CN111046735A - Lane line point cloud extraction method, electronic device and storage medium - Google Patents
Lane line point cloud extraction method, electronic device and storage medium Download PDFInfo
- Publication number
- CN111046735A CN111046735A CN201911108643.7A CN201911108643A CN111046735A CN 111046735 A CN111046735 A CN 111046735A CN 201911108643 A CN201911108643 A CN 201911108643A CN 111046735 A CN111046735 A CN 111046735A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- lane line
- intensity
- frequency distribution
- segmentation threshold
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30248—Vehicle exterior or interior
- G06T2207/30252—Vehicle exterior; Vicinity of vehicle
- G06T2207/30256—Lane; Road marking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a lane line point cloud extraction method, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring pavement marking point clouds, and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clusters; after segmenting the lane line point cloud, counting the frequency distribution of the data intensity of each segment of lane line point cloud to generate a frequency distribution histogram; calculating a segmentation threshold value of the point cloud intensity according to the frequency distribution histogram and an Otsu algorithm; and performing two-segmentation on the lane line point cloud data of each segment by using the segmentation threshold value of the point cloud intensity so as to extract highlighted lane line point cloud. By the scheme, the problems that the conventional method for extracting the point cloud of the lane line is time-consuming and accuracy is difficult to guarantee are solved, the point cloud of the lane line can be accurately and quickly extracted, and the data of the edge points on two sides of the lane line are reserved to the maximum extent.
Description
Technical Field
The invention relates to the field of electronic maps, in particular to a lane line point cloud extraction method, electronic equipment and a storage medium.
Background
In a high-precision map, the drawing of a lane line usually needs to be performed by means of laser point cloud data, and the accuracy of the lane line point cloud and the actual boundary before the vectorization of the lane line point cloud needs to be guaranteed within 5cm, so that the maximum boundary information is reserved in the extraction of the lane line point cloud, and the accurate acquisition of the lane line point cloud boundary is of great importance.
At present, a common lane line point cloud extraction method is to extract the lane line point cloud based on semantic segmentation, although boundary information can be retained to the maximum extent, a deep learning model is needed, and training of the model needs to provide a large number of labeled samples, which is time-consuming. The lane line point cloud boundary obtained based on the traditional classification is easily influenced by the abrasion of the lane line, and is narrower than the actual width, and the boundary point cloud extraction is not accurate.
Therefore, it is necessary to provide a simple and time-consuming method for accurately extracting the point cloud of the lane line
Disclosure of Invention
In view of this, embodiments of the present invention provide a lane line point cloud extraction method, an electronic device, and a storage medium, so as to solve the problems that the existing extraction method is time-consuming and is difficult to ensure accuracy.
In a first aspect of the embodiments of the present invention, a lane line point cloud extraction method is provided, including:
acquiring pavement marking point clouds, and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clusters;
after segmenting the lane line point cloud, counting the frequency distribution of the data intensity of each segment of lane line point cloud to generate a frequency distribution histogram;
calculating a segmentation threshold value of the point cloud intensity according to the frequency distribution histogram and an Otsu algorithm;
and performing two-segmentation on the lane line point cloud data of each segment by using the segmentation threshold value of the point cloud intensity so as to extract highlighted lane line point cloud.
In a second aspect of the embodiments of the present invention, there is provided an electronic device for lane line point cloud extraction, including:
the extraction module is used for acquiring pavement marking point clouds and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clusters;
the statistical module is used for counting the frequency distribution of the intensity of the point cloud data of each section of lane line after segmenting the point cloud of the lane line to generate a frequency distribution histogram;
the calculation module is used for calculating a segmentation threshold of the point cloud intensity according to the frequency distribution histogram and the Otsu algorithm;
and the segmentation module is used for carrying out two-segmentation on the point cloud data of the lane line of each segment by utilizing the segmentation threshold value of the point cloud intensity so as to extract the highlighted point cloud of the lane line.
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 by 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, which stores a computer program, which when executed by a processor implements the steps of the method provided by the first aspect of the embodiments of the present invention.
In the embodiment of the invention, the initial lane line point cloud is extracted from the road surface marking point cloud, after the initial lane line point cloud is segmented, the intensity frequency distribution histogram of each segmented lane line point cloud is counted, the intensity segmentation threshold is calculated according to the intensity frequency distribution histogram and the robust algorithm to extract the highlight point cloud data, thereby effectively ensuring the accurate extraction of the lane line boundary point cloud data, retaining complete lane line information, solving the problems of time-consuming extraction and inaccurate classification extraction caused by the traditional requirement of a large number of marked samples, simply and quickly extracting the lane line point cloud, simultaneously effectively solving the problem that the lane line point cloud and the road noise points are difficult to segment, reducing the influence of the road surface point cloud noise on the extraction of the lane line point cloud, furthest retaining the left edge point and right edge point information of the lane line point cloud, particularly abrasion of the lane line, even under the condition that the point cloud of the lane line is fuzzy, most of edge points on the left side and the right side of the point cloud of the lane line can still be reserved, and the accuracy and the reliability of the point cloud extraction of the lane line are guaranteed.
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 those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a lane line point cloud extraction method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a system for extracting a point cloud of a lane line according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device for lane line point cloud extraction 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. 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.
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, a schematic flow chart of a method for extracting a point cloud of a lane line according to an embodiment of the present invention includes:
s101, acquiring pavement marking point clouds, and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clustering;
the road surface marking point cloud also comprises point cloud data of other markings, such as a left-turn marking, a straight marking, a deceleration marking and the like, besides the road marking point cloud. Because different marking lines have different shape characteristics, such as arrow shapes and rectangles, different marking lines can be distinguished based on the point cloud shape of the pavement marking lines, and then the point cloud of the lane lines can be preliminarily extracted.
S102, after segmenting the lane line point cloud, counting the frequency distribution of the data intensity of each segment of lane line point cloud to generate a frequency distribution histogram;
in practice, the lane line is generally a long rectangle or a line, and the lane line marking line is segmented according to a certain length, that is, the point cloud of the lane line is segmented, for example, every 3 meters, and each segment is processed independently.
Optionally, after segmenting the point cloud of the lane line, taking the point cloud of the lane line of each segment as a center, and expanding a predetermined width range to two sides of the lane line.
The point cloud of the lane line is used as the center part and is expanded to a certain range, such as 10cm, the point cloud data after the outward expansion possibly comprises other point cloud data, the outward expansion based on the lane line can ensure that the point cloud data of the lane line is comprehensively obtained, omission is avoided, and the accuracy of the accurate extraction of the point cloud of the lane line is further ensured.
The point cloud data intensity is used for reflecting the reflection intensity information of the laser, and the clearer the general lane line is, the higher the point cloud reflection intensity is. And counting the intensity of the midpoint of the point cloud of the initial lane line to obtain a frequency distribution histogram of the intensity of the point cloud. The frequency distribution histogram is used for representing the intensity distribution condition of the point cloud, and the point cloud segmentation intensity value can be conveniently determined according to the frequency distribution histogram.
S103, calculating a segmentation threshold of the point cloud intensity according to the frequency distribution histogram and an Otsu algorithm;
based on the distribution histogram of the point cloud intensity and the Otsu algorithm, the intensity threshold value of the extracted point cloud can be determined, and the frequency segmentation threshold value can be more accurately determined by combining the peak-valley method of the frequency distribution histogram and the Otsu algorithm.
Specifically, the method comprises the following steps:
s1, obtaining coordinates corresponding to peak values and valley values in the frequency distribution histogram, and matching according to the distribution of the peak values and the valley values and a preset peak-valley matching rule;
s2, calculating the area of a polygon formed by peaks and valleys after peak-valley pairing, comparing the area of the polygon with a preset threshold value, removing initial valleys smaller than the preset threshold value, and determining the type of peak-valley pairing;
and S3, merging the peaks and the valleys of the same pairing type according to the sequence of the peaks and the valleys.
The coordinates of all the valley bottoms and the peaks in the frequency distribution histogram are detected and obtained, adjacent valleys and peaks are paired according to a group of peak valley peaks or valley peak valleys, and the coordinates of the valley bottoms and the peak top are taken as vertexes to form a polygon. Calculating three polygon areas, removing smaller valleys based on the polygon areas compared to a preset threshold, and determining an initial peak-valley shape type: left singlet, right singlet, and bimodal valley. The initial peaks and valleys of the three shape types are combined and the final frequency distribution histogram can be represented by one single left peak, several peaks and valleys and one single right peak resulting from the combination. And weighting the related valley values according to a certain weight in the merging process to obtain the merged valley value.
Further, based on the combined initial peak and valley obtained at S3, the method further includes:
s4, performing two segmentation on the intensity value of the point cloud data of the lane line of each segment through an Otsu algorithm to obtain a first intensity segmentation threshold;
and S5, correspondingly combining and forming the positions of peaks and valleys in the frequency distribution histogram according to the intensity segmentation threshold, and taking the corresponding valley values as first initial segmentation threshold values.
A segmentation threshold can be obtained through an algorithm, but the segmentation threshold is not accurate, and a valley bottom value corresponding to a position of the segmentation threshold in the initial peak-valley can be used as the initial segmentation threshold, namely the first initial segmentation threshold.
Further, the method also comprises the following steps:
s6, intercepting point clouds with intensity ranges between [ v-I, v + I ], and generating a second frequency distribution histogram according to the intensity interval as I/2, wherein v is an initial segmentation threshold value, and I is the intensity interval of the frequency distribution histogram;
s7, performing secondary segmentation on the intensity value of the intercepted point cloud data through an Otsu algorithm to obtain a second intensity segmentation threshold, and taking a corresponding valley value of the second intensity segmentation threshold in a second frequency histogram as a second initial segmentation threshold;
and S8, when the first initial segmentation threshold value and the second initial segmentation threshold value are smaller than the preset value, taking the second initial segmentation threshold value as a final strength segmentation threshold value.
Intercepting the point cloud with the intensity range between [ v-I, v + I ] to regenerate a frequency distribution histogram, obtaining a second segmentation threshold value through the processing flow of the steps S1-S5, when the first intensity segmentation threshold value and the second intensity segmentation threshold value are smaller than a preset value, if the preset value is set as 10, taking the second initial segmentation threshold value as a final intensity segmentation threshold value, otherwise, repeating the steps S6 and S7 to obtain a new initial segmentation threshold value, namely, taking the second initial segmentation threshold value as the first initial segmentation threshold value, taking the newly generated initial segmentation threshold value as the second initial segmentation threshold value, judging whether the value is smaller than the preset value again, and if the value is not smaller than the preset value, continuing to repeat the process until the value is smaller than the preset value.
The frequency distribution histogram and the Otsu algorithm are repeatedly utilized, and the determination of the segmentation threshold of the point cloud intensity can be accurately performed step by step.
And S104, performing secondary segmentation on the lane line point cloud data of each segment by using the segmentation threshold of the point cloud intensity to extract highlighted lane line point clouds.
And when the intensity of the point cloud of the lane line is higher than the segmentation threshold, the point cloud of the lane line is retained, otherwise, the point cloud of the lane line is deleted. Based on point cloud segmentation, most point cloud edge points can be reserved, and meanwhile road noise point clouds can be reduced.
According to the method provided by the embodiment, the point cloud range is expanded, and the threshold value is divided by combining the statistical histogram and the precision strength of the Otsu algorithm, so that the point cloud data of the edge of the lane line is kept to the maximum extent, and the abrasion influence of the lane line is reduced.
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, but should not constitute any limitation to the implementation process of the embodiments of the present invention,
fig. 2 is a schematic structural diagram of an electronic device for lane line point cloud extraction according to a second embodiment of the present invention, where the electronic device includes:
the extraction module 210 is configured to obtain a road marking point cloud, and extract a lane line point cloud from the road marking point cloud according to a shape feature of the road marking point cloud cluster;
optionally, the extracting module 210 includes:
and the external expansion unit is used for expanding the preset width range towards the two sides of the lane line by taking the point cloud of the lane line of each segment as the center after the point cloud of the lane line is segmented.
The statistical module 220 is configured to perform statistics on frequency distribution of the intensity of each section of lane line point cloud data after segmenting the lane line point cloud, and generate a frequency distribution histogram;
a calculating module 230, configured to calculate a segmentation threshold of the point cloud intensity according to the frequency distribution histogram and the greater body fluid algorithm;
optionally, the calculating module 230 includes:
the matching unit is used for acquiring coordinates corresponding to peak values and valley values in the frequency distribution histogram and matching according to the distribution of the peak values and the valley values and a preset peak-valley matching rule;
the comparison unit is used for calculating the area of a polygon formed by peaks and valleys after peak-valley pairing, comparing the area of the polygon with a preset threshold, removing initial valleys smaller than the preset threshold, and determining the type of peak-valley pairing;
and the merging unit merges the peaks and the valleys of the same pairing type according to the appearance sequence of the peaks and the valleys.
Further, the method also comprises the following steps:
the segmentation unit is used for carrying out secondary segmentation on the intensity value of the point cloud data of the lane line of each segment through an Otsu algorithm to obtain a first intensity segmentation threshold;
and the first determining unit is used for taking the corresponding valley value as a first initial segmentation threshold value according to the position of the intensity segmentation threshold value in the peak valley formed by correspondingly combining the frequency distribution histograms.
Further, also comprises
The generating unit intercepts point clouds with the intensity ranges between [ v-I, v + I ], and generates a second frequency distribution histogram according to the intensity interval of I/2, wherein v is an initial segmentation threshold value, and I is the intensity interval of the frequency distribution histogram;
the second determining unit is used for carrying out secondary segmentation on the intensity value of the intercepted point cloud data through an Otsu algorithm to obtain a second intensity segmentation threshold value, and taking a corresponding valley value of the second intensity segmentation threshold value in a second frequency histogram as a second initial segmentation threshold value;
and the judging unit is used for taking the second intensity division threshold value as the final intensity division threshold value when the first initial division threshold value and the second initial division threshold value are smaller than the preset value.
And a segmentation module 240, configured to perform binary segmentation on the lane line point cloud data of each segment by using a segmentation threshold of the point cloud intensity to extract a highlighted lane line point cloud.
Through the electronic equipment of the embodiment, the road surface marking line point cloud data can be accurately segmented and extracted, and meanwhile, the speed is high and the efficiency is high.
Fig. 3 is a schematic structural diagram of an electronic device for lane line point cloud extraction according to an embodiment of the present invention, where the electronic device is a device that provides computing services, including but not limited to a smart phone, a tablet, a notebook, and the like, and as shown in fig. 3, the electronic device 3 of the embodiment includes: memory 310, processor 320, said memory 310 comprising executable program 3101 stored thereon, it being understood by those skilled in the art that the electronic device structure shown in fig. 3 does not constitute a limitation of the electronic terminal device or apparatus, may comprise more or less components than shown, or may combine certain components, or a different arrangement of components.
The following describes each component of the electronic device in detail with reference to fig. 3:
the memory 310 may be used to store software programs and modules, and the processor 320 executes various functional applications and data processing of the electronic terminal device by operating the software programs and modules stored in the memory 310. The memory 310 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required by at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may store data (such as audio data, a phonebook, etc.) created according to the use of the electronic terminal device, and the like. Further, the memory 310 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
An executable program 3101 for a method of project engineering initialization is contained on the memory 310, the executable program 3101 may be divided into one or more modules/units, which are stored in the memory 310 and executed by the processor 320 to implement lane line point cloud data extraction, and may be a series of computer program instruction segments for describing the execution process of the computer program 3101 in the electronic terminal device, which can perform specific functions. For example, the computer program 3101 may be partitioned into a computation module, a definition module, a traversal module, and a squaring module.
The processor 320 is a control center of the electronic terminal device, connects various parts of the whole electronic terminal device by using various interfaces and lines, and performs various functions of the electronic terminal device and processes data by running or executing software programs and/or modules stored in the memory 310 and calling data stored in the memory 310, thereby performing overall monitoring of the electronic terminal device. Optionally, processor 620 may include one or more processing units; preferably, the processor 320 may integrate an application processor, which mainly handles operating systems, user interfaces, application programs, etc., and a modem processor, which mainly handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into processor 320.
The electronic device may also include at least one sensor, such as light sensors, motion sensors, and other sensors, an input device, such as a touch screen, keyboard, and others, an output device, such as a speaker, display, and others. Other constituent elements are not described in detail herein.
In this embodiment of the present invention, the executable program executed by the processor 320 included in the electronic device is specifically:
acquiring pavement marking point clouds, and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clusters;
after segmenting the lane line point cloud, counting the frequency distribution of the data intensity of each segment of lane line point cloud to generate a frequency distribution histogram;
calculating a segmentation threshold value of the point cloud intensity according to the frequency distribution histogram and an Otsu algorithm;
and performing two-segmentation on the lane line point cloud data of each segment by using the segmentation threshold value of the point cloud intensity so as to extract highlighted lane line point cloud.
Further, after segmenting the lane line point cloud, counting the frequency distribution of the intensity of each segment of lane line point cloud data, and generating a frequency distribution histogram further includes:
and after segmenting the lane line point clouds, expanding a preset width range outwards from two sides of the lane line by taking the lane line point cloud of each segment as a center.
Further, the calculating a segmentation threshold of the point cloud intensity according to the frequency distribution histogram and the greater fluid algorithm includes:
acquiring coordinates corresponding to peak values and valley values in the frequency distribution histogram, and matching according to the distribution of the peak values and the valley values and a preset peak-valley matching rule;
calculating the area of a polygon formed by peaks and valleys after peak-valley pairing, comparing the area of the polygon with a preset threshold, removing initial valleys smaller than the preset threshold, and determining the type of peak-valley pairing;
and merging the peaks and the valleys of the same pairing type according to the sequence of the peaks and the valleys.
Further, the calculating a segmentation threshold of the point cloud intensity according to the frequency distribution histogram and the greater fluid algorithm further includes:
performing two segmentation on the intensity value of the point cloud data of the lane line of each segment through an Otsu algorithm to obtain a first intensity segmentation threshold;
and correspondingly combining the positions of the intensity segmentation threshold values in the frequency distribution histogram to form peak-valley values, and taking the corresponding valley values as first initial segmentation threshold values.
Further, the taking a corresponding valley value as an initial segmentation threshold value according to the position of the intensity segmentation threshold value in the peak valley of the frequency distribution histogram includes:
intercepting point clouds with intensity ranges between [ v-I, v + I ], and generating a second frequency distribution histogram according to the intensity interval of I/2, wherein v is an initial segmentation threshold value, and I is the intensity interval of the frequency distribution histogram;
performing secondary segmentation on the intensity value of the intercepted point cloud data through an Otsu algorithm to obtain a second intensity segmentation threshold value, and taking a corresponding valley value of the second intensity segmentation threshold value in a second frequency histogram as a second initial segmentation threshold value;
and when the first initial segmentation threshold and the second initial segmentation threshold are smaller than a preset value, taking the second intensity segmentation threshold as a final intensity segmentation threshold.
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 lane line point cloud extraction method is characterized by comprising the following steps:
acquiring pavement marking point clouds, and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clusters;
after segmenting the lane line point cloud, counting the frequency distribution of the data intensity of each segment of lane line point cloud to generate a frequency distribution histogram;
calculating a segmentation threshold value of the point cloud intensity according to the frequency distribution histogram and an Otsu algorithm;
and performing two-segmentation on the lane line point cloud data of each segment by using the segmentation threshold value of the point cloud intensity so as to extract highlighted lane line point cloud.
2. The method of claim 1, wherein after segmenting the lane line point cloud, counting a frequency distribution of intensity of each segment of the lane line point cloud data, and generating a frequency distribution histogram further comprises:
and after segmenting the lane line point clouds, expanding a preset width range outwards from two sides of the lane line by taking the lane line point cloud of each segment as a center.
3. The method according to claim 1, wherein the calculating a segmentation threshold for point cloud intensity according to the histogram of frequency distribution and the Otsu algorithm comprises:
acquiring coordinates corresponding to peak values and valley values in the frequency distribution histogram, and matching according to the distribution of the peak values and the valley values and a preset peak-valley matching rule;
calculating the area of a polygon formed by peaks and valleys after peak-valley pairing, comparing the area of the polygon with a preset threshold, removing initial valleys smaller than the preset threshold, and determining the type of peak-valley pairing;
and merging the peaks and the valleys of the same pairing type according to the sequence of the peaks and the valleys.
4. The method of claim 3, wherein merging peaks and valleys of the same pairing type in order of their occurrence further comprises:
performing two segmentation on the intensity value of the point cloud data of the lane line of each segment through an Otsu algorithm to obtain a first intensity segmentation threshold;
and correspondingly combining the positions of the intensity segmentation threshold values in the frequency distribution histogram to form peak-valley values, and taking the corresponding valley values as first initial segmentation threshold values.
5. The method of claim 4, wherein said determining a corresponding valley value as a first initial segmentation threshold according to the location of the intensity segmentation threshold in the histogram of the frequency distribution where the corresponding combination forms a peak and a valley further comprises:
intercepting point clouds with intensity ranges between [ v-I, v + I ], and generating a second frequency distribution histogram according to the intensity interval of I/2, wherein v is an initial segmentation threshold value, and I is the intensity interval of the frequency distribution histogram;
performing secondary segmentation on the intensity value of the intercepted point cloud data through an Otsu algorithm to obtain a second intensity segmentation threshold value, and taking a corresponding valley value of the second intensity segmentation threshold value in a second frequency histogram as a second initial segmentation threshold value;
and when the first initial segmentation threshold and the second initial segmentation threshold are smaller than a preset value, taking the second intensity segmentation threshold as a final intensity segmentation threshold.
6. An electronic device for lane line point cloud extraction, comprising:
the extraction module is used for acquiring pavement marking point clouds and extracting lane line point clouds from the pavement marking point clouds according to shape features of the pavement marking point cloud clusters;
the statistical module is used for counting the frequency distribution of the intensity of the point cloud data of each section of lane line after segmenting the point cloud of the lane line to generate a frequency distribution histogram;
the calculation module is used for calculating a segmentation threshold of the point cloud intensity according to the frequency distribution histogram and the Otsu algorithm;
and the segmentation module is used for carrying out two-segmentation on the point cloud data of the lane line of each segment by utilizing the segmentation threshold value of the point cloud intensity so as to extract the highlighted point cloud of the lane line.
7. The electronic device of claim 6, wherein the extraction module comprises:
and the external expansion unit is used for expanding the preset width range towards the two sides of the lane line by taking the point cloud of the lane line of each segment as the center after the point cloud of the lane line is segmented.
8. The electronic device of claim 6, wherein the computing module comprises:
the matching unit is used for acquiring coordinates corresponding to peak values and valley values in the frequency distribution histogram and matching according to the distribution of the peak values and the valley values and a preset peak-valley matching rule;
the comparison unit is used for calculating the area of a polygon formed by peaks and valleys after peak-valley pairing, comparing the area of the polygon with a preset threshold, removing initial valleys smaller than the preset threshold, and determining the type of peak-valley pairing;
and the merging unit merges the peaks and the valleys of the same pairing type according to the appearance sequence of the peaks and the valleys.
9. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the lane line point cloud extraction method of any of claims 1 to 5.
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 lane line point cloud extraction method according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911108643.7A CN111046735B (en) | 2019-11-13 | 2019-11-13 | Lane line point cloud extraction method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911108643.7A CN111046735B (en) | 2019-11-13 | 2019-11-13 | Lane line point cloud extraction method, electronic device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111046735A true CN111046735A (en) | 2020-04-21 |
| CN111046735B CN111046735B (en) | 2022-10-25 |
Family
ID=70231905
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911108643.7A Active CN111046735B (en) | 2019-11-13 | 2019-11-13 | Lane line point cloud extraction method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111046735B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111462141A (en) * | 2020-05-19 | 2020-07-28 | 北京爱笔科技有限公司 | Method and device for acquiring point cloud plane, equipment and computer readable storage medium |
| CN111696115A (en) * | 2020-04-29 | 2020-09-22 | 山东省国土测绘院 | Zebra line corner extraction method and system based on point cloud scanning line |
| CN112508111A (en) * | 2020-12-12 | 2021-03-16 | 武汉中海庭数据技术有限公司 | Rod fusion method and system based on road structure, server and medium |
| CN113238209A (en) * | 2021-04-06 | 2021-08-10 | 宁波吉利汽车研究开发有限公司 | Road sensing method, system, equipment and storage medium based on millimeter wave radar |
| CN115049826A (en) * | 2022-05-18 | 2022-09-13 | 洛伦兹(宁波)科技有限公司 | Lane line detection method, device and system |
| CN115407364A (en) * | 2022-09-06 | 2022-11-29 | 安徽蔚来智驾科技有限公司 | Point cloud map processing method, lane marking data acquisition method, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107463918A (en) * | 2017-08-17 | 2017-12-12 | 武汉大学 | Lane line extracting method based on laser point cloud and image data fusion |
| CN109165549A (en) * | 2018-07-09 | 2019-01-08 | 厦门大学 | Road markings acquisition methods, terminal device and device based on three dimensional point cloud |
| CN110349260A (en) * | 2019-07-11 | 2019-10-18 | 武汉中海庭数据技术有限公司 | A kind of pavement strip extraction method and device |
| US20190325738A1 (en) * | 2018-04-18 | 2019-10-24 | Here Global B.V. | Lane-level geometry and traffic information |
-
2019
- 2019-11-13 CN CN201911108643.7A patent/CN111046735B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN107463918A (en) * | 2017-08-17 | 2017-12-12 | 武汉大学 | Lane line extracting method based on laser point cloud and image data fusion |
| US20190325738A1 (en) * | 2018-04-18 | 2019-10-24 | Here Global B.V. | Lane-level geometry and traffic information |
| CN109165549A (en) * | 2018-07-09 | 2019-01-08 | 厦门大学 | Road markings acquisition methods, terminal device and device based on three dimensional point cloud |
| CN110349260A (en) * | 2019-07-11 | 2019-10-18 | 武汉中海庭数据技术有限公司 | A kind of pavement strip extraction method and device |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111696115A (en) * | 2020-04-29 | 2020-09-22 | 山东省国土测绘院 | Zebra line corner extraction method and system based on point cloud scanning line |
| CN111696115B (en) * | 2020-04-29 | 2023-04-14 | 山东省国土测绘院 | Zebra line corner extraction method and system based on point cloud scanning line |
| CN111462141A (en) * | 2020-05-19 | 2020-07-28 | 北京爱笔科技有限公司 | Method and device for acquiring point cloud plane, equipment and computer readable storage medium |
| CN111462141B (en) * | 2020-05-19 | 2024-01-12 | 北京爱笔科技有限公司 | Point cloud plane acquisition method and device, equipment and computer readable storage medium |
| CN112508111A (en) * | 2020-12-12 | 2021-03-16 | 武汉中海庭数据技术有限公司 | Rod fusion method and system based on road structure, server and medium |
| CN112508111B (en) * | 2020-12-12 | 2022-05-31 | 武汉中海庭数据技术有限公司 | Rod fusion method and system based on road structure, server and medium |
| CN113238209A (en) * | 2021-04-06 | 2021-08-10 | 宁波吉利汽车研究开发有限公司 | Road sensing method, system, equipment and storage medium based on millimeter wave radar |
| CN113238209B (en) * | 2021-04-06 | 2024-01-16 | 宁波吉利汽车研究开发有限公司 | Road perception method, system, equipment and storage medium based on millimeter wave radar |
| CN115049826A (en) * | 2022-05-18 | 2022-09-13 | 洛伦兹(宁波)科技有限公司 | Lane line detection method, device and system |
| CN115407364A (en) * | 2022-09-06 | 2022-11-29 | 安徽蔚来智驾科技有限公司 | Point cloud map processing method, lane marking data acquisition method, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111046735B (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111046735B (en) | Lane line point cloud extraction method, electronic device and storage medium | |
| Prasad et al. | Edge curvature and convexity based ellipse detection method | |
| US11157737B2 (en) | Cultivated land recognition method in satellite image and computing device | |
| CN109272016B (en) | Target detection method, device, terminal equipment and computer readable storage medium | |
| CN110334762B (en) | Feature matching method based on quad tree combined with ORB and SIFT | |
| Lari et al. | An adaptive approach for the segmentation and extraction of planar and linear/cylindrical features from laser scanning data | |
| CN109902541B (en) | Image recognition method and system | |
| CN110503682B (en) | Rectangular control identification method and device, terminal and storage medium | |
| CN110852257B (en) | Method and device for detecting key points of human face and storage medium | |
| CN107545223B (en) | Image recognition method and electronic equipment | |
| CN111435436A (en) | Perimeter anti-intrusion method and device based on target position | |
| CN114972947B (en) | Depth scene text detection method and device based on fuzzy semantic modeling | |
| CN111260564A (en) | Image processing method and device and computer storage medium | |
| CN101567045B (en) | Accurate positioning method of human face characteristic points | |
| CN113989300A (en) | Lane line segmentation method and device, electronic equipment and storage medium | |
| CN117593420A (en) | Plane drawing labeling method, device, medium and equipment based on image processing | |
| CN114255352A (en) | River channel extraction method and device and computer readable storage medium | |
| CN112464753B (en) | Method and device for detecting key points in image and terminal equipment | |
| CN112183229B (en) | Word lattice extraction method and device of operation paper image based on calculation dynamic parameters | |
| CN115661444A (en) | Image processing method, device, equipment, storage medium and product | |
| CN108475339B (en) | Method and system for classifying objects in an image | |
| CN109815791B (en) | Blood vessel-based identity recognition method and device | |
| JP2021182243A (en) | Image determination device, method, and program | |
| CN114627456A (en) | Bill text information detection method, device and system | |
| Sun et al. | Contextual models for automatic building extraction in high resolution remote sensing image using object-based boosting method |
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 |