CN112581478A - Centroid-based road center line extraction method - Google Patents
Centroid-based road center line extraction method Download PDFInfo
- Publication number
- CN112581478A CN112581478A CN202011472499.8A CN202011472499A CN112581478A CN 112581478 A CN112581478 A CN 112581478A CN 202011472499 A CN202011472499 A CN 202011472499A CN 112581478 A CN112581478 A CN 112581478A
- Authority
- CN
- China
- Prior art keywords
- area
- center line
- road
- centroid
- current
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/68—Analysis of geometric attributes of symmetry
Abstract
The invention provides a road center line extraction method based on a centroid, which comprises the following steps: s1: acquiring a binary image of a road; s2: dividing the binary image into a plurality of areas along the extending direction of the road; s3: calculating the centroid coordinates of each area; s4: taking one area positioned at the end part of each area as a first area; taking an area adjacent to the first area as a second area; s5: determining a centerline equation of the first area and the second area according to the centroid coordinates of the first area and the second area; s6: judging whether an adjacent area exists on one side of the second area, which is far away from the first area; s7: taking the current second area as a new first area, and taking an adjacent area of the current second area far away from the original first area as a new second area; returning to step S5; s8: and obtaining the center line of the road according to the whole center line equation. The method for extracting the center line of the road based on the centroid can efficiently and accurately extract the center line of the road.
Description
Technical Field
The invention relates to the technical field of navigation, in particular to a road center line extraction method based on a centroid.
Background
With the progress of society and the rapid development of satellite navigation technology, the dependence of people on navigation is greater and greater, and the extraction of the road center line is very important to the accuracy of navigation, so that the improvement of the quality and efficiency of the extraction of the road center line is urgently needed.
At present, a road center line extraction method mainly comprises manual drawing extraction and image processing extraction, wherein the image processing extraction method also comprises a plurality of different methods, such as morphology processing and an extraction method based on a Hessian matrix. The manual drawing and extraction of the central line needs manual calculation of the road, the central line is determined according to the central points of different roads, and although higher accuracy can be guaranteed through manual extraction of the central line of the road, a large amount of manpower and material resources need to be consumed, and the efficiency is extremely low. The morphological method determines whether the center line is the center line according to the correlation between each pixel point and the adjacent pixel point, and the method is easily influenced by image noise and is difficult to ensure the accuracy of center line extraction. In addition, the normal direction of the road is calculated through a Hessian matrix, and then the center line of the road is further acquired through Taylor expansion.
At present, the method for extracting the center line of the road has the defects of low efficiency or low accuracy, the existing method for extracting the center line cannot have high efficiency and high accuracy at the same time, a large improvement space still exists, and some methods are too complicated, and a large error can occur in the extraction process.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the road center line extraction method based on the mass center, which can efficiently and accurately extract the road center line.
In order to achieve the above object, the present invention provides a centroid-based road centerline extraction method, comprising the steps of:
s1: acquiring a binary image of a road;
s2: dividing the binary image into a plurality of regions along the road extension direction;
s3: establishing a rectangular coordinate system and calculating the centroid coordinates (x, y) of each region;
s4: one of the regions located at the end of each of the regions is taken as a first region; taking one of the areas adjacent to the first area as a second area;
s5: determining centerline equations for the first and second regions from the centroid coordinates of the first and second regions;
s6: judging whether an adjacent area exists on one side of the second area, which is far away from the first area; if yes, the step is continued, otherwise, the step is jumped to step S8;
s7: taking the current second area as a new first area, and taking an adjacent area of the current second area far away from the original first area as the new second area; returning to step S5;
s8: and obtaining the center line of the road according to all the center line equations.
Preferably, in the S3 step, the centroid coordinate (x, y) satisfies formula (1):
wherein i represents a natural number greater than zero, xiRepresenting the coordinates of the ith pixel of the current region in the x direction, PiDenotes xiA corresponding pixel value; y isiRepresenting the coordinates of the ith pixel of the current area in the y direction, QiDenotes yiA corresponding pixel value; m represents the number of pixel points in the x direction of the current area; n represents the number of pixel points in the y direction of the current region.
Preferably, in the S5 step, the centerline equation satisfies formula (2)
Wherein (x ', y') isCoordinates of points on the centerline equation; (x)1,y1) Is the coordinate value of the center of mass of the first area; (x)2,y2) Is the coordinate value of the center of mass of the second area.
Due to the adoption of the technical scheme, the invention has the following beneficial effects:
according to the method, the binary image entry region of the road is divided, the centroid of each region image is respectively obtained, the center point of each region road section can be rapidly determined according to the properties of the image centroid, and finally the center line of the whole image road section is determined according to the center point of each region road section. The center line of the road binary image is extracted through region division and based on the centroid property, the center line of the road can be accurately extracted, extraction time can be effectively saved through region division, and extraction efficiency is improved.
Drawings
Fig. 1 is a flowchart of a centroid-based road centerline extraction method according to an embodiment of the present invention.
Detailed Description
The following description of the preferred embodiment of the present invention, with reference to the accompanying drawings and fig. 1, will provide a better understanding of the function and features of the invention.
Referring to fig. 1, a method for extracting a center line of a road based on a centroid according to an embodiment of the present invention includes:
s1: acquiring a binary image of a road;
s2: dividing the binary image into a plurality of areas along the extending direction of the road;
s3: establishing a rectangular coordinate system and calculating the mass center coordinates (x, y) of each region;
in the S3 step, the centroid coordinates (x, y) satisfy formula (1):
wherein i represents a natural number greater than zero, xiRepresenting the coordinates of the ith pixel of the current area in the x-direction, PiDenotes xiA corresponding pixel value; y isiRepresenting the coordinates of the ith pixel of the current area in the y-direction, QiDenotes yiA corresponding pixel value; m represents the number of pixel points in the x direction of the current area; n represents the number of pixel points in the y direction of the current area;
s4: taking one area positioned at the end part of each area as a first area; taking an area adjacent to the first area as a second area;
s5: determining a centerline equation of the first area and the second area according to the centroid coordinates of the first area and the second area;
in step S5, the centerline equation satisfies equation (2)
Wherein, (x ', y') is the coordinates of a point on the centerline equation; (x)1,y1) Is the coordinate value of the center of mass of the first area; (x)2,y2) Is the centroid coordinate value of the second area;
s6: judging whether an adjacent area exists on one side of the second area, which is far away from the first area; if yes, the step is continued, otherwise, the step is jumped to step S8;
s7: taking the current second area as a new first area, and taking an adjacent area of the current second area far away from the original first area as a new second area; returning to step S5;
s8: and obtaining the center line of the road according to the whole center line equation.
The road center line extraction method based on the centroid creatively combines the centroid with the image center line; the method does not need a large amount of manual participation, is not complex in the process of extraction method, firstly divides the regions and then calculates the centroid in the process of processing the road image, and finally extracts the road center line according to the centroid coordinates of each region, thereby taking into account the quality and the efficiency of center line extraction; the method has a good application prospect in the technical field of navigation.
While the present invention has been described in detail and with reference to the embodiments thereof as illustrated in the accompanying drawings, it will be apparent to one skilled in the art that various changes and modifications can be made therein. Therefore, certain details of the embodiments are not to be interpreted as limiting, and the scope of the invention is to be determined by the appended claims.
Claims (3)
1. A road center line extraction method based on a centroid comprises the following steps:
s1: acquiring a binary image of a road;
s2: dividing the binary image into a plurality of regions along the road extension direction;
s3: establishing a rectangular coordinate system and calculating the centroid coordinates (x, y) of each region;
s4: one of the regions located at the end of each of the regions is taken as a first region; taking one of the areas adjacent to the first area as a second area;
s5: determining centerline equations for the first and second regions from the centroid coordinates of the first and second regions;
s6: judging whether an adjacent area exists on one side of the second area, which is far away from the first area; if yes, the step is continued, otherwise, the step is jumped to step S8;
s7: taking the current second area as a new first area, and taking an adjacent area of the current second area far away from the original first area as the new second area; returning to step S5;
s8: and obtaining the center line of the road according to all the center line equations.
2. The centroid-based road center line extraction method as claimed in claim 1, wherein in the step S3, the centroid coordinates (x, y) satisfy formula (1):
wherein i represents a natural number greater than zero, xiRepresenting the coordinates of the ith pixel of the current region in the x direction, PiDenotes xiA corresponding pixel value; y isiRepresenting the coordinates of the ith pixel of the current area in the y direction, QiDenotes yiA corresponding pixel value; m represents the number of pixel points in the x direction of the current area; n represents the number of pixel points in the y direction of the current region.
3. The centroid-based road center line extraction method as claimed in claim 2, wherein in the step S5, the center line equation satisfies formula (2)
Wherein, (x ', y') is the coordinates of a point on the centerline equation; (x)1,y1) Is the coordinate value of the center of mass of the first area; (x)2,y2) Is the coordinate value of the center of mass of the second area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011472499.8A CN112581478A (en) | 2020-12-15 | 2020-12-15 | Centroid-based road center line extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011472499.8A CN112581478A (en) | 2020-12-15 | 2020-12-15 | Centroid-based road center line extraction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112581478A true CN112581478A (en) | 2021-03-30 |
Family
ID=75136201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011472499.8A Pending CN112581478A (en) | 2020-12-15 | 2020-12-15 | Centroid-based road center line extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112581478A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112488A (en) * | 2021-04-22 | 2021-07-13 | 广州市城市规划勘测设计研究院 | Road center line extraction method and device, storage medium and terminal equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448046A (en) * | 2018-10-15 | 2019-03-08 | 辽宁工程技术大学 | A kind of semi-automatic road axis rapid extracting method based on more description |
| CN109816720A (en) * | 2018-12-21 | 2019-05-28 | 歌尔股份有限公司 | Road-center detection method, airborne equipment and storage medium |
| CN110751315A (en) * | 2019-09-23 | 2020-02-04 | 中南大学 | Man-machine interactive line selection method, system and controller for strip mine road system |
| CN111721316A (en) * | 2020-06-22 | 2020-09-29 | 重庆大学 | High-performance lane line identification region-of-interest prediction method |
| CN112053324A (en) * | 2020-08-03 | 2020-12-08 | 上海电机学院 | Complex material volume measurement method based on deep learning |
-
2020
- 2020-12-15 CN CN202011472499.8A patent/CN112581478A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109448046A (en) * | 2018-10-15 | 2019-03-08 | 辽宁工程技术大学 | A kind of semi-automatic road axis rapid extracting method based on more description |
| CN109816720A (en) * | 2018-12-21 | 2019-05-28 | 歌尔股份有限公司 | Road-center detection method, airborne equipment and storage medium |
| CN110751315A (en) * | 2019-09-23 | 2020-02-04 | 中南大学 | Man-machine interactive line selection method, system and controller for strip mine road system |
| CN111721316A (en) * | 2020-06-22 | 2020-09-29 | 重庆大学 | High-performance lane line identification region-of-interest prediction method |
| CN112053324A (en) * | 2020-08-03 | 2020-12-08 | 上海电机学院 | Complex material volume measurement method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 王小娟 等: "基于机器视觉的丘陵山区田间道路虚拟中线提取方法", 《西南大学学报（自然科学版）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113112488A (en) * | 2021-04-22 | 2021-07-13 | 广州市城市规划勘测设计研究院 | Road center line extraction method and device, storage medium and terminal equipment |
| CN113112488B (en) * | 2021-04-22 | 2021-10-29 | 广州市城市规划勘测设计研究院 | Road center line extraction method and device, storage medium and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8116530B2 (en) | Map change detection device, map change detection method, and program | |
| CN104463870A (en) | Image salient region detection method | |
| CN105354832A (en) | Method for automatically registering mountainous area satellite image to geographical base map | |
| CN116032823B (en) | Method and system for rapidly calculating scattering communication link based on digital elevation map | |
| CN114463286A (en) | Road surface point cloud smoothing and crack information processing method based on moving window | |
| CN112581478A (en) | Centroid-based road center line extraction method | |
| CN101447079A (en) | Method for extracting area target of image based on fuzzytopology | |
| CN105303566A (en) | Target contour clipping-based SAR image target azimuth estimation method | |
| CN104851105B (en) | A kind of improved froth images dividing method based on watershed transform | |
| CN101937577A (en) | Method capable of generating shadow with boundary pixel oversampling effect | |
| CN111210452B (en) | Certificate photo portrait segmentation method based on graph segmentation and mean shift | |
| Zhang et al. | A road extraction method based on high resolution remote sensing image | |
| CN111311586B (en) | Nonlinear health analysis system-based data multi-index dynamic integration algorithm and system | |
| CN107808160B (en) | Three-dimensional building extraction method and device | |
| CN108765329B (en) | Thick cloud removing method and system for remote sensing image | |
| CN103679170A (en) | Method for detecting salient regions based on local features | |
| CN105205826A (en) | SAR image target azimuth angle estimation method based on direction straight line screening | |
| CN112381838A (en) | Automatic image cutting method for digital pathological section image | |
| CN112862847A (en) | Line segment sequence detection method for expressing surface feature edge | |
| CN113592877B (en) | Method and device for identifying red line exceeding of pumped storage power station | |
| CN117389972B (en) | Strip-shaped space data compression method and device, electronic equipment and storage medium | |
| CN113436092B (en) | Method for identifying cloud region of panchromatic remote sensing image | |
| CN116109934B (en) | Geological fault identification method and system based on image identification technology | |
| CN117308794B (en) | Line width measuring method, system and computer storage medium | |
| CN115830043B (en) | Boundary detection method, device, equipment and storage medium for wireless charging magnet |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210330 |