CN114187537A - Railway track and central line extraction method based on aerial remote sensing image - Google Patents
Railway track and central line extraction method based on aerial remote sensing image Download PDFInfo
- Publication number
- CN114187537A CN114187537A CN202111550857.7A CN202111550857A CN114187537A CN 114187537 A CN114187537 A CN 114187537A CN 202111550857 A CN202111550857 A CN 202111550857A CN 114187537 A CN114187537 A CN 114187537A
- Authority
- CN
- China
- Prior art keywords
- line
- railway
- image
- track
- aerial
- 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
- 238000000605 extraction Methods 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000005070 sampling Methods 0.000 claims abstract description 14
- 238000013461 design Methods 0.000 claims description 8
- 230000000694 effects Effects 0.000 abstract description 5
- 238000005259 measurement Methods 0.000 abstract description 5
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 238000013507 mapping Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013102 re-test Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a railway track and center line extraction method based on aerial remote sensing images. The prior art is mainly completed by an artificial total station and a laser scanner, the artificial measurement has low efficiency, and the laser scanner is high in cost and occupies railway operation. According to the method, image control point distribution is designed according to the railway trend, an aviation coverage image is acquired, and air-to-three calculation is carried out on the aviation coverage image; extracting the line segment information of each aviation covering image by using a line segment extraction algorithm; drawing a homonymous trajectory from the image pair, and recovering the spatial position information of the spatial real line; and finally, extracting the track central line and constructing a railway line information database. The invention adopts a non-contact spatial position sampling method, does not need to use a rail car, does not influence normal railway operation activities in the data acquisition process, and has the characteristics of high efficiency, low cost and high operation safety.
Description
Technical Field
The invention belongs to the technical field of railway survey, and particularly relates to a railway track and center line extraction method based on aerial remote sensing images.
Background
The existing track line reconstruction, retest and check technology is a conforming technology for railway design and construction, is a reconstruction and duplication technology for existing line design line data, can even be used as a foundation stability detection technology, and plays an important role in railway construction and operation management. The traditional method is a manual line measurement or semi-automatic scanning mode, and equipment such as a total station and a laser scanner is used, however, the method using the total station can only measure the parameters of the line, recover the designed geometric nodes and curvature, cannot truly express the space form of the existing railway due to insufficient sampling, and has lower linear goodness of fit; in order to solve the problem caused by insufficient sampling, the subsequent method uses a laser scanner mode, and can realize the spatial position precision of 2cm through the control of a POS system and a target along the line, but the method not only needs expensive laser scanning equipment and high-precision measurement efficiency of more than million times/second, but also needs to occupy space and time for normal railway running and influences economic activities such as normal railway operation.
The invention discloses a method for extracting an existing railway center line based on laser point cloud data, which utilizes a binarization result to calculate the railway center line, but the method needs high-quality point cloud, depends on the effects of point cloud filtering and point cloud reflection intensity, and has serious prior knowledge constraint; [ patent CN105844995A ] proposes a railway line operation maintenance measurement method of vehicle-mounted LiDAR, which relies on the effect of classifying rail surface data and needs to process the component with complex fork structure separately to extract and form a line element information table to complete the railway plane and longitudinal map.
Disclosure of Invention
In order to make up for the defects of the prior art, the invention provides a railway track and center line extraction method based on aerial remote sensing images, and solves the problems that the existing railway track and center line extraction technology cannot achieve both high efficiency and economy, and cannot achieve both high precision and reliability and low cost.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
the railway track and central line extraction method based on the aerial remote sensing image comprises the following steps:
the method comprises the following steps: designing image control point distribution according to the railway trend, wherein the image control points are distributed in pairs on two sides of a railway line;
step two: acquiring an aerial coverage image of the image control point, wherein the overlapping degree of the aerial coverage image is more than or equal to 3 degrees of overlapping requirement;
step three: arranging routes with the length of 2 base lines outside the measuring area along the railway;
step four: performing space-three solution on the aerial coverage images to obtain three-dimensional attitude information and camera distortion parameter model coefficients of each aerial coverage image in an object space;
step five: extracting the line segment information of each aviation coverage image by using a line segment extraction algorithm to serve as a prediction candidate value for the later-stage accelerated semi-automatic trajectory prediction extraction;
step six: acquiring an image pair with a spatial relationship through the fourth step, semi-automatically tracking and drawing a homonymous trajectory from the image pair, and recovering spatial position information of a real spatial line through a least square homonymous trajectory fitting mode;
step seven: extracting a track central line;
step eight: and (4) combining the design standard parameters to construct a railway line information database.
Specifically, the track centerline extraction comprises the following steps:
the method comprises the following steps: acquiring left and right track reference lines of the track according to the position of the homonymous track and the spatial position information of the spatial real line obtained in the step six;
step two: calculating a sampling line segment of the track central line according to the left and right track reference lines by the principle of normal vector intersection;
step three: and directly fitting the data parameters of the derailment line according to the sampling line segment to realize the reconstruction of the rail surface information.
The invention has the beneficial effects that:
1) the invention adopts a non-contact spatial position sampling method, does not need to use a rail car, does not influence normal railway operation activities in the data acquisition process, and has important significance in retesting the existing railway lines;
2) the aerial line mapping method takes a photogrammetry technology as a core, the space measurement precision of the aerial line mapping method is consistent with that of aerial mapping, the line mapping precision of 1:500 is met, and the line mapping precision can be improved to a millimeter level by improving the resolution;
3) the invention has the characteristics of high efficiency, low cost and high operation safety, does not need complex parameter setting and subsequent post-processing, has controllable precision and is beneficial to reducing the capital investment in railway operation and maintenance;
4) the invention can reconstruct and obtain the spatial position information of the railway track and the original design parameters without setting the threshold value by personnel with prior knowledge, classifying and filtering redundant ground point information and investing a large amount of labor cost.
Drawings
FIG. 1 is a flow chart of the operation of the present invention;
FIG. 2 is a diagram of image control point layout along a railway;
FIG. 3 is a schematic diagram of aerial photography homonym line extraction;
FIG. 4 is a diagram of a railroad track dotted line tracking.
Detailed Description
The present invention will be described in detail with reference to specific embodiments.
The invention utilizes the current mature unmanned aerial vehicle aerial photography remote sensing mode with high cost performance and reliable precision to efficiently realize a non-contact type line reconstruction method, which not only can check the line construction precision, but also can be used as a reliable existing railway center line reconstruction means. As shown in fig. 1, the present invention specifically includes the following steps:
the method comprises the following steps: designing image control point distribution according to the railway trend, wherein the image control point distribution density, the image resolution and the camera parameters are set according to the precision requirement of the project achievement; as shown in fig. 2, the image control points are arranged in pairs at both sides of the railway line;
step two: acquiring an aerial coverage image of an image control point, wherein the overlapping degree of the aerial coverage image is more than or equal to 3 degrees of overlapping requirement;
step three: in order to meet the requirement of stability of air-to-air three solution, routes with the length of 2 base lines are required to be arranged outside the measuring area range along the railway, and the stability of the long strip-shaped measuring area is required to be improved by the design idea of constructing the routes;
step four: performing space-three calculation on the aerial coverage images, and calculating three-dimensional attitude information and camera distortion parameter model coefficients of each image in an object space according to the obtained aerial images, POS information and image control point information;
step five: extracting the line segment information of each aviation coverage image by using a line segment extraction algorithm to serve as a prediction candidate value for the later-stage accelerated semi-automatic trajectory prediction extraction;
step six: acquiring an image pair with a spatial relationship through the fourth step, semi-automatically tracking and drawing a homonymous trajectory from the image pair, and recovering spatial position information of a real spatial line through a least square homonymous trajectory fitting mode;
1) since the homonymous trajectory has epipolar constraint relationship in different images, the homonymous trajectory necessarily has epipolar restriction relationship in different images, as shown in fig. 3, this relationship is a constraint relationship of a basic matrix F in computer vision, and the specific presentation mode is shown in formula (1), where x1 and x2 are homonymous points in left and right images, such as homonymous points in trajectories, and the basic matrix F can be obtained by setting an internal parameter K and an external parameter M of left and right stereoscopic images to [ R T ], as shown in formula (2).
2) Besides the space geometric constraint existing in the stereo image pair, the track line in a single image also has the characteristics of extremely strong smoothness and vividness, so that the image gray tracking track algorithm is another one-dimensional constraint of the track;
3) combining 1) and 2), as shown in fig. 4, utilizing the one-dimensional gray track and the constraint of the spatial fundamental matrix, realizing the semi-automatic update along the track;
4) due to the regular nature of the orbit itself, the spatial constraint in 1) can be considered as a line segment constraint, and the epipolar equation in the right image of the left image is
Then, the edge line segment of the nearest neighbor domain can be selected in the right image;
5) performing space trajectory fitting, namely extracting a pixel line segment from each image by semi-automatic trajectory drawing in the steps 1) to 4), performing space multi-surface space intersection by segmentation to fit a best fit line, considering flatness and smoothness constraints of the whole line segment, and increasing first derivative smoothing constraint in a fitting function, wherein a specific fitting energy function is shown in the following formula 2, wherein CiThe space curved surface corresponding to the homonymous line segment in the image i is obtained, the first term formula in the formula (3) is a fitting intersection formula, and the second term formula is used for ensuring that the fitted space curve has smooth characteristics;
step seven: track centerline extraction
1) Acquiring left and right track reference lines of the track according to the position of the homonymous track and the spatial position information of the spatial real line obtained in the step six;
2) according to the left and right track reference lines, a normal line which is perpendicular to the reference lines of the left and right aisle surfaces at the same time is searched through the principle of normal vector intersection, and the midpoint of the left and right intersection points is obtained, namely the sampling point of the railway center line;
3) and directly fitting the data parameters of the derailment line according to the sampling line segment to realize the reconstruction of the rail surface information.
The obtained sampling points are all represented by oversampling on the actual rail surface, and have a large amount of redundant information, so that the redundant information cannot be directly stored in a corresponding design database, and therefore, the sampling data also needs to be merged in the axial direction of the sampling data; the basis for eliminating redundant data is whether adjacent sampling points and lines are coaxial or not;
step eight: and recording track parameters by combining design standard parameters, such as track gauge, track height, waist thickness and the like in the track, and constructing a railway line information database.
Examples of applications are as follows:
for example, the length of an operation railway in a certain section of a hilly area is about 10km, the south-north trend is that the existing bridge roadbed and the ordinary road foundation section exist along the route, the existing CPI control network is directly used as a known control network through collection and early exploration in the early stage, then regional image control points are established, the plane absolute precision is better than 2cm, the vertical absolute precision is better than 3cm, the image control points are arranged in pairs along the two sides of a railway line, and the average length of 8 base lines is that the image control points are arranged in pairs about 200 meters. The aerial image data quality requirement is clear, the color is saturated, and the ground resolution is set to be better than 1 cm. The real attitude data of the high-precision image space is obtained through space-three solution, the relative precision is in millimeter level, the error in the absolute plane position of the rail surface can reach less than or equal to 2cm, and the error in the absolute elevation position can reach less than or equal to 3cm, so that the measurement precision in millimeter level can be achieved if the ground resolution and the control point precision are improved. And comparing the resolving precision with the measured railway data, wherein the precision meets the retest requirement.
In the description of the present invention, unless otherwise expressly specified or limited, the terms "disposed," "mounted," "connected," and "secured" are to be construed broadly, e.g., as meaning fixedly connected, detachably connected, or integral to; can be mechanically or electrically connected; either directly or indirectly through intervening media, either internally or in any other relationship. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
The invention is not limited to the examples, and any equivalent changes to the technical solution of the invention by a person skilled in the art after reading the description of the invention are covered by the claims of the invention.
Claims (2)
1. The railway track and center line extraction method based on the aerial remote sensing image is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: designing image control point distribution according to the railway trend, wherein the image control points are distributed in pairs on two sides of a railway line;
step two: acquiring an aerial coverage image of the image control point, wherein the overlapping degree of the aerial coverage image is more than or equal to 3 degrees of overlapping requirement;
step three: arranging routes with the length of 2 base lines outside the measuring area along the railway;
step four: performing space-three solution on the aerial coverage images to obtain three-dimensional attitude information and camera distortion parameter model coefficients of each aerial coverage image in an object space;
step five: extracting the line segment information of each aviation coverage image by using a line segment extraction algorithm to serve as a prediction candidate value for the later-stage accelerated semi-automatic trajectory prediction extraction;
step six: acquiring an image pair with a spatial relationship through the fourth step, semi-automatically tracking and drawing a homonymous trajectory from the image pair, and recovering spatial position information of a real spatial line through a least square homonymous trajectory fitting mode;
step seven: extracting a track central line;
step eight: and (4) combining the design standard parameters to construct a railway line information database.
2. The railway track and central line extraction method based on aerial remote sensing images as claimed in claim 1, wherein: the track centerline extraction comprises the following steps:
the method comprises the following steps: acquiring left and right track reference lines of the track according to the position of the homonymous track and the spatial position information of the spatial real line obtained in the step six;
step two: calculating a sampling line segment of the track central line according to the left and right track reference lines by the principle of normal vector intersection;
step three: and directly fitting the data parameters of the derailment line according to the sampling line segment to realize the reconstruction of the rail surface information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111550857.7A CN114187537B (en) | 2021-12-17 | 2021-12-17 | Railway track and midline extraction method based on aerial remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111550857.7A CN114187537B (en) | 2021-12-17 | 2021-12-17 | Railway track and midline extraction method based on aerial remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114187537A true CN114187537A (en) | 2022-03-15 |
| CN114187537B CN114187537B (en) | 2024-04-30 |
Family
ID=80544348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111550857.7A Active CN114187537B (en) | 2021-12-17 | 2021-12-17 | Railway track and midline extraction method based on aerial remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114187537B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100653627B1 (en) * | 2006-01-27 | 2006-12-05 | (자)한진개발공사 | Method for three-dimensional determining of basic design road route using three-dimensional geological spatial information treatment and aerial photograph |
| CN105844995A (en) * | 2016-05-20 | 2016-08-10 | 中铁第勘察设计院集团有限公司 | Railway line operation and maintenance measuring method based on vehicle-mounted LiDAR technology |
| CN106087621A (en) * | 2016-05-31 | 2016-11-09 | 中铁第四勘察设计院集团有限公司 | A kind of Existing Railway Line repetition measurement method based on mobile lidar technology |
| CN108763575A (en) * | 2018-06-06 | 2018-11-06 | 湖南省第测绘院 | Photo control point automatically selecting method based on photo control point database |
| RU2726256C1 (en) * | 2020-03-01 | 2020-07-10 | Дмитрий Александрович Рощин | Method of constructing three-dimensional model of terrain along railway track bed |
| CN113155098A (en) * | 2021-04-20 | 2021-07-23 | 中国铁路设计集团有限公司 | Existing railway track line high-precision three-dimensional reconstruction method based on unmanned aerial vehicle multi-view images |
-
2021
- 2021-12-17 CN CN202111550857.7A patent/CN114187537B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR100653627B1 (en) * | 2006-01-27 | 2006-12-05 | (자)한진개발공사 | Method for three-dimensional determining of basic design road route using three-dimensional geological spatial information treatment and aerial photograph |
| CN105844995A (en) * | 2016-05-20 | 2016-08-10 | 中铁第勘察设计院集团有限公司 | Railway line operation and maintenance measuring method based on vehicle-mounted LiDAR technology |
| CN106087621A (en) * | 2016-05-31 | 2016-11-09 | 中铁第四勘察设计院集团有限公司 | A kind of Existing Railway Line repetition measurement method based on mobile lidar technology |
| CN108763575A (en) * | 2018-06-06 | 2018-11-06 | 湖南省第测绘院 | Photo control point automatically selecting method based on photo control point database |
| RU2726256C1 (en) * | 2020-03-01 | 2020-07-10 | Дмитрий Александрович Рощин | Method of constructing three-dimensional model of terrain along railway track bed |
| CN113155098A (en) * | 2021-04-20 | 2021-07-23 | 中国铁路设计集团有限公司 | Existing railway track line high-precision three-dimensional reconstruction method based on unmanned aerial vehicle multi-view images |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114187537B (en) | 2024-04-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023019709A1 (en) | Automatic detection method of conductor height and pull-out value of overhead line system based on vehicle-mounted mobile laser point cloud | |
| CN110647798B (en) | Automatic track center line detection method based on vehicle-mounted mobile laser point cloud | |
| CN111429498B (en) | Railway business line three-dimensional center line manufacturing method based on point cloud and image fusion technology | |
| CN107792115B (en) | It is a kind of to automatically extract both wired rail crest level methods using three-dimensional laser point cloud | |
| CN110986878B (en) | Method for automatically extracting rail section based on mobile measurement system | |
| CN107092020B (en) | Merge the surface evenness monitoring method of unmanned plane LiDAR and high score image | |
| CN112414309B (en) | High-speed rail contact line height-guiding and pull-out value inspection method based on airborne laser radar | |
| CN108362308B (en) | Mileage correction method for mobile laser measurement system by using tunnel circular seam | |
| Papasaika et al. | Fusion of digital elevation models using sparse representations | |
| CN113125444A (en) | Railway bridge disease monitoring method based on unmanned aerial vehicle carrying three-dimensional scanner | |
| Fujii et al. | Urban object reconstruction using airborne laser elevation image and aerial image | |
| CN108917591A (en) | Rail profile autoegistration method and device under a kind of dynamic environment | |
| CN102914290A (en) | Metro gauge detecting system and detecting method thereof | |
| CN109544607A (en) | A kind of cloud data registration method based on road mark line | |
| CN111768417A (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
| CN110986877A (en) | Railway engineering clearance detection method based on high-precision vehicle-mounted laser mobile measurement system | |
| CN110926417B (en) | Vehicle-mounted railway tunnel detection system based on machine vision | |
| CN114897777A (en) | Full-automatic extraction method of laser point cloud of overhead line system supporting facility considering spatial relationship | |
| CN112285738A (en) | Positioning method and device for rail transit vehicle | |
| Kremer et al. | The RailMapper–A dedicated mobile LiDAR mapping system for railway networks | |
| CN114187537B (en) | Railway track and midline extraction method based on aerial remote sensing image | |
| CN113673011A (en) | Method for intelligently identifying tunnel invasion boundary in operation period based on point cloud data | |
| CN107024175A (en) | Motorbus vehicle body critical size detecting system solution based on multi-vision visual | |
| CN104268836A (en) | Watershed segmentation mark point extraction method based on local area homogeneity indexes | |
| Labarile et al. | Ballast 3D reconstruction by a matching pursuit based stereo matcher |
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 |