CN113886955B - Design method of integrated parking test site - Google Patents
Design method of integrated parking test site Download PDFInfo
- Publication number
- CN113886955B CN113886955B CN202111152174.6A CN202111152174A CN113886955B CN 113886955 B CN113886955 B CN 113886955B CN 202111152174 A CN202111152174 A CN 202111152174A CN 113886955 B CN113886955 B CN 113886955B
- Authority
- CN
- China
- Prior art keywords
- parking
- parking space
- size
- scene
- key
- 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.)
- Active
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000013461 design Methods 0.000 title claims abstract description 28
- 239000013598 vector Substances 0.000 claims abstract description 32
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 238000007689 inspection Methods 0.000 claims abstract description 4
- 238000012216 screening Methods 0.000 claims description 13
- 239000000463 material Substances 0.000 claims description 8
- 238000009825 accumulation Methods 0.000 claims description 4
- 238000011161 development Methods 0.000 abstract description 10
- 238000012795 verification Methods 0.000 abstract description 2
- 238000010276 construction Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 239000004579 marble Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Automation & Control Theory (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a design method of an integrated parking test site, which comprises the steps of establishing a parking parameter characteristic database, obtaining parameters in a parking scene, extracting the size of a set threshold value as a key size lower limit value of a parking space, extracting a non-key size value of the parking space corresponding to the lower limit value of the parking space according to the extracted key size lower limit value, extracting the non-key size within the range of a decimal value of the lower limit size +/-Delta of the key size, checking the rationality of the size of the parking space, and establishing a parking scene characteristic vector group; extracting a parking scene; and (4) parking scene inspection, parking test scene results and integrated parking test field design. The design method of the integrated parking test site can guide the extraction of the parking test scene characteristics and the extraction of the test cases, the extracted result is closer to a real scene, and the design method has practical significance for parking development and verification; the method combines the fixed scene and the movable boundary characteristics, and has strong scene expansibility.
Description
Technical Field
The invention belongs to the technical field of intelligent networked automobiles, and particularly relates to a design method of an integrated parking test site.
Background
With the rapid development of the intelligent internet automobile technology, the automatic parking and passenger-assistant parking functions are favored by consumers. The sizes of parking spaces and parking scenes in all parts of the country are greatly different due to the reasons of regions, city construction, traffic conditions and the like. At present, most of whole car factories adopt a development mode of parking test in a typical city in a car development stage, and the development mode has high development cost and long development period. Therefore, in order to meet the development requirement of the automatic parking function, a design method of an integrated parking test site needs to be developed, and the integrated parking test site can be designed based on the method; the parking space size and parking test scene designed by the method can represent different parking places, such as an indoor parking place, an outdoor parking place, an on-road parking place, an off-road parking place and the like, and can also represent the characteristics of a typical urban parking place in China.
In the prior art, extraction, virtual reconstruction or classification of typical parking scenes is disclosed. After the scenes are screened, the two scenes with the closest distance are combined into a new scene, and the scene parameters are clustered and combined for multiple times until the final scene number reaches the preset number, so that the method is easy to discard the actual scenes with medium occurrence frequency; the parameters of the scenes are clustered respectively and then combined into parking scenes for testing, and the method combines the parameters with high scene frequency together, so that scenes with low occurrence frequency in actual scenes can be combined. The virtual reconstruction of the parking scene is to expand after dimensionality reduction so as to reconstruct an infinite virtual parking scene for a virtual test working condition, and the virtual reconstruction does not relate to extraction methods of parking space size, terrain type, space occupying facilities, limiting facilities, gradient, step height and the like, and has a single parking space boundary type. The classification of typical parking scenes only defines a specified number of parking scenes, and describes each parking scene through the standard of the specified number of typical parking scenes, which cannot represent different parking places and the characteristics of the parking places in typical cities of China.
The prior art discloses a method for testing an automatic driving vehicle, which comprises the steps of establishing a human driving behavior model, determining a random variable of human driving behavior following a specific probability distribution according to the human driving behavior model in a target scene, acquiring first driving data of the automatic driving vehicle, selecting, simulating and expanding the first driving data to obtain testing driving data, and testing the automatic driving vehicle by combining the random variable of the human driving behavior.
However, after the extraction method of the typical parking scene screens the scenes, the two scenes with the closest distance are merged into a new scene, and the scene parameters are clustered and merged for multiple times until the final number of the scenes reaches the preset number. This approach tends to discard real scenes that occur moderately frequently. In addition, parameters of the scenes are clustered respectively and then combined into parking scenes for testing, and the scenes with low occurrence frequency in actual scenes can be combined by combining the parameters with high scene frequency together by the method.
The prior art also discloses a parking scene classification method for a parking assistance system of a motor vehicle, wherein a predefined number of parking scenes are defined and each parking scene is described by a criterion of a predefined number of typical parking scenes, wherein the criterion is based at least on parameters of a specific parking space, and wherein the method has the following steps: the method comprises the steps of determining data of the surroundings of the motor vehicle by means of surroundings sensors of the motor vehicle, determining parameters of a specific parking space from the surroundings data, checking criteria of the individual parking scenes by means of the parameters of the specific parking space, and classifying the individual parking scenes by means of the checked criteria.
However, this classification method defines only a prescribed number of parking scenes, and describes each parking scene by a standard of a prescribed number of typical parking scenes, which is a method of classifying parking scenes. This method cannot be implemented.
Disclosure of Invention
The invention aims to provide a design method of an integrated parking test site, which aims to solve the problems of extracting a parking test scene, designing a real-vehicle parking test site and enhancing the scene expansibility; the designed field can be provided with more parking scenes containing various characteristics or expandable characteristics in the smallest field area, covers all actual parking space arrangement modes, standard-size parking spaces and nonstandard-size parking spaces, comprises a specific number of fixed parking scenes, can realize scene expansion, and realizes quick construction of different scene boundaries, including terrains such as level roads, ramps and the like and various ground materials.
The purpose of the invention is realized by the following technical scheme:
a design method of an integrated parking test site comprises the following steps:
step 10, establishing a parking parameter characteristic database, and acquiring parameters in a parking scene;
step 20, size extraction: acquiring a parking space size data distribution map, and extracting the size of a parking space according to a clustering method; extracting the size of a set threshold value as a key size lower limit value of the parking space;
step 21: extracting a non-key size value of the parking space corresponding to the parking space lower limit value according to the key size lower limit value extracted in the step 20; extracting non-critical dimensions within the range of the lower limit dimension +/-Delta quantile value of the critical dimensions;
step 22: checking the rationality of the parking space size:
counting the occupation ratio of the parking spaces composed of the key sizes and the non-key sizes obtained in the step 20 and the step 21 in the database;
step 30, establishing a parking scene feature vector group: screening key parameters in a parking scene, combining the key parameters into a parking space feature vector group, clustering the parking space feature vector group according to the type of parking spaces, and counting a multivariate combined probability distribution according to the key size of the parking spaces by the clustered feature vector group;
step 40, parking scene extraction: extracting parking scene features under the accumulation probability of a set threshold value from the feature vector group obtained in the step 30, and screening out parking scenes with non-key features so as to obtain a typical parking scene;
step 50, parking scene inspection: the feature vector group obtained in step 40 is fused with the parking space size extracted in step 20, and the fused parking space features are compared with the difference of the parking space features in the database;
step 60, parking test scene results: screening out features with large differences according to the parking space feature difference results obtained in the step 50, and finally extracting parking space type results of a parking test site;
step 70: designing an integrated parking test field: and according to the result of the step 60, comprehensively designing a parking test site.
Further, in step 10, the parking parameters include, but are not limited to, a collection city, a collection date, a weather condition, a parking space type, a parking space angle, a parking space length, a parking space width, a boundary type, illuminance, topographic information of a parking area, and the like.
Further, step 20 includes the following steps: and marking the parking bit length size and the parking bit width size as a critical size and a non-critical size respectively according to the type of the parking space, acquiring normal distribution of the key size of the parking space, and extracting a lower limit value of the key size according to a set threshold value.
Furthermore, the selection of the delta value needs to integrate the parking space line width and the parking space line drawing error factors and is within the error range of the parking space size.
Still further, Δ ═ 10.
Further, in step 30, the components of the feature vector at least include parking space parameters of a parking space type, a terrain, a step type, and a space boundary.
Still further, the spatial boundaries include a front boundary, a rear boundary, a left boundary, and a right boundary.
Further, step 40 includes counting the probability distribution of the non-critical boundary types respectively, and extracting the non-critical boundary types with set thresholds.
Furthermore, the non-critical boundary characteristics include a material of a parking space area, a width of a parking space line, a line type of the parking space line, a color of the parking space line, an occupying facility, a limiting facility and a parking space direction indication.
Further, step 60, for the result combination, a standard parking space needs to be reserved, a parking space with a lower limit size is reserved, and a complex boundary covers a simple boundary.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention discloses a design method of an integrated parking test site, which is used for design guidance of a real vehicle parking test site and aims to extract typical parking spaces from various types of parking spaces so as to solve the special site design problem of automatic parking test;
2. the invention provides a method for extracting the size of the parking space, and provides methods for extracting factors such as landform, occupation facilities, limiting facilities, steps, space boundaries and the like which have influence on the automatic parking function, so that the method can guide the extraction of the parking test scene characteristics and the extraction of test cases;
3. the invention provides a design method of parking space size, and a method of combined scene parameter analysis is adopted for scene extraction, so that the extracted result is closer to a real scene, and the method has practical significance for parking development and verification.
4. The method combines the fixed scene and the movable boundary characteristics, and has strong scene expansibility.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.
FIG. 1 vertical parking spaces;
FIG. 2 is a view of parallel parking spaces;
FIG. 3 shows an oblique parking space;
FIG. 4 is a ground plane diagram of an integrated parking test field;
fig. 5 is a flowchart of a design method of an integrated parking test yard.
Detailed Description
The invention is further illustrated by the following examples:
the present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.
The invention provides a design method of an integrated parking test site, which is used for extracting a parking test scene and guiding the design of the integrated parking test site according to the extracted parking test scene; the parking test scene meets the actual parking scene and the parking test requirements, and meanwhile, the boundary characteristics of the parking test scene have expandability and the scene expansion requirements in the development process are met.
The invention relates to a design method of an integrated parking test site, which comprises the following steps:
and step 10, establishing a parking parameter characteristic database and acquiring parameters in a parking scene.
The parking parameters include, but are not limited to, city acquisition, date acquisition, weather conditions, parking space type, parking space included angle, parking space length, parking space width, boundary type, illuminance, parking area topographic information, and the like.
Step 20, size extraction:
and acquiring a parking space size data distribution map, and extracting the size of the parking space according to a clustering method, so as to ensure that the parking success rate of the parking space with the standard size is the basic requirement of the vehicle with the automatic parking function. Therefore, clustering results larger than the standard size need to be screened out; and extracting the size of the set threshold value as a lower limit value of the key size of the parking space, wherein the lower limit value is used for a stricter parking test scene. The threshold is set based on the principle of statistical analysis, and events with a probability of occurrence of less than 5% are regarded as low-probability events.
Step 21: extracting a non-key size value of the parking space corresponding to the parking space lower limit value according to the key size lower limit value extracted in the step 20; and extracting non-critical dimensions, integrating factors such as the line width of the parking space and the line drawing error of the parking space line, and the like within the range of the lower limit dimension +/-Delta of the critical dimension, wherein the Delta value is selected within the error range of the parking space dimension.
Preferably, the Δ selected in the present invention is 10.
Step 22: checking the rationality of the parking space size:
counting the occupation ratio of the parking spaces composed of the key sizes and the non-key sizes obtained in the step 20 and the step 21 in the database; the ratio value is used for checking the authenticity of the extracted parking space size (length and width).
Because the parking space size is divided into two dimensions of length and width, in the invention, the step 20 is used for extracting the key size dimension of the parking space, and the step 21 is used for extracting the secondary size dimension of the parking space. The parking space length and width formed by the results extracted in the two steps may not exist in the acquired parking space, and the results cannot be used for testing, so that the occupation ratio needs to be calculated to verify the authenticity of the extracted parking space size, and meanwhile, the distribution condition of the extracted results in the acquired data can be obtained.
Step 30, establishing a parking scene feature vector group:
the characteristic vector at least comprises parking space parameters such as a parking space type, a terrain, a step type, a space boundary (a front boundary, a rear boundary, a left boundary and a right boundary), and the like, and the multivariate combined probability distribution of the characteristic vector group under the dimension of the parking space size is obtained.
Step 40, parking scene extraction:
and (3) extracting parking scene features according to a set threshold value of the cumulative probability, and screening out small-probability events and abnormal events in the feature vector group obtained in the step 30. The feature vector group of step 30 screens out non-critical boundary type features, which results in effectively reducing the variety of feature vectors; respectively counting the probability distribution of the non-key boundary types, and extracting the non-key boundary types with set thresholds; the non-critical boundary characteristics include the material of the parking space area, the width of the parking space line, the line type of the parking space line, the color of the parking space line, the occupation facility, the limit facility, the direction indication of the parking space and the like.
Step 50, parking scene inspection:
and (4) fusing the results of the step (20) and the step (40), analyzing the difference between the fused result and the real scene in the database according to the reality principle in the fusion process, and rejecting the extreme scene fusion of the step (20) and the extreme scene of the step (40). The fusion result of the step eliminates small-probability events, covers at least 90% of parking scenes, and can be applied to fixed scene testing. And taking the result fused in the step as a main line, extracting the dynamic characteristics of the self-vehicle, the characteristics of the traffic participants and the environmental characteristics, and extracting part of parking test cases.
Step 60, parking test scene results:
since more parking scenes are extracted in step 50, the parking scenes should be combined to reduce the number of fixed scenes and reduce the floor area of the parking lot.
The principle of combining the results in the step is as follows:
1. reserving a standard parking space;
2. reserving a parking space with a lower limit size;
3. complex boundaries cover simple boundaries;
extracting a parking test scene according to the principle; the scenario of this step is for a scalable boundary scheme.
Step 70, designing a parking test site: and according to the result of the step 60, comprehensively designing a parking test site.
Example 1
As shown in fig. 5, a method for designing an integrated parking test site includes the following steps:
step 10: according to an electronic form collected by a parking scene, a parking characteristic database is established, and parking space scene parameters of different parking space arrangement modes are obtained;
step 20: respectively marking the length size and the width size of the parking space as a critical size and a non-critical size according to the type of the parking space, acquiring normal distribution of the critical size of the parking space, and extracting a lower limit value of the critical size according to a set threshold value;
step 21: extracting a non-critical dimension value of the parking space with the lower limit value according to the critical dimension lower limit value extracted in the step 20; extracting non-critical dimensions within the range of the lower limit dimension +/-Delta quantile value of the critical dimensions, wherein Delta is 10;
step 22: checking the rationality of the parking space size: counting the occupation ratio of the parking spaces composed of the key sizes and the non-key sizes obtained in the step 20 and the step 21 in the database;
step 30: screening key parameters in a parking scene, combining the key parameters into a parking space feature vector group, clustering the parking space feature vector group according to the type of parking spaces, and counting a multivariate combined probability distribution according to the key size of the parking spaces by the clustered feature vector group;
step 40: extracting parking scene features under the accumulation probability of a set threshold value from the feature vector group obtained in the step 30, and screening out parking scenes with non-key features so as to obtain a typical parking scene;
step 50: the feature vector group obtained in step 40 is fused with the parking space size extracted in step 20, and the fused parking space features are compared with the difference of the parking space features in the database;
step 60: screening out features with large differences according to the parking space feature difference results obtained in the step 50, and finally extracting parking space type results of a parking test site;
step 70: and (4) designing an integrated parking test site.
The parking space characteristic parameter information is shown in a table 1 and a table 2:
TABLE 1
TABLE 2
As shown in Table 3, the parking scenario parameter database includes, but is not limited to, the illustrated parameters.
Example 2
In the embodiment, according to the design method of the invention, an integrated parking test site is designed.
As shown in fig. 1 to fig. 3, the parking test scenario plans three parking space types, namely a vertical parking space, a parallel parking space and an oblique parking space, and the parking mode may be reverse parking or forward parking.
As shown in fig. 4, according to the obtained feature vector group, parking scene features under a set threshold cumulative probability are extracted, and parking scenes with non-key features are screened out, so as to obtain a typical parking scene. The ground material of the parking lot field is extracted and applied to the scheme, wherein the ground material of the areas A and D is asphalt, the ground material of the areas B is square bricks and marble, and the ground material of the areas C is cement.
As shown in fig. 4, the topographic features include horizontal ground areas (areas a and D) and ramp areas (areas B and C); slope grade extraction the method according to step 40, in this embodiment, the grade is designed as a multi-grade slope; and a field is reserved in the C area and is used for expanding and building the first type of parking space.
The length and width of the parking space are extracted according to the following steps:
respectively marking the length size and the width size of a parking space as a critical size and a non-critical size according to the type of the parking space, acquiring normal distribution of the critical size of the parking space, and extracting a lower limit value of the critical size according to a set threshold value; the length dimension of the parallel parking spaces is marked as a key dimension, and the width dimension is marked as a non-key dimension; the width dimension of the vertical parking space and the oblique parking space is marked as a key dimension, and the length dimension is marked as a non-key dimension; extracting the parking space size of the corresponding parking space type according to a set threshold value;
extracting a non-key size value of the parking space with the lower limit value according to the extracted key size lower limit value; extracting non-critical dimensions within the range of the lower limit dimension +/-Delta quantile value of the critical dimensions, wherein Delta is 10;
checking the rationality of the parking space size: the extracted key size and non-key size are the 2-dimensional size of the parking space, in order to verify the authenticity of the parking space size, the authenticity of an extraction result needs to be represented by the percentage of the extracted parking space size in a database, if the result is 0%, the extraction result does not exist, and the step needs to be returned for extraction again.
In the present embodiment, the standard size and the lower limit size are included.
The spatial boundary is extracted according to the following steps:
screening key parameters in a parking scene, combining the key parameters into a parking space feature vector group, clustering the parking space feature vector group according to the type of parking spaces, and counting multivariate joint probability distribution according to the key size of the parking spaces by the clustered feature vector group;
extracting parking scene features under the accumulation probability of a set threshold value from the obtained feature vector group, and screening out parking scenes with non-key features so as to obtain a typical parking scene;
and fusing the obtained feature vector group with the extracted parking space size, and comparing the fused parking space features with the parking space feature difference in the database.
In this embodiment, except for the wall rear boundary and the curb, the rest of space boundaries are movable and expandable space boundaries, so that flexible layout of a field is realized, and the requirement for test scene expansion is met. The characteristics such as car position line type, parking stall line colour, parking stall line closure, occupy-place facility, spacing facility, parking stall shape are drawed to be applied to the embodiment with the result.
And screening out features with large differences according to the obtained difference results of the parking space features, and finally extracting parking space type results of the parking test site to obtain the integrated parking test site.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. Those skilled in the art will appreciate that the present invention is not limited to the particular embodiments described herein, and that various obvious changes, rearrangements and substitutions will now be apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in some detail by the above embodiments, the invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the invention, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. A design method of an integrated parking test site is characterized by comprising the following steps:
step 10, establishing a parking parameter characteristic database, and acquiring parameters in a parking scene;
step 20, size extraction: acquiring a parking space size data distribution map, and extracting the size of a parking space according to a clustering method; extracting the size of a set threshold value as a key size lower limit value of the parking space;
step 21: extracting a non-key size value of the parking space corresponding to the parking space lower limit value according to the key size lower limit value extracted in the step 20; extracting non-critical dimensions within the range of the lower limit dimension +/-delta quantile value of the critical dimensions;
step 22: checking the rationality of the parking space size:
counting the proportion of parking spaces composed of the key sizes and the non-key sizes obtained in the steps 20 and 21 in a database;
step 30, establishing a parking scene feature vector group: screening key parameters in a parking scene, combining the key parameters into a parking space feature vector group, clustering the parking space feature vector group according to the type of parking spaces, and counting a multivariate combined probability distribution according to the key size of the parking spaces by the clustered feature vector group;
step 40, parking scene extraction: extracting parking scene features under the accumulation probability of a set threshold value from the feature vector group obtained in the step 30, and screening out parking scenes with non-key features so as to obtain a typical parking scene;
step 50, parking scene inspection: the feature vector group obtained in the step 40 is fused with the parking space size extracted in the step 20, and the fused parking space feature is compared with the difference of the parking space feature in the database;
step 60, parking test scene results: screening out features with large differences according to the parking space feature difference results obtained in the step 50, and finally extracting parking space type results of a parking test site;
step 70: designing an integrated parking test field: and according to the result of the step 60, comprehensively designing a parking test site.
2. The design method of the integrated parking test yard according to claim 1, wherein: step 10, the parking parameters include, but are not limited to, city acquisition, date acquisition, weather conditions, parking space type, parking space included angle, parking space length, parking space width, boundary type, illuminance, parking area topographic information, and the like.
3. The design method for the integrated parking test site according to claim 1, wherein the step 20 comprises the following specific steps: and marking the parking bit length size and the parking bit width size as a critical size and a non-critical size respectively according to the type of the parking space, acquiring normal distribution of the key size of the parking space, and extracting a lower limit value of the key size according to a set threshold value.
4. The design method of the integrated parking test yard according to claim 1, wherein: the selection of the delta value needs to integrate the parking space line width and the parking space line drawing error factors and is within the error range of the parking space size.
5. The design method of the integrated parking test yard according to claim 4, wherein: the delta is 10.
6. The design method of the integrated parking test yard according to claim 1, wherein: and step 30, the composition of the characteristic vector at least comprises parking space parameters of a parking space type, a terrain, a step type and a space boundary.
7. The design method of the integrated parking test yard according to claim 6, wherein: the spatial boundary includes a front boundary, a rear boundary, a left boundary, and a right boundary.
8. The design method of the integrated parking test site according to claim 1, wherein: and step 40, respectively counting the probability distribution of the non-key boundary types, and extracting the non-key boundary types with set thresholds.
9. The method of claim 8, wherein the step of designing the integrated parking test yard comprises the steps of: the non-key boundary characteristics comprise a parking space area material, a parking space line width, a parking space line type, a parking space line color, an occupying facility, a limiting facility and a parking space direction indication.
10. The design method of the integrated parking test yard according to claim 1, wherein: and step 60, reserving standard parking spaces for the result combination, reserving parking spaces with a lower limit size and covering simple boundaries with complex boundaries.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152174.6A CN113886955B (en) | 2021-09-29 | 2021-09-29 | Design method of integrated parking test site |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111152174.6A CN113886955B (en) | 2021-09-29 | 2021-09-29 | Design method of integrated parking test site |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113886955A CN113886955A (en) | 2022-01-04 |
| CN113886955B true CN113886955B (en) | 2022-09-09 |
Family
ID=79008174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111152174.6A Active CN113886955B (en) | 2021-09-29 | 2021-09-29 | Design method of integrated parking test site |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113886955B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115828608A (en) * | 2022-12-12 | 2023-03-21 | 中汽院智能网联科技有限公司 | Scene construction method for intelligent parking test |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7818698B2 (en) * | 2007-06-29 | 2010-10-19 | Taiwan Semiconductor Manufacturing Company, Ltd. | Accurate parasitic capacitance extraction for ultra large scale integrated circuits |
| CN109910872B (en) * | 2019-03-18 | 2019-12-10 | 中国汽车工程研究院股份有限公司 | parking scene extraction system and method based on natural driving data |
| CN110032809A (en) * | 2019-04-16 | 2019-07-19 | 中国汽车工程研究院股份有限公司 | One kind is parked scene virtual reconstruction method |
| 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 |
-
2021
- 2021-09-29 CN CN202111152174.6A patent/CN113886955B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113886955A (en) | 2022-01-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107665603B (en) | Real-time detection method for judging parking space occupation | |
| Hinz et al. | Automatic extraction of urban road networks from multi-view aerial imagery | |
| Serna et al. | Paris-rue-Madame database: A 3D mobile laser scanner dataset for benchmarking urban detection, segmentation and classification methods | |
| EP2313741B1 (en) | Method for updating a geographic database for a vehicle navigation system | |
| EP2603770B1 (en) | Parking lot detection using probe data | |
| CN105138525B (en) | Traffic video processing unit and method and retrieval device and method | |
| CN107067781B (en) | GIS road black spot map generation method for advanced driving assistance system application | |
| CN111311918A (en) | Traffic management method and device based on visual analysis | |
| CN113886955B (en) | Design method of integrated parking test site | |
| CN112365595A (en) | Analysis method for identifying traffic accident multi-point based on alarm data point element | |
| CN112229411A (en) | Data processing method and device | |
| DE102022134876A1 (en) | ROAD MAP GENERATION SYSTEM AND METHODS OF USE | |
| DE102011075412A1 (en) | A method and system for detecting a static scene, determining raw events, and detecting free areas in an observation area | |
| CN113408654B (en) | Urban road network fusion method, system and storage medium based on hierarchical merging | |
| CN114898243A (en) | Traffic scene analysis method and device based on video stream | |
| Puan et al. | Applicability of an automatic pneumatic–tube–based traffic counting device for collecting data under mixed traffic | |
| CN109544981A (en) | Image processing method, device, equipment and medium | |
| CN115587463A (en) | Automatic driving test scene design method based on scene classification | |
| Madhu et al. | Identification of different vehicle-following manoeuvres for heterogeneous weak-lane disciplined traffic condition from vehicle trajectory data | |
| WO2019063208A1 (en) | Method for automatically identifying parking areas and/or non-parking areas | |
| CN110298253B (en) | Urban building virtual display method and system based on population big data | |
| CN116168538B (en) | Planar road vehicle passing space identification method | |
| Noh et al. | SafetyCube: Framework for potential pedestrian risk analysis using multi-dimensional OLAP | |
| Saito et al. | Crash prediction modeling for curved segments of rural two-lane two-way highways in Utah. | |
| CN114003582A (en) | Traffic accident foreground derivation method for automatic driving vehicle and 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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231218 Address after: No.1, xinhongqi street, automobile economic and Technological Development Zone, Changchun, Jilin Province Patentee after: China Faw Co.,Ltd. Patentee after: CHANGCHUN AUTOMOTIVE TEST CENTER Co.,Ltd. Address before: 130011 No.1, xinhongqi street, Changchun automobile economic and Technological Development Zone, Changchun City, Jilin Province Patentee before: China Faw Co.,Ltd. |
|
| TR01 | Transfer of patent right |