available parking space information can be efficiently obtained, the vehicle can be accurately parked in the available parking space, the automatic parking efficiency is high, the automatic parking efficiency is improved, the automatic parking process is completely separated from the control of the user, the user does not need to participate, and the use experience of the user is improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments of the present application or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings of the embodiments of the present application.
FIG. 1 is a schematic flow chart diagram of an automated parking method in one embodiment of the present application;
FIG. 2 is a schematic diagram of a deployment of multiple in-vehicle cameras in one embodiment of the present application;
FIG. 3A is a schematic flow chart diagram of an automated parking method in one embodiment of the present application;
3B-3F are schematic diagrams of finding available parking spaces in one embodiment of the present application;
FIG. 4A is a schematic flow chart diagram of an automated parking method in one embodiment of the present application;
FIGS. 4B-4E are schematic parking diagrams in one embodiment of the present application;
fig. 5 is a schematic structural view of an automatic parking apparatus according to an embodiment of the present application;
fig. 6 is a hardware configuration diagram of an in-vehicle control system according to an embodiment of the present application.
Detailed Description
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein is meant to encompass any and all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in the embodiments of the present application to describe various information, the information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. Depending on the context, moreover, the word "if" as used may be interpreted as "at … …" or "when … …" or "in response to a determination".
The embodiment of the application provides an automatic parking method, which can be applied to a vehicle-mounted control system, wherein the vehicle-mounted control system is used for controlling automatic parking of a vehicle, namely, the vehicle is automatically parked in an available parking space of a parking lot, the parking lot can be an indoor parking lot or an outdoor parking lot, the parking lot can also be a public parking lot or a private parking lot, and the type of the parking lot is not limited. In the embodiment, in the driving process of the vehicle, the vehicle-mounted control system can acquire the guide mark information and determine the available parking spaces around the vehicle according to the guide mark information, so that the available parking spaces around the vehicle are automatically determined, a user does not need to drive the vehicle to the position near the available parking spaces, the user does not need to continuously search for the available parking spaces, the automatic parking process is completely separated from the control of the user, the participation of the user is not needed, and the parking efficiency and the use experience are improved.
Referring to fig. 1, a flow chart of an automatic parking method may include:
and step 101, controlling the vehicle to run according to a specified route.
After a user drives a vehicle to a certain area, the automatic parking function can be started, and a default path is set, wherein the default path is set by the user at will, and is not limited. During the running process of the vehicle, the vehicle-mounted control system can adjust the path. After the automatic parking function is started, the user can get off and leave, or can stay on the vehicle, which is not limited to this. In the subsequent automatic parking process, no user is required to participate.
And the vehicle-mounted control system acquires the appointed path after learning that the automatic parking function is started by the user, and controls the vehicle to run according to the appointed path. Illustratively, if the user does not set a default path, the vehicle-mounted control system randomly selects one path as an appointed path; if the user sets the default path, the vehicle-mounted control system takes the default path set by the user as the designated path, or randomly selects one path as the designated path. During the running process of the vehicle, the vehicle-mounted control system adjusts the path and takes the adjusted path as the designated path.
Step 102, in the vehicle running process (i.e. the process that the vehicle runs according to the specified route), a first image is collected through a vehicle-mounted camera arranged on the vehicle, and the guide sign information is obtained according to the first image.
One or more vehicle-mounted cameras can be deployed on the vehicle, and a schematic diagram of 1 front-view vehicle-mounted camera and 4 all-around vehicle-mounted cameras is shown in fig. 2. Of course, the number of the onboard cameras can be configured arbitrarily, and is not limited thereto. The front-view vehicle-mounted camera can be a monocular long-focus camera and is used for collecting images in front of the vehicle; the look-around vehicle-mounted camera can be a fisheye camera and is used for collecting images around the vehicle.
During the running process of the vehicle, the vehicle-mounted camera can acquire images in real time, such as images in front of the vehicle and images around the vehicle. Based on the images acquired by the vehicle-mounted camera, the vehicle-mounted control system can acquire the images, analyze the images according to the images and then perform corresponding processing according to the analysis result.
For a large number of images acquired by the vehicle-mounted camera, an image including the guidance sign information may be referred to as a first image, the first image may be an image acquired by a single vehicle-mounted camera, or may be a panorama formed by splicing images acquired by a plurality of vehicle-mounted cameras, and the type of the first image is not limited.
For example, the in-vehicle control system may acquire guidance mark information from the first image, the guidance mark information including, but not limited to: the parking space line state and/or the lighting state of the parking space indicating lamp are/is used for indicating whether the parking space is available or not, and the lighting state of the parking space indicating lamp is used for indicating whether the parking space is available or not.
The parking space line state comprises a complete parking space line or an incomplete parking space line. For example, a carport line is typically composed of four sides, and the four sides constitute a rectangle. If the vehicle-mounted control system detects four sides of the parking space line according to the first image and the four sides form a rectangle, the parking space line state is determined to be complete and used for indicating that a parking space is available. If the vehicle-mounted control system does not detect the four sides of the parking space line according to the first image, or detects the four sides of the parking space line, but the four sides do not form a rectangle, the parking space line state is determined to be incomplete, and the parking space line state is used for indicating that a parking space is unavailable.
In summary, when the parking space line state of a certain parking space is the parking space line is complete, it indicates that the vehicle is not parked in the parking space, and the parking space is an available parking space. When the parking space line state of a certain parking space is that the parking space line is not complete, the parking space indicates that the vehicle is parked in the parking space, and the parking space is not an available parking space.
In a possible implementation manner, the lighting state of the parking space indicator lamp includes that the indicator lamp is turned on or the indicator lamp is not turned on, when the lighting state of the parking space indicator lamp of a certain parking space is that the indicator lamp is turned on, it indicates that the vehicle is not parked in the parking space, the parking space is an available parking space, and when the lighting state of the parking space indicator lamp of the certain parking space is that the indicator lamp is not turned on, it indicates that the vehicle is parked in the parking space, and the parking space is not an available parking space. Or when the light state of the parking space indicator lamp of a certain parking space is that the indicator lamp is turned on, the parking space indicates that the vehicle is already parked in the parking space, and the parking space is not an available parking space.
In another possible embodiment, the lighting state of the parking space indicator light includes that the indicator light lights up in a first color (e.g., green) or the indicator light lights up in a second color (e.g., red), when the lighting state of the parking space indicator light of a certain parking space is that the indicator light lights up in the first color, it indicates that the parking space does not stop the vehicle, the parking space is an available parking space, and when the lighting state of the parking space indicator light of a certain parking space is that the indicator light lights up in the second color, it indicates that the parking space stops the vehicle, and the parking space is not an available parking space.
Of course, the above is only an example of the car position line state and the lighting state of the parking space indicator lamp, and no limitation is made to this, as long as the car position line state can indicate whether the parking space is an available parking space, and the lighting state of the parking space indicator lamp can indicate whether the parking space is an available parking space.
The vehicle-mounted control system may have a deep learning calculation capability, for example, the vehicle-mounted control system includes a neural network, and the neural network is used to construct a corresponding relationship between the feature vector and the guidance sign information, such as a complete corresponding relationship between the feature vector a and the parking space line, an incomplete corresponding relationship between the feature vector B and the parking space line, a corresponding relationship between the feature vector C and the indicator light, a corresponding relationship between the feature vector D and the indicator light that is not lit, and the like.
For example, a large number of training images may be input to the neural network, and these training images may include a label value, and the label value is used to indicate that the carport line is complete, the carport line is incomplete, the indicator light is on, the indicator light is not on, and so on. Based on the training images and the label values corresponding to the training images, the neural network can construct the corresponding relation between the feature vectors and the guide mark information, and the construction process is not limited.
In summary, after obtaining the first image, the vehicle-mounted control system may input the first image to the neural network, obtain the feature vector of the first image by the neural network, and determine the guidance sign information corresponding to the feature vector, where the vehicle-mounted control system determines that the vehicle-mounted line state is a complete vehicle position line, or the vehicle-mounted line state is an incomplete vehicle position line, or the lighting state of the vehicle position indicator light is that the indicator light is turned on, or the lighting state of the vehicle position indicator light is that the indicator light is not turned on.
Of course, the implementation of the neural network is only an example, and is not limited to the implementation of the neural network, as long as the vehicle-mounted control system can acquire the guidance mark information according to the first image.
And 103, if at least one available parking space exists around the vehicle according to the guiding mark information, selecting one available parking space from the at least one available parking space as a target available parking space.
For example, if it is determined that the first space is available according to the space line state, it is determined that the first space is an available space around the vehicle. For example, for a certain parking space (for convenience of description, referred to as a first parking space), if the guidance sign information of the first parking space is obtained according to the first image corresponding to the first parking space and the guidance sign information includes the position line state, it is determined whether the first parking space is an available parking space around the vehicle according to the position line state. If the position line state is that the position line is complete, determining that the first position is an available position around the vehicle; and if the position line state is that the position line is not complete, determining that the first position is not an available position around the vehicle.
For example, if it is determined that the second parking space is available according to the lighting state of the parking space indicator lamp, it is determined that the second parking space is an available parking space around the vehicle. For example, for a certain parking space (for convenience of description, referred to as a second parking space), if the guidance sign information of the second parking space is obtained according to the first image corresponding to the second parking space and the guidance sign information includes the lighting state of the parking space indicator lamp, it is determined whether the second parking space is an available parking space around the vehicle according to the lighting state of the parking space indicator lamp. If the lighting state of the parking space indicator lamp is that the indicator lamp is on, determining that the second parking space is an available parking space around the vehicle; and if the lighting state of the parking space indicator lamp is that the indicator lamp is not lighted, determining that the second parking space is not an available parking space around the vehicle.
For example, if it is determined that the third parking space is available according to the parking space line state and it is determined that the third parking space is available according to the lighting state of the parking space indicator lamp, it is determined that the third parking space is an available parking space around the vehicle. For example, for a certain parking space (for convenience of description, referred to as a third parking space), if the guidance sign information of the third parking space is obtained according to the first image corresponding to the third parking space and the guidance sign information includes the vehicle location line state and the lighting state of the parking space indicator, it is determined whether the third parking space is an available parking space around the vehicle according to the vehicle location line state and the lighting state of the parking space indicator. And if the parking space line state is that the parking space line is complete and the lighting state of the parking space indicator lamp is that the indicator lamp is on, determining that the third parking space is an available parking space around the vehicle. If the parking space line state is that the parking space line is incomplete, no matter the lighting state of the parking space indicating lamp is that the indicating lamp is on or the indicating lamp is not on, the third parking space can be determined to be not an available parking space around the vehicle.
For example, if the fourth parking space is determined to be available according to the parking space line state and the fourth parking space is determined to be unavailable according to the lighting state of the parking space indicator lamp, the fourth parking space is determined to be an available parking space around the vehicle. For example, for a certain parking space (for convenience of description, referred to as a fourth parking space), if the guidance sign information of the fourth parking space is acquired according to the first image corresponding to the fourth parking space and the guidance sign information includes the vehicle location line state and the lighting state of the parking space indicator, it is determined whether the fourth parking space is an available parking space around the vehicle according to the vehicle location line state and the lighting state of the parking space indicator. And if the parking space line state is that the parking space line is complete and the lighting state of the parking space indicating lamp is that the indicating lamp is not on, determining that the fourth parking space is an available parking space around the vehicle. If the parking space line state is that the parking space line is incomplete, whether the lighting state of the parking space indicating lamp is that the indicating lamp is on or the indicating lamp is not on, the fourth parking space is determined to be not an available parking space around the vehicle.
In summary, when the guidance sign information includes the vehicle location line state and the lighting state of the parking space indicator, the priority of the parking space line state may be higher than the priority of the lighting state of the parking space indicator, that is, it is determined whether the parking space is an available parking space around the vehicle based on the determination result of the vehicle location line state.
For example, selecting one available space from at least one available space as the target available space includes, but is not limited to: and if one available parking space exists, taking the available parking space as the target available parking space. Or if more than two available parking spaces exist, selecting one available parking space from the more than two available parking spaces as the target available parking space according to the distance and/or direction between each available parking space and the vehicle.
For example, for each of the more than two available parking spaces, the in-vehicle control system may obtain the distance between the available parking space and the vehicle, and use the available parking space with the smallest distance as the target available parking space.
During the running process of the vehicle, the vehicle-mounted camera can acquire images in real time, such as images in front of the vehicle and images around the vehicle. Based on the images acquired by the vehicle-mounted camera, the vehicle-mounted control system can acquire the images, analyze the images according to the images and then perform corresponding processing according to the analysis result.
Based on this, for each available parking space, the vehicle-mounted control system may acquire the distance between the available parking space and the vehicle according to the image including the available parking space, and the acquisition mode of the distance is not limited. For example, the vehicle-mounted control system may obtain a distance 1 between the available parking space 1 and the vehicle, and a distance 2 between the available parking space 2 and the vehicle, and if the distance 1 is smaller than the distance 2, the available parking space 1 corresponding to the distance 1 is taken as the target available parking space.
For example, for each of the more than two available parking spaces, the vehicle-mounted control system may acquire the available parking space and the direction of the vehicle, and use the available parking space in the designated direction as the target available parking space. The specified direction is a right direction of the vehicle or a left direction of the vehicle, and the right direction is taken as an example for explanation.
For each available parking space, the vehicle-mounted control system may acquire the available parking space and the direction of the vehicle according to the image including the available parking space, and the acquisition mode is not limited. For example, an available space 1 and a direction 1 of the vehicle and an available space 2 and a direction 2 of the vehicle are acquired, and if the direction 1 is a right direction of the vehicle and the direction 2 is a left direction of the vehicle, the available space 1 corresponding to the right direction is set as a target available space.
For example, for each of the more than two available slots, the in-vehicle control system obtains the distance from the vehicle to the available slot and the direction of the vehicle. And if the available parking space with the minimum distance is one, taking the available parking space with the minimum distance as the target available parking space. If the available parking spaces with the minimum distance are not one, selecting the available parking spaces in the appointed direction (such as the right direction of the vehicle or the left direction of the vehicle) from the available parking spaces with the minimum distance, and taking the available parking spaces in the appointed direction as target available parking spaces.
For each available parking space, the vehicle-mounted control system can acquire the distance between the available parking space and the vehicle according to the image comprising the available parking space, and the directions of the available parking space and the vehicle do not limit the acquisition mode. For example, the vehicle-mounted control system may obtain a distance 1 between the available parking space 1 and the vehicle, a direction 1 between the available parking space 1 and the vehicle, a distance 2 between the available parking space 2 and the vehicle, and a direction 2 between the available parking space 2 and the vehicle, and if the distance 1 is smaller than the distance 2, the available parking space 1 corresponding to the distance 1 may be used as the target available parking space. Assuming that the distance 1 is equal to the distance 2, the available space 1 corresponding to the right direction may be used as the target available space.
In summary, when the distance between the available parking space and the vehicle is obtained, the available parking space with the smallest distance is preferentially selected as the target available parking space. When the available parking spaces and the directions of the vehicles are obtained, the available parking spaces in the right direction are preferentially selected as the target available parking spaces. When the distance between the available parking spaces and the vehicle and the directions of the available parking spaces and the vehicle are obtained, the priority of the distance is higher than the priority of the direction, that is, the available parking space with the minimum distance is preferentially selected as the target available parking space, and when the available parking spaces with the minimum distance are at least two, the available parking space in the right direction is preferentially selected as the target available parking space from the available parking spaces with the minimum distance.
And 104, if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy. And if the vehicle cannot be parked in the target available parking space, prohibiting the vehicle from being parked in the target available parking space, and returning to execute the step 101.
For example, after selecting one available parking space from at least one available parking space as the target available parking space, the vehicle-mounted control system may further determine whether the target available parking space is capable of parking the vehicle.
And if so, acquiring a parking control strategy of the vehicle, and parking the vehicle at the target available parking space according to the parking control strategy. The parking control strategy may include, but is not limited to: the parking control strategy is not limited as long as the vehicle can be parked at the target available parking space according to the parking control strategy. In the process of parking the vehicle in the target available parking space, the parking control strategy of the vehicle can be continuously adjusted, so that the vehicle-mounted control system can successfully park the vehicle in the target available parking space according to the parking control strategy. In a word, the parking control strategy of the vehicle can be continuously adjusted according to the position relation between the vehicle and the target available parking space, the posture of the vehicle body is adjusted according to the parking control strategy, and then the vehicle is successfully parked at the target available parking space.
If not, the situation shows that the vehicle cannot be parked in the target available parking space, the vehicle-mounted control system prohibits the vehicle from being parked in the target available parking space, and returns to execute the step 101, so that a new available parking space can be selected as the target available parking space, the step 104 is executed again, and the like is repeated until the vehicle is successfully parked in the target available parking space.
For example, the vehicle-mounted control system may acquire a third image (the third image may be the same as or different from the first image, and is not limited thereto) through a vehicle-mounted camera deployed on the vehicle, and determine whether a target available parking space has a parking prohibition object according to the third image; if so, determining that the target available parking space can not stop the vehicle; and if not, determining that the target available parking space can stop the vehicle.
The stay-prohibited object may include, but is not limited to: the exclusive parking space mark, the parking forbidding mark, and the barrier (such as other vehicles, ground locks, garbage cans and the like, the barrier is not limited), so that the parking forbidding object is not limited.
For example, for a large number of images collected by the vehicle-mounted camera, an image including the target available parking space may be referred to as a third image, and the vehicle-mounted control system may determine whether a parking prohibition object exists in the target available parking space according to the third image. For example, if the vehicle-mounted control system detects that one or more of a target available parking space exclusive parking space mark, a parking prohibition mark and an obstacle exist in the target available parking space according to the third image, it is determined that a parking prohibition object exists in the target available parking space. And if the vehicle-mounted control system detects that the target available parking space does not have any exclusive parking space mark, a forbidden parking mark or any one of the obstacles according to the third image, determining that the target available parking space does not have a forbidden parking object.
For example, the vehicle-mounted control system may include a neural network, and the neural network is configured to construct a corresponding relationship between a feature vector and a parking prohibition object, such as a corresponding relationship between a feature vector 1 and an exclusive parking space sign, a corresponding relationship between a feature vector 2 and a parking prohibition sign, a corresponding relationship between a feature vector 3 and an obstacle, and the like. For example, a number of training images may be input to the neural network, which may include tag values, and the tag values are used to represent a parking target such as a parking lot marker, a parking prohibition marker, an obstacle, and the like. Based on the training images and the label values corresponding to the training images, the neural network can construct the corresponding relation between the feature vectors and the stop-forbidden objects, and the construction process is not limited.
In summary, after obtaining the third image, the vehicle-mounted control system inputs the third image to the neural network, the neural network obtains a feature vector of the third image, and if the feature vector corresponds to a forbidden object (such as an exclusive parking space mark, a forbidden parking mark, or an obstacle), it is determined that the forbidden object exists in the target available parking space. And if the characteristic vector does not correspond to all the forbidden objects, determining that no forbidden object exists in the target available parking space.
Of course, the implementation manner of the neural network is only an example, and is not limited to the implementation manner of the neural network, as long as the vehicle-mounted control system can determine whether the target available parking space has the forbidden object.
In a possible implementation manner, in the driving process of a vehicle, if it is determined that there is no available parking space around the vehicle according to the guidance sign information, that is, no available parking space is found, acquiring a second image (the second image may be the same as or different from the first image, and is not limited thereto) by using a vehicle-mounted camera disposed on the vehicle, and acquiring available parking space indication information according to the second image, where the available parking space indication information is used to indicate the number of available parking spaces in each direction, for example, the number of available parking spaces in each direction may be indicated by an available parking space indication board, or the number of available parking spaces in each direction may be displayed by a display screen, and is not limited thereto; then, the driving route of the vehicle is updated according to the available parking space indication information, the updated driving route is determined as the designated route, and the vehicle is controlled to drive according to the designated route, namely, the step 101 is returned.
For a large number of images collected by the vehicle-mounted camera, the image including the available parking space indication information can be referred to as a second image. The vehicle-mounted control system may determine, according to the second image, the parking space indication information indicating the number of available parking spaces in each direction, such as the number of available parking spaces in the front path, the number of available parking spaces in the left path, the number of available parking spaces in the right path, and the like. Based on the number of available parking spaces in each direction, the vehicle-mounted control system can update the driving path of the vehicle, determine the updated driving path as the designated path, and control the vehicle to drive according to the designated path. For example, the route with the largest number of available parking spaces is updated to the designated route, and if the number of available parking spaces on the right-side route is the largest, the right-side route is updated to the designated route.
For example, the second image may include parking space indication information, which may include a left arrow and a corresponding number thereof, and the in-vehicle control system determines the number of available parking spaces of the left path according to the information; the parking space indication information can comprise a right arrow and the corresponding number of the right arrow, and the vehicle-mounted control system determines the number of available parking spaces on the right path according to the information; the space indication information may include a forward arrow and its corresponding number, from which the onboard control system determines the number of available spaces on the forward path.
Of course, the above implementation manner is only an example, and the vehicle-mounted control system is not limited as long as the vehicle-mounted control system can determine the parking space indication information (such as the number of available parking spaces on the left-side path) according to the second image.
In one possible implementation, obtaining the parking control strategy of the vehicle may include, but is not limited to: and acquiring a fourth image (the fourth image may be the same as or different from the first image, and is not limited to the first image) through a vehicle-mounted camera deployed on the vehicle, and if it is determined that obstacles (such as a wall surface, a cylinder and the like) exist around the target available parking space according to the fourth image, determining that the parking control strategy comprises a reversing strategy.
For a large number of images acquired by the vehicle-mounted camera, an image including the target available parking space may be referred to as a fourth image (the fourth image is distinguished from the third image by emphasizing information around the target available parking space and used for detecting whether an obstacle exists around the target available parking space, and the third image is emphasized by emphasizing information in the target available parking space and used for detecting whether a parking prohibition object exists in the target available parking space), and the vehicle-mounted control system may determine whether an obstacle (such as a wall surface, a cylinder, and the like) exists around the target available parking space according to the fourth image.
For example, the vehicle-mounted control system may include a neural network, and the neural network is used to construct a corresponding relationship between the feature vector and the obstacle around the parking space, and the construction process is not limited, and may be obtained by training the neural network based on a large number of training images. For example, a number of training images may be input to the neural network, which may include tag values, and the tag values are used to represent obstacles around the parking space. Based on the training images and the label values of the training images, the neural network constructs the corresponding relation between the characteristic vectors and the obstacles around the parking space, and the construction process is not limited.
In summary, after obtaining the fourth image, the vehicle-mounted control system inputs the fourth image to the neural network, the neural network obtains a feature vector of the fourth image, and if the feature vector corresponds to an obstacle around the parking space, it is determined that an obstacle exists around the target available parking space. And if the characteristic vector does not correspond to the obstacles around the parking space, determining that no obstacle exists around the target available parking space. Of course, the above manner is only an example, and the present invention is not limited thereto, as long as the vehicle-mounted control system can determine whether there is an obstacle around the target available parking space.
According to the technical scheme, in the embodiment of the application, the vehicle-mounted control system can acquire the guide mark information and determine the available parking spaces around the vehicle according to the guide mark information in the driving process of the vehicle, so that the available parking spaces around the vehicle can be automatically determined, a user does not need to drive the vehicle to the position near the available parking spaces, and the user does not need to continuously search for the available parking spaces. According to the mode, the available parking space information can be efficiently obtained, the vehicle can be accurately parked in the available parking space, the automatic parking efficiency is high, the automatic parking efficiency is improved, the automatic parking process is completely separated from the control of the user, the user does not need to participate, and the use experience of the user is improved.
In one possible implementation, see fig. 3A, a schematic diagram of determining a target available parking space is shown.
After the vehicle-mounted control system is started, a specified path is set, and the vehicle is controlled to travel according to the specified path.
And determining whether at least one available parking space exists around the vehicle according to the guiding mark information during the driving process of the vehicle. If not, the vehicle is continuously controlled to run according to the specified route.
If so, selecting one available parking space from the at least one available parking space as a target available parking space, and judging whether the target available parking space can stop the vehicle. And if the vehicle can be parked, parking the vehicle in the target available parking space. And if the vehicle cannot be parked, controlling the vehicle to travel according to the specified route.
Referring to fig. 3B, in the driving process of the vehicle, available parking spaces a, B, C and the like are identified, the available parking space a and the available parking space C are located on the right side of the vehicle, the available parking space B is located on the left side of the vehicle, the distance between the available parking space a and the vehicle is smaller than the distance between the available parking space C and the vehicle, and the available parking space a is used as a target available parking space.
Referring to fig. 3C, in the driving process of the vehicle, the available parking spaces B and C are identified, the available parking space C is located on the right side of the vehicle, the available parking space B is located on the left side of the vehicle, the distance between the available parking space B and the vehicle is smaller than the distance between the available parking space C and the vehicle, and the available parking space B is used as a target available parking space.
Referring to fig. 3D, in the driving process of the vehicle, the available parking space indication information (used for indicating the number of available parking spaces in each direction) and the available parking space D are identified, and the available parking space D is taken as the target available parking space.
Referring to fig. 3E, in the driving process of the vehicle, available parking space indication information (for indicating the number of available parking spaces in each direction) is identified, the available parking space indication information indicates that the number of available parking spaces at the right side of the intersection is 58, the number of available parking spaces at the front of the intersection is 14, and the number of available parking spaces at the left side of the intersection is 0, that is, the number of available parking spaces at the right side of the intersection is greater than the number of available parking spaces at the front of the intersection, and the number of available parking spaces at the right side of the intersection is greater than the. Therefore, the vehicle-mounted control system can update the driving path of the vehicle according to the available parking space indication information, namely, the driving path of the vehicle is updated to be driven to the right instead of being driven to the front, and the left driving is also identified. And then, determining the updated driving path as an appointed path, and controlling the vehicle to drive according to the appointed path, namely controlling the vehicle to drive to the right by the vehicle-mounted control system to continuously search for the available parking space.
Referring to fig. 3F, in the driving process of the vehicle, it is recognized that there is an available parking space E at the right side of the intersection, and there is a wall surface or an obstacle at the right side of the available parking space E, so that the vehicle-mounted control system determines that the parking control strategy includes a reverse strategy, that is, the vehicle-mounted control system selects to reverse to enter the right road.
For example, referring to fig. 4A, a schematic diagram of parking a vehicle in a target available space is shown.
And controlling the vehicle to reach the position near the target available parking space, and detecting whether the target available parking space is available. If not, the library searching stage is re-entered, i.e. the flow shown in fig. 3A is executed. And if so, acquiring a parking control strategy of the vehicle, and parking the vehicle at the target available parking space according to the parking control strategy. And judging whether the vehicle body is at an expected position in the target available parking space or not in the process of parking the vehicle at the target available parking space. If so, the automatic parking is finished. If not, whether the target available parking space is available is detected again, and the like.
Referring to fig. 4B, in the driving process of the vehicle, the available parking space a is used as the target available parking space, and the vehicle needs to be parked to the available parking space a, and in the process of parking the vehicle to the available parking space a, it is sensed that an obstacle exists in the available parking space a, so that the available parking space a is abandoned, the vehicle is controlled to drive according to the designated path, and the target available parking space is selected again. For example, the available space B is used as the target available space, and the vehicle needs to be parked to the available space B, and in the process of parking the vehicle to the available space B, it is sensed that no obstacle exists in the available space B, so that the vehicle can be successfully parked to the available space B.
Referring to fig. 4C, in the driving process of the vehicle, the available parking space a is used as the target available parking space, and the vehicle needs to be parked to the available parking space a, and in the process of parking the vehicle to the available parking space a, it is sensed that an obstacle exists in the available parking space a, so that the available parking space a is abandoned, the vehicle is controlled to drive according to the designated path, and the target available parking space is selected again. For example, the available space B is used as the target available space, and the vehicle needs to be parked to the available space B, and in the process of parking the vehicle to the available space B, it is sensed that no obstacle exists in the available space B, so that the vehicle can be successfully parked to the available space B.
Referring to fig. 4D and 4E, in the driving process of the vehicle, the available parking space a is used as a target available parking space, the vehicle is controlled to reverse into the available parking space a in the process of parking the vehicle to the available parking space a, in the process of entering into the available parking space a, the position relation between the vehicle and surrounding obstacles and a parking line is continuously detected, and the posture of the vehicle body is continuously adjusted until the vehicle body completely enters into the available parking space a.
Based on the same application concept as the above method, an automatic parking apparatus is provided in the embodiment of the present application, and as shown in fig. 5, the apparatus may include:
the control module 51 is used for controlling the vehicle to run according to a specified path;
the acquiring module 52 is configured to acquire a first image through a vehicle-mounted camera deployed on a vehicle in a vehicle driving process, and acquire guidance sign information according to the first image;
a selecting module 53, configured to select one available parking space from the at least one available parking space as a target available parking space if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information;
and the processing module 54 is configured to, if it is determined that the target available parking space can be used for parking the vehicle, obtain a parking control policy of the vehicle, and park the vehicle in the target available parking space according to the parking control policy.
For example, when the selection module 53 selects one available parking space from the at least one available parking space as the target available parking space, it is specifically configured to: and if more than two available parking spaces exist, selecting one available parking space from the more than two available parking spaces as a target available parking space according to the distance and/or direction between each available parking space and the vehicle.
Illustratively, the guidance sign information includes a parking space line state and/or a lighting state of a parking space indicator lamp; the parking space line state is used for indicating whether the parking space is available, and the lighting state of the parking space indicating lamp is used for indicating whether the parking space is available. The selection module 53 is specifically configured to, when determining that at least one available space exists around the vehicle according to the guidance sign information: if the first parking space is determined to be available according to the parking space line state, determining that the first parking space is an available parking space around the vehicle; or if the second parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the second parking space is an available parking space around the vehicle; or if the third parking space is determined to be available according to the parking space line state and the third parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the third parking space is an available parking space around the vehicle; or if the fourth parking space is determined to be available according to the parking space line state and the fourth parking space is determined to be unavailable according to the lighting state of the parking space indicator lamp, determining that the fourth parking space is the available parking space around the vehicle.
The obtaining module 52 is further configured to: in the running process of a vehicle, if no available parking space is found, acquiring a second image through a vehicle-mounted camera deployed on the vehicle, and acquiring available parking space indication information according to the second image; the available parking space indication information is used for indicating the number of available parking spaces in each direction;
the control module 51 is further configured to: and updating the running path of the vehicle according to the available parking space indication information, determining the updated running path as a specified path, and controlling the vehicle to run according to the specified path.
Illustratively, the processing module 54 is further configured to: and if the target available parking space cannot be used for parking the vehicle, prohibiting the vehicle from being parked in the target available parking space.
Illustratively, the processing module 54 is further configured to: acquiring a third image through a vehicle-mounted camera deployed on the vehicle, and determining whether a target available parking space has a forbidden object according to the third image;
if so, determining that the vehicle cannot be parked in the target available parking space;
and if not, determining that the target available parking space can park the vehicle.
For example, the processing module 54 is specifically configured to, when obtaining the parking control strategy of the vehicle: and acquiring a fourth image through a vehicle-mounted camera deployed on the vehicle, and determining that the parking control strategy comprises a reversing strategy if the obstacles around the target available parking space are determined according to the fourth image.
Based on the same application concept as the method, the embodiment of the present application provides an onboard control system, where the onboard control system is deployed on a vehicle, the onboard control system includes an onboard camera and an onboard processor, where: the vehicle-mounted camera is used for acquiring a first image in the running process of a vehicle and outputting the first image to the vehicle-mounted processor;
the vehicle-mounted processor is used for controlling the vehicle to run according to a specified path; acquiring guide sign information according to the first image in the running process of the vehicle; if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space; and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
For example, the onboard processor is specifically configured to, when selecting one available space from the at least one available space as the target available space:
and if more than two available parking spaces exist, selecting one available parking space from the more than two available parking spaces as a target available parking space according to the distance and/or direction between each available parking space and the vehicle.
Illustratively, the guidance sign information includes a parking space line state and/or a lighting state of a parking space indicator lamp; the parking space line state is used for indicating whether a parking space is available or not, and the lighting state of the parking space indicating lamp is used for indicating whether the parking space is available or not;
the onboard processor is specifically configured to, when determining that at least one available parking space exists around the vehicle according to the guidance sign information: if the first parking space is determined to be available according to the parking space line state, determining that the first parking space is an available parking space around the vehicle; or if the second parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the second parking space is an available parking space around the vehicle; or if the third parking space is determined to be available according to the parking space line state and the third parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the third parking space is an available parking space around the vehicle; or if the fourth parking space is determined to be available according to the parking space line state and the fourth parking space is determined to be unavailable according to the lighting state of the parking space indicator lamp, determining that the fourth parking space is the available parking space around the vehicle.
Based on the same application concept as the method, the embodiment of the present application provides an on-board control system, as shown in fig. 6, the on-board control system includes: an onboard processor 61 and a machine-readable storage medium 62, the machine-readable storage medium 62 storing machine-executable instructions executable by the onboard processor 61; the onboard processor 61 is configured to execute machine executable instructions to perform the steps of:
controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera deployed on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image;
if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space;
and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
Based on the same application concept as the method, embodiments of the present application further provide a machine-readable storage medium, where several computer instructions are stored on the machine-readable storage medium, and when the computer instructions are executed by a processor, the automatic parking method disclosed in the above example of the present application can be implemented.
For example, the computer instructions, when executed by a processor, enable the following steps:
controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera deployed on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image;
if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space;
and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
The machine-readable storage medium may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and the like. For example, the machine-readable storage medium may be: a RAM (random Access Memory), a volatile Memory, a non-volatile Memory, a flash Memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., an optical disk, a dvd, etc.), or similar storage medium, or a combination thereof.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. A typical implementation device is a computer, which may take the form of a personal computer, laptop computer, cellular telephone, camera phone, smart phone, personal digital assistant, media player, navigation device, email messaging device, game console, tablet computer, wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Furthermore, these computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (13)

1. An automatic parking method, characterized in that the method comprises:
controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera deployed on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image;
if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space;
and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
2. The method according to claim 1, wherein the selecting one of the at least one available space as the target available space specifically comprises:
and if more than two available parking spaces exist, selecting one available parking space from the more than two available parking spaces as a target available parking space according to the distance and/or direction between each available parking space and the vehicle.
3. The method of claim 1, wherein the guidance sign information includes a parking line status and/or a lighting status of a parking space indicator light; the parking space line state is used for indicating whether the parking space is available, and the lighting state of the parking space indicating lamp is used for indicating whether the parking space is available.
4. The method according to claim 3, wherein the determining that there is at least one available space around the vehicle according to the guidance sign information specifically comprises:
if the first parking space is determined to be available according to the parking space line state, determining that the first parking space is an available parking space around the vehicle; or,
if the second parking space is available according to the lighting state of the parking space indicator lamp, determining that the second parking space is an available parking space around the vehicle; or,
if the third parking space is determined to be available according to the position line state and the third parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the third parking space is an available parking space around the vehicle; or,
and if the fourth parking space is determined to be available according to the parking space line state and the fourth parking space is determined to be unavailable according to the lighting state of the parking space indicator lamp, determining that the fourth parking space is an available parking space around the vehicle.
5. The method of claim 1, wherein prior to determining that there is at least one available space around the vehicle based on the direction indicator information, the method further comprises:
in the running process of a vehicle, if no available parking space is found, acquiring a second image through a vehicle-mounted camera deployed on the vehicle, and acquiring available parking space indication information according to the second image; the available parking space indication information is used for indicating the number of available parking spaces in each direction;
and updating the running path of the vehicle according to the available parking space indication information, determining the updated running path as a specified path, and controlling the vehicle to run according to the specified path.
6. The method of claim 1, wherein after selecting one of the at least one available slot as the target available slot, the method further comprises:
and if the target available parking space is determined to be incapable of parking the vehicle, prohibiting the vehicle from parking in the target available parking space, and returning to execute control of the vehicle to travel according to the designated path.
7. The method according to claim 1 or 6,
the determination method of whether the target available parking space can park the vehicle includes:
acquiring a third image through a vehicle-mounted camera deployed on the vehicle, and determining whether a target available parking space has a forbidden object according to the third image;
if so, determining that the vehicle cannot be parked in the target available parking space;
and if not, determining that the target available parking space can park the vehicle.
8. The method of claim 1,
the obtaining of the parking control strategy of the vehicle comprises:
and acquiring a fourth image through a vehicle-mounted camera deployed on the vehicle, and determining that the parking control strategy comprises a reversing strategy if the obstacles around the target available parking space are determined according to the fourth image.
9. An onboard control system deployed on a vehicle, the onboard control system comprising an onboard camera and an onboard processor, wherein:
the vehicle-mounted camera is used for acquiring a first image in the running process of a vehicle and outputting the first image to the vehicle-mounted processor;
the vehicle-mounted processor is used for controlling the vehicle to run according to a specified path; acquiring guide sign information according to the first image in the running process of the vehicle; if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space; and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
10. The on-board control system of claim 9, wherein the on-board processor is further configured to, when selecting one of the at least one available slot as the target available slot:
and if more than two available parking spaces exist, selecting one available parking space from the more than two available parking spaces as a target available parking space according to the distance and/or direction between each available parking space and the vehicle.
11. The vehicle-mounted control system according to claim 9, wherein the guidance sign information includes a vehicle line state and/or a lighting state of a parking space indicator light; the parking space line state is used for indicating whether a parking space is available or not, and the lighting state of the parking space indicating lamp is used for indicating whether the parking space is available or not;
the onboard processor is specifically configured to, when determining that at least one available parking space exists around the vehicle according to the guidance sign information: if the first parking space is determined to be available according to the parking space line state, determining that the first parking space is an available parking space around the vehicle; or if the second parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the second parking space is an available parking space around the vehicle; or if the third parking space is determined to be available according to the parking space line state and the third parking space is determined to be available according to the lighting state of the parking space indicator lamp, determining that the third parking space is an available parking space around the vehicle; or if the fourth parking space is determined to be available according to the parking space line state and the fourth parking space is determined to be unavailable according to the lighting state of the parking space indicator lamp, determining that the fourth parking space is the available parking space around the vehicle.
12. An onboard control system, comprising: an onboard processor and a machine-readable storage medium storing machine-executable instructions executable by the onboard processor; the onboard processor is configured to execute machine executable instructions to perform the steps of:
controlling the vehicle to run according to a specified path; acquiring a first image through a vehicle-mounted camera deployed on a vehicle in the running process of the vehicle, and acquiring guide sign information according to the first image;
if it is determined that at least one available parking space exists around the vehicle according to the guidance sign information, selecting one available parking space from the at least one available parking space as a target available parking space;
and if the target available parking space is determined to be capable of parking the vehicle, acquiring a parking control strategy of the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
13. An automatic parking apparatus, characterized in that the apparatus comprises:
the control module is used for controlling the vehicle to run according to the specified path;
the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring a first image through a vehicle-mounted camera arranged on a vehicle in the driving process of the vehicle and acquiring guide sign information according to the first image;
the selection module is used for selecting one available parking space from the at least one available parking space as a target available parking space if the situation that the at least one available parking space exists around the vehicle is determined according to the guiding mark information;
and the processing module is used for acquiring a parking control strategy of the vehicle if the target available parking space is determined to be capable of parking the vehicle, and parking the vehicle in the target available parking space according to the parking control strategy.
CN201911155478.0A 2019-11-22 2019-11-22 Automatic parking method, device and system Pending CN112835350A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911155478.0A CN112835350A (en) 2019-11-22 2019-11-22 Automatic parking method, device and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911155478.0A CN112835350A (en) 2019-11-22 2019-11-22 Automatic parking method, device and system

Publications (1)

Publication Number Publication Date
CN112835350A true CN112835350A (en) 2021-05-25

Family

ID=75921583

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911155478.0A Pending CN112835350A (en) 2019-11-22 2019-11-22 Automatic parking method, device and system

Country Status (1)

Country Link
CN (1) CN112835350A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113724323A (en) * 2021-08-24 2021-11-30 杭州海康威视数字技术股份有限公司 Map construction method, device and equipment
CN114141051A (en) * 2021-11-25 2022-03-04 浙江吉利控股集团有限公司 Parking assist method, parking assist system, and computer-readable storage medium
CN114512024A (en) * 2022-02-10 2022-05-17 北京百度网讯科技有限公司 Parking space identification method, device, equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146468A (en) * 2017-07-12 2017-09-08 中国地质大学(武汉) The recognition methods of parking position and system and management method and system
CN109147382A (en) * 2018-09-25 2019-01-04 深圳市元征科技股份有限公司 A kind of intelligent parking method and system
CN109493632A (en) * 2018-11-16 2019-03-19 广州小鹏汽车科技有限公司 Automatic parking method and vehicle control syetem based on more parking stall measures
CN110281917A (en) * 2019-05-31 2019-09-27 惠州市德赛西威汽车电子股份有限公司 A kind of autonomous parking control method
CN110329245A (en) * 2019-06-26 2019-10-15 浙江吉利控股集团有限公司 A kind of automatic parking method, apparatus, equipment and vehicle
CN110415555A (en) * 2019-08-30 2019-11-05 的卢技术有限公司 A kind of recognition methods of effective scribing line parking stall and system based on deep learning

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107146468A (en) * 2017-07-12 2017-09-08 中国地质大学(武汉) The recognition methods of parking position and system and management method and system
CN109147382A (en) * 2018-09-25 2019-01-04 深圳市元征科技股份有限公司 A kind of intelligent parking method and system
CN109493632A (en) * 2018-11-16 2019-03-19 广州小鹏汽车科技有限公司 Automatic parking method and vehicle control syetem based on more parking stall measures
CN110281917A (en) * 2019-05-31 2019-09-27 惠州市德赛西威汽车电子股份有限公司 A kind of autonomous parking control method
CN110329245A (en) * 2019-06-26 2019-10-15 浙江吉利控股集团有限公司 A kind of automatic parking method, apparatus, equipment and vehicle
CN110415555A (en) * 2019-08-30 2019-11-05 的卢技术有限公司 A kind of recognition methods of effective scribing line parking stall and system based on deep learning

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113724323A (en) * 2021-08-24 2021-11-30 杭州海康威视数字技术股份有限公司 Map construction method, device and equipment
CN114141051A (en) * 2021-11-25 2022-03-04 浙江吉利控股集团有限公司 Parking assist method, parking assist system, and computer-readable storage medium
CN114141051B (en) * 2021-11-25 2023-03-14 浙江吉利控股集团有限公司 Parking assist method, parking assist system, and computer-readable storage medium
CN114512024A (en) * 2022-02-10 2022-05-17 北京百度网讯科技有限公司 Parking space identification method, device, equipment and storage medium

Similar Documents

Publication Publication Date Title
CN108140319B (en) Parking assistance method and parking assistance device
CN108431881B (en) Parking assistance information display method and parking assistance device
CN108140311B (en) Parking assistance information display method and parking assistance device
US11745730B2 (en) Automatic parking control method and apparatus
CN108230731B (en) Parking lot navigation system and method
EP4246491A1 (en) Navigation method, apparatus, and system
US10319233B2 (en) Parking support method and parking support device
CN112835350A (en) Automatic parking method, device and system
CN109522784B (en) Device and method for distinguishing between surmountable and non-surmountable objects
KR20200094652A (en) Learning method and learning device, and testing method and testing device for detecting parking spaces by using point regression results and relationship between points to thereby provide an auto-parking system
CN111028534B (en) Parking space detection method and device
CN111539484B (en) Method and device for training neural network
JP2007072665A (en) Object discrimination device, object discrimination method and object discrimination program
CN106379235B (en) The implementation method and device of aid parking
CN112216136A (en) Parking space detection method and device, vehicle and storage medium
CN111376895A (en) Around-looking parking sensing method and device, automatic parking system and vehicle
DE102012213344A1 (en) Method for driver assistance on board of motor vehicle, particularly for traffic sign recognition, involves determining direction change of motor vehicle, selecting camera image as function of direction change, and determining traffic sign
CN110858452A (en) Parking management system and method
US20190130748A1 (en) Apparatus and method for parking assist
CN102779427B (en) Parking stall guide system and method
CN109920261A (en) A kind of method, apparatus of information alert, mobile unit and readable storage medium storing program for executing
CN112363511A (en) Vehicle path planning method and device, vehicle-mounted device and storage medium
CN114084167B (en) Road network data generation method, device and computer program for automatic driving vehicle
CN113008249B (en) Avoidance point detection method and avoidance method of mobile robot and mobile robot
CN113989772A (en) Traffic light detection method and device, vehicle and readable storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination