CN106845321B - Method and device for processing pavement marking information - Google Patents

Method and device for processing pavement marking information Download PDF

Info

Publication number
CN106845321B
CN106845321B CN201510882685.1A CN201510882685A CN106845321B CN 106845321 B CN106845321 B CN 106845321B CN 201510882685 A CN201510882685 A CN 201510882685A CN 106845321 B CN106845321 B CN 106845321B
Authority
CN
China
Prior art keywords
road surface
point cloud
cloud data
pavement
reflectivity
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
Application number
CN201510882685.1A
Other languages
Chinese (zh)
Other versions
CN106845321A (en
Inventor
贾双成
陈岳
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.)
Alibaba China Co Ltd
Original Assignee
Autonavi Software 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 Autonavi Software Co Ltd filed Critical Autonavi Software Co Ltd
Priority to CN201510882685.1A priority Critical patent/CN106845321B/en
Publication of CN106845321A publication Critical patent/CN106845321A/en
Application granted granted Critical
Publication of CN106845321B publication Critical patent/CN106845321B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a method and a device for processing pavement marking information. The processing method comprises the following steps: obtaining pavement point cloud data of the target road based on the track point information of the laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road; dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range; obtaining a reflectivity screening threshold value of a road surface area, and screening road surface marking data from road surface point cloud data of the road surface area according to the reflectivity screening threshold value of the road surface area and a preset extraction window, wherein the reflectivity screening threshold values of at least two road surface areas in a plurality of road surface areas are different; pavement markings in the pavement marking data are identified. The invention solves the technical problem of low recognition accuracy of the pavement marker.

Description

Method and device for processing pavement marking information
Technical Field
The invention relates to the field of map data processing, in particular to a method and a device for processing pavement marking information.
Background
The prior art methods for detecting pavement markings are roughly classified into the following two methods:
the first is to make a lane graph using manual and video playback. The method is very primitive, field industry is responsible for video recording, field industry uses the video recording of field industry to preliminarily determine the lane width or lane change of the road, and after the lane width or lane is determined, the lane edge is determined as the lane line, and the accuracy and efficiency are too low by using the scheme.
The second type uses the difference in reflectivity of the collected laser point cloud of the road to identify the mark on the road. The method utilizes the difference of the reflectivity of the laser point cloud to different colors to determine the mark of the laser point cloud data of the road pavement. When the laser point cloud of the road is collected, the reflectivity of the road surface marks (such as white lane lines) with the same color under different collection conditions (such as different angles facing the sunlight, different sides of the laser collection vehicle and the like) is different, and too many noise points which do not belong to the road marks are obtained in the obtained marking data of the road surface, so the identification effect is very poor, and the method has no practical value basically. For example, the white color may have a reflectance of 3000 in one place and 5000 in another place, and the same-color acquisition object may be different depending on the acquisition conditions such as day or night, or the acquisition accuracy of the laser acquisition vehicle itself.
As shown in the effect diagram of fig. 1, the marked data obtained by the scheme has much noise; in the effect diagram shown in fig. 2, the lane lines in the middle indicated by the marking arrows are not recognized at all, and the recognition accuracy of the road surface markings is low in both fig. 1 and fig. 2.
In view of the above, it is desirable to provide a method and an apparatus for processing road marking information with high recognition accuracy and high efficiency.
Disclosure of Invention
According to an aspect of an embodiment of the present invention, there is provided a processing method of road surface marking information, the processing method including: obtaining pavement point cloud data of the target road based on the track point information of the laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road; dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range; acquiring a reflectivity screening threshold of a road surface area, and screening road surface marking data from road surface point cloud data of the road surface area according to the reflectivity screening threshold of the road surface area, wherein the reflectivity screening thresholds of at least two road surface areas in a plurality of road surface areas are different; pavement markings in the pavement marking data are identified.
According to another aspect of the embodiments of the present invention, there is also provided a processing apparatus of road surface marking information, the apparatus including: the acquisition unit is used for acquiring pavement point cloud data of the target road based on the track point information of the laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road; the dividing unit is used for dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range; the screening unit is used for acquiring a reflectivity screening threshold of the road surface area, screening road surface marking data from road surface point cloud data of the road surface area according to the reflectivity screening threshold of the road surface area, wherein the reflectivity screening thresholds of at least two road surface areas in the plurality of road surface areas are different; and the identification unit is used for identifying the pavement marks in the pavement mark data.
By adopting the method and the device, different reflectivity screening thresholds are used for screening the pavement marking data for different pavement areas in the area to which the pavement point cloud data belongs, and different thresholds can be used for screening the point clouds with the same color but different reflectivity, so that the problems of low identification accuracy and low efficiency caused by the fact that the pavement markings with different reflectivities are processed by using the same threshold are solved, and the effect of efficiently and accurately identifying the pavement markings is realized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a diagram of the recognition effect of a pavement marker according to the prior art;
FIG. 2 is a graph of the recognition effect of another pavement marker according to the prior art;
FIG. 3 is a schematic diagram of a network environment of a computer terminal according to an embodiment of the present invention;
FIG. 4 is a flow chart of a method of processing pavement marking information according to an embodiment of the present invention;
FIG. 5 is a diagram illustrating a preset range and a preset extraction window according to an embodiment of the present invention;
FIG. 6 is a flow chart of an alternative method of processing pavement marking information in accordance with an embodiment of the present invention;
FIG. 7 is a graph of the effects of pavement marking data according to the prior art;
FIG. 8 is an effect diagram of pavement marking data according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating the effects of an identified pavement marker in accordance with an embodiment of the present invention;
FIG. 10 is a schematic view of a pavement marking information processing apparatus according to an embodiment of the present invention;
FIG. 11 is a schematic view of an alternative pavement marking information processing apparatus according to an embodiment of the present invention;
fig. 12 is a block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
There is also provided, in accordance with an embodiment of the present invention, a method embodiment of a method of processing pavement marking information, it being noted that the steps illustrated in the flowchart of the drawings may be carried out in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be carried out in an order different than here.
The method provided by the first embodiment of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking the example of the processing method running on a computer terminal, optionally, in this embodiment, the processing method of the three-dimensional map may be applied to a hardware environment formed by the terminal 10 and the server 30 shown in fig. 3, and the terminal may establish a connection with the server through a network. The terminal and the server can be provided with processors, and the terminal can be arranged on the server. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The above-mentioned terminal includes but is not limited to a mobile terminal, and the mobile terminal includes: smart phones, vehicle systems, tablet computers, and the like.
Under the above-described operating environment, the present application provides a method of processing road marking information as shown in fig. 4. As shown in fig. 4, the method may include the steps of:
step S401: and obtaining road surface point cloud data of the target road based on the track point information of the laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the road surface point cloud data is used for describing the road surface information of the target road.
Step S403: and dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range.
Step S405: the method comprises the steps of obtaining a reflectivity screening threshold value of a road surface area, screening road surface marking data from road surface point cloud data of the road surface area according to the reflectivity screening threshold value of the road surface area and a preset extraction window, wherein the reflectivity screening threshold values of at least two road surface areas in a plurality of road surface areas are different.
Step S407: the pavement markings represented by the pavement marking data are identified.
By adopting the method and the device, different reflectivity screening thresholds are used for screening the pavement marking data for different pavement areas in the area to which the pavement point cloud data belongs, and different thresholds can be used for screening the point clouds with the same color but different reflectivity, so that the problems of low identification accuracy and low efficiency caused by the fact that the pavement markings with different reflectivities are processed by using the same threshold are solved, and the effect of efficiently and accurately identifying the pavement markings is realized.
In the above embodiment, dynamic adaptive binarization processing may be performed on different road surface areas of the road surface point cloud data, and road surface marking data in the road surface point cloud data belonging to the road surface area is obtained by screening, so that road surface marking data identification may be performed on the road surface point cloud data representing different road surface areas by using different reflectivity screening thresholds. The dynamic self-adaptive binarization is to divide all data into N windows according to a moving rule, and divide the data into two parts for each of the N windows according to a uniform threshold and a preset extraction window method. For the embodiment, different threshold values can be adopted for data windows representing different road surface areas to carry out binarization processing by adopting a dynamic self-adaptive binarization processing mode, so that different threshold values are used for screening the same different reflectivity, and different problems are marked.
The laser Point Cloud is also called Point Cloud, and is a set of a series of massive points expressing target space distribution and target surface characteristics, which are obtained by acquiring the space coordinates of each sampling Point on the surface of an object under the same space reference system by using laser, and the Point set is called Point Cloud. The laser point cloud data comprises information of longitude, latitude, height and reflectivity of the point cloud under an earth coordinate system.
In the above embodiment of the present invention, the laser point cloud data of the target road and the track point information of the laser acquisition device may be acquired by the laser acquisition device, after the laser point cloud data and the track point information are acquired, the road surface height of the target road is determined based on the track point information, the road surface point cloud data representing the road surface information is extracted from the laser point cloud data based on the road surface height, the data representing different road surface areas in the road surface point cloud data are subjected to screening processing of different thresholds by using different thresholds and a method of presetting an extraction window, so as to obtain the road surface marking data, and the road surface marking data are identified to obtain the road surface marking.
Through the embodiment, the recognition effect is clear, the success rate is high, and pavement marks cannot be missed.
The above embodiments are detailed below with autopilot as an application scenario:
after the automatic driving is started, the laser point cloud data of the current running road (namely, the target road in the above embodiment) of the automatic driving vehicle and the track point information of the laser acquisition device can be acquired in real time through the laser acquisition device installed on the automatic driving vehicle, the road surface point cloud data of the target road is determined based on the track point information and the laser point cloud data, dynamic self-adaptive binarization processing is performed on different road surface areas corresponding to the road surface marking point cloud data (namely, different reflectivity screening threshold values are used for screening the data corresponding to the different road surface areas), the road surface marking data is obtained, the road surface marks in the road surface marking data are identified, and the identified road surface marks are displayed on a display of a vehicle-mounted system of the automatic driving vehicle.
In the above embodiment of the present invention, acquiring the reflectivity screening threshold of the road surface area includes: and determining a reflectivity screening threshold corresponding to the road surface area by using the reflectivity of the road surface point cloud data belonging to the road surface area.
The method for determining the reflectivity screening threshold corresponding to the road surface area by utilizing the reflectivity of the road surface point cloud data belonging to the road surface area comprises the following steps: and acquiring a first average value of the reflectivity of the road surface point cloud data belonging to the road surface area, and taking the first average value as a reflectivity screening threshold value corresponding to the road surface area.
Specifically, screening the road surface mark data from the road surface point cloud data of the road surface area according to the reflectivity screening threshold corresponding to the road surface area and a preset extraction window comprises: traversing the road surface point cloud data of the road surface area by using a preset extraction window, and executing the following steps on the traversed road surface point cloud data in the extraction window: and screening out the pavement marking data in the pavement point cloud data of the pavement area based on the reflectivity screening threshold value of the pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window.
In the above embodiment, screening out the road surface marking data in the road surface point cloud data of the road surface area based on the reflectivity screening threshold of the road surface area and the reflectivity average value of the road surface point cloud data within the preset extraction window includes: acquiring the ratio of the reflectivity average value of the road point cloud data in the preset extraction window to the reflectivity screening threshold value of the road area;
and judging whether the ratio is greater than a preset threshold value, if so, determining all the road surface point cloud data in a preset extraction window as road surface marking data.
The preset extraction window at least comprises data of two points in the road surface point cloud data belonging to the current road surface area.
According to the above-described embodiment, the screening step may be performed starting from the first one of the plurality of road surface areas, until all the road surface marking data are screened out by traversing the plurality of road surface areas, wherein the current road surface area is initialized to the first one of the plurality of road surface areas.
Specifically, the screening step comprises: determining whether all the pavement point cloud data in the preset extraction window are reserved or not based on the reflectivity screening threshold value of the current pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window, and using the reserved pavement point cloud data as pavement marking data of the current pavement area; and taking the next road surface area of the current road surface area as the current road surface area of the next screening operation.
Optionally, traversing the current road surface area by using the preset extraction window in the above embodiment may traverse the road surface point cloud data in each current road surface area by using the preset extraction window according to the preset sliding step length.
Optionally, after acquiring the road surface point cloud data, acquiring the road surface marking data in the road surface point cloud data by:
s1, dividing the area to which the road point cloud data belongs into a plurality of road surface areas according to a preset range;
s2, acquiring a reflectivity screening threshold value of the current road surface area;
and S3, circularly executing the following steps from the first road surface area in the plurality of road surface areas until the plurality of road surface areas are traversed, wherein the current road surface area is initialized to be the first road surface area in the plurality of road surface areas, and the circularly executing step comprises the following steps:
s31, dividing the current road surface area into a plurality of extraction windows by using preset extraction windows, wherein each preset extraction window comprises data of at least two road surface points;
s32, circularly executing the steps S321 and S322 from the first extraction window in the plurality of extraction windows until traversing the plurality of extraction windows, wherein the current extraction window is initialized to the first extraction window in the plurality of extraction windows:
s321: if the ratio of the average reflectivity (namely the reflectivity average value) of all the road surface point cloud data in the current extraction window to the reflectivity screening threshold value of the current road surface area is greater than a preset threshold value, keeping all the road surface point cloud data in the preset extraction window as road surface marking data;
s322: and taking the next extraction window of the current extraction window as the current extraction window of the next circulation operation.
S33: the next road surface area of the current road surface area is taken as the current road surface area of the next cycle operation.
The road surface marking data in the road surface point cloud data in the above embodiment includes the road surface marking data in each current preset extraction window in each current road surface area.
As shown in fig. 5, two preset frames (the preset range and the preset extraction window) are used, the average reflectivity (i.e., the B average value shown in fig. 5) in the large frame (i.e., the preset range, and the frame B in fig. 5) is used to determine the parameter (e.g., the reflectivity screening threshold) of the background (i.e., the current road surface area), the average reflectivity (i.e., the a average value shown in fig. 5) in the small frame (i.e., the preset extraction window, and the frame a in fig. 5) is used to determine the point cloud that should be retained, and the retained road surface point cloud data is the road surface marking data.
The reason why the human eye can recognize the object is that the pixel value of the object is different from the pixel value of the surrounding background, and by using this idea in the above embodiment, the preset range is set, and the average pixel of the background is determined by the reflectance of the data therein, and an accurate recognition result can be obtained.
The preset range and the preset extraction window in the above embodiments may be squares, the side length of the preset range may be no greater than the distance between two lane lines (e.g., between 0.9m and 1 m), and the side length of the preset extraction window may be 1/3 or 1/2 (e.g., 1/3 or 1/2, such as 0.5 m, marking the size of an arrow) of the length or width of the pavement marker.
Optionally, the preset range is determined based on a preset area, and if the preset area is 1 square meter, the coverage area of the preset range is 1 square meter; the preset range may also be determined based on a preset length and a preset width, such as a preset length of 0.95 meter and a preset width of 0.9 meter.
Optionally, the preset extraction window is determined based on a preset area, and if the preset area is 0.25 square meter, the coverage area of the preset extraction window is 0.25 square meter; the preset extraction window range may also be determined based on a preset length and a preset width, such as a preset length of 0.2 meters and a preset width of 0.3 meters.
Specifically, determining parameters (such as a reflectivity screening threshold) of the background by using an average value of the reflectivity of the road surface point cloud data in the large frame (i.e., the preset range), determining the point cloud to be retained by using an average value of the reflectivity in the small frame (i.e., the preset extraction window), and if the average value of the reflectivity of the point cloud in the small frame is greater than a preset multiple (i.e., the preset threshold in the above embodiment, such as 1.5) of the average value of the reflectivity of the point cloud in the large frame, retaining the road surface point cloud data in the small frame; otherwise, deleting the road surface point cloud data in the small frame.
In this embodiment, all the road surface point cloud data of which the average reflectivity of the road surface point cloud data of the extraction window is lower than the reflectivity screening threshold of the current window (large frame) are removed, and all the selected road surface point cloud data in the preset extraction window are obtained, namely the road surface marking data.
Alternatively, the reflectivity screening threshold may be a value between the average of the reflectivity of all the point cloud data and the average of the reflectivity (e.g., arrow) of the pavement marker.
According to the above embodiment of the present invention, obtaining the road surface point cloud data of the target road based on the track point information of the laser collecting device and the laser point cloud data of the target road may include:
acquiring the height of a track point from the track point information of the laser acquisition equipment; calculating the relative height of the laser acquisition equipment relative to the ground of the target road; calculating the difference between the height of the track point and the relative height, wherein the obtained difference is the road surface height of the target road; and removing the laser point cloud data with the difference between the height in the laser point cloud data and the height of the road surface of the target road exceeding a preset height (such as 10 centimeters) to obtain the road surface point cloud data of the target road.
Specifically, the laser collecting device can be installed on an automatic driving vehicle or a special laser collecting vehicle, track point information of the laser collecting device can be collected through the laser collecting vehicle, the track point information can include information of a central point of the laser collecting device, the height of the central point is used as the height of a track point of the laser collecting device, the height of a target road pavement is determined by utilizing the track point information of the laser collecting device and laser point cloud data of the target road, point cloud noise points, of which the difference between the height and the height of the target road pavement exceeds a preset height, in the laser point cloud data are removed, and road surface point cloud data of the target road are obtained.
Specifically, the relative height between the center point of the laser acquisition device and the ground of the target road can be obtained from the track point information of the laser acquisition device, the difference value between the height of the track point and the relative height is calculated, and the obtained difference value is the road surface height of the target road.
By the embodiment, the dynamic self-adaptive binarization processing can be performed on the road surface point cloud data without noise points, so that a more accurate identification result is obtained.
In the above embodiment, identifying pavement markings in the pavement marking data may include: acquiring a convex hull of the pavement marking data; and identifying the shape of the convex hull to obtain the pavement mark in the pavement mark data.
Alternatively, after the road surface marking data is acquired, a peripheral convex hull of the road surface marking data is acquired, and the shape of the peripheral convex hull is recognized to obtain the road surface marking (including a text mark and a road mark).
The above-mentioned embodiment of the present invention is described in detail below with reference to fig. 6 to 9, and as shown in fig. 6, the embodiment can be implemented by the following steps:
step S601: determining the road surface height of the target road by using the track points of the laser acquisition vehicle and the laser point cloud data of the target road, and removing point cloud noise points in the laser point cloud data based on the road surface height of the target road to obtain the road surface point cloud data of the target road.
Since there are many vehicles or other noisy data in the original laser point cloud data, these noisy data can be removed before binarization and identification thereof. The removing method is to delete all the laser point cloud data which are higher or lower than the preset height (such as 10 centimeters) of the road surface height of the target road.
Specifically, after track point information of a central point of laser acquisition equipment and laser point cloud data of a target road are obtained, road surface point cloud data of the target road are obtained; acquiring the track point height corresponding to the central point of the laser acquisition equipment from the track point information; calculating the relative height of the central point of the laser acquisition equipment relative to the ground of the target road; calculating the difference between the height of the track point and the relative height, wherein the obtained difference is the road surface height of the target road; and removing the laser point cloud data with the difference between the height in the laser point cloud data and the height of the road surface of the target road exceeding a preset height (such as 10 centimeters) to obtain the road surface point cloud data of the target road.
Step S603: and acquiring two preset frame bodies with different sizes, determining the background by using the average value of the reflectivity in the large frame, and determining the point cloud to be reserved by using the average value of the reflectivity in the small frame.
Optionally, in this embodiment, a large box is set to determine the average pixels of the surrounding background. As shown in fig. 5, the range of the large frame is generally not greater than the distance between two lane lines, and may be 0.9-1 m; the range of the small box takes 1/3 or 1/2 of the size of the arrow on the road, and the minimum number of points in the small box is: 2 pieces of the Chinese herbal medicines.
When the pavement marking data are obtained, if the average value of the reflectivity of the point cloud in the small frame is more than 1.5 times (the 1.5 times is a preset value) of the average value of the reflectivity of the point cloud in the large frame, the point cloud in the small frame is reserved.
In this embodiment, the large box sequentially traverses the entire road surface point cloud data, and in each step, the small box sequentially traverses the entire large box, and finally, the data retained in the small box is the road surface marking data to be determined.
As shown in fig. 5, in the embodiment, two preset frames (the preset range and the preset extraction window) are used, the reflectivity in the large frame (i.e., the preset range) is used to determine a parameter (e.g., a reflectivity screening threshold) of the background, the reflectivity in the small frame (i.e., the preset extraction window) is used to determine the point cloud to be retained, and the retained point cloud data is the road surface marking data.
In the embodiment, the color identification of the background and the pavement marker is realized by comparing the average values of the reflectivity of the pavement point cloud data in the large frame and the small frame, and the identification accuracy is high.
Step S605: and the retained point cloud in the small frame is the road surface marking data, and the convex hull is used for identifying lane marks or road character marks.
After the pavement marking data is obtained, the pavement marking may be further processed using methods such as convex hulls.
As shown in fig. 7 and 8, fig. 7 is the road surface marking data obtained by the method in the prior art, and fig. 8 is the road surface marking data obtained by the above embodiment, it can be seen that the road surface marking data obtained by the scheme of the present application has no noise.
After the pavement marking data shown in fig. 8 is obtained, the convex hull is obtained, and the convex hull is identified, so as to obtain the pavement marking shown in fig. 9, where the thicker lines in fig. 9 are all the identified pavement markings, which are exemplarily marked in fig. 9.
The laser point cloud-based pavement marking detection in the above embodiments of the present invention can be applied to the following three application scenarios:
(1) and (3) generating a high-precision lane: the high-precision lane can be generated only by needing a lane line, and the key for generating the high-precision lane is that the lane line can be accurately detected.
(2) The turning arrows on the road are correctly identified so that the intersection can be correctly generated.
(3) Automatic driving of the vehicle: autonomous vehicles require real-time detection of surrounding laser point clouds to identify marking information on the road for the vehicle to make proper driving decisions.
The above-described embodiments of the present invention are detailed below with the generation of high-precision lanes as application scenarios:
after a request for detecting a pavement marker of a target road is received, laser point cloud data of the target road and track point information of the laser acquisition equipment can be acquired in real time through laser acquisition equipment installed on a laser acquisition vehicle, the pavement height of the target road is determined by utilizing the track point information of the central point of the laser acquisition vehicle and the laser point cloud data of the target road, point cloud noise points with the height higher than or lower than the preset height of the pavement height of the target road in the laser point cloud data are removed, and pavement point cloud data of the target road are obtained.
After obtaining the road surface point cloud data of the target road, obtaining two preset frame bodies with different ranges, determining parameters (such as a reflectivity screening threshold value) of a background by utilizing the reflectivity in a large frame (namely the road surface area), determining the point cloud to be reserved by utilizing the parameters of the reflectivity in a small frame (namely the preset extraction window), and the reserved road surface point cloud data is the road surface marking data. Specifically, the whole road surface point cloud data is traversed by the large frame in sequence, in each step, the small frame traverses the whole large frame in sequence, and finally the data retained in the small frame is the road surface marking data to be determined.
After the pavement marking data to be determined are obtained, denoising processing is carried out on the retained pavement point cloud data in each small frame, and the pavement point cloud data with the reflectivity average value larger than a given value (the value is a value between the average value of all point cloud pavements and the average value of an arrow) in each small frame is used as the pavement marking data. After obtaining the road surface marking data, the road surface marking data may be recognized by a method such as a convex hull to obtain a road surface marking such as a lane marking or a road surface character marking.
The embodiment of the invention can remove noise points, and the dynamic self-adaptive threshold value binarization algorithm can quickly identify roads, and has high identification rate and low misjudgment rate; in addition, by adopting the embodiment, manual operation is not needed, so that the cost is low, and the practicability is high.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the invention. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required by the invention.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
Example 2
According to an embodiment of the present invention, there is also provided a processing apparatus for implementing the above-described processing method of road surface marking information, as shown in fig. 10, the apparatus including: an acquisition unit 20, a dividing unit 40, a screening unit 60, and an identification unit 80.
The acquiring unit 20 is configured to acquire road surface point cloud data of the target road based on the track point information of the laser acquisition device and the laser point cloud data of the target road, where the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition device, and the road surface point cloud data is used for describing road surface information of the target road.
The dividing unit 40 is configured to divide an area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range;
the screening unit 60 is configured to obtain a reflectivity screening threshold of the road surface area, and screen the road surface marking data from the road surface point cloud data of the road surface area according to the reflectivity screening threshold of the road surface area and a preset extraction window, where the reflectivity screening thresholds of at least two of the plurality of road surface areas are different.
An identification unit 80 for identifying the pavement markings in the pavement marking data.
By adopting the invention, the screening unit screens the road marking data by using different reflectivity screening threshold values for different road surface areas in the area to which the road point cloud data belongs, and screens the point clouds with the same color but different reflectivity by using different threshold values, thereby overcoming the problems of low identification accuracy and low efficiency caused by processing the road markings with different reflectivity by using the same threshold value, and realizing the effect of efficiently and accurately identifying the road markings.
In the above embodiment, dynamic adaptive binarization processing may be performed on different road surface areas of the road surface point cloud data, and road surface marking data in the road surface point cloud data is obtained by screening, so that different threshold values may be used for identifying the road surface marking data for the point cloud data representing different road surface areas. The dynamic self-adaptive binarization is to divide all data into N windows according to a moving rule, and divide the data into two parts for each of the N windows according to a uniform threshold and a method for setting an extraction window. For the embodiment, different threshold values can be adopted for data windows representing different road surface areas to carry out binarization processing by adopting a dynamic self-adaptive binarization processing mode, so that the problem that the reflectivity of different marks at different places is different is solved.
The laser Point Cloud is also called Point Cloud, and is a set of a series of massive points expressing target space distribution and target surface characteristics, which are obtained by acquiring the space coordinates of each sampling Point on the surface of an object under the same space reference system by using laser, and the Point set is called Point Cloud. The laser point cloud data comprises information of longitude, latitude, height and reflectivity of the point cloud under an earth coordinate system.
In the above embodiment, dynamic adaptive binarization processing may be performed on different road surface areas of the road surface point cloud data, and road surface marking data in the road surface point cloud data belonging to the road surface area is obtained by screening, so that road surface marking data identification may be performed on the road surface point cloud data representing different road surface areas by using different reflectivity screening thresholds. The dynamic self-adaptive binarization is to divide all data into N windows according to a moving rule, and divide the data into two parts for each of the N windows according to a uniform threshold and a method for setting an extraction window. For the embodiment, different threshold values can be adopted for data windows representing different road surface areas to carry out binarization processing by adopting a dynamic self-adaptive binarization processing mode, so that different threshold values are used for screening the same different reflectivity, and different problems are marked.
Through the embodiment, the recognition effect is clear, the success rate is high, and omission is avoided.
The above embodiments are detailed below with autopilot as an application scenario:
after the automatic driving is started, the laser point cloud data of the current running road (namely, the target road in the above embodiment) of the automatic driving vehicle and the track point information of the laser acquisition device can be acquired in real time through the laser acquisition device installed on the automatic driving vehicle, the road surface point cloud data of the target road is determined based on the track point information and the laser point cloud data, dynamic self-adaptive binarization processing is performed on different road surface areas corresponding to the road surface marking point cloud data (namely, different reflectivity screening threshold values are used for screening the data corresponding to the different road surface areas), the road surface marking data is obtained, the road surface marks in the road surface marking data are identified, and the identified road surface marks are displayed on a display of a vehicle-mounted system of the automatic driving vehicle.
As in the embodiment shown in fig. 11, the screening unit 60 may include: and a threshold determining module 41, configured to determine a reflectivity screening threshold corresponding to the road surface area by using the reflectivity of the road surface point cloud data belonging to the road surface area.
Wherein the threshold determination module comprises: and the threshold value determining submodule is used for acquiring a first average value of the reflectivity of the pavement point cloud data belonging to the pavement area, and taking the first average value as a reflectivity screening threshold value corresponding to the pavement area.
Specifically, the screening unit may include: the screening submodule 43 is configured to traverse the road surface point cloud data of the road surface area by using a preset extraction window, and execute the following steps on the traversed road surface point cloud data in the extraction window: and screening out the pavement marking data in the pavement point cloud data of the pavement area based on the reflectivity screening threshold value of the pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window.
Wherein, screening submodule includes: the retention submodule is used for acquiring the submodule and is used for acquiring the ratio of the reflectivity average value of the road point cloud data in the preset extraction window to the reflectivity screening threshold value of the road area; and the retention submodule is used for judging whether the ratio is greater than a preset threshold value, and if so, determining all the road surface point cloud data in the preset extraction window as the road surface marking data.
The average value of the reflectivity of all the road surface point cloud data in the preset extraction window is the average reflectivity of the road surface point cloud data in the preset extraction window.
The screening submodule 431 may obtain the road marking data of each current road area in the following manner:
dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range;
circularly executing the following steps from a first road surface area in the plurality of road surface areas until the plurality of road surface areas are traversed, wherein the current road surface area is initialized to be the first road surface area in the plurality of road surface areas, and the circularly executing step comprises the following steps:
the method comprises the steps of dividing a current road surface area into a plurality of extraction windows by utilizing a reflectivity screening threshold value of the current road surface area and preset extraction windows, wherein each preset extraction window comprises data of at least two road surface points.
And circularly executing the steps from the first extraction window in the plurality of extraction windows until the plurality of extraction windows are traversed, wherein the current extraction window is initialized to the first extraction window in the plurality of extraction windows: if the ratio of the average reflectivity of all the road surface point cloud data in the current extraction window to the reflectivity screening threshold of the current road surface area is larger than a preset threshold, keeping all the road surface point cloud data in the preset extraction window as road surface marking data; and taking the next extraction window of the current extraction window as the current extraction window of the next circulation operation.
The next road surface area of the current road surface area is taken as the current road surface area of the next cycle operation.
The road surface marking data in the road surface point cloud data in the above embodiment includes the road surface marking data in each current extraction window in each current road surface area.
As shown in fig. 5, two preset frames (the preset range and the preset extraction window) are used, the average reflectivity (i.e., the B average value shown in fig. 5) in the large frame (i.e., the preset range, and the frame B in fig. 5) is used to determine the parameter (e.g., the reflectivity screening threshold) of the background (i.e., the current road surface area), the average reflectivity (i.e., the a average value shown in fig. 5) in the small frame (i.e., the preset extraction window, and the frame a in fig. 5) is used to determine the point cloud that should be retained, and the retained road surface point cloud data is the road surface marking data.
The reason why the human eye can recognize the object is that the pixel value of the object is different from the pixel value of the surrounding background, and by using this idea in the above embodiment, the preset range is set, and the average pixel of the background is determined by the reflectance of the data therein, and an accurate recognition result can be obtained.
The preset range and the preset extraction window in the above embodiments may be squares, the side length of the preset range may be no greater than the distance between two lane lines (e.g., between 0.9m and 1 m), and the side length of the preset extraction window may be 1/3 or 1/2 (e.g., 1/3 or 1/2 of the marked arrow size) of the length or width of the pavement marker.
Optionally, before determining the road surface marking data, a second average value of the reflectivity of all road surface point cloud data in the preset extraction window is obtained, and the second average value is used as the reflectivity average value of the road surface point cloud data in the preset extraction window.
Specifically, determining parameters (such as a reflectivity screening threshold) of the background by using an average value of the reflectivity of the road surface point cloud data in the large frame (i.e., the preset range), determining the point cloud to be retained by using an average value of the reflectivity in the small frame (i.e., the preset extraction window), and if the average value of the reflectivity of the point cloud in the small frame is greater than a preset multiple (i.e., the preset threshold in the above embodiment, such as 1.5) of the average value of the reflectivity of the point cloud in the large frame, retaining the road surface point cloud data in the small frame; otherwise, deleting the road surface point cloud data in the small frame.
In this embodiment, after obtaining the retained road surface point cloud data based on the preset range and the preset extraction window, the road surface marking data is obtained, specifically, all the road surface point cloud data of which the average reflectivity value of the road surface point cloud data of the extraction window is lower than the reflectivity screening threshold value of the current window (large frame) are removed, and all the selected road surface point cloud data in the preset extraction window are obtained, that is, the road surface marking data is obtained.
Alternatively, the reflectivity screening threshold may be a value between the average of the reflectivity of all the point cloud data and the average of the reflectivity (e.g., arrow) of the pavement marker.
Before the road surface mark data are identified, denoising processing is carried out on the road surface mark data, and a more accurate and clear identification result is obtained.
According to the above embodiment of the present invention, the acquisition unit includes: the height acquisition module is used for acquiring the height of the track point from the track point information of the laser acquisition equipment; the first calculation module is used for calculating the relative height of the laser acquisition equipment relative to the ground of the target road; the second calculation module is used for calculating the difference value between the height of the track point and the relative height, and the obtained difference value is the height of the road surface of the target road; and the removing module is used for removing the laser point cloud data with the difference between the height in the laser point cloud data and the road surface height of the target road exceeding a preset height (such as 10 centimeters) to obtain the road surface point cloud data of the target road.
By the embodiment, the dynamic self-adaptive binarization processing can be performed on the road surface point cloud data without noise points, so that a more accurate identification result is obtained.
Further optionally, the identification unit comprises: the acquisition module is used for acquiring a convex hull of the pavement marking data; and the identification module is used for identifying the shape of the convex hull to obtain the pavement marker in the pavement marker data.
Alternatively, after the road surface marking data is acquired, a peripheral convex hull of the road surface marking data is acquired, and the shape of the peripheral convex hull is recognized to obtain the road surface marking (including a text mark and a road mark).
Each module provided in this embodiment is the same as the use method provided in the corresponding step of the method embodiment, and the application scenario may also be the same. Of course, it should be noted that the solution related to the modules may not be limited to the content and the scenario in the above embodiments, and the modules may be executed in a computer terminal or a mobile terminal, and may be implemented by software or hardware.
Example 3
The embodiment of the invention can provide a computer terminal which can be any computer terminal device in a computer terminal group. Optionally, in this embodiment, the computer terminal may also be replaced with a terminal device such as a mobile terminal.
As shown in fig. 12, the terminal includes: one or more processors 201 (only one is shown), a memory 203, and a transmission device 205 (such as the transmission device in the above embodiment), as shown in fig. 12, the terminal may further include an input/output device 207.
The memory 203 may be used to store software programs and modules, such as program instructions/modules corresponding to the method and apparatus for processing pavement marking information in the embodiment of the present invention, and the processor 201 executes various functional applications and data processing by running the software programs and modules stored in the memory 203, that is, implements the method for processing pavement marking information. The memory 203 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 203 may further include memory located remotely from the processor 201, which may be connected to the terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 205 is used for receiving or sending data via a network, and can also be used for data transmission between a processor and a memory. Examples of the network may include a wired network and a wireless network. In one example, the transmission device 205 includes a Network adapter (NIC) that can be connected to a router via a Network cable and other Network devices to communicate with the internet or a local area Network. In one example, the transmission device 205 is a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
Wherein the memory 203 is specifically used for storing application programs.
In this embodiment, the processor of the computer terminal may execute the following steps in the processing method of the road marking information: obtaining pavement point cloud data of the target road based on the track point information of the laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road; dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range; obtaining a reflectivity screening threshold value of a road surface area, and screening road surface marking data from road surface point cloud data of the road surface area according to the reflectivity screening threshold value of the road surface area and a preset extraction window, wherein the reflectivity screening threshold values of at least two road surface areas in a plurality of road surface areas are different; pavement markings in the pavement marking data are identified.
In this embodiment, the processor may further perform the following steps: and determining a reflectivity screening threshold corresponding to the road surface area by using the reflectivity of the road surface point cloud data belonging to the road surface area.
In this embodiment, the processor may further perform the following steps: and acquiring a first average value of the reflectivity of the road surface point cloud data belonging to the road surface area, and taking the first average value as a reflectivity screening threshold value corresponding to the road surface area.
In this embodiment, the processor may further perform the following steps: traversing the road surface point cloud data of the road surface area by using a preset extraction window, and executing the following steps on the traversed road surface point cloud data in the extraction window: and screening out the pavement marking data in the pavement point cloud data of the pavement area based on the reflectivity screening threshold value of the pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window.
In this embodiment, the processor may further perform the following steps: acquiring the ratio of the reflectivity average value of the road point cloud data in the preset extraction window to the reflectivity screening threshold value of the road area; and judging whether the ratio is larger than a preset threshold value, if so, determining all the road surface point cloud data in a preset extraction window as the road surface marking data.
By adopting the method and the device, different reflectivity screening thresholds are used for screening the pavement marking data for different pavement areas in the area to which the pavement point cloud data belongs, and different thresholds can be used for screening the point clouds with the same color but different reflectivity, so that the problems of low identification accuracy and low efficiency caused by the fact that the pavement markings with different reflectivities are processed by using the same threshold are solved, and the effect of efficiently and accurately identifying the pavement markings is realized.
It can be understood by those skilled in the art that the structure shown in fig. 12 is only an illustration, and the computer terminal may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 12 is a diagram illustrating a structure of the electronic device. For example, the computer terminal 10 may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 12, or have a different configuration than shown in FIG. 12.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by a program instructing hardware associated with the terminal device, where the program may be stored in a computer-readable storage medium, and the storage medium may include: flash disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
Example 4
The embodiment of the invention also provides a storage medium. Alternatively, in this embodiment, the storage medium may be used to store the program code executed by the processing method of the road surface marking information provided in the first embodiment.
Optionally, in this embodiment, the storage medium may be located in any one of computer terminals in a computer terminal group in a computer network, or in any one of mobile terminals in a mobile terminal group.
Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: acquiring pavement point cloud data of a target road based on track point information of laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road; carrying out dynamic self-adaptive binarization processing on the pavement point cloud data by utilizing the reflectivity of the pavement point cloud data to obtain pavement marking data in the pavement point cloud data; pavement markings in the pavement marking data are identified.
In the present embodiment, the storage medium is configured to store program code for performing the steps of: obtaining pavement point cloud data of the target road based on the track point information of the laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road; dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range; obtaining a reflectivity screening threshold value of a road surface area, and screening road surface marking data from road surface point cloud data of the road surface area according to the reflectivity screening threshold value of the road surface area and a preset extraction window, wherein the reflectivity screening threshold values of at least two road surface areas in a plurality of road surface areas are different; pavement markings in the pavement marking data are identified.
In the present embodiment, the storage medium is configured to store program code for performing the steps of: and determining a reflectivity screening threshold corresponding to the road surface area by using the reflectivity of the road surface point cloud data belonging to the road surface area.
In the present embodiment, the storage medium is configured to store program code for performing the steps of: and acquiring a first average value of the reflectivity of the road surface point cloud data belonging to the road surface area, and taking the first average value as a reflectivity screening threshold value corresponding to the road surface area.
In the present embodiment, the storage medium is configured to store program code for performing the steps of: traversing the road surface point cloud data of the road surface area by using a preset extraction window, and executing the following steps on the traversed road surface point cloud data in the extraction window: and screening out the pavement marking data in the pavement point cloud data of the pavement area based on the reflectivity screening threshold value of the pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window.
In the present embodiment, the storage medium is configured to store program code for performing the steps of: acquiring the ratio of the reflectivity average value of the road point cloud data in the preset extraction window to the reflectivity screening threshold value of the road area; and judging whether the ratio is larger than a preset threshold value, if so, determining all the road surface point cloud data in a preset extraction window as the road surface marking data.
By adopting the method and the device, different reflectivity screening thresholds are used for screening the pavement marking data for different pavement areas in the area to which the pavement point cloud data belongs, and different thresholds can be used for screening the point clouds with the same color but different reflectivity, so that the problems of low identification accuracy and low efficiency caused by the fact that the pavement markings with different reflectivities are processed by using the same threshold are solved, and the effect of efficiently and accurately identifying the pavement markings is realized.
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 above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated into one divided unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims (14)

1. A method of processing pavement marking information, comprising:
obtaining pavement point cloud data of a target road based on track point information of laser acquisition equipment and the laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing the pavement information of the target road;
dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range;
obtaining a reflectivity screening threshold value of a road surface area, and screening road surface mark data from road surface point cloud data of the road surface area according to the reflectivity screening threshold value of the road surface area and a preset extraction window, wherein the reflectivity screening threshold values of at least two road surface areas in the plurality of road surface areas are different;
identifying pavement markings in the pavement marking data.
2. The process of claim 1, wherein obtaining a reflectivity screening threshold for the pavement area comprises:
and determining a reflectivity screening threshold corresponding to the road surface area by using the reflectivity of the road surface point cloud data belonging to the road surface area.
3. The processing method according to claim 2, wherein determining the reflectivity screening threshold corresponding to the road surface area by using the reflectivity of the road surface point cloud data belonging to the road surface area comprises:
and acquiring a first average value of the reflectivity of the road surface point cloud data belonging to the road surface area, and taking the first average value as a reflectivity screening threshold value corresponding to the road surface area.
4. The processing method according to claim 1, wherein the screening of the road surface marking data in the road surface point cloud data belonging to the road surface area according to the reflectivity screening threshold corresponding to the road surface area and a preset extraction window comprises:
and traversing the road surface point cloud data of the road surface area by using the preset extraction window, and executing the following steps on the traversed road surface point cloud data in the extraction window:
and screening out the pavement marking data in the pavement point cloud data of the pavement area based on the reflectivity screening threshold value of the pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window.
5. The processing method according to claim 4, wherein screening out the road surface marking data in the road surface point cloud data of the road surface area based on the reflectivity screening threshold value of the road surface area and the reflectivity average value of the road surface point cloud data within the preset extraction window comprises:
acquiring the ratio of the reflectivity average value of the road point cloud data in the preset extraction window to the reflectivity screening threshold value of the road area;
and judging whether the ratio is larger than a preset threshold value or not, and if so, determining all the road surface point cloud data in the preset extraction window as the road surface marking data.
6. The processing method according to claim 1, wherein obtaining the road surface point cloud data of the target road based on the track point information of the laser acquisition device and the laser point cloud data of the target road comprises:
acquiring the height of the track point from the track point information of the laser acquisition equipment;
calculating the relative height of the laser acquisition equipment relative to the ground of a target road;
calculating the difference value between the height of the track point and the relative height, wherein the obtained difference value is the road surface height of the target road;
and removing the laser point cloud data with the difference between the height in the laser point cloud data and the road surface height of the target road exceeding a preset height to obtain the road surface point cloud data of the target road.
7. The processing method of claim 1, wherein identifying pavement markings in the pavement marking data comprises:
acquiring a convex hull of the pavement marking data;
and identifying the shape of the convex hull to obtain the pavement marker in the pavement marker data.
8. A processing apparatus of road surface marking information, characterized by comprising:
the acquisition unit is used for acquiring pavement point cloud data of the target road based on track point information of laser acquisition equipment and laser point cloud data of the target road, wherein the laser point cloud data is obtained by performing point cloud measurement on the target road through the laser acquisition equipment, and the pavement point cloud data is used for describing pavement information of the target road;
the dividing unit is used for dividing the area to which the road surface point cloud data belongs into a plurality of road surface areas according to a preset range;
the screening unit is used for obtaining a reflectivity screening threshold value of a road surface area, and screening road surface mark data from road surface point cloud data of the road surface area according to the reflectivity screening threshold value of the road surface area and a preset extraction window, wherein the reflectivity screening threshold values of at least two road surface areas in the plurality of road surface areas are different;
and the identification unit is used for identifying the pavement marks in the pavement mark data.
9. The processing apparatus according to claim 8, wherein the screening unit comprises:
and the threshold value determining module is used for determining a reflectivity screening threshold value corresponding to the road surface area by utilizing the reflectivity of the road surface point cloud data belonging to the road surface area.
10. The processing apparatus as defined in claim 9, wherein the threshold determination module comprises:
and the threshold value determining submodule is used for acquiring a first average value of the reflectivity of the pavement point cloud data belonging to the pavement area, and taking the first average value as a reflectivity screening threshold value corresponding to the pavement area.
11. The processing apparatus according to claim 8, wherein the screening unit comprises:
the screening submodule is used for utilizing the preset extraction window to traverse the road surface point cloud data of the road surface area and executing the following steps on the traversed road surface point cloud data in the extraction window:
and screening out the pavement marking data in the pavement point cloud data of the pavement area based on the reflectivity screening threshold value of the pavement area and the reflectivity average value of the pavement point cloud data in the preset extraction window.
12. The processing apparatus of claim 11, wherein the screening submodule comprises:
the obtaining submodule is used for obtaining the ratio of the reflectivity average value of the road point cloud data in the preset extracting window to the reflectivity screening threshold value of the road area;
and the reservation submodule is used for judging whether the ratio is greater than a preset threshold value or not, and if so, determining all the pavement point cloud data in the preset extraction window as pavement marking data.
13. The processing apparatus according to claim 8, wherein the acquisition unit includes:
the height acquisition module is used for acquiring the height of the track point from the track point information of the laser acquisition equipment;
the first calculation module is used for calculating the relative height of the laser acquisition equipment relative to the ground of a target road;
the second calculation module is used for calculating the difference value between the height of the track point and the relative height, and the obtained difference value is the height of the road surface of the target road;
and the removing module is used for removing the laser point cloud data of which the difference between the height in the laser point cloud data and the road surface height of the target road exceeds a preset height to obtain the road surface point cloud data of the target road.
14. The processing apparatus according to claim 8, wherein the identification unit comprises:
the acquisition module is used for acquiring a convex hull of the pavement marking data;
and the identification module is used for identifying the shape of the convex hull to obtain the pavement marker in the pavement marker data.
CN201510882685.1A 2015-12-03 2015-12-03 Method and device for processing pavement marking information Active CN106845321B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510882685.1A CN106845321B (en) 2015-12-03 2015-12-03 Method and device for processing pavement marking information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510882685.1A CN106845321B (en) 2015-12-03 2015-12-03 Method and device for processing pavement marking information

Publications (2)

Publication Number Publication Date
CN106845321A CN106845321A (en) 2017-06-13
CN106845321B true CN106845321B (en) 2020-03-27

Family

ID=59148804

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510882685.1A Active CN106845321B (en) 2015-12-03 2015-12-03 Method and device for processing pavement marking information

Country Status (1)

Country Link
CN (1) CN106845321B (en)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109508579B (en) * 2017-09-15 2022-02-22 百度在线网络技术（北京）有限公司 Method and device for acquiring virtual point cloud data
CN109506672B (en) * 2017-09-15 2023-05-12 阿里巴巴（中国）有限公司 Method and device for acquiring laser point cloud of pavement marker
CN109726728B (en) * 2017-10-31 2020-12-15 阿里巴巴（中国）有限公司 Training data generation method and device
CN111009040B (en) * 2018-10-08 2023-04-18 阿里巴巴集团控股有限公司 Point cloud entity marking system, method and device and electronic equipment
CN111174777A (en) * 2018-11-09 2020-05-19 阿里巴巴集团控股有限公司 Positioning method and device and electronic equipment
CN109633681A (en) * 2018-12-05 2019-04-16 芜湖智久机器人有限公司 A kind of reflector recognition methods and device
CN109711336A (en) * 2018-12-26 2019-05-03 深圳高速工程顾问有限公司 Roadmarking determines method, apparatus, storage medium and computer equipment
CN111670379A (en) * 2019-01-09 2020-09-15 深圳市大疆创新科技有限公司 Echo signal processing method, device and storage medium
CN110031823B (en) 2019-04-22 2020-03-24 上海禾赛光电科技有限公司 Noise point identification method for laser radar and laser radar system
CN110988847A (en) 2019-04-22 2020-04-10 上海禾赛光电科技有限公司 Noise point identification method for laser radar and laser radar system
CN110361754B (en) * 2019-07-15 2021-07-16 武汉中海庭数据技术有限公司 Road print growth type clustering method and device based on laser point cloud data
CN111192322B (en) * 2019-12-31 2022-09-30 武汉中海庭数据技术有限公司 Method and system for automatically calculating height of signboard based on point cloud track
KR20210102182A (en) * 2020-02-07 2021-08-19 선전 센스타임 테크놀로지 컴퍼니 리미티드 Road marking recognition method, map generation method, and related products
CN111649752B (en) * 2020-05-29 2021-09-21 北京四维图新科技股份有限公司 Map data processing method, device and equipment for congested road section
CN112835055A (en) * 2020-12-30 2021-05-25 潍柴动力股份有限公司 Positioning method and system of laser SLAM equipment
CN113640823B (en) * 2021-07-15 2023-11-21 北京三快在线科技有限公司 Method and device for map drawing based on laser reflectivity base map
CN113960572B (en) * 2021-10-20 2024-05-03 北京轻舟智航科技有限公司 Processing method and device for filtering noise point cloud of buried lamp
CN115824237B (en) * 2022-11-29 2023-09-26 重庆赛迪奇智人工智能科技有限公司 Rail pavement recognition method and device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103499343A (en) * 2013-09-25 2014-01-08 武汉海达数云技术有限公司 Automatic classifying and identifying method for road line point cloud based on three-dimensional laser reflection strength
CN103743383A (en) * 2014-02-11 2014-04-23 天津市星际空间地理信息工程有限公司 Automatic extraction method for road information based on point cloud
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
CN105069395A (en) * 2015-05-17 2015-11-18 北京工业大学 Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103499343A (en) * 2013-09-25 2014-01-08 武汉海达数云技术有限公司 Automatic classifying and identifying method for road line point cloud based on three-dimensional laser reflection strength
CN103743383A (en) * 2014-02-11 2014-04-23 天津市星际空间地理信息工程有限公司 Automatic extraction method for road information based on point cloud
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
CN105069395A (en) * 2015-05-17 2015-11-18 北京工业大学 Road marking automatic identification method based on terrestrial three-dimensional laser scanning technology

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Automated Extraction of Road Markings from Mobile Lidar Point Clouds;Bisheng Yang 等;《Photogrammetric Engineering & Remote Sensing》;20120430;第78卷(第04期);第331-338页 *
移动车载激光点云的道路标线自动识别与提取;邹晓亮 等;《测绘与空间地理信息》;20120930;第35卷(第09期);第5-8页 *

Also Published As

Publication number Publication date
CN106845321A (en) 2017-06-13

Similar Documents

Publication Publication Date Title
CN106845321B (en) Method and device for processing pavement marking information
CN109840880B (en) Pavement identification method and device
Gavankar et al. Automatic building footprint extraction from high-resolution satellite image using mathematical morphology
CN111274865A (en) Remote sensing image cloud detection method and device based on full convolution neural network
CN106845324B (en) Method and device for processing guideboard information
CN109241846B (en) Method and device for estimating space-time change of remote sensing image and storage medium
WO2017041396A1 (en) Driving lane data processing method, device, storage medium and apparatus
CN111209780A (en) Lane line attribute detection method and device, electronic device and readable storage medium
CN108268867B (en) License plate positioning method and device
CN111191570B (en) Image recognition method and device
CN107341810B (en) Vehicle automatic identification method and device and electronic equipment
Beumier et al. Digital terrain models derived from digital surface model uniform regions in urban areas
Giuliani et al. Using crowdsourced web content for informing water systems operations in snow-dominated catchments
CN106228134A (en) Drivable region detection method based on pavement image, Apparatus and system
CN111339989A (en) Water body extraction method, device, equipment and storage medium
CN112634260A (en) Map evaluation method and device, electronic equipment and storage medium
Li et al. A lane marking detection and tracking algorithm based on sub-regions
CN110852236A (en) Target event determination method and device, storage medium and electronic device
Yuan et al. Road segmentation in aerial images by exploiting road vector data
CN104951765A (en) Remote sensing image target division method based on shape priori information and vision contrast ratio
WO2017015076A8 (en) Method of placing an antenna of a radio access network (ran) asset in a wireless communication network
CN113743151A (en) Method and device for detecting road surface sprinkled object and storage medium
Wu et al. A comparison of 4 shadow compensation techniques for land cover classification of shaded areas from high radiometric resolution aerial images
Liu et al. A framework of road extraction from airborne lidar data and aerial imagery
Adu-Gyamfi et al. Functional evaluation of pavement condition using a complete vision system

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: 20200608

Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province

Patentee after: Alibaba (China) Co.,Ltd.

Address before: 100102, No. 18, No., Changsheng Road, Changping District science and Technology Park, Beijing, China. 1-5

Patentee before: AUTONAVI SOFTWARE Co.,Ltd.

TR01 Transfer of patent right