CN113158726A - Method for identifying rural highway pavement types based on remote sensing images - Google Patents
Method for identifying rural highway pavement types based on remote sensing images Download PDFInfo
- Publication number
- CN113158726A CN113158726A CN202011604455.6A CN202011604455A CN113158726A CN 113158726 A CN113158726 A CN 113158726A CN 202011604455 A CN202011604455 A CN 202011604455A CN 113158726 A CN113158726 A CN 113158726A
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- image
- rural highway
- identifying
- rural
- 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 OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/005—Tree description, e.g. octree, quadtree
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- Computer Graphics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Remote Sensing (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Road Repair (AREA)
Abstract
The invention discloses a method for identifying rural highway pavement types based on remote sensing images, which comprises the following steps: step 1: an algorithm framework; step 2: and identifying a rural highway pavement type framework. The invention aims at the image data with the precision requirement superior to 1 meter of the remote sensing image precision; reading the line shape of the rural highway route, superposing the line shape with the remote sensing image under the same coordinate system to obtain the spatial position of the rural highway route in the remote sensing image, and then carrying out characteristic identification on the rural highway pavement type according to the remote sensing image so as to obtain the pavement type of the rural highway. The algorithm adopts a quadtree weighting algorithm method to identify the rural highway pavement types on the remote sensing images, can effectively improve the pavement type identification rate, eliminates the influence that the rural highway alignment cannot be fitted with the local alignment of the remote sensing images due to GPS precision errors in the acquisition process, and simultaneously eliminates the influence of local shadows caused by buildings or other trees on the remote sensing images on the rural highway pavement shielding.
Description
Technical Field
The invention relates to the field of rural highway management, and the name is as follows: a method for identifying rural highway pavement types based on remote sensing images.
Background
At present, technologies such as remote sensing images, GIS and GPS are widely used in the traffic industry, and fine management of rural highways is improved. In order to accurately master the development condition, construction demand and construction process of rural roads, the transportation department organizes and develops special investigation work of national rural road access condition in 2005, and geographic information data and attribute data of all rural roads nationwide are respectively acquired by using a GPS technical means. When rural highway data is used in the industry, the situation that the types of the rural highway road surfaces in some places are inconsistent with the actual situation is found, the method for identifying the types of the rural highway road surfaces based on remote sensing image identification is provided for improving the accuracy of basic data, and the problems that the data in the industry is not updated timely and inaccurate are solved.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides a remote sensing image rural highway pavement type identification method based on a quadtree search mode.
In order to solve the technical problems, the invention provides the following technical scheme:
the invention relates to a method for identifying rural highway pavement types based on remote sensing images, which comprises the following steps:
step 1: an algorithm framework;
step 2: identifying a rural highway pavement type framework;
as a preferred technical solution of the present invention, the algorithm architecture includes the following steps:
step 101: the algorithm adopts a quadtree weighting method to construct the road surface type of each pixel point of the rural highway buffer area-shaped element on the image;
step 102: setting pixel points f of input imageiThe output image after identifying and extracting the road network by the quadtree weighting method is foThen there is fo＝FN1(fi) In which F isN1A processing framework formed by a quadtree weighting method, and No＝FN1(fi) In which N isoThe road surface type characteristic value is obtained;
step 103: and traversing by using a quadtree weighting method when identifying rural highway roads in each area.
As a preferred technical scheme of the invention, the architecture for identifying the pavement type of the rural highway comprises the following steps:
step 201: traversing and circularly reading vector buffer surface area L of each rural roadi；
Step 202: obtaining a rural highway planar area LiMinimum circumscribed rectangle Qi；
Step 203: with the rectangle QiCutting the remote sensing image of the road network to be extracted, and keeping the image in the rectangular area if QiAll remote sensing images I related to the region not in one remote sensing image need to be foundi；
Step 204: image IiAfter being spliced together, the images are divided into n images with fixed format sizes by 320 multiplied by 320 pixels, and the images are sequentially input into a quadtree weighting method formed by an algorithm to obtain output images f of n two-dimensional matrixeso(N) and road surface type NoA characteristic value;
step 205: will f iso(n) splicing according to the framing sequence, and converting the grid pixels of the GIS into a vector algorithm, therebyConverting the road surface on the image into a vector polygon of the image on the same coordinate system and weighting the road surface type characteristic value N of the image of all pixel points in the polygono；
Step 206: calculating a route LiRoad surface type N of inner pixel pointoAn average of the eigenvalues;
step 207: according to the route LiInner road surface type NoAnd fitting the average value of the characteristic values to the pavement types of the rural highways.
The remote sensing image identification is to cut the minimum external rectangular remote sensing image of the rural highway planar graph into pictures with fixed sizes, search all image files and pixel points in the files in a quadtree mode, identify the image files by using a neural network identification module, separate the image files to form raster data of the rural highway on the image, convert the raster data into vector data by using a GIS tool, form the vector data into closed polygonal vector data, calculate and average the rural highway pavement type characteristic values in the polygonal vector data, and fit the rural highway pavement type according to the pavement type average characteristic value of the polygonal vector.
The invention has the beneficial effects that: the method for identifying the type of the rural highway pavement based on the remote sensing image uses a quadtree weighting algorithm, can effectively improve the accuracy of identifying the type of the rural highway pavement from the remote sensing image, eliminates the accuracy of identifying the type of the rural highway pavement caused by low alignment accuracy of the rural highway, simultaneously eliminates the influence of local shadow caused by buildings or other trees on the rural highway pavement shielding on the remote sensing image, and improves the accuracy of identifying the type of the rural highway pavement.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of the present invention for identifying the road surface type of a rural highway based on remote sensing images;
FIG. 2 is a flow chart of the present invention for identifying the road surface type of a rural highway based on remote sensing images;
FIG. 3 is a schematic diagram of a step of identifying the road surface type of the rural highway based on the remote sensing image according to the invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
Example (b): as shown in fig. 1, fig. 2 and fig. 3, the method for identifying the road surface type of the rural highway based on the remote sensing image comprises the following steps:
step 1: an algorithm framework;
step 2: identifying a rural highway pavement type framework;
as a preferred technical solution of the present invention, the algorithm architecture includes the following steps:
step 101: the algorithm adopts a quadtree weighting method to construct the road surface type of each pixel point of the rural highway buffer area-shaped element on the image;
step 102: setting pixel points f of input imageiThe output image after identifying and extracting the road network by the quadtree weighting method is foThen there is
Wherein
A processing framework constructed by the quadtree weighting method, and
wherein N isoThe road surface type characteristic value is obtained;
step 103: and traversing by using a quadtree weighting method when identifying rural highway roads in each area.
As a preferred technical scheme of the invention, the architecture for identifying the pavement type of the rural highway comprises the following steps:
step 201: traversing and circularly reading vector buffer surface area L of each rural roadi；
Step 202: obtaining a rural highway planar area LiMinimum circumscribed rectangle Qi；
Step 203: with the rectangle QiCutting the remote sensing image of the road network to be extracted, and keeping the image in the rectangular area if QiAll remote sensing images I related to the region not in one remote sensing image need to be foundi；
Step 204: image IiAfter being spliced together, the images are divided into n images with fixed format sizes by 320 multiplied by 320 pixels, and the images are sequentially input into a quadtree weighting method formed by an algorithm to obtain output images f of n two-dimensional matrixeso(N) and road surface type NoA characteristic value;
step 205: will f iso(N) splicing according to the framing sequence, and applying the grid pixel conversion of GIS to vector algorithm, thereby converting the road surface on the image into the vector polygon of the image on the same coordinate system and the road surface type weighted characteristic value N of all pixel point images in the polygono；
Step 206: calculating a route LiRoad surface type N of inner pixel pointoAn average of the eigenvalues;
step 207: according to the route LiInner road surface type NoAnd fitting the average value of the characteristic values to the pavement types of the rural highways.
The method realizes the automatic identification and comparison of the rural highway pavement type and the corresponding position of the remote sensing image; the method can effectively eliminate a large number of small patches generated in the road network extraction process, and short road surface breaks generated by trees or building shielding can be effectively connected and identified.
The invention designs an algorithm for automatically identifying the road surface type of the rural road based on the remote sensing image of the quadtree and a software process for extracting the road network of the rural road and the remote sensing image and identifying the road surface type based on the algorithm. The algorithm can effectively improve the identification precision, and the comparison process based on the algorithm can greatly improve the road planning, construction and management efficiency based on the high-resolution remote sensing image.
In the description of the present invention, it should be noted that the terms "vertical", "upper", "lower", "horizontal", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present invention.
In the description of the present invention, it should also be noted that, unless otherwise explicitly specified or limited, the terms "disposed," "mounted," "connected," and "connected" are to be construed broadly and may, for example, be fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (5)
1. A method for identifying rural highway pavement types based on remote sensing images is characterized by comprising the following steps:
step 1: an algorithm framework;
step 2: identifying a rural highway pavement type framework;
the algorithm architecture comprises the following steps:
step 101: the algorithm adopts a quadtree weighting method to construct the road surface type of each pixel point of the rural highway buffer area-shaped element on the image;
step 102: setting pixel points f of input imageiThe output image after identifying and extracting the road network by the quadtree weighting method is foThen there is
Wherein
A processing framework constructed by the quadtree weighting method, and
wherein N isoThe road surface type characteristic value is obtained;
step 103: and traversing by using a quadtree weighting method when identifying rural highway roads in each area.
2. The method for identifying the pavement type of the rural highway based on the remote sensing image as claimed in claim 1, wherein the processing involves post-stage pavement type classification analysis.
3. The method for identifying the type of the road surface of the rural highway based on the remote sensing image as claimed in claim 1, wherein the dirty spots on the image are eliminated.
4. The method for identifying the type of the rural highway pavement based on the remote sensing image according to claim 1, wherein the architecture for identifying the type of the rural highway pavement comprises the following steps:
step 201: traversing and circularly reading vector buffer surface area L of each rural roadi；
Step 202: obtaining a rural highway planar area LiMinimum circumscribed rectangle Qi；
Step 203: with the rectangle QiCutting the remote sensing image of the road network to be extracted, and keeping the image in the rectangular area if QiRemote sensing of regions not in oneAll remote sensing images I related to the image need to be found in the imagei；
Step 204: image IiAfter being spliced together, the images are divided into n images with fixed format sizes by 320 multiplied by 320 pixels, and the images are sequentially input into a quadtree weighting method formed by an algorithm to obtain output images f of n two-dimensional matrixeso(N) and road surface type NoA characteristic value;
step 205: will f iso(N) splicing according to the framing sequence, and applying the grid pixel conversion of GIS to vector algorithm, thereby converting the road surface on the image into the vector polygon of the image on the same coordinate system and the road surface type weighted characteristic value N of all pixel point images in the polygono；
Step 206: calculating a route LiRoad surface type N of inner pixel pointoAn average of the eigenvalues;
step 207: according to the route LiInner road surface type NoAnd fitting the average value of the characteristic values to the pavement types of the rural highways.
5. The method for identifying the rural highway pavement type based on the remote sensing image according to claim 1 is characterized in that the remote sensing image identification is to cut the minimum external rectangular remote sensing image of a rural highway planar graph into pictures with fixed size, search all image files and pixel points in the files in a quadtree mode, identify the image files by using a neural network identification module, separate the image files to form raster data of rural highways on the images, convert the raster data into vector data by using a GIS tool, form the vector data into closed polygonal vector data, evaluate and average the rural highway pavement type characteristic values in the polygonal vector data, and fit the rural highway pavement type according to the average characteristic value of the pavement type of the polygonal vector.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011604455.6A CN113158726A (en) | 2020-12-30 | 2020-12-30 | Method for identifying rural highway pavement types based on remote sensing images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011604455.6A CN113158726A (en) | 2020-12-30 | 2020-12-30 | Method for identifying rural highway pavement types based on remote sensing images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113158726A true CN113158726A (en) | 2021-07-23 |
Family
ID=76878141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011604455.6A Pending CN113158726A (en) | 2020-12-30 | 2020-12-30 | Method for identifying rural highway pavement types based on remote sensing images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158726A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119323702A (en) * | 2024-12-19 | 2025-01-17 | 交通运输部科学研究院 | Spark distributed identification method and device for rural highway pavement types, electronic equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106124454A (en) * | 2016-06-30 | 2016-11-16 | 中国交通通信信息中心 | A kind of bituminous paving aging performance monitoring method based on remote sensing image |
| WO2019109262A1 (en) * | 2017-12-06 | 2019-06-13 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining new roads on a map |
| CN110728752A (en) * | 2019-10-21 | 2020-01-24 | 西南交通大学 | Construction method of three-dimensional terrain scene model of road |
| CN110929690A (en) * | 2019-12-10 | 2020-03-27 | 交通运输部科学研究院 | Remote sensing image road network extraction method based on deep neural network |
| CN111241994A (en) * | 2020-01-09 | 2020-06-05 | 中国交通通信信息中心 | Method for extracting remote sensing image rural highway desertification road section for deep learning |
| CN111539297A (en) * | 2020-04-20 | 2020-08-14 | 武汉中地数码科技有限公司 | High-resolution remote sensing image road information semi-automatic extraction method |
-
2020
- 2020-12-30 CN CN202011604455.6A patent/CN113158726A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106124454A (en) * | 2016-06-30 | 2016-11-16 | 中国交通通信信息中心 | A kind of bituminous paving aging performance monitoring method based on remote sensing image |
| WO2019109262A1 (en) * | 2017-12-06 | 2019-06-13 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining new roads on a map |
| CN110728752A (en) * | 2019-10-21 | 2020-01-24 | 西南交通大学 | Construction method of three-dimensional terrain scene model of road |
| CN110929690A (en) * | 2019-12-10 | 2020-03-27 | 交通运输部科学研究院 | Remote sensing image road network extraction method based on deep neural network |
| CN111241994A (en) * | 2020-01-09 | 2020-06-05 | 中国交通通信信息中心 | Method for extracting remote sensing image rural highway desertification road section for deep learning |
| CN111539297A (en) * | 2020-04-20 | 2020-08-14 | 武汉中地数码科技有限公司 | High-resolution remote sensing image road information semi-automatic extraction method |
Non-Patent Citations (3)
| Title |
|---|
| RENBAO LIAN: "road extraction methods in high-resolution remote sensingimages：A comprehensive review", 《IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING》 * |
| 邱一丹等: "山区高速公路边坡类型划分研究", 《交通节能与环保》 * |
| 马骁等: "面向农村公路高分遥感影像道路提取的卷积神经网络架构", 《交通运输研究》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119323702A (en) * | 2024-12-19 | 2025-01-17 | 交通运输部科学研究院 | Spark distributed identification method and device for rural highway pavement types, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102125959B1 (en) | Method and apparatus for determining a matching relationship between point cloud data | |
| CN110598784B (en) | Machine learning-based construction waste classification method and device | |
| CN110728200A (en) | Real-time pedestrian detection method and system based on deep learning | |
| CN109271861B (en) | Multi-scale fusion point cloud traffic signboard automatic extraction method | |
| CN110929690B (en) | Remote sensing image road network extraction method based on deep neural network | |
| CN114648471A (en) | Point cloud processing method and device, electronic equipment and system | |
| CN116543312A (en) | Construction and update method of remote sensing inversion sample library for large-scale river and lake water quality parameters | |
| CN113034511A (en) | Rural Building Recognition Algorithm Based on High Resolution Remote Sensing Image and Deep Learning | |
| CN107203761A (en) | Road width method of estimation based on high-resolution satellite image | |
| CN114373009A (en) | An intelligent calculation method for building shadow height measurement based on high-resolution remote sensing images | |
| CN112883900A (en) | Method and device for bare-ground inversion of visible images of remote sensing images | |
| CN114722944A (en) | Point cloud precision determination method, electronic device and computer storage medium | |
| CN118279741A (en) | Intelligent cloud supervision platform for construction waste | |
| US10380423B2 (en) | Utility infrastructure mapping | |
| CN118918169B (en) | Road facility height calculation method based on monocular camera image | |
| CN113158726A (en) | Method for identifying rural highway pavement types based on remote sensing images | |
| Liu et al. | A framework of road extraction from airborne lidar data and aerial imagery | |
| Hammoudi et al. | Extracting wire-frame models of street facades from 3D point clouds and the corresponding cadastral map | |
| Herold et al. | Automatically georeferenced maps as a source for high resolution urban growth analyses | |
| CN118691666A (en) | A positioning method, device and system for surveying and mapping | |
| Baltsavias | Integration of ortho-images in GIS | |
| CN118196635A (en) | Street scene element distribution feature recognition method and system based on CLIP model | |
| CN107941241A (en) | A kind of resolving power test target and its application method for aerophotogrammetry quality evaluation | |
| CN117522981A (en) | A data collection method based on DSM and DOM | |
| CN113155033A (en) | Method for calculating rural highway pavement width based on remote sensing image |
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: 20210723 |