CN111626348A - Automatic parking test model construction method, device, storage medium and device - Google Patents

Automatic parking test model construction method, device, storage medium and device Download PDF

Info

Publication number
CN111626348A
CN111626348A CN202010439758.0A CN202010439758A CN111626348A CN 111626348 A CN111626348 A CN 111626348A CN 202010439758 A CN202010439758 A CN 202010439758A CN 111626348 A CN111626348 A CN 111626348A
Authority
CN
China
Prior art keywords
parking space
information
parking
automatic
automatic 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.)
Granted
Application number
CN202010439758.0A
Other languages
Chinese (zh)
Other versions
CN111626348B (en
Inventor
郑芳芳
郭干
黄筝筝
李洋
刘应彬
刘兰骏
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.)
Anhui Jianghuai Automobile Group Corp
Original Assignee
Anhui Jianghuai Automobile Group Corp
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 Anhui Jianghuai Automobile Group Corp filed Critical Anhui Jianghuai Automobile Group Corp
Priority to CN202010439758.0A priority Critical patent/CN111626348B/en
Publication of CN111626348A publication Critical patent/CN111626348A/en
Application granted granted Critical
Publication of CN111626348B publication Critical patent/CN111626348B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/40—Scenes; Scene-specific elements in video content
    • G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items

Abstract

The invention discloses a method, equipment, a storage medium and a device for constructing an automatic parking test model, wherein the method comprises the following steps: acquiring image information, radar information and driver behavior data in a parking scene, generating initial parking space information according to the image information and the radar information, preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data, establishing an automatic parking test evaluation scene according to the target parking space information, and constructing an automatic parking test model according to the automatic parking test evaluation scene and the target driver behavior data; according to the invention, the image information, the radar information and the driver behavior data are processed in advance, so that an automatic parking test model adaptive to parking spaces in various conditions can be easily constructed, and the accuracy of an automatic parking test is improved.

Description

Automatic parking test model construction method, device, storage medium and device
Technical Field
The invention relates to the technical field of automobile testing, in particular to a method, equipment, a storage medium and a device for constructing an automatic parking test model.
Background
At present, with the continuous development of the automatic parking technology, the automatic parking technology gradually enters the public life. In real life, due to the fact that parking spaces of various specifications and different scenes exist, the automatic parking technology is not practical in actual use, and misjudgment and safety problems are prone to occurring.
In the prior art, a test is often performed only for a common parking scene, and a comprehensive test working condition and a test scene are lacked. Therefore, how to construct an automatic parking test model adaptive to parking spaces in various situations is a technical problem to be solved urgently.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a method, equipment, a storage medium and a device for constructing an automatic parking test model, and aims to solve the technical problem of how to construct an automatic parking test model adaptive to parking spaces under various conditions in the prior art.
In order to achieve the above object, the present invention provides an automatic parking test model construction method, including the steps of:
acquiring image information, radar information and driver behavior data in a parking scene;
generating initial parking space information according to the image information and the radar information;
preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data;
and establishing an automatic parking test evaluation scene according to the target parking space information, and establishing an automatic parking test model according to the automatic parking test evaluation scene and the target driver behavior data.
Preferably, the generating initial parking space information according to the image information and the radar information includes:
generating a parking space image according to the image information, and cutting the parking space image to obtain sub-images;
calculating a statistical histogram of the subimages through a preset image algorithm, and determining parking space sample information corresponding to the image information according to the statistical histogram;
and generating initial parking space information according to the parking space sample information and the radar information.
Preferably, the calculating a statistical histogram of the sub-images by a preset image algorithm, and determining parking space sample information corresponding to the image information according to the statistical histogram, includes:
calculating a statistical histogram of the subimage through a preset image algorithm, and calculating a Manhattan distance between the statistical histogram and a preset statistical histogram sample;
and determining parking space sample information corresponding to the image information according to the Manhattan distance.
Preferably, the preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data includes:
classifying the initial parking space information according to a preset parking space classification table to obtain a parking space classification;
searching a parking space weight corresponding to the parking space category in a preset mapping relation table, and performing data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information;
and extracting the driver behavior data according to a preset standardized model to obtain target driver behavior data.
Preferably, the classifying the initial parking space information according to a preset parking space classification table further includes, before obtaining the parking space classification:
extracting information of the initial parking space information according to a preset parking space line extraction model to obtain parking space line information;
carrying out information screening on the initial parking space information according to the parking line information to obtain parking space information to be classified;
correspondingly, the classifying the initial parking space information according to a preset parking space classification table to obtain a parking space classification includes:
and classifying the parking space information to be classified according to a preset parking space classification table to obtain the classification of the parking spaces.
Preferably, the searching for the parking space weight corresponding to the classification category in a preset parking space classification table, and performing data cleaning on the initial parking space information according to the parking space weight to obtain the target parking space information includes:
searching a parking space weight corresponding to the parking space category in a preset mapping relation table, and sequencing the initial parking space information according to the parking space weight to obtain a sequencing result;
and deleting the information of the initial parking space according to the sequencing result to obtain the information of the target parking space.
Preferably, after the automatic parking test evaluation scenario is established according to the target parking space information, and an automatic parking test model is established according to the automatic parking test evaluation scenario and the target driver behavior data, the method further includes:
carrying out real-time test on the automatic parking vehicle based on the automatic parking test model, and receiving test data fed back by the automatic parking vehicle;
and judging whether the automatic parking vehicle passes an automatic parking test or not according to the test data and the target driver behavior data.
In addition, to achieve the above object, the present invention further provides an automatic parking test model building apparatus including a memory, a processor, and an automatic parking test model building program stored on the memory and executable on the processor, the automatic parking test model building program being configured to implement the steps of the automatic parking test model building method as described above.
In addition, to achieve the above object, the present invention further provides a storage medium having an automatic parking test model building program stored thereon, wherein the automatic parking test model building program, when executed by a processor, implements the steps of the automatic parking test model building method as described above.
In addition, in order to achieve the above object, the present invention further provides an automatic parking test model building apparatus, including: the parking space information acquisition system comprises an acquisition module, a parking space information generation module, a preprocessing module and a model establishment module;
the acquisition module is used for acquiring image information, radar information and driver behavior data in a parking scene;
the parking space information generating module is used for generating initial parking space information according to the image information and the radar information;
the preprocessing module is used for preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data;
the model establishing module is used for establishing an automatic parking test evaluation scene according to the target parking space information and establishing an automatic parking test model according to the automatic parking test evaluation scene and the target driver behavior data.
In the invention, image information, radar information and driver behavior data in a parking scene are acquired, initial parking space information is generated according to the image information and the radar information, the initial parking space information and the driver behavior data are preprocessed to obtain target parking space information and target driver behavior data, an automatic parking test evaluation scene is established according to the target parking space information, and an automatic parking test model is established according to the automatic parking test evaluation scene and the target driver behavior data; according to the invention, the image information, the radar information and the driver behavior data are processed in advance, so that an automatic parking test model adaptive to parking spaces in various conditions can be easily constructed, and the accuracy of an automatic parking test is improved.
Drawings
Fig. 1 is a schematic structural diagram of an automatic parking test model building apparatus for a hardware operating environment according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a first exemplary embodiment of a method for building an automatic parking test model according to the present invention;
FIG. 3 is a flowchart illustrating a second embodiment of the method for building an automatic parking test model according to the present invention;
FIG. 4 is a flowchart illustrating a third exemplary embodiment of a method for building an automatic parking test model according to the present invention;
fig. 5 is a block diagram showing the configuration of the automatic parking test model building apparatus according to the first embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an automatic parking test model building apparatus for a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the automatic parking test model building apparatus may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), and the optional user interface 1003 may further include a standard wired interface and a wireless interface, and the wired interface for the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., a WIreless-FIdelity (WI-FI) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory or a Non-volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 1 does not constitute a limitation of the automated parking test model construction apparatus and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 1, a memory 1005, identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an automatic parking test model building program.
In the automatic parking test model building apparatus shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting user equipment; the automatic parking test model building apparatus calls the automatic parking test model building program stored in the memory 1005 through the processor 1001, and executes the automatic parking test model building method provided by the embodiment of the present invention.
Based on the hardware structure, the embodiment of the automatic parking test model construction method is provided.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for building an automatic parking test model according to a first embodiment of the present invention.
In a first embodiment, the automatic parking test model construction method includes the steps of:
step S10: image information, radar information and driver behavior data in a parking scene are obtained.
It should be understood that the execution subject of the present embodiment is the automatic parking test model building apparatus, wherein the automatic parking test model building apparatus may be an electronic apparatus such as a personal computer or a server having an information acquisition capability and an information processing capability.
It should be noted that the driver behavior data may be driving data of a driver during parking space search and parking, where the driving data may be data of a speed and a driving track during parking space search and parking, which is not limited in this embodiment;
the parking scene can be a scene of randomly collecting parking of a plurality of drivers in a plurality of parking spaces.
It can be understood that the automatic parking test model building device may receive an image sent by a camera mounted on a test vehicle, where the camera may be a 360-degree panoramic camera, to obtain image information in a parking scene; the automatic parking test model building equipment is used for obtaining radar information in a parking scene, wherein the radar information can be received from a radar sensor arranged on a test vehicle; the data of the driver behavior in the parking scene acquired by the automatic parking test model building device may be data of the driver driving the test vehicle to park, which is sent by a Controller Area Network (CAN) bus installed on the test vehicle.
Step S20: and generating initial parking space information according to the image information and the radar information.
It should be understood that the automatic parking test model building device may generate initial parking space information according to the image information and the radar information, or may generate a parking space image according to the image information, cut the parking space image to obtain sub-images, calculate a statistical histogram of the sub-images through a preset image algorithm, determine parking space sample information corresponding to the image information according to the statistical histogram, and generate initial parking space information according to the parking space sample information and the radar information.
It should be understood that the automatic parking test model building device may generate the parking space image according to the image information by recognizing the image information, obtaining a recognition result, and generating the parking space image according to the recognition result, in a specific implementation, for example, recognizing whether the image information contains parking line information;
the automatic parking test model building device cuts the image information to obtain the subimages, which may be the cutting of the parking space image according to a preset image cutting strategy to obtain the subimages.
It should be noted that the preset image cutting strategy may be to divide the parking space image into non-overlapping sub-images with preset sizes, where the preset size may be set by a manufacturer of the automatic parking test model building device, or may be set by a user according to actual requirements, and this embodiment is not limited thereto.
It should be understood that the automatic parking test model building device calculates the statistical histogram of the subimage through a preset image algorithm, and determines the parking space sample information corresponding to the image information according to the statistical histogram, which may be calculating the statistical histogram of the subimage through the preset image algorithm, calculating the manhattan distance between the statistical histogram and a preset statistical histogram sample, and determining the parking space sample information corresponding to the image information according to the manhattan distance.
It should be understood that the automatic parking test model building device may generate initial parking space information according to the parking space sample information and the radar information, and may fuse the radar information and the parking space sample information to obtain initial parking space information.
Step S30: and preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data.
It can be understood that the preprocessing is performed on the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data, and the preprocessing may be performed on the initial parking space information according to a preset parking space classification table to obtain a parking space class, search for a parking space weight corresponding to the parking space class in a preset mapping table, perform data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information, and extract the driver behavior data according to a preset standardized model to obtain target driver behavior data.
It should be noted that the preset parking space classification table may be a pre-stored classification table of various parking spaces.
It should be understood that the automatic parking test model construction device classifies the initial parking space information according to a preset parking space classification table, and obtaining the parking space category may be matching the initial parking space information with parking space category information in the preset parking space classification table to obtain a matching result, and determining the parking space category according to the matching result.
It should be noted that the preset mapping relationship table stores a corresponding relationship between the parking space categories and the parking space weights, where the corresponding relationship may be set by a manufacturer of the automatic parking test model building device according to the total number of the parking space categories in actual life.
It should be understood that the automatic parking test model building device searches parking space weights corresponding to the parking space categories in a preset mapping relation table, performs data cleaning on the initial parking space information according to the parking space weights, and obtains target parking space information, where the target parking space information may be obtained by searching parking space weights corresponding to the parking space categories in a preset mapping relation table, sorting the initial parking space information according to the parking space weights to obtain a sorting result, and deleting information from the initial parking space information according to the sorting result to obtain target parking space information.
It should be noted that the preset standardized model may be a model for calculating the distribution of the driver behavior data.
It should be understood that the automatic parking test model building device extracts the driver behavior data according to a preset standardized model, and the obtaining of the target driver behavior data may be extracting the driver behavior data located in a target interval, where the target interval is set according to actual needs of users.
Step S40: and establishing an automatic parking test evaluation scene according to the target parking space information, and establishing an automatic parking test model according to the automatic parking test evaluation scene and the target driver behavior data.
It should be understood that the automatic parking test model building device may build an automatic parking test evaluation scene according to the target parking space information, where the automatic parking test evaluation scene is built according to the arranged scene by performing field arrangement according to the target parking space information.
In a first embodiment, image information, radar information and driver behavior data in a parking scene are acquired, initial parking space information is generated according to the image information and the radar information, the initial parking space information and the driver behavior data are preprocessed to obtain target parking space information and target driver behavior data, an automatic parking test evaluation scene is established according to the target parking space information, and an automatic parking test model is established according to the automatic parking test evaluation scene and the target driver behavior data; according to the automatic parking test method and device, the image information, the radar information and the driver behavior data are processed in advance, so that an automatic parking test model adaptive to parking spaces in various conditions can be constructed easily, and the automatic parking test accuracy is improved.
Referring to fig. 3, fig. 3 is a flowchart illustrating a second embodiment of the method for building an automatic parking test model according to the present invention, and the second embodiment of the method for building an automatic parking test model according to the present invention is proposed based on the first embodiment illustrated in fig. 2.
In the second embodiment, the step S20 includes:
step S201: and generating a parking space image according to the image information, and cutting the parking space image to obtain sub-images.
It should be understood that the automatic parking test model building device may generate the parking space image according to the image information by recognizing the image information, obtaining a recognition result, and generating the parking space image according to the recognition result, in a specific implementation, for example, recognizing whether the image information contains parking line information;
the automatic parking test model building device cuts the image information to obtain the subimages, which may be the cutting of the parking space image according to a preset image cutting strategy to obtain the subimages.
It should be noted that the preset image cutting strategy may be to divide the parking space image into non-overlapping sub-images with preset sizes, where the preset size may be set by a manufacturer of the automatic parking test model building device, or may be set by a user according to actual requirements, and this embodiment is not limited thereto.
Step S202: and calculating a statistical histogram of the subimages through a preset image algorithm, and determining parking space sample information corresponding to the image information according to the statistical histogram.
It should be understood that the automatic parking test model building device calculates the statistical histogram of the subimage through a preset image algorithm, and determines the parking space sample information corresponding to the image information according to the statistical histogram, which may be calculating the statistical histogram of the subimage through the preset image algorithm, calculating the manhattan distance between the statistical histogram and a preset statistical histogram sample, and determining the parking space sample information corresponding to the image information according to the manhattan distance.
Further, the step S202 includes:
calculating a statistical histogram of the subimage through a preset image algorithm, and calculating a Manhattan distance between the statistical histogram and a preset statistical histogram sample;
and determining parking space sample information corresponding to the image information according to the Manhattan distance.
It should be noted that the preset image algorithm may be an algorithm such as an LBP algorithm for describing local texture features of an image, which is not limited in this embodiment;
the preset statistical histogram sample may be a statistical histogram corresponding to a sub-image of each parking space image pre-stored by a manufacturer of the automatic parking test model building apparatus during production.
It should be understood that the automatic parking test model building apparatus may calculate the manhattan distance between the statistical histogram and the preset statistical histogram samples by selecting a preset statistical histogram sample set of the position where the statistical histogram is located, then selecting a preset statistical histogram sample with the largest use frequency from the preset statistical histogram sample set, then calculating the manhattan distance between the statistical histogram and the preset statistical histogram sample, and then calculating the preset statistical histogram sample with the second use frequency from the statistical histogram sample set until the calculation of all the preset statistical histogram samples in the preset statistical histogram sample set is completed.
It can be understood that the automatic parking test model construction equipment determines the parking space sample information corresponding to the image information according to the manhattan distance, and may be configured to sort the preset statistical histogram samples in the preset statistical histogram sample set according to the manhattan distance to obtain a sorting result, use the preset statistical histogram sample with the smallest manhattan distance as a target preset statistical histogram sample, and use the information corresponding to the target preset statistical histogram sample as the parking space sample information corresponding to the image information.
Step S203: and generating initial parking space information according to the parking space sample information and the radar information.
It should be understood that the automatic parking test model building device may generate initial parking space information according to the parking space sample information and the radar information, and may fuse the radar information and the parking space sample information to obtain initial parking space information.
In the second embodiment, after the step S40, the method further includes:
step S50: and carrying out real-time test on the automatic parking vehicle based on the automatic parking test model, and receiving test data fed back by the automatic parking vehicle.
It can be understood that the automatic parking test model building device performs the real-time test on the automatic parking vehicle based on the automatic parking test model, and may reconstruct a test parking space according to the automatic parking test model, and perform the test parking test on the automatic parking vehicle in the test parking space;
the test data fed back by the automatic parking vehicle can be received through 4G, 5G, the Internet of things and other modes.
Step S60: and judging whether the automatic parking vehicle passes an automatic parking test or not according to the test data and the target driver behavior data.
It should be understood that the automatic parking test model building device may judge whether the automatic parking vehicle passes an automatic parking test according to the test data and the target driver behavior data, or may judge whether the test data is the same as the target driver behavior data, and if so, judge that the automatic parking vehicle passes the automatic parking test; and when the vehicle number is different, judging that the automatic parking vehicle does not pass the automatic parking test.
In a second embodiment, a parking space image is generated according to the image information, the image information is cut to obtain sub-images, a statistical histogram of the sub-images is calculated through a preset image algorithm, parking space sample information corresponding to the image information is determined according to the statistical histogram, and initial parking space information is generated according to the parking space sample information and the radar information; in the embodiment, the parking space information can be easily extracted from the image information by calculating the statistical histogram of the sub-images.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for building an automatic parking test model according to a third embodiment of the present invention, which is proposed based on the first embodiment shown in fig. 2.
In the third embodiment, the step S30 includes:
step S301: and classifying the initial parking space information according to a preset parking space classification table to obtain a parking space classification.
It should be noted that the preset parking space classification table may be a pre-stored classification table of various parking spaces.
It should be understood that the automatic parking test model construction device classifies the initial parking space information according to a preset parking space classification table, and obtaining the parking space category may be matching the initial parking space information with parking space category information in the preset parking space classification table to obtain a matching result, and determining the parking space category according to the matching result.
Further, before the step S301, the method further includes:
extracting information of the initial parking space information according to a preset parking space line extraction model to obtain parking space line information;
carrying out information screening on the initial parking space information according to the parking line information to obtain parking space information to be classified;
accordingly, the step S301 includes:
and classifying the parking space information to be classified according to a preset parking space classification table to obtain the classification of the parking spaces.
It should be noted that the preset parking space line extraction model may be a line identification model for identifying lines.
It should be understood that the automatic parking test model construction device performs information screening on the initial parking space information according to the parking line information, and the obtaining of the parking space information to be classified may be deleting the initial parking space information with repeated parking line information to obtain the parking space information to be classified.
Step S302: and searching the parking space weight corresponding to the parking space category in a preset mapping relation table, and performing data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information.
It should be noted that the preset mapping relationship table stores a corresponding relationship between the parking space categories and the parking space weights, where the corresponding relationship may be set by a manufacturer of the automatic parking test model building device according to the total number of the parking space categories in actual life.
It should be understood that the automatic parking test model building device searches parking space weights corresponding to the parking space categories in a preset mapping relation table, performs data cleaning on the initial parking space information according to the parking space weights, and obtains target parking space information, where the target parking space information may be obtained by searching parking space weights corresponding to the parking space categories in a preset mapping relation table, sorting the initial parking space information according to the parking space weights to obtain a sorting result, and deleting information from the initial parking space information according to the sorting result to obtain target parking space information.
Further, the step S302 includes:
searching a parking space weight corresponding to the parking space category in a preset mapping relation table, and sequencing the initial parking space information according to the parking space weight to obtain a sequencing result;
and deleting the information of the initial parking space according to the sequencing result to obtain the information of the target parking space.
It should be understood that, the obtaining of the ranking result by ranking the initial parking space information according to the parking space weight may be the obtaining of the ranking result by ranking the initial parking space information from large to small according to the size of the parking space weight.
It can be understood that the deleting of the information of the initial parking space information according to the sorting result may be deleting a preset number of initial parking space information according to the sorting result, wherein the preset number may be set according to actual use requirements of users.
Step S303: and extracting the driver behavior data according to a preset standardized model to obtain target driver behavior data.
It should be noted that the preset standardized model may be a model for calculating the distribution of the driver behavior data.
It should be understood that the automatic parking test model building device extracts the driver behavior data according to a preset standardized model, and the obtaining of the target driver behavior data may be extracting the driver behavior data located in a target interval, where the target interval is set according to actual needs of users.
In a third embodiment, the initial parking space information is classified according to a preset parking space classification table to obtain a parking space category, a parking space weight corresponding to the parking space category is searched in a preset mapping relation table, data cleaning is performed on the initial parking space information according to the parking space weight to obtain target parking space information, and the driver behavior data is extracted according to a preset standardized model to obtain target driver behavior data, so that common parking space information and standard driver behavior data can be extracted, and the reliability of a test basis is increased or decreased.
Furthermore, an embodiment of the present invention further provides a storage medium, where an automatic parking test model building program is stored, and the automatic parking test model building program, when executed by a processor, implements the steps of the automatic parking test model building method described above.
In addition, referring to fig. 5, an embodiment of the present invention further provides an automatic parking test model building apparatus, where the automatic parking test model building apparatus includes: the system comprises an acquisition module 10, a parking space information generation module 20, a preprocessing module 30 and a model building module 40;
the obtaining module 10 is configured to obtain image information, radar information, and driver behavior data in a parking scene.
It should be understood that the execution subject of the present embodiment is the automatic parking test model building apparatus, wherein the automatic parking test model building apparatus may be an electronic apparatus such as a personal computer or a server having an information acquisition capability and an information processing capability.
It should be noted that the driver behavior data may be driving data of a driver during parking space search and parking, where the driving data may be data of a speed and a driving track during parking space search and parking, which is not limited in this embodiment;
the parking scene can be a scene of randomly collecting parking of a plurality of drivers in a plurality of parking spaces.
It can be understood that the automatic parking test model building device may receive an image sent by a camera mounted on a test vehicle, where the camera may be a 360-degree panoramic camera, to obtain image information in a parking scene; the automatic parking test model building equipment is used for obtaining radar information in a parking scene, wherein the radar information can be received from a radar sensor arranged on a test vehicle; the automatic parking test model building device may receive driver data, which is sent by a Controller Area Network (CAN) bus installed on a test vehicle, of a driver when the test vehicle is driven, where the driver behavior data in a parking scene is obtained.
The parking space information generating module 20 is configured to generate initial parking space information according to the image information and the radar information.
It should be understood that the automatic parking test model building device may generate initial parking space information according to the image information and the radar information, or may generate a parking space image according to the image information, cut the parking space image to obtain sub-images, calculate a statistical histogram of the sub-images through a preset image algorithm, determine parking space sample information corresponding to the image information according to the statistical histogram, and generate initial parking space information according to the parking space sample information and the radar information.
It should be understood that the automatic parking test model building device may generate the parking space image according to the image information by recognizing the image information, obtaining a recognition result, and generating the parking space image according to the recognition result, in a specific implementation, for example, recognizing whether the image information contains parking line information;
the automatic parking test model building device cuts the image information to obtain the subimages, which may be the cutting of the parking space image according to a preset image cutting strategy to obtain the subimages.
It should be noted that the preset image cutting strategy may be to divide the parking space image into non-overlapping sub-images with preset sizes, where the preset size may be set by a manufacturer of the automatic parking test model building device, or may be set by a user according to actual requirements, and this embodiment is not limited thereto.
It should be understood that the automatic parking test model building device calculates the statistical histogram of the subimage through a preset image algorithm, and determines the parking space sample information corresponding to the image information according to the statistical histogram, which may be calculating the statistical histogram of the subimage through the preset image algorithm, calculating the manhattan distance between the statistical histogram and a preset statistical histogram sample, and determining the parking space sample information corresponding to the image information according to the manhattan distance.
It should be understood that the automatic parking test model building device may generate initial parking space information according to the parking space sample information and the radar information, and may fuse the radar information and the parking space sample information to obtain initial parking space information.
The preprocessing module 30 is configured to preprocess the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data.
It can be understood that the preprocessing is performed on the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data, and the preprocessing may be performed on the initial parking space information according to a preset parking space classification table to obtain a parking space class, search for a parking space weight corresponding to the parking space class in a preset mapping table, perform data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information, and extract the driver behavior data according to a preset standardized model to obtain target driver behavior data.
It should be noted that the preset parking space classification table may be a pre-stored classification table of various parking spaces.
It should be understood that the automatic parking test model construction device classifies the initial parking space information according to a preset parking space classification table, and obtaining the parking space category may be matching the initial parking space information with parking space category information in the preset parking space classification table to obtain a matching result, and determining the parking space category according to the matching result.
It should be noted that the preset mapping relationship table stores a corresponding relationship between the parking space categories and the parking space weights, where the corresponding relationship may be set by a manufacturer of the automatic parking test model building device according to the total number of the parking space categories in actual life.
It should be understood that the automatic parking test model building device searches parking space weights corresponding to the parking space categories in a preset mapping relation table, performs data cleaning on the initial parking space information according to the parking space weights, and obtains target parking space information, where the target parking space information may be obtained by searching parking space weights corresponding to the parking space categories in a preset mapping relation table, sorting the initial parking space information according to the parking space weights to obtain a sorting result, and deleting information from the initial parking space information according to the sorting result to obtain target parking space information.
It should be noted that the preset standardized model may be a model for calculating the distribution of the driver behavior data.
It should be understood that the automatic parking test model building device extracts the driver behavior data according to a preset standardized model, and the obtaining of the target driver behavior data may be extracting the driver behavior data located in a target interval, where the target interval is set according to actual needs of users.
The model establishing module 40 is configured to establish an automatic parking test evaluation scenario according to the target parking space information, and establish an automatic parking test model according to the automatic parking test evaluation scenario and the target driver behavior data.
It should be understood that the automatic parking test model building device may build an automatic parking test evaluation scene according to the target parking space information, where the automatic parking test evaluation scene is built according to the arranged scene by performing field arrangement according to the target parking space information.
In the embodiment, image information, radar information and driver behavior data in a parking scene are acquired, initial parking space information is generated according to the image information and the radar information, the initial parking space information and the driver behavior data are preprocessed to obtain target parking space information and target driver behavior data, an automatic parking test evaluation scene is established according to the target parking space information, and an automatic parking test model is established according to the automatic parking test evaluation scene and the target driver behavior data; according to the automatic parking test method and device, the image information, the radar information and the driver behavior data are processed in advance, so that an automatic parking test model adaptive to parking spaces in various conditions can be constructed easily, and the automatic parking test accuracy is improved.
In an embodiment, the parking space information generating module is further configured to generate a parking space image according to the image information, cut the parking space image to obtain a sub-image, calculate a statistical histogram of the sub-image through a preset image algorithm, determine parking space sample information corresponding to the image information according to the statistical histogram, and generate initial parking space information according to the parking space sample information and the radar information;
in an embodiment, the parking space information generating module is further configured to calculate a statistical histogram of the sub-image through a preset image algorithm, calculate a manhattan distance between the statistical histogram and a preset statistical histogram sample, and determine parking space sample information corresponding to the image information according to the manhattan distance;
in an embodiment, the preprocessing module is further configured to classify the initial parking space information according to a preset parking space classification table to obtain a parking space class, search a parking space weight corresponding to the parking space class in a preset mapping relation table, perform data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information, and extract the driver behavior data according to a preset standardized model to obtain target driver behavior data;
in one embodiment, the automatic parking test model building apparatus further includes: an extraction module;
the extraction module is used for extracting information of the initial parking space information according to a preset parking space line extraction model to obtain parking space line information, and screening the information of the initial parking space information according to the parking space line information to obtain parking space information to be classified;
in an embodiment, the preprocessing module is further configured to search a parking space weight corresponding to the type of the parking space in a preset mapping table, sort the initial parking space information according to the parking space weight to obtain a sorting result, and delete the information of the initial parking space information according to the sorting result to obtain target parking space information;
in one embodiment, the automatic parking test model building apparatus further includes: a verification module;
the verification module is used for carrying out real-time test on the automatic parking vehicle based on the automatic parking test model, receiving test data fed back by the automatic parking vehicle, and judging whether the automatic parking vehicle passes the automatic parking test or not according to the test data and the target driver behavior data.
Other embodiments or specific implementation manners of the automatic parking test model construction device provided by the invention can refer to the above method embodiments, and are not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order, but rather the words first, second, third, etc. are to be interpreted as names.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be substantially implemented or a part contributing to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., a Read Only Memory (ROM)/Random Access Memory (RAM), a magnetic disk, an optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (10)

1. An automatic parking test model construction method is characterized by comprising the following steps:
acquiring image information, radar information and driver behavior data in a parking scene;
generating initial parking space information according to the image information and the radar information;
preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data;
and establishing an automatic parking test evaluation scene according to the target parking space information, and establishing an automatic parking test model according to the automatic parking test evaluation scene and the target driver behavior data.
2. The method for constructing an automatic parking test model according to claim 1, wherein the step of generating initial parking space information from the image information and the radar information specifically includes:
generating a parking space image according to the image information, and cutting the parking space image to obtain sub-images;
calculating a statistical histogram of the subimages through a preset image algorithm, and determining parking space sample information corresponding to the image information according to the statistical histogram;
and generating initial parking space information according to the parking space sample information and the radar information.
3. The method for constructing an automatic parking test model according to claim 2, wherein the step of calculating a statistical histogram of the sub-images by a preset image algorithm and determining parking space sample information corresponding to the image information according to the statistical histogram specifically comprises:
calculating a statistical histogram of the subimage through a preset image algorithm, and calculating a Manhattan distance between the statistical histogram and a preset statistical histogram sample;
and determining parking space sample information corresponding to the image information according to the Manhattan distance.
4. The method for constructing an automatic parking test model according to claim 1, wherein the step of preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data specifically comprises:
classifying the initial parking space information according to a preset parking space classification table to obtain a parking space classification;
searching a parking space weight corresponding to the parking space category in a preset mapping relation table, and performing data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information;
and extracting the driver behavior data according to a preset standardized model to obtain target driver behavior data.
5. The method for constructing an automatic parking test model according to claim 4, wherein before the step of classifying the initial parking space information according to a preset parking space classification table to obtain a parking space classification, the method for constructing an automatic parking test model further comprises:
extracting information of the initial parking space information according to a preset parking space line extraction model to obtain parking space line information;
carrying out information screening on the initial parking space information according to the parking line information to obtain parking space information to be classified;
correspondingly, the step of classifying the initial parking space information according to a preset parking space classification table to obtain a parking space classification specifically includes:
and classifying the parking space information to be classified according to a preset parking space classification table to obtain the classification of the parking spaces.
6. The method for constructing an automatic parking test model according to claim 4, wherein the step of searching for the parking space weight corresponding to the classification category in a preset parking space classification table, and performing data cleaning on the initial parking space information according to the parking space weight to obtain target parking space information specifically comprises:
searching a parking space weight corresponding to the parking space category in a preset mapping relation table, and sequencing the initial parking space information according to the parking space weight to obtain a sequencing result;
and deleting the information of the initial parking space according to the sequencing result to obtain the information of the target parking space.
7. The automatic parking test model construction method according to any one of claims 1 to 6, wherein after the step of establishing an automatic parking test evaluation scenario according to the target parking space information and constructing an automatic parking test model according to the automatic parking test evaluation scenario and the target driver behavior data, the automatic parking test model construction method further comprises:
carrying out real-time test on the automatic parking vehicle based on the automatic parking test model, and receiving test data fed back by the automatic parking vehicle;
and judging whether the automatic parking vehicle passes an automatic parking test or not according to the test data and the target driver behavior data.
8. An automatic parking test model construction apparatus, characterized by comprising: a memory, a processor and an automatic parking test model building program stored on the memory and executable on the processor, the automatic parking test model building program, when executed by the processor, implementing the steps of the automatic parking test model building method according to any one of claims 1 to 7.
9. A storage medium, characterized in that the storage medium has stored thereon an automatic parking test model construction program that, when executed by a processor, implements the steps of the automatic parking test model construction method according to any one of claims 1 to 7.
10. An automatic parking test model construction device, characterized by comprising: the parking space information acquisition system comprises an acquisition module, a parking space information generation module, a preprocessing module and a model establishment module;
the acquisition module is used for acquiring image information, radar information and driver behavior data in a parking scene;
the parking space information generating module is used for generating initial parking space information according to the image information and the radar information;
the preprocessing module is used for preprocessing the initial parking space information and the driver behavior data to obtain target parking space information and target driver behavior data;
the model establishing module is used for establishing an automatic parking test evaluation scene according to the target parking space information and establishing an automatic parking test model according to the automatic parking test evaluation scene and the target driver behavior data.
CN202010439758.0A 2020-05-20 2020-05-20 Automatic parking test model construction method, equipment, storage medium and device Active CN111626348B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010439758.0A CN111626348B (en) 2020-05-20 2020-05-20 Automatic parking test model construction method, equipment, storage medium and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010439758.0A CN111626348B (en) 2020-05-20 2020-05-20 Automatic parking test model construction method, equipment, storage medium and device

Publications (2)

Publication Number Publication Date
CN111626348A true CN111626348A (en) 2020-09-04
CN111626348B CN111626348B (en) 2024-02-02

Family

ID=72272138

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010439758.0A Active CN111626348B (en) 2020-05-20 2020-05-20 Automatic parking test model construction method, equipment, storage medium and device

Country Status (1)

Country Link
CN (1) CN111626348B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112132111A (en) * 2020-10-10 2020-12-25 安徽江淮汽车集团股份有限公司 Parking typical scene extraction method, device, storage medium and device
CN112537267A (en) * 2020-11-26 2021-03-23 安徽江淮汽车集团股份有限公司 Method, equipment, storage medium and device for testing reversing early warning performance
CN113032272A (en) * 2021-03-31 2021-06-25 东风柳州汽车有限公司 Automatic parking system test evaluation method, device, equipment and storage medium
CN113076261A (en) * 2021-04-29 2021-07-06 安徽江淮汽车集团股份有限公司 Automatic parking test method, automatic parking test equipment, storage medium and automatic parking test device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008014130A1 (en) * 2008-03-13 2009-09-17 Valeo Schalter Und Sensoren Gmbh Method for controlling a parking assistance system for vehicles and parking assistance system
CN110696822A (en) * 2019-11-25 2020-01-17 安徽江淮汽车集团股份有限公司 Automatic parking control method, device, equipment and storage medium
CN110816520A (en) * 2019-11-27 2020-02-21 安徽江淮汽车集团股份有限公司 Automatic parking method, automatic parking equipment, storage medium and automatic parking device
WO2020056874A1 (en) * 2018-09-17 2020-03-26 魔门塔(苏州)科技有限公司 Automatic parking system and method based on visual recognition

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102008014130A1 (en) * 2008-03-13 2009-09-17 Valeo Schalter Und Sensoren Gmbh Method for controlling a parking assistance system for vehicles and parking assistance system
WO2020056874A1 (en) * 2018-09-17 2020-03-26 魔门塔(苏州)科技有限公司 Automatic parking system and method based on visual recognition
CN110696822A (en) * 2019-11-25 2020-01-17 安徽江淮汽车集团股份有限公司 Automatic parking control method, device, equipment and storage medium
CN110816520A (en) * 2019-11-27 2020-02-21 安徽江淮汽车集团股份有限公司 Automatic parking method, automatic parking equipment, storage medium and automatic parking device

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
江浩斌;叶浩;马世典;陈龙;: "基于多传感器数据融合的自动泊车系统高精度辨识车位的方法" *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112132111A (en) * 2020-10-10 2020-12-25 安徽江淮汽车集团股份有限公司 Parking typical scene extraction method, device, storage medium and device
CN112537267A (en) * 2020-11-26 2021-03-23 安徽江淮汽车集团股份有限公司 Method, equipment, storage medium and device for testing reversing early warning performance
CN113032272A (en) * 2021-03-31 2021-06-25 东风柳州汽车有限公司 Automatic parking system test evaluation method, device, equipment and storage medium
CN113032272B (en) * 2021-03-31 2024-02-02 东风柳州汽车有限公司 Automatic parking system test evaluation method, device, equipment and storage medium
CN113076261A (en) * 2021-04-29 2021-07-06 安徽江淮汽车集团股份有限公司 Automatic parking test method, automatic parking test equipment, storage medium and automatic parking test device

Also Published As

Publication number Publication date
CN111626348B (en) 2024-02-02

Similar Documents

Publication Publication Date Title
CN111626348B (en) Automatic parking test model construction method, equipment, storage medium and device
EP3505962B1 (en) Method and apparatus for processing point cloud data
CN111563494B (en) Behavior identification method and device based on target detection and computer equipment
CN112100461B (en) Questionnaire data processing method, device, server and medium based on data analysis
CN110780965B (en) Vision-based process automation method, equipment and readable storage medium
CN112078571B (en) Automatic parking method, automatic parking equipment, storage medium and automatic parking device
CN112432647B (en) Carriage positioning method, device and system and computer readable storage medium
CN113221804B (en) Disordered material detection method and device based on monitoring video and application
CN111191201A (en) User identification method, device and equipment based on data buried points and storage medium
CN111666848B (en) Method, device and equipment for detecting arrival of transport vehicle and storage medium
CN112307994A (en) Obstacle identification method based on sweeper, electronic device and storage medium
CN111753610A (en) Weather identification method and device
CN111144372A (en) Vehicle detection method, device, computer equipment and storage medium
CN114429640A (en) Drawing segmentation method and device and electronic equipment
CN108647570B (en) Zebra crossing detection method and device and computer readable storage medium
CN112926601A (en) Image recognition method, device and equipment based on deep learning and storage medium
CN111027601B (en) Plane detection method and device based on laser sensor
CN112132111A (en) Parking typical scene extraction method, device, storage medium and device
CN110660000A (en) Data prediction method, device, equipment and computer readable storage medium
CN114582012A (en) Skeleton human behavior recognition method, device and equipment
CN114821978A (en) Method, device and medium for eliminating false alarm
CN114283361A (en) Method and apparatus for determining status information, storage medium, and electronic apparatus
CN113657179A (en) Image recognition and modeling method and device, electronic equipment and storage medium
CN112528893A (en) Abnormal state identification method and device and computer readable storage medium
CN109685069B (en) Image detection method, device and computer 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
GR01 Patent grant
GR01 Patent grant