CN116385592B - Basic mapping road data generation method and system based on remote sensing interpretation - Google Patents
Basic mapping road data generation method and system based on remote sensing interpretation Download PDFInfo
- Publication number
- CN116385592B CN116385592B CN202310664602.6A CN202310664602A CN116385592B CN 116385592 B CN116385592 B CN 116385592B CN 202310664602 A CN202310664602 A CN 202310664602A CN 116385592 B CN116385592 B CN 116385592B
- Authority
- CN
- China
- Prior art keywords
- road
- center line
- line
- basic mapping
- interpretation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013507 mapping Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000011156 evaluation Methods 0.000 claims abstract description 36
- 230000000295 complement effect Effects 0.000 claims abstract description 29
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000002159 abnormal effect Effects 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- 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
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Abstract
The invention provides a basic mapping road data generation method and system based on remote sensing interpretation, and belongs to the technical field of road mapping. The method comprises the following steps: based on the assigned center lines of all road sections, evaluating the road center line of the basic mapping road pavement, and processing the basic mapping road center line according to the evaluation result; matching the processed basic mapping road center line with the assigned road section center line, extracting the road width to the basic mapping data center line, and constructing a buffer area according to one half of the road width to generate a complement road section surface corresponding to each road section; and extracting road surface edge nodes of the road opening part, performing curve fitting, and connecting the road surface edge nodes with edges of the complement road surface corresponding to each road section in series to obtain complete road surface complement data. The invention reduces the workload of manually collecting road surfaces and solves the problem that the road interpretation result of remote sensing data cannot be directly utilized.
Description
Technical Field
The invention relates to the technical field of geographic mapping, in particular to a basic mapping road data generation method and system based on remote sensing interpretation.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Currently, the accuracy of the remote sensing interpretation result is greatly improved, but the current remote sensing interpretation result does not have regularity, as shown in fig. 1, the road boundary of the remote sensing interpretation is characterized by waving; as shown in fig. 2, the remotely interpreted road result has a fragmentation feature.
The inventor finds that the remote sensing interpretation result cannot be directly used for generating basic mapping data, the requirement of basic mapping on road data results is higher and higher, a large amount of road data represented by structural center lines in the basic mapping data results need to be mapped on road surfaces, the current supplementary mapping scheme is realized by adopting a mode of manually collecting data or manually calibrating, the mapping efficiency is low, and the precision is low.
Disclosure of Invention
In order to solve the defects of the prior art, the invention provides a basic mapping road data generation method and system based on remote sensing interpretation, which are used for carrying out automatic complement measurement by combining the existing basic mapping road data, so that the workload of manually collecting road surfaces is reduced, the problem that the road interpretation result of remote sensing data cannot be directly utilized is solved, and the efficiency and the accuracy of basic mapping road data complement measurement are improved.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the invention provides a basic mapping road data generation method based on remote sensing interpretation.
A basic mapping road data generation method based on remote sensing interpretation comprises the following steps:
obtaining a road center line according to the obtained road interpretation vector surface;
obtaining an intersection point of the intersecting center lines according to the road center lines, breaking the road center lines according to the intersection point, and taking the broken road center lines as road section center lines;
constructing equal interval normals according to the road section central line, obtaining the road section surface width in the road interpretation vector surface, removing abnormal values, and assigning the abnormal values to the corresponding road section central line;
based on the assigned center lines of all road sections, evaluating the road center line of the basic mapping road pavement, and processing the basic mapping road center line according to the evaluation result;
matching the processed basic mapping road center line with the assigned road section center line, extracting the road width to the basic mapping data center line, and constructing a buffer area according to one half of the road width to generate a complement road section surface corresponding to each road section;
and extracting road boundary nodes of the road part road surface based on the road interpretation vector surface, performing curve fitting, and connecting the road boundary nodes with the boundary of the complement road surface corresponding to each road section in series to obtain complete road surface complement data.
As a further definition of the first aspect of the present invention, the obtained road interpretation vector surface includes:
and obtaining a road interpretation vector surface by using a remote sensing classification method based on deep learning by taking the aerial photography with set resolution or satellite remote sensing orthophoto as a data source.
As a further limitation of the first aspect of the present invention, obtaining a road center line according to the obtained road interpretation vector surface includes:
and extracting a road center line by adopting a triangular segmentation algorithm according to the obtained road interpretation vector surface.
As a further limitation of the first aspect of the present invention, the extracting the road center line by using a triangle segmentation algorithm includes:
converting the road vector surface data into triangular grids by using a triangular segmentation algorithm, detecting all line segments intersecting with the vector surface edges in the triangular grids, and establishing a topological relation by using the relation between the detected edge line segments and the triangular edges;
and extracting a central line from the triangular mesh according to the topological relation and the geometric constraint condition, and carrying out smoothing treatment on the central line to obtain a final road central line.
As a further limitation of the first aspect of the present invention, constructing equally-spaced normals according to a road section center line to obtain a road section plane width in a road interpretation vector plane, and assigning the obtained value to a corresponding road section center line after removing an abnormal value, including:
calculating the slope of the central line segment according to the positions of the interval nodes of the central line of the road;
extracting a normal line with the position length of the interval node as a set threshold value by taking the interval node as a center according to the slope of the central line segment;
calculating two intersection points of the obtained normal line and the road surface side line;
taking the length of the normal between two intersection points as the width of the interpreted vector surface road corresponding to the current interval node position;
and counting the width values of all the interval node positions, removing abnormal values with the variance of more than 2 times, calculating an average value to be used as the road width of the road section, and assigning the average value to the extracted road center line.
As a further limitation of the first aspect of the present invention, the evaluation of the road centerline of the basic mapping road surface based on the obtained road section centerline comprises:
finding a reference line of the intersection part with the buffer zone in the buffer range of the road center line of the basic mapping road pavement, wherein the obtained road center line is taken as the reference line;
calculating the angles between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the angles larger than a set threshold value;
calculating the distance between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the distance larger than a set threshold value;
acquiring the ratio of the length of the rest reference line to the length of the central line of the road of the basic mapping road after adding, and if the ratio is larger than an evaluation threshold value, considering that the ratio is completely consistent; if the ratio is less than the evaluation threshold, the partial agreement is considered; if the ratio is less than 100 and the evaluation threshold is different, the change is considered.
As a further limitation of the first aspect of the present invention, the processing of the base mapping roadway centerline according to the evaluation result includes:
the completely matched basic mapping road center line is not processed, the partially matched basic mapping road center line is modified based on aerial images or satellite remote sensing orthographic images, and the changed basic mapping road center line is deleted.
The second aspect of the invention provides a basic mapping road data generation system based on remote sensing interpretation.
A remote sensing interpretation based basic mapping road data generation system, comprising:
the road segment center line generation module is configured to: obtaining a road center line according to the obtained road interpretation vector surface, obtaining an intersection point of the intersecting center lines according to the road center line, breaking the road center line according to the intersection point, and taking the broken road center line as a road section center line;
a link width generation module configured to: constructing equal interval normals according to the road section central line, obtaining the road section surface width in the road interpretation vector surface, removing abnormal values, and assigning the abnormal values to the corresponding road section central line;
a base mapping road evaluation module configured to: based on the assigned center lines of all road sections, evaluating the road center line of the basic mapping road pavement, and processing the basic mapping road center line according to the evaluation result;
the complement road surface generation module is configured to: matching the processed basic mapping road center line with the assigned road section center line, extracting the road width to the basic mapping data center line, and constructing a buffer area according to one half of the road width to generate a complement road section surface corresponding to each road section;
an intersection correction module configured to: and extracting road boundary nodes of the road part road surface based on the road interpretation vector surface, performing curve fitting, and connecting the road boundary nodes with the boundary of the complement road surface corresponding to each road section in series to obtain complete road surface complement data.
As a further limitation of the second aspect of the present invention, constructing equally spaced normals according to a road section center line to obtain a road section plane width in a road interpretation vector plane, and assigning the obtained value to a corresponding road section center line after removing an abnormal value, including:
calculating the slope of the central line segment according to the positions of the interval nodes of the central line of the road;
extracting a normal line with the position length of the interval node as a set threshold value by taking the interval node as a center according to the slope of the central line segment;
calculating two intersection points of the obtained normal line and the road surface side line;
taking the length of the normal between two intersection points as the width of the interpreted vector surface road corresponding to the current interval node position;
and counting the width values of all the interval node positions, removing abnormal values with the variance of more than 2 times, calculating an average value to be used as the road width of the road section, and assigning the average value to the extracted road center line.
As a further limitation of the second aspect of the present invention, the evaluation of the road center line of the basic mapping road surface based on the obtained road center line includes:
finding a reference line of the intersection part with the buffer zone in the buffer range of the road center line of the basic mapping road pavement, wherein the obtained road center line is taken as the reference line;
calculating the angles between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the angles larger than a set threshold value;
calculating the distance between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the distance larger than a set threshold value;
acquiring the ratio of the length of the rest reference line to the length of the central line of the road of the basic mapping road after adding, and if the ratio is larger than an evaluation threshold value, considering that the ratio is completely consistent; if the ratio is less than the evaluation threshold, the partial agreement is considered; if the ratio is less than 100 and the evaluation threshold is different, the change is considered.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention creatively provides a basic mapping road data generation method and system based on remote sensing interpretation, which combine the existing basic mapping road data to carry out automatic complement measurement, thereby reducing the workload of manually collecting road surfaces.
2. The invention creatively provides a basic mapping road data generation method and system based on remote sensing interpretation, solves the problem that the road interpretation result of remote sensing data cannot be directly utilized, and improves the efficiency and accuracy of basic mapping road data complement measurement.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
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 invention.
FIG. 1 is a schematic diagram of a conventional remote sensing interpretation road according to the background of the invention;
FIG. 2 is a schematic diagram of a conventional remote sensing interpretation road according to the background of the invention;
fig. 3 is a flowchart of a basic mapping road data generating method based on remote sensing interpretation according to embodiment 1 of the present invention;
fig. 4 is a schematic diagram of road width calculation according to embodiment 1 of the present invention;
fig. 5 is a schematic view of the evaluation of the center line of the roadway according to embodiment 1 of the present invention;
FIG. 6 is a processed basic mapping road provided in embodiment 1 of the present invention;
fig. 7 is a schematic diagram of a basic mapping road data generating system based on remote sensing interpretation according to embodiment 2 of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
Embodiments of the invention and features of the embodiments may be combined with each other without conflict.
Example 1:
as shown in fig. 3, embodiment 1 of the present invention provides a method for generating basic mapping road data based on remote sensing interpretation, which includes the following steps:
s1: and obtaining the road surface interpretation result of the remote sensing data channel.
And extracting road interpretation vector surface data by using a deep learning remote sensing classification method by taking aerial or satellite remote sensing orthophotos with the resolution of 0.05 m to 0.5 m as a data source.
A step of deep learning remote sensing classification, comprising:
s1.1: marking data, namely marking roads in the images to generate a training data set and a testing data set;
s1.2: model training, namely selecting a convolutional neural network (Convolutional Neural Networks, CNN) deep learning model to train the model by using a marked data set, and performing parameter tuning until the accuracy and generalization capability of the model reach satisfactory levels;
s1.3: interpreting data, namely interpreting a large number of remote sensing images by using a trained model to obtain binary grid interpretation data;
s1.4: vectorization, converting the road extraction result into vector surface elements through an image segmentation algorithm by utilizing the obtained binary grid interpretation data.
S2: and extracting a road center line.
Based on the road vector surface data result obtained in the step S1, adopting a Delaunay triangle segmentation algorithm to extract the road center line vector data, and specifically comprising the following steps:
s2.1: generating triangular grids, and converting the road vector surface data into the triangular grids by using a Delaunay triangular segmentation algorithm;
s2.2: and detecting edges, namely detecting all line segments intersecting with the edges of the vector surface in the triangular meshes. These line segments typically connect the intersections on the vertices and edges of the triangle;
s2.3: establishing a topological relation, namely establishing the topological relation by using the relation between the detected edge line segments and the triangle edges;
s2.4: extracting a central line from the triangular mesh according to the topological relation and the geometric constraint condition;
s2.5: center line smoothing: and smoothing the central line and outputting a result.
S3: road segmentation.
And (3) extracting an intersection point (namely a road mouth) of the intersecting center line based on the extracted road center line, breaking the road center line according to the intersection point, and taking the broken road center line as the road section center line data.
S4: and (5) calculating the road width.
As shown in fig. 4, based on the extracted road section center line data, equally spaced normals are constructed, the in-plane length is intercepted, all the normals are counted, the outliers are removed based on the variance, the road section plane width is obtained, and the road section plane width is assigned to the corresponding road section center line, specifically, the method comprises the following steps:
s4.1: calculating a central line segment slope K according to the positions of the central line interval nodes of the road;
s4.2: extracting normal lines with the position length of the interval node of 100-200 meters (threshold range) by taking the current interval node as a center according to the slope K of the central line segment;
s4.3: calculating two intersection points of the normal direction and the road surface side line;
s4.4: according to the positions of the two intersection points, calculating the length of a normal line between the two intersection points, and taking the length as the width of an interpretation vector surface road corresponding to the position of the current interval node;
s4.5: and counting the width values of all the interval node positions, removing abnormal values with the variance of more than 2 times, calculating an average value to be used as the road width of the road section, and assigning the average value to the extracted road center line.
S5: and (5) evaluating the center line of the road.
Based on the road section central line data with width information obtained in the last step, the quality evaluation is carried out on the road central line data of the existing road surface needing to be subjected to the road complement, and the method specifically comprises the following steps:
as shown in fig. 5, assuming that the road center line is a line to be evaluated, marked as a; the road center line obtained by remote sensing interpretation is used as a reference line and marked as B, and the evaluation rule is as follows:
s5.1: within the A target line buffer range, B reference lines of the intersecting part of the A buffer area are found and marked as Bi (wherein Bi possibly is a plurality of line segments, and A and B belong to a 1-to-many relation);
s5.2: calculating A, bi angle, excluding Bi reference line with larger angle deviation (i.e. greater than set threshold value)
S5.3: calculating A, bi distance difference, excluding Bi reference lines with large distance difference (i.e. greater than a set threshold value)
S5.4: summing the lengths of the rest Bi reference lines, and considering that the Sum (Bi)/A ratio is completely consistent if the ratio is larger than an evaluation threshold; if the ratio is less than the evaluation threshold, the partial agreement is considered; if the ratio is less than the 100-evaluation threshold, it is considered to have changed.
S6: and (5) evaluating result processing.
And (3) processing the road center line in the basic mapping data according to the evaluation result of the step (S5), wherein the completely matched part is not processed, the partially matched part is repaired based on the image, and the changed center line is deleted.
S7: road section construction.
After the processing of the road center line in the basic mapping data is completed based on the evaluation result, the center line is used for matching and interpreting the road section center line, the road width is extracted to the basic mapping data center line, the buffer area construction is carried out according to one half of the road width, and the complement road section surface data is generated.
S8: and (5) processing the road junction.
And extracting road boundary nodes of the road part road surface based on the interpreted road surface, performing curve fitting, and connecting the road boundary nodes with the boundary of the complement road surface data generated in the step S7 in series to form complete road surface complement data, as shown in fig. 6.
Example 2:
as shown in fig. 7, embodiment 2 of the present invention provides a system for generating basic mapping road data based on remote sensing interpretation, which includes:
the road segment center line generation module is configured to: obtaining a road center line according to the obtained road interpretation vector surface, obtaining an intersection point of the intersecting center lines according to the road center line, breaking the road center line according to the intersection point, and taking the broken road center line as a road section center line;
a link width generation module configured to: constructing equal interval normals according to the road section central line, obtaining the road section surface width in the road interpretation vector surface, removing abnormal values, and assigning the abnormal values to the corresponding road section central line;
a base mapping road evaluation module configured to: based on the assigned center lines of all road sections, evaluating the road center line of the basic mapping road pavement, and processing the basic mapping road center line according to the evaluation result;
the complement road surface generation module is configured to: matching the processed basic mapping road center line with the assigned road section center line, extracting the road width to the basic mapping data center line, and constructing a buffer area according to one half of the road width to generate a complement road section surface corresponding to each road section;
an intersection correction module configured to: and extracting road boundary nodes of the road part road surface based on the road interpretation vector surface, performing curve fitting, and connecting the road boundary nodes with the boundary of the complement road surface corresponding to each road section in series to obtain complete road surface complement data.
In this embodiment, in the road section width generating module, an equidistant normal is configured according to a road section center line, to obtain a road section plane width in a road interpretation vector plane, and the road section plane width is assigned to a corresponding road section center line after an abnormal value is removed, including:
calculating the slope of the central line segment according to the positions of the interval nodes of the central line of the road;
extracting a normal line with the position length of the interval node as a set threshold value by taking the interval node as a center according to the slope of the central line segment;
calculating two intersection points of the obtained normal line and the road surface side line;
taking the length of the normal between two intersection points as the width of the interpreted vector surface road corresponding to the current interval node position;
and counting the width values of all the interval node positions, removing abnormal values with the variance of more than 2 times, calculating an average value to be used as the road width of the road section, and assigning the average value to the extracted road center line.
In this embodiment, the basic mapping road evaluation module evaluates the road center line of the basic mapping road surface based on the obtained road section center line, and includes:
finding a reference line of the intersection part with the buffer zone in the buffer range of the road center line of the basic mapping road pavement, wherein the obtained road center line is taken as the reference line;
calculating the angles between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the angles larger than a set threshold value;
calculating the distance between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the distance larger than a set threshold value;
acquiring the ratio of the length of the rest reference line to the length of the central line of the road of the basic mapping road after adding, and if the ratio is larger than an evaluation threshold value, considering that the ratio is completely consistent; if the ratio is less than the evaluation threshold, the partial agreement is considered; if the ratio is less than 100 and the evaluation threshold is different, the change is considered.
More specifically, the detailed operation of each module is the same as that provided in embodiment 1, and will not be repeated here.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The basic mapping road data generation method based on remote sensing interpretation is characterized by comprising the following steps of:
obtaining a road center line according to the obtained road interpretation vector surface, obtaining an intersection point of the intersecting center lines according to the road center line, breaking the road center line according to the intersection point, and taking the broken road center line as a road section center line;
constructing equal interval normals according to the road section central line, obtaining the road section surface width in the road interpretation vector surface, removing abnormal values, and assigning the abnormal values to the corresponding road section central line; comprising the following steps:
calculating the slope of the central line segment according to the positions of the interval nodes of the central line of the road;
extracting a normal line with the position length of the interval node as a set threshold value by taking the interval node as a center according to the slope of the central line segment;
calculating two intersection points of the obtained normal line and the road surface side line;
taking the length of the normal between two intersection points as the width of the interpreted vector surface road corresponding to the current interval node position;
counting the width values of all the interval node positions, removing abnormal values with more than 2 times of variance, calculating an average value as the road width of the road section, and assigning the average value to the extracted road center line;
based on the assigned center lines of all road sections, evaluating the road center line of the basic mapping road pavement, and processing the basic mapping road center line according to the evaluation result;
matching the processed basic mapping road center line with the assigned road section center line, extracting the road width to the basic mapping data center line, and constructing a buffer area according to one half of the road width to generate a complement road section surface corresponding to each road section;
and extracting road boundary nodes of the road part road surface based on the road interpretation vector surface, performing curve fitting, and connecting the road boundary nodes with the boundary of the complement road surface corresponding to each road section in series to obtain complete road surface complement data.
2. The method of claim 1, wherein the remote sensing interpretation based basic mapping road data generation method,
the obtained road interpretation vector surface comprises the following components:
and obtaining a road interpretation vector surface by using a remote sensing classification method based on deep learning by taking the aerial photography with set resolution or satellite remote sensing orthophoto as a data source.
3. The method for generating basic mapping road data based on remote sensing interpretation according to claim 1 or 2, characterized in that,
obtaining a road center line according to the obtained road interpretation vector surface, comprising:
and extracting a road center line by adopting a triangular segmentation algorithm according to the obtained road interpretation vector surface.
4. The method for generating basic survey road data based on remote sensing interpretation as claimed in claim 3,
extracting a road center line by adopting a triangle segmentation algorithm, comprising:
converting the road vector surface data into triangular grids by using a triangular segmentation algorithm, detecting all line segments intersecting with the vector surface edges in the triangular grids, and establishing a topological relation by using the relation between the detected edge line segments and the triangular edges;
and extracting a central line from the triangular mesh according to the topological relation and the geometric constraint condition, and carrying out smoothing treatment on the central line to obtain a final road central line.
5. The method of claim 1, wherein the remote sensing interpretation based basic mapping road data generation method,
based on the obtained road section center line, evaluating the road center line of the basic mapping road surface, comprising:
finding a reference line of the intersection part with the buffer zone in the buffer range of the road center line of the basic mapping road pavement, wherein the obtained road center line is taken as the reference line;
calculating the angles between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the angles larger than a set threshold value;
calculating the distance between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the distance larger than a set threshold value;
acquiring the ratio of the length of the rest reference line to the length of the central line of the road of the basic mapping road after adding, and if the ratio is larger than an evaluation threshold value, considering that the ratio is completely consistent; if the ratio is less than the evaluation threshold, the partial agreement is considered; if the ratio is less than 100 and the evaluation threshold is different, the change is considered.
6. The method of claim 5, wherein the remote sensing interpretation based basic mapping road data generation method,
processing the center line of the basic mapping road according to the evaluation result, including:
the completely matched basic mapping road center line is not processed, the partially matched basic mapping road center line is modified based on aerial images or satellite remote sensing orthographic images, and the changed basic mapping road center line is deleted.
7. A system for generating basic mapping road data based on remote sensing interpretation, comprising:
the road segment center line generation module is configured to: obtaining a road center line according to the obtained road interpretation vector surface, obtaining an intersection point of the intersecting center lines according to the road center line, breaking the road center line according to the intersection point, and taking the broken road center line as a road section center line;
a link width generation module configured to: constructing equal interval normals according to the road section central line, obtaining the road section surface width in the road interpretation vector surface, removing abnormal values, and assigning the abnormal values to the corresponding road section central line; comprising the following steps:
calculating the slope of the central line segment according to the positions of the interval nodes of the central line of the road;
extracting a normal line with the position length of the interval node as a set threshold value by taking the interval node as a center according to the slope of the central line segment;
calculating two intersection points of the obtained normal line and the road surface side line;
taking the length of the normal between two intersection points as the width of the interpreted vector surface road corresponding to the current interval node position;
counting the width values of all the interval node positions, removing abnormal values with more than 2 times of variance, calculating an average value as the road width of the road section, and assigning the average value to the extracted road center line;
a base mapping road evaluation module configured to: based on the assigned center lines of all road sections, evaluating the road center line of the basic mapping road pavement, and processing the basic mapping road center line according to the evaluation result;
the complement road surface generation module is configured to: matching the processed basic mapping road center line with the assigned road section center line, extracting the road width to the basic mapping data center line, and constructing a buffer area according to one half of the road width to generate a complement road section surface corresponding to each road section;
an intersection correction module configured to: and extracting road boundary nodes of the road part road surface based on the road interpretation vector surface, performing curve fitting, and connecting the road boundary nodes with the boundary of the complement road surface corresponding to each road section in series to obtain complete road surface complement data.
8. The remote sensing interpretation based underlying mapping road data generation system as claimed in claim 7,
constructing equal interval normals according to the road section central line to obtain the road section surface width in the road interpretation vector surface, and assigning the value to the corresponding road section central line after removing the abnormal value, comprising the following steps:
calculating the slope of the central line segment according to the positions of the interval nodes of the central line of the road;
extracting a normal line with the position length of the interval node as a set threshold value by taking the interval node as a center according to the slope of the central line segment;
calculating two intersection points of the obtained normal line and the road surface side line;
taking the length of the normal between two intersection points as the width of the interpreted vector surface road corresponding to the current interval node position;
and counting the width values of all the interval node positions, removing abnormal values with the variance of more than 2 times, calculating an average value to be used as the road width of the road section, and assigning the average value to the extracted road center line.
9. The remote sensing interpretation based underlying mapping road data generation system as claimed in claim 7,
based on the obtained road section center line, evaluating the road center line of the basic mapping road surface, comprising:
finding a reference line of the intersection part with the buffer zone in the buffer range of the road center line of the basic mapping road pavement, wherein the obtained road center line is taken as the reference line;
calculating the angles between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the angles larger than a set threshold value;
calculating the distance between the road center line of the basic mapping road pavement and each reference line, and removing the reference lines with the distance larger than a set threshold value;
acquiring the ratio of the length of the rest reference line to the length of the central line of the road of the basic mapping road after adding, and if the ratio is larger than an evaluation threshold value, considering that the ratio is completely consistent; if the ratio is less than the evaluation threshold, the partial agreement is considered; if the ratio is less than 100 and the evaluation threshold is different, the change is considered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664602.6A CN116385592B (en) | 2023-06-07 | 2023-06-07 | Basic mapping road data generation method and system based on remote sensing interpretation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310664602.6A CN116385592B (en) | 2023-06-07 | 2023-06-07 | Basic mapping road data generation method and system based on remote sensing interpretation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116385592A CN116385592A (en) | 2023-07-04 |
| CN116385592B true CN116385592B (en) | 2023-08-15 |
Family
ID=86963770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310664602.6A Active CN116385592B (en) | 2023-06-07 | 2023-06-07 | Basic mapping road data generation method and system based on remote sensing interpretation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116385592B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001084357A (en) * | 1999-09-14 | 2001-03-30 | Hitachi Ltd | Method for extracting road width data |
| JP2004246554A (en) * | 2003-02-13 | 2004-09-02 | Zenrin Co Ltd | Road data generation method |
| CN104050237A (en) * | 2014-05-23 | 2014-09-17 | 北京中交兴路信息科技有限公司 | Road surveying and mapping method and road surveying and mapping system |
| CN106528740A (en) * | 2016-11-04 | 2017-03-22 | 中科宇图科技股份有限公司 | Delaunay triangular net-based road center line extraction method |
| CN107145872A (en) * | 2017-05-12 | 2017-09-08 | 河海大学 | Desert Riparian Forest spatial distribution acquisition methods based on GIS buffer zone analysis |
| CN108830897A (en) * | 2018-06-11 | 2018-11-16 | 东南大学 | A kind of road axis extracting method |
| CN110543885A (en) * | 2019-08-13 | 2019-12-06 | 武汉大学 | method for interactively extracting high-resolution remote sensing image road and generating road network |
| CN110619258A (en) * | 2018-10-26 | 2019-12-27 | 国交空间信息技术（北京）有限公司 | Road track checking method based on high-resolution remote sensing image |
| CN111046768A (en) * | 2019-12-04 | 2020-04-21 | 武汉大学 | Deep learning method for simultaneously extracting road pavement and center line of remote sensing image |
| CN115855020A (en) * | 2022-11-24 | 2023-03-28 | 中国测绘科学研究院 | Road intersection extraction method based on center line |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101090925B1 (en) * | 2009-12-24 | 2011-12-08 | 금강수계관리위원회 | methodology of GIS based accurate centerline map drawing support system using digital maps for stream and road |
-
2023
- 2023-06-07 CN CN202310664602.6A patent/CN116385592B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001084357A (en) * | 1999-09-14 | 2001-03-30 | Hitachi Ltd | Method for extracting road width data |
| JP2004246554A (en) * | 2003-02-13 | 2004-09-02 | Zenrin Co Ltd | Road data generation method |
| CN104050237A (en) * | 2014-05-23 | 2014-09-17 | 北京中交兴路信息科技有限公司 | Road surveying and mapping method and road surveying and mapping system |
| CN106528740A (en) * | 2016-11-04 | 2017-03-22 | 中科宇图科技股份有限公司 | Delaunay triangular net-based road center line extraction method |
| CN107145872A (en) * | 2017-05-12 | 2017-09-08 | 河海大学 | Desert Riparian Forest spatial distribution acquisition methods based on GIS buffer zone analysis |
| CN108830897A (en) * | 2018-06-11 | 2018-11-16 | 东南大学 | A kind of road axis extracting method |
| CN110619258A (en) * | 2018-10-26 | 2019-12-27 | 国交空间信息技术（北京）有限公司 | Road track checking method based on high-resolution remote sensing image |
| CN110543885A (en) * | 2019-08-13 | 2019-12-06 | 武汉大学 | method for interactively extracting high-resolution remote sensing image road and generating road network |
| CN111046768A (en) * | 2019-12-04 | 2020-04-21 | 武汉大学 | Deep learning method for simultaneously extracting road pavement and center line of remote sensing image |
| CN115855020A (en) * | 2022-11-24 | 2023-03-28 | 中国测绘科学研究院 | Road intersection extraction method based on center line |
Non-Patent Citations (1)
| Title |
|---|
| Wei Yujun ; Hu Xiangyun ; Gong Jinqi.End-to-End Road Centerline Extraction via Learning a Confidence Map.2018 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS).2018,全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116385592A (en) | 2023-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110276732B (en) | Mountain area point cloud cavity repairing method considering topographic characteristic line elements | |
| CN108197583B (en) | Building change detection method based on graph cut optimization and image structure characteristics | |
| Hermosilla et al. | Using street based metrics to characterize urban typologies | |
| CN102147250B (en) | Digital line graph mapping method | |
| Sohn et al. | An implicit regularization for 3D building rooftop modeling using airborne lidar data | |
| CN112712596B (en) | Dense matching point cloud building structured model fine reconstruction method | |
| Yang et al. | A pattern‐based approach for matching nodes in heterogeneous urban road networks | |
| CN112733781B (en) | City functional area identification method combining POI data, storage medium and electronic equipment | |
| Kabolizade et al. | Design and implementation of an algorithm for automatic 3D reconstruction of building models using genetic algorithm | |
| CN111814597A (en) | Urban function partitioning method coupling multi-label classification network and YOLO | |
| US11663499B2 (en) | Method, data processing apparatus and computer program product for determining road intersections | |
| Yang et al. | A map‐algebra‐based method for automatic change detection and spatial data updating across multiple scales | |
| Hashemi | Automatic inference of road and pedestrian networks from spatial-temporal trajectories | |
| CN111209805B (en) | Rapid fusion optimization method for multi-channel segment data of lane line crowdsourcing data | |
| Sainju et al. | A hidden markov contour tree model for spatial structured prediction | |
| Aljumaily et al. | Voxel change: Big data–based change detection for aerial urban LiDAR of unequal densities | |
| Zhang et al. | Knowledge-based image analysis for 3D edge extraction and road reconstruction | |
| Jarzabek-Rychard | Reconstruction of building outlines in dense urban areas based on LiDAR data and address points | |
| CN116385592B (en) | Basic mapping road data generation method and system based on remote sensing interpretation | |
| Gösseln et al. | Change detection and integration of topographic updates from ATKIS to geoscientific data sets | |
| KR102156085B1 (en) | Method for forest area change detection and regional change of pervious/impervious map utilizing high-resolution drone image | |
| Ziems et al. | Multiple-model based verification of road data | |
| CN115861816A (en) | Three-dimensional low vortex identification method and device, storage medium and terminal | |
| Liu et al. | Road density analysis based on skeleton partitioning for road generalization | |
| CN112733782B (en) | Urban functional area identification method based on road network, storage medium and electronic equipment |
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 |