CN112435336A - Curve type identification method and device, electronic equipment and storage medium - Google Patents

Curve type identification method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112435336A
CN112435336A CN202011271209.3A CN202011271209A CN112435336A CN 112435336 A CN112435336 A CN 112435336A CN 202011271209 A CN202011271209 A CN 202011271209A CN 112435336 A CN112435336 A CN 112435336A
Authority
CN
China
Prior art keywords
central axis
road surface
point
calculating
clustering
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
CN202011271209.3A
Other languages
Chinese (zh)
Other versions
CN112435336B (en
Inventor
刘圆
刘春成
惠念
刘奋
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.)
Heading Data Intelligence Co Ltd
Original Assignee
Heading Data Intelligence Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Heading Data Intelligence Co Ltd filed Critical Heading Data Intelligence Co Ltd
Priority to CN202011271209.3A priority Critical patent/CN112435336B/en
Publication of CN112435336A publication Critical patent/CN112435336A/en
Application granted granted Critical
Publication of CN112435336B publication Critical patent/CN112435336B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/05—Geographic models
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
    • G06T17/20—Finite element generation, e.g. wire-frame surface description, tesselation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
    • G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Geometry (AREA)
  • Multimedia (AREA)
  • Computer Graphics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Remote Sensing (AREA)
  • Processing Or Creating Images (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a method and a device for identifying a curve type, electronic equipment and a storage medium, wherein the method comprises the following steps: collecting road surface point clouds, projecting the road surface point clouds into a plane image, extracting a road surface central axis, expanding the road surface central axis, and calculating the central axis attribute; calculating the image moment of the central axis projection drawing, and calculating the key characteristics of the central axis; clustering the central axis feature set through hierarchical clustering, clustering the central axis feature set through a K-means clustering method based on an initial clustering center, and outputting a feature vector to a model file; and extracting the characteristic vector of the data to be identified, calculating the Mahalanobis distance between the characteristic vector to be identified and the characteristic vector of the model, and determining the type of the data to be identified. By the scheme, the curve type can be automatically identified, the adaptability of road identification and the accuracy of an identification result in high-precision map manufacturing are improved, accurate processing algorithms and configuration parameters can be conveniently selected for different curve scenes, and the road extraction effect is guaranteed.

Description

Curve type identification method and device, electronic equipment and storage medium
Technical Field
The invention relates to the field of high-precision map making, in particular to a curve type identification method and device, electronic equipment and a storage medium.
Background
In the high-precision map making, compared with the traditional manual vectorization map making, the automatic auxiliary map making has the advantages of automatic process, high making efficiency, low overall cost and the like. Due to the diversity of road scenes in the map field, corresponding processing algorithms need to be developed for different scenes in the automatic auxiliary mapping, wherein a curve area is a special road scene.
Compared with a general road area, the curve area has a special spatial form and a special element type, and a processing algorithm applicable to the general road area cannot be completely applicable to the curve area. For example, the depth direction distance corresponding to the forward-looking projection algorithm needs to be shorter than that of a common road area, the elevation filtering algorithm needs to consider the influence of the ground gradient, the lane line incomplete complement algorithm needs to consider the transverse gradient, the direction heuristic threshold needs to be adjusted when linear elements such as road edge stones, guardrails, lane lines and the like are automatically extracted, common divergence or confluence ground markings generally appear near the curve area, and linear induction marks generally appear in the ramp area. The spatial form and the element type corresponding to different types of curves are slightly different, and the threshold value configuration of the processing algorithm may be different for different types of curves.
At present, most of the existing curve identification methods are directly applied to automatic driving scenes, namely, road scenes are collected in real time and are subjected to visual analysis, driving control is carried out, the problem of algorithm time complexity needs to be considered, and curve identification is hardly applied to high-precision map making. Some common road identification methods in the drawing field have poor adaptability in identification of different types of curves and low accuracy of identification results.
Disclosure of Invention
In view of this, embodiments of the present invention provide a curve type identification method, an apparatus, an electronic device, and a storage medium, so as to solve the problems of poor adaptability and low accuracy of identification results in the existing different types of curve identification methods.
In a first aspect of the embodiments of the present invention, a method for identifying a curve type is provided, including:
collecting road surface point clouds through a vehicle-mounted laser radar, projecting the road surface point clouds into a two-dimensional XOY plane image, extracting a road surface central axis through an image morphology operator, expanding the road surface central axis, and calculating the attribute of the expanded road surface central axis;
projecting the central axis of the road surface to a two-dimensional XOY plane, calculating the image moment of a projection drawing, and calculating the key characteristics of each central axis;
clustering the central axis feature set through hierarchical clustering to obtain an initial clustering center, clustering the central axis feature set through a K-means clustering method based on the initial clustering center, outputting a central feature vector of a cluster to a model file, and determining a curve type corresponding to the model file;
extracting the characteristic vector of the data to be identified, calculating the Mahalanobis distance between the characteristic vector of the data to be identified and the characteristic vector of the model, and selecting the curve type closest to the characteristic vector as the type of the data to be identified.
In a second aspect of embodiments of the present invention, there is provided an apparatus for curve type identification, including:
the system comprises a preprocessing module, a vehicle-mounted laser radar, a road surface point cloud processing module and a data processing module, wherein the preprocessing module is used for acquiring the road surface point cloud through the vehicle-mounted laser radar, projecting the road surface point cloud into a two-dimensional XOY plane image, extracting a road surface central axis through an image morphology operator, expanding the road surface central axis, and calculating the attribute of the expanded road surface central axis;
the feature extraction module is used for projecting the central axis of the road surface to a two-dimensional XOY plane, calculating the image moment of a projection drawing and calculating the key feature of each central axis;
the model generation module is used for clustering the central axis feature set through hierarchical clustering to obtain an initial clustering center, clustering the central axis feature set through a K-means clustering method based on the initial clustering center, outputting a central feature vector of the cluster to a model file, and determining a curve type corresponding to the model file;
and the data identification module is used for extracting the characteristic vector of the data to be identified, calculating the Mahalanobis distance between the characteristic vector of the data to be identified and the characteristic vector of the model, and selecting the type of the curve closest to the characteristic vector as the type of the data to be identified.
In a third aspect of the embodiments of the present invention, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method according to the first aspect of the embodiments of the present invention.
In a fourth aspect of the embodiments of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method provided in the first aspect of the embodiments of the present invention.
In the embodiment of the invention, different road surface point clouds are processed to extract central axes and calculate the attributes of the central axes, key features on the central axes are extracted, models of different curves are determined through a clustering algorithm, and finally, different scene data are classified based on the curve models. The method and the device can realize curve type classification of road data, enhance the adaptability of a curve identification algorithm and guarantee the accuracy of an identification result. When a high-precision map is produced, a proper processing algorithm and configuration parameters can be selected for a specific scene, the problem of poor data extraction effect caused by non-corresponding algorithm scenes is solved, the processing complexity of a single algorithm is reduced, and the overall generation efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings described below are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart illustrating a curve type identification method according to an embodiment of the present invention;
FIG. 2 is another schematic flow chart of a curve type identification method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus for curve type identification according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons skilled in the art without any inventive work shall fall within the protection scope of the present invention, and the principle and features of the present invention shall be described below with reference to the accompanying drawings.
The terms "comprises" and "comprising," when used in this specification and claims, and in the accompanying drawings and figures, are intended to cover non-exclusive inclusions, such that a process, method or system, or apparatus that comprises a list of steps or elements is not limited to the listed steps or elements.
The terms "comprises" and "comprising," when used in this specification and claims, and in the accompanying drawings and figures, are intended to cover non-exclusive inclusions, such that a process, method or system, or apparatus that comprises a list of steps or elements is not limited to the listed steps or elements. In addition, "first" and "second" are used to distinguish different objects, and are not used to describe a specific order.
Referring to fig. 1, fig. 1 is a schematic flow chart of a curve type identification method according to an embodiment of the present invention, including:
s101, collecting road surface point clouds through a vehicle-mounted laser radar, projecting the road surface point clouds into a two-dimensional XOY plane image, extracting a road surface central axis through an image morphology operator, expanding the road surface central axis, and calculating the attribute of the expanded road surface central axis;
the road surface point cloud is a point set of the appearance of a three-dimensional object in space, and the three-dimensional point cloud data is projected to a two-dimensional plane, so that the extraction of the central axis, the feature calculation and the like can be facilitated. The two-dimensional XOY plane is a two-dimensional plane, the road surface point cloud data is projected to the two-dimensional plane according to a certain direction, and an XY two-dimensional coordinate system is arranged on the two-dimensional plane.
And projecting the road surface point cloud into a two-dimensional XOY plane image, and recording projection parameters, wherein the projection parameters comprise real coordinates of a projection area and actual lengths corresponding to each pixel.
It will be appreciated that in one embodiment, the mid-point cloud axis is replaced with POS data (positioning and attitude determination system, i.e. IMU/DGPS combined high precision position and attitude measurement system) at the time of vehicle laser point cloud resolution. Each point of the POS data replaces a central axis point at equal intervals, a ro l angle (roll angle) of the corresponding point replaces a transverse slope, a pitch angle (pitch angle) of the corresponding point replaces a longitudinal slope, and a yaw angle (course angle) of the corresponding point replaces a course angle.
S102, projecting the central axis of the road surface to a two-dimensional XOY plane, calculating the image moment of a projection drawing, and calculating the key characteristics of each central axis;
and projecting each central axis along an XOY plane to obtain a projection drawing, and calculating the Hu moment of the projection drawing, wherein the image moment, namely the Hu moment, is used for carrying out parameter description on image characteristics, so that the calculation and extraction of the image characteristics are facilitated.
Illustratively, the projected pattern is 1024 pixels wide and 1024 pixels high, with a single pixel representing a real 10 centimeters.
The key features of the central axis at least comprise a mean value and a standard deviation of a transverse gradient of the central axis, a mean value and a standard deviation of a longitudinal gradient of the central axis, a ratio of actual length to original length of the central axis and a course of a central axis point. The actual length is the length corresponding to the pixel after the projection of the central axis, and the original length is the length before the projection of the central axis.
S103, clustering the central axis feature set through hierarchical clustering to obtain an initial clustering center, clustering the central axis feature set through a K-means clustering method based on the initial clustering center, outputting a central feature vector of the cluster to a model file, and determining a curve type corresponding to the model file;
the hierarchical clustering is to perform high-low sequencing on the similarity by calculating the similarity between the nodes, and perform hierarchical nested clustering. And clustering the feature sets of all the central axes by a hierarchical clustering method, and taking the cluster center as an initial clustering center. Based on the known initial clustering center, the feature set of the central axis is clustered by a K-means clustering method, the clustering convergence speed is high, and the Mahalanobis distance is selected from the clustering for distance measurement.
And clustering all the central axis features, and outputting the cluster center feature vectors to files, wherein the files correspond to model data of curves of different types.
S104, extracting the characteristic vector of the data to be identified, calculating the Mahalanobis distance between the characteristic vector of the data to be identified and the characteristic vector of the model, and selecting the type of the curve closest to the characteristic vector as the type of the data to be identified.
The Mahalanobis distance is used for representing the similarity of unknown samples, and the similarity of the unidentified characteristic data and the characteristic vectors in the curve model is judged by calculating the Mahalanobis distance between the unidentified characteristic data and the characteristic vectors in the curve model, so that the curve type corresponding to the data to be identified is judged.
In another embodiment of the present invention, on the basis of step S101, another flow chart of the curve type identification method is provided, which includes:
the method comprises the steps of collecting road surface point clouds through a vehicle-mounted laser radar, projecting the road surface point clouds into a two-dimensional XOY plane image, extracting road surface central axes through an image morphology operator, expanding the road surface central axes, and calculating the attributes of the expanded road surface central axes
S1011, collecting road surface point clouds through a vehicle-mounted laser radar;
the laser point cloud is segmented according to a certain collection mileage interval, the segmentation direction is perpendicular to the collection track, and the collection mileage interval can be 200 meters or other.
S1012, projecting the road surface point cloud into a two-dimensional XOY plane image;
and after the point cloud projection, recording projection parameters, wherein the projection parameters at least comprise real coordinates of a projection area and actual lengths corresponding to each pixel.
S1013, extracting the central axis of the road surface through an image morphology operator;
specifically, holes on the point cloud of the road surface are filled through an expansion operator, and a central axis of the road surface is extracted through a corrosion operator; fitting optimization is carried out on the axle line shape points of the road surface based on a least square method, and the coordinates of the axle line shape points of the road surface are inversely calculated into real coordinates according to projection parameters; and carrying out rarefying treatment on the axle line points of the road surface at preset intervals. Illustratively, the time intervals for extracting the central axis of the road are 1 meter.
S1014, expanding the central axis of the road surface;
specifically, on a two-dimensional XOY plane, a perpendicular line is drawn through a current central axis point to form a connection line between the current central axis point and a next central axis point, two points with a predetermined distance (for example, 1.5 meters) are taken from two sides of the central axis point, and the two points are taken as a transverse expansion point of the current central axis point;
and acquiring XY coordinates of the central axis point and the transverse expansion point, searching adjacent points in a preset range in the road surface point cloud, and taking the Z coordinate mean value of the adjacent points as the Z coordinate of the transverse expansion point.
S1015, calculating the central axis attribute of the expanded road surface;
the central axis attributes at least comprise a transverse slope, a longitudinal slope, a course angle and a ratio of course angle deviation value to distance. The method for calculating the ratio of the course angle deviation value to the distance comprises the following steps: the course angle deviation value is the absolute value of the difference value between the course of the current central axis point and the course of the next central axis point, and the distance is the linear distance between the current central axis point and the next central axis point.
And S1016, filtering the central axis point.
Specifically, traversing each central axis point, and calculating a course deviation value of each central axis point; and if the deviation value of the course angle is smaller than a preset threshold (such as 2 degrees), deleting the corresponding central axis point.
The method provided by the embodiment can automatically identify the JCT and I C, turn to the special road and other types of curves, provide differentiated curve scene information for subsequent processing, enhance the adaptability and accuracy of road identification, and facilitate the subsequent processing to select proper algorithms and configuration parameters, thereby efficiently and accurately completing high-precision map making.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Fig. 3 is a schematic structural diagram of an apparatus for curve type identification according to an embodiment of the present invention, where the apparatus includes:
the preprocessing module 310 is used for acquiring road surface point clouds through a vehicle-mounted laser radar, projecting the road surface point clouds into a two-dimensional XOY plane image, extracting road surface central axes through an image morphology operator, expanding the road surface central axes, and calculating the attributes of the expanded road surface central axes;
wherein, the extracting of the road surface central axis through the image morphology operator comprises:
filling holes on the road surface point cloud by using an expansion operator, and extracting a road surface central axis by using a corrosion operator; fitting optimization is carried out on the axle line shape points of the road surface based on a least square method, and the coordinates of the axle line shape points of the road surface are inversely calculated into real coordinates according to projection parameters; and carrying out rarefying treatment on the axle line points of the road surface at preset intervals.
Wherein, expand road surface axis and include:
on a two-dimensional XOY plane, a perpendicular line for connecting a current central axis point with a next central axis point is made through the current central axis point, two points with a preset distance are taken from two sides of the central axis point, and the two points are used as transverse expansion points of the current central axis point; and searching adjacent points in a preset range in the road surface point cloud, and taking the Z coordinate mean value of the adjacent points as the Z coordinate of the transverse expansion point.
The central axis attributes at least comprise transverse gradient, longitudinal gradient, course angle and the ratio of course angle deviation value to distance.
Optionally, the preprocessing module 310 further includes:
the filtering unit is used for traversing each central axis point and calculating the course deviation value of each central axis point; and if the course angle deviation value is smaller than a preset threshold value, deleting the corresponding central axis point.
The feature extraction module 320 is configured to project the central axis of the road surface onto a two-dimensional XOY plane, calculate an image moment of a projection diagram, and calculate a key feature of each central axis;
the key characteristics of the central axis at least comprise a central axis transverse gradient mean value and standard deviation, a central axis longitudinal gradient mean value and standard deviation, a ratio of the central axis actual length to the original length, and a central axis point course.
The model generation module 330 is configured to cluster the central axis feature set through hierarchical clustering to obtain an initial clustering center, cluster the central axis feature set through a K-means clustering method based on the initial clustering center, output a central feature vector of the cluster to a model file, and determine a curve type corresponding to the model file;
the data identification module 340 is configured to extract a feature vector of the data to be identified, calculate a mahalanobis distance between the feature vector of the data to be identified and the feature vector of the model, and select a curve type closest to the feature vector of the data to be identified as the data type to be identified.
It is understood that in one embodiment, the electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program performs steps S101 to S104 as in the first embodiment, and the processor implements automatic identification of the curve type when executing the computer program.
Those skilled in the art will understand that all or part of the steps in the method for implementing the above embodiments may be implemented by a program to instruct associated hardware, where the program may be stored in a computer-readable storage medium, and when executed, the program includes steps S101 to S104, where the storage medium includes, for example: ROM/RAM, magnetic disk, optical disk, etc.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. A curve type identification method, comprising:
collecting road surface point clouds through a vehicle-mounted laser radar, projecting the road surface point clouds into a two-dimensional XOY plane image, extracting a road surface central axis through an image morphology operator, expanding the road surface central axis, and calculating the attribute of the expanded road surface central axis;
projecting the central axis of the road surface to a two-dimensional XOY plane, calculating the image moment of a projection drawing, and calculating the key characteristics of each central axis;
clustering the central axis feature set through hierarchical clustering to obtain an initial clustering center, clustering the central axis feature set through a K-means clustering method based on the initial clustering center, outputting a central feature vector of a cluster to a model file, and determining a curve type corresponding to the model file;
extracting the characteristic vector of the data to be identified, calculating the Mahalanobis distance between the characteristic vector of the data to be identified and the characteristic vector of the model, and selecting the curve type closest to the characteristic vector as the type of the data to be identified.
2. The method of claim 1, wherein extracting the road surface central axis by the image morphology operator comprises:
filling holes on the road surface point cloud by using an expansion operator, and extracting a road surface central axis by using a corrosion operator;
fitting optimization is carried out on the axle line shape points of the road surface based on a least square method, and the coordinates of the axle line shape points of the road surface are inversely calculated into real coordinates according to projection parameters;
and carrying out rarefying treatment on the axle line points of the road surface at preset intervals.
3. The method of claim 1, wherein the expanding the median road surface axis comprises:
on a two-dimensional XOY plane, a perpendicular line for connecting a current central axis point with a next central axis point is made through the current central axis point, two points with a preset distance are taken from two sides of the central axis point, and the two points are used as the transverse expansion points of the current central axis point.
4. The method according to claim 3, wherein the taking two points with a predetermined distance on both sides of the central axis point and using the two points as the current central axis point lateral expansion point further comprises:
and acquiring XY coordinates of the transverse expansion point corresponding to the central axis point, searching adjacent points in a preset range of the transverse expansion point in the road surface point cloud, and taking the Z coordinate mean value of the adjacent points as the Z coordinate of the transverse expansion point.
5. The method of claim 1, wherein the axis attributes include at least a lateral grade, a longitudinal grade, a heading angle, and a ratio of a heading angle deviation value to a distance.
6. The method of claim 1, wherein calculating the extended rear road surface centerline property further comprises:
traversing each central axis point, and calculating a course deviation value of each central axis point;
and if the course angle deviation value is smaller than a preset threshold value, deleting the corresponding central axis point.
7. The method as claimed in claim 1, wherein the key features of the central axis at least include a mean value and a standard deviation of a transverse gradient of the central axis, a mean value and a standard deviation of a longitudinal gradient of the central axis, a ratio of an actual length of the central axis to an original length of the central axis, and a heading of a central axis point.
8. An apparatus for curve type identification, comprising:
the system comprises a preprocessing module, a vehicle-mounted laser radar, a road surface point cloud processing module and a data processing module, wherein the preprocessing module is used for acquiring the road surface point cloud through the vehicle-mounted laser radar, projecting the road surface point cloud into a two-dimensional XOY plane image, extracting a road surface central axis through an image morphology operator, expanding the road surface central axis, and calculating the attribute of the expanded road surface central axis;
the feature extraction module is used for projecting the central axis of the road surface to a two-dimensional XOY plane, calculating the image moment of a projection drawing and calculating the key feature of each central axis;
the model generation module is used for clustering the central axis feature set through hierarchical clustering to obtain an initial clustering center, clustering the central axis feature set through a K-means clustering method based on the initial clustering center, outputting a central feature vector of the cluster to a model file, and determining a curve type corresponding to the model file;
and the data identification module is used for extracting the characteristic vector of the data to be identified, calculating the Mahalanobis distance between the characteristic vector of the data to be identified and the characteristic vector of the model, and selecting the type of the curve closest to the characteristic vector as the type of the data to be identified.
9. An electronic device comprising a processor, a memory and a computer program stored in the memory and running on the processor, characterized in that the processor, when executing the computer program, carries out the steps of the curve type identification method according to any one of claims 1 to 7.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the curve type identification method as claimed in any one of claims 1 to 7.
CN202011271209.3A 2020-11-13 2020-11-13 Curve type identification method and device, electronic equipment and storage medium Active CN112435336B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011271209.3A CN112435336B (en) 2020-11-13 2020-11-13 Curve type identification method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011271209.3A CN112435336B (en) 2020-11-13 2020-11-13 Curve type identification method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN112435336A true CN112435336A (en) 2021-03-02
CN112435336B CN112435336B (en) 2022-04-19

Family

ID=74701286

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011271209.3A Active CN112435336B (en) 2020-11-13 2020-11-13 Curve type identification method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112435336B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114550121A (en) * 2022-02-28 2022-05-27 重庆长安汽车股份有限公司 Clustering-based automatic driving lane change scene classification method and recognition method
CN117649635A (en) * 2024-01-30 2024-03-05 湖北经济学院 Method, system and storage medium for detecting shadow eliminating point of narrow water channel scene

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104197897A (en) * 2014-04-25 2014-12-10 厦门大学 Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud
CN106503678A (en) * 2016-10-27 2017-03-15 厦门大学 Roadmarking automatic detection and sorting technique based on mobile laser scanning point cloud
CN107679458A (en) * 2017-09-07 2018-02-09 中国地质大学（武汉） The extracting method of roadmarking in a kind of road color laser point cloud based on K Means
US20180188059A1 (en) * 2016-12-30 2018-07-05 DeepMap Inc. Lane Line Creation for High Definition Maps for Autonomous Vehicles
CN108470159A (en) * 2018-03-09 2018-08-31 腾讯科技（深圳）有限公司 Lane line data processing method, device, computer equipment and storage medium
CN110866449A (en) * 2019-10-21 2020-03-06 北京京东尚科信息技术有限公司 Method and device for identifying target object in road
WO2020154967A1 (en) * 2019-01-30 2020-08-06 Baidu.Com Times Technology (Beijing) Co., Ltd. Map partition system for autonomous vehicles

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104197897A (en) * 2014-04-25 2014-12-10 厦门大学 Urban road marker automatic sorting method based on vehicle-mounted laser scanning point cloud
CN106503678A (en) * 2016-10-27 2017-03-15 厦门大学 Roadmarking automatic detection and sorting technique based on mobile laser scanning point cloud
US20180188059A1 (en) * 2016-12-30 2018-07-05 DeepMap Inc. Lane Line Creation for High Definition Maps for Autonomous Vehicles
CN107679458A (en) * 2017-09-07 2018-02-09 中国地质大学（武汉） The extracting method of roadmarking in a kind of road color laser point cloud based on K Means
CN108470159A (en) * 2018-03-09 2018-08-31 腾讯科技（深圳）有限公司 Lane line data processing method, device, computer equipment and storage medium
WO2020154967A1 (en) * 2019-01-30 2020-08-06 Baidu.Com Times Technology (Beijing) Co., Ltd. Map partition system for autonomous vehicles
CN110866449A (en) * 2019-10-21 2020-03-06 北京京东尚科信息技术有限公司 Method and device for identifying target object in road

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114550121A (en) * 2022-02-28 2022-05-27 重庆长安汽车股份有限公司 Clustering-based automatic driving lane change scene classification method and recognition method
CN117649635A (en) * 2024-01-30 2024-03-05 湖北经济学院 Method, system and storage medium for detecting shadow eliminating point of narrow water channel scene

Also Published As

Publication number Publication date
CN112435336B (en) 2022-04-19

Similar Documents

Publication Publication Date Title
CN108470159B (en) Lane line data processing method and device, computer device and storage medium
CN108564874B (en) Ground mark extraction method, model training method, device and storage medium
CN111192284B (en) Vehicle-mounted laser point cloud segmentation method and system
CN105667518B (en) The method and device of lane detection
CN112801022B (en) Method for rapidly detecting and updating road boundary of unmanned mining card operation area
CN109584294B (en) Pavement point cloud extraction method and device based on laser point cloud
WO2018068653A1 (en) Point cloud data processing method and apparatus, and storage medium
CN108280840B (en) Road real-time segmentation method based on three-dimensional laser radar
CN111209291B (en) Method and system for updating high-precision map by using crowdsourcing perception map
Soheilian et al. 3D road marking reconstruction from street-level calibrated stereo pairs
EP4120123A1 (en) Scan line-based road point cloud extraction method
CN112435336B (en) Curve type identification method and device, electronic equipment and storage medium
CN109285163B (en) Laser point cloud based lane line left and right contour line interactive extraction method
CN112184736A (en) Multi-plane extraction method based on European clustering
JP2022522385A (en) Road sign recognition methods, map generation methods, and related products
CN115294293B (en) Method for automatically compiling high-precision map road reference line based on low-altitude aerial photography result
CN114863376A (en) Road marking segmentation method and system based on vehicle-mounted laser point cloud data
CN117576652B (en) Road object identification method and device, storage medium and electronic equipment
CN115599119A (en) Unmanned aerial vehicle keeps away barrier system
KR20210098534A (en) Methods and systems for creating environmental models for positioning
Tripodi et al. Automated chain for large-scale 3d reconstruction of urban scenes from satellite images
Mattson et al. Reducing ego vehicle energy-use by LiDAR-based lane-level positioning
Chang et al. The implementation of semi-automated road surface markings extraction schemes utilizing mobile laser scanned point clouds for HD maps production
Ma et al. Road Curbs Extraction from Mobile Laser Scanning Point Clouds with Multidimensional Rotation‐Invariant Version of the Local Binary Pattern Features
Reddy et al. Implementation of Lane Detection Algorithms for Autonomous Vehicle Using Lidar Point Cloud Data

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