CN113408419A - Method for measuring and calculating building height by utilizing multi-feature fusion - Google Patents
Method for measuring and calculating building height by utilizing multi-feature fusion Download PDFInfo
- Publication number
- CN113408419A CN113408419A CN202110682573.7A CN202110682573A CN113408419A CN 113408419 A CN113408419 A CN 113408419A CN 202110682573 A CN202110682573 A CN 202110682573A CN 113408419 A CN113408419 A CN 113408419A
- Authority
- CN
- China
- Prior art keywords
- shadow
- building
- length
- height
- feature fusion
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000004927 fusion Effects 0.000 title claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 31
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 9
- 238000000605 extraction Methods 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000003595 spectral effect Effects 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method for measuring and calculating building height by utilizing multi-feature fusion, which aims at complex scenes to realize building shadow detection by utilizing multi-feature fusion, adopts a curvature scale space method to combine with an Euclidean distance formula to calculate shadow length, utilizes a multi-data source combined elevation model to correct shadow length, then, the height of the building is calculated by utilizing geometric calculation according to the length of the shadow of the building, the multi-feature fusion is carried out aiming at the complex scene to realize the detection of the shadow of the building, by statistically analyzing the spectrum and space characteristics of the building shadow in the remote sensing image and adopting a building shadow detection method combining the multi-characteristic component of the image with a rule-based object-oriented method, the invention integrates and utilizes multi-characteristic fusion to realize a building height measurement and calculation algorithm based on high-definition images under complex conditions, and finally improves the accuracy of building height measurement and calculation.
Description
Technical Field
The invention relates to the technical field of intelligent control, in particular to a method for measuring and calculating the height of a building by utilizing multi-feature fusion.
Background
The urban transition monitoring package expands two aspects of urban horizontal space and urban vertical space, the height of an urban building is not only one of important attribute information of the building, but also embodies the urban vertical space, and is also an important parameter for urban three-dimensional reconstruction, urban planning management, urban information research and the like, the data characteristic of the height of the building is found from image map data, the coverage and accuracy of the urban building data can be effectively improved by accurately measuring and calculating the height of the building, and the urban transition monitoring package has important significance for improving urban planning and commercial marketing;
the conventional method needs to consume a large amount of manpower and material resources, and is relatively low in efficiency, and the image interpretation method mostly adopts remote sensing images to complete information acquisition, so that the efficiency is high;
due to the fusion of artificial intelligence, big data, space remote sensing and multi-source heterogeneous data, the remote sensing technology is gradually applied to urban planning, and therefore, the utilization of remote sensing images to obtain the height information of urban buildings becomes one of important technical means.
Disclosure of Invention
The invention provides a method for measuring and calculating the height of a building by utilizing multi-feature fusion, which can effectively solve the problem that the remote sensing technology is gradually applied to urban planning due to the fusion of artificial intelligence, big data, space remote sensing and multi-source heterogeneous data in the background technology, so that the acquisition of urban building height information by utilizing remote sensing images becomes one of important technical means.
In order to achieve the purpose, the invention provides the following technical scheme: the method for measuring and calculating the height of the building by utilizing the multi-feature fusion is used for measuring and calculating the height of the building by utilizing the multi-feature fusion aiming at a complex scene, performing the multi-feature fusion to realize the shadow detection of the building, calculating the shadow length by adopting a curvature scale space method and combining an Euclidean distance formula, correcting the shadow length by utilizing a combination elevation model of multiple data sources, and then measuring and calculating the height of the building by utilizing geometric calculation according to the length of the shadow of the building;
aiming at a complex scene, carrying out multi-feature fusion to realize building shadow detection, carrying out statistical analysis on the spectral and spatial features of the building shadow in the remote sensing image, and adopting a building shadow detection method combining image multi-feature components with a rule-based object-oriented method;
the characteristic components are as follows in sequence: a principal component first component PC1, an HIS color space enhanced S component, a green light wave band G and a normalized vegetation index;
the method for constructing the multi-feature fusion based rule-oriented object classification method according to the analysis of the image mainly comprises the following steps:
s1, performing first principal component analysis on the image, distinguishing buildings, roads and vegetation land features by utilizing a PC1 component, and eliminating non-shadows, wherein the obtained shadow area still contains a small amount of vegetation;
s2, after HIS color space transformation is carried out on the image, the difference between the shadow and other ground features is enhanced by using the S component, the shadow area is compressed, and the shadow and darker ground features, such as a plastic playground, are effectively distinguished;
s3, removing large-area vegetation, roads and dark ground objects by using the difference of vegetation and shadows in a green wave band, wherein the vegetation and shadows overlap in the remaining shadow area;
s4, removing vegetation in the shadow coverage area by using the normalized vegetation index to achieve coarse extraction of shadow information;
s5, after the 4 types of feature components are subjected to wave band combination, the images are further segmented and merged, a shadow extraction rule set is constructed by combining the shadow features of the buildings, strip-type non-building shadows and vegetation shadows with areas close to the building shadows are removed, and finally a detection result with high precision is obtained.
According to the technical scheme, the shadow length is calculated by combining a curvature scale space method and an Euclidean distance formula;
firstly, calculating the corner points on the shadow edge outline by using a curvature scale space method (CSS);
then, calculating the shortest distance from each corner point in the shadow and the corner point set on the surface boundary to the building and the corner point set on the shadow boundary one by utilizing an Euclidean distance formula, selecting the corner point distance with the distance difference meeting a certain threshold range from the obtained distance set to carry out statistical averaging, taking the corner point distance as the shadow length perpendicular to the trend of the building, calculating the shadow length perpendicular to the trend of the building by utilizing a corner point nearest distance statistical averaging method, and converting the distance between two points into the average distance between multiple points;
the method comprises the following specific steps:
a1, extracting an edge from the original image, and extracting an edge contour from the edge image;
a2, calculating curvature by using the maximum scale, and judging candidate corner points by comparing the local maximum of curvature with a threshold and an adjacent minimum;
a3, tracking the corner points by using the minimum dimension to improve the positioning precision, comparing the curvature of the corner points with the detected corner points, and removing the corner points with very close curvature values;
and A4, carrying out statistical averaging on the distance sets of the candidate corner points, and taking the average value as the shadow length perpendicular to the trend of the building so as to reduce the calculation error of the shadow length to the maximum extent.
According to the technical scheme, the shadow length correction is carried out by utilizing the combination of multiple data sources and an elevation model, including the situation of a simple scene, the height measurement and calculation of the building are completed by utilizing simple geometric calculation, and the measured shadow length of the building is the slant distance because the actual bottom surface is in a non-horizontal state, and the corresponding correction processing needs to be carried out on the result.
According to the technical scheme, the simple scene is that the shape of the building is simple, and the ground shadow can be clearly obtained at the position.
According to the technical scheme, the calculation of the height of the building with the complex scene can use the combination of multiple data sources, and a local DEM elevation model is utilized to determine the elevations of the bottom surface of the building and the end points of the shadow characteristic lines, so that the detected shadow length can be corrected conveniently.
According to the technical scheme, the height of the building is measured and calculated by utilizing geometric calculation according to the length of the shadow of the building;
the method is specifically divided into two types:
1) the sun and the satellite are positioned on different sides;
2) the sun and the satellite are positioned at the same side;
these two cases will be described below.
When the sun and the satellite are positioned on different sides, the difference between the azimuth angle of the sun and the azimuth angle of the satellite is more than 180 degrees, at the moment, the satellite can observe all shadow areas of the building, and at the moment, the shadow and the height of the building are in the following relationship:
H＝L×tan(ω)
wherein H is the building height, L is the shadow length, and omega is the solar altitude;
using the known building height, a series of K's are calculatediCalculating the height of the building by taking the average value of K as tan (omega);
when the sun and the satellite are positioned at the same side, namely the difference between the satellite azimuth angle and the sun azimuth angle is 0-180 degrees, the relationship between the building height and the length of the visible shadow is as follows:
wherein H is the building height, L2Is the length of the visible shadow of the satellite, omega is the solar altitude, beta is the solar azimuth, alpha is the satellite azimuth,
Is a building azimuth.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps that a target ground object shadow in a remote sensing image has a specific geometric relationship with the altitude angles and the azimuth angles of the sun and the satellite and the azimuth angle of the target ground object, the height information of the ground object can be calculated by analyzing the functional relationship among the target ground object shadow, specifically, under the condition of aiming at a complex scene, multi-feature fusion is firstly carried out to realize building shadow detection, then, a curvature scale space method is adopted to be combined with an Euclidean distance formula to carry out shadow length calculation, then, a multi-data source combined elevation model is utilized to correct the shadow length, and then, the geometric calculation is utilized to realize building height measurement and calculation according to the length of the building shadow.
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 process steps of the present invention;
FIG. 2 is a schematic view of the invention with the elevation of the bottom of the building being less than the elevation of the shadow;
FIG. 3 is a schematic representation of the geometric relationship between solar and satellite parameters and building shadows according to the present invention;
FIG. 4 is a schematic of the geometric relationship between building shading, building height and solar parameters of the present invention;
FIG. 5 is a schematic of the geometric relationship between the solar and satellite parameters of the present invention and building shadows.
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, the present invention provides a technical solution, a method for building height measurement and calculation by using multi-feature fusion, for complex scenes, performing multi-feature fusion to realize building shadow detection, performing shadow length calculation by using a curvature scale space method in combination with an euclidean distance formula, performing shadow length correction by using a multi-data source in combination with an elevation model, and then performing building height measurement and calculation by using geometric calculation according to the length of building shadows;
aiming at a complex scene, performing multi-feature fusion to realize building shadow detection, analyzing the spectrum and space features of the building shadow in the remote sensing image through statistics, and adopting a building shadow detection method combining image multi-feature components with a rule-based object-oriented method;
the characteristic components are as follows in sequence: a principal component first component PC1, an HIS color space enhanced S component, a green light wave band G and a normalized vegetation index;
the method for constructing the multi-feature fusion based rule-oriented object classification method according to the analysis of the image mainly comprises the following steps:
s1, performing first principal component analysis on the image, distinguishing buildings, roads and vegetation land features by utilizing a PC1 component, and eliminating non-shadows, wherein the obtained shadow area still contains a small amount of vegetation;
s2, after HIS color space transformation is carried out on the image, the difference between the shadow and other ground features is enhanced by using the S component, the shadow area is compressed, and the shadow and darker ground features, such as a plastic playground, are effectively distinguished;
s3, removing large-area vegetation, roads and dark ground objects by using the difference of vegetation and shadows in a green wave band, wherein the vegetation and shadows overlap in the remaining shadow area;
s4, removing vegetation in the shadow coverage area by using the normalized vegetation index to achieve coarse extraction of shadow information;
s5, after the 4 types of feature components are subjected to wave band combination, the images are further segmented and merged, a shadow extraction rule set is constructed by combining the shadow features of the buildings, strip-type non-building shadows and vegetation shadows with areas close to the building shadows are removed, and finally a detection result with high precision is obtained.
According to the technical scheme, a curvature scale space method is combined with an Euclidean distance formula to calculate the shadow length;
firstly, calculating the corner points on the shadow edge outline by using a curvature scale space method (CSS);
then, calculating the shortest distance from each corner point in the shadow and the corner point set on the surface boundary to the building and the corner point set on the shadow boundary one by utilizing an Euclidean distance formula, selecting the corner point distance with the distance difference meeting a certain threshold range from the obtained distance set to carry out statistical averaging, taking the corner point distance as the shadow length perpendicular to the trend of the building, calculating the shadow length perpendicular to the trend of the building by utilizing a corner point nearest distance statistical averaging method, and converting the distance between two points into the average distance between multiple points;
the method comprises the following specific steps:
a1, extracting an edge from the original image, and extracting an edge contour from the edge image;
a2, calculating curvature by using the maximum scale, and judging candidate corner points by comparing the local maximum of curvature with a threshold and an adjacent minimum;
a3, tracking the corner points by using the minimum dimension to improve the positioning precision, comparing the curvature of the corner points with the detected corner points, and removing the corner points with very close curvature values;
and A4, carrying out statistical averaging on the distance sets of the candidate corner points, and taking the average value as the shadow length perpendicular to the trend of the building so as to reduce the calculation error of the shadow length to the maximum extent.
According to the technical scheme, shadow length correction is carried out by utilizing a combined elevation model of multiple data sources, including the situation of a simple scene, height measurement and calculation of a building are completed by utilizing simple geometric calculation, and the measured shadow length of the building is the slant distance because the actual bottom surface is in a non-horizontal state, and corresponding correction processing needs to be carried out on the result.
According to the technical scheme, the simple scene is that the shape of the building is simple, and the ground shadow can be clearly obtained at the position.
According to the technical scheme, the calculation of the height of the building with the complex scene can use the combination of multiple data sources, and a local DEM elevation model is utilized to determine the elevation of the bottom surface of the building and the elevation of the end point of the shadow characteristic line, so that the detected shadow length can be corrected conveniently.
According to the technical scheme, the height of the building is measured and calculated by utilizing geometric calculation according to the length of the shadow of the building;
as shown in figure 2 of the drawings, in which,
1. the elevation of the bottom surface of the building is smaller than that of the shadow:
when the satellite and the sun are positioned on different sides, the shadow and the height of the building are independent of the satellite parameters, and the geometric relationship between the sun parameters and the building information is shown in the following chart:
in the figure: BD is the total shadow length, BC is the detectable shadow length in the image, AB is the actual shadow length, BE is the building height H, ω is the solar altitude, the elevation at point B is H, i.e., the building floor elevation, and the elevation at shadow line end point D is H1, i.e., DC.
The corrected actual shadow length AB is:
as shown in fig. 3, when the sun and satellite azimuth angles are between 0 ° and 180 °, in the figure: BD is the shadow length detected in the image, and AC is the actual shadow length. Omega is the solar altitude, theta is the satellite altitude, the elevation of the E point is h, namely the elevation of the bottom surface of the building, the elevations of H, G points at two ends of the shadow line are h1 and h2 respectively, and are respectively expressed as HD and GB.
The corrected actual shadow length AC is:
as shown in figure 4 of the drawings,
the elevation of the bottom surface of the building is larger than that of the surface where the shadow is positioned
When the satellite and the sun are positioned on different sides, the satellite parameters are irrelevant to the detection result.
In the figure: BD is the shadow length detected in the image, and CD is the actual shadow length. Omega is the solar altitude, the altitude of the point D is h, namely the altitude of the bottom surface of the building, and the altitude of the shadow line endpoint B is h 1.
The corrected actual shadow length BC is:
as shown in fig. 5, when the sun and satellite azimuth angles are between 0 ° and 180 °, in the figure: AC is the shadow length detected in the image, and BD is the actual shadow length. Omega is the solar altitude, theta is the satellite altitude, the elevation of the F point is h, namely the elevation of the bottom surface of the building, and the elevations of two end points G, H of the shadow line are h1 and h2 respectively.
The corrected actual shadow length BD is:
the method is specifically divided into two types:
1) the sun and the satellite are positioned on different sides;
2) the sun and the satellite are positioned at the same side;
these two cases will be described below.
When the sun and the satellite are positioned on different sides, the difference between the azimuth angle of the sun and the azimuth angle of the satellite is more than 180 degrees, at the moment, the satellite can observe all shadow areas of the building, and at the moment, the shadow and the height of the building are in the following relationship:
H＝L×tan(ω)
wherein H is the building height, L is the shadow length, and omega is the solar altitude;
using the known building height, a series of K's are calculatediCalculating the height of the building by taking the average value of K as tan (omega);
when the sun and the satellite are positioned at the same side, namely the difference between the satellite azimuth angle and the sun azimuth angle is 0-180 degrees, the relationship between the building height and the length of the visible shadow is as follows:
wherein H is the building height, L2Is the length of the visible shadow of the satellite, omega is the solar altitude, beta is the solar azimuth, alpha is the satellite azimuth,
Is a building azimuth.
Compared with the prior art, the invention has the beneficial effects that: the method comprises the steps that a target ground object shadow in a remote sensing image has a specific geometric relationship with the altitude angles and the azimuth angles of the sun and the satellite and the azimuth angle of the target ground object, the height information of the ground object can be calculated by analyzing the functional relationship among the target ground object shadow, specifically, under the condition of aiming at a complex scene, multi-feature fusion is firstly carried out to realize building shadow detection, then, a curvature scale space method is adopted to be combined with an Euclidean distance formula to carry out shadow length calculation, then, a multi-data source combined elevation model is utilized to correct the shadow length, and then, the geometric calculation is utilized to realize building height measurement and calculation according to the length of the building shadow.
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 (6)
1. The method for measuring and calculating the height of the building by utilizing multi-feature fusion is characterized by comprising the following steps of: aiming at a complex scene, performing multi-feature fusion to realize building shadow detection, performing shadow length calculation by combining a curvature scale space method and an Euclidean distance formula, performing shadow length correction by using a combination elevation model of multiple data sources, and then performing geometric calculation according to the length of the building shadow to realize building height measurement and calculation;
aiming at a complex scene, carrying out multi-feature fusion to realize building shadow detection, carrying out statistical analysis on the spectral and spatial features of the building shadow in the remote sensing image, and adopting a building shadow detection method combining image multi-feature components with a rule-based object-oriented method;
the characteristic components are as follows in sequence: a principal component first component PC1, an HIS color space enhanced S component, a green light wave band G and a normalized vegetation index;
the method for constructing the multi-feature fusion based rule-oriented object classification method according to the analysis of the image mainly comprises the following steps:
s1, performing first principal component analysis on the image, distinguishing buildings, roads and vegetation land features by utilizing a PC1 component, and eliminating non-shadows, wherein the obtained shadow area still contains a small amount of vegetation;
s2, after HIS color space transformation is carried out on the image, the difference between the shadow and other ground features is enhanced by using the S component, the shadow area is compressed, and the shadow and darker ground features, such as a plastic playground, are effectively distinguished;
s3, removing large-area vegetation, roads and dark ground objects by using the difference of vegetation and shadows in a green wave band, wherein the vegetation and shadows overlap in the remaining shadow area;
s4, removing vegetation in the shadow coverage area by using the normalized vegetation index to achieve coarse extraction of shadow information;
s5, after the 4 types of feature components are subjected to wave band combination, the images are further segmented and merged, a shadow extraction rule set is constructed by combining the shadow features of the buildings, strip-type non-building shadows and vegetation shadows with areas close to the building shadows are removed, and finally a detection result with high precision is obtained.
2. The method for building height estimation by multi-feature fusion according to claim 1, wherein the shadow length calculation is performed by combining a curvature scale space method with an Euclidean distance formula;
firstly, calculating the corner points on the shadow edge outline by using a curvature scale space method (CSS);
then, calculating the shortest distance from each corner point in the shadow and the corner point set on the surface boundary to the building and the corner point set on the shadow boundary one by utilizing an Euclidean distance formula, selecting the corner point distance with the distance difference meeting a certain threshold range from the obtained distance set to carry out statistical averaging, taking the corner point distance as the shadow length perpendicular to the trend of the building, calculating the shadow length perpendicular to the trend of the building by utilizing a corner point nearest distance statistical averaging method, and converting the distance between two points into the average distance between multiple points;
the method comprises the following specific steps:
a1, extracting an edge from the original image, and extracting an edge contour from the edge image;
a2, calculating curvature by using the maximum scale, and judging candidate corner points by comparing the local maximum of curvature with a threshold and an adjacent minimum;
a3, tracking the corner points by using the minimum dimension to improve the positioning precision, comparing the curvature of the corner points with the detected corner points, and removing the corner points with very close curvature values;
and A4, carrying out statistical averaging on the distance sets of the candidate corner points, and taking the average value as the shadow length perpendicular to the trend of the building so as to reduce the calculation error of the shadow length to the maximum extent.
3. The method for building height estimation using multi-feature fusion as claimed in claim 1, wherein the shadow length correction using the combined elevation model with multiple data sources, including the case of simple scenario, is performed by using simple geometric calculation, and since the actual bottom surface is not horizontal, the measured shadow length of the building is the slant distance, and the corresponding correction processing is required.
4. The method for building height estimation using multi-feature fusion as claimed in claim 3, wherein the simple scene is a simple shape of the building, and the ground shadow can be clearly obtained at the position.
5. The method for building height estimation using multi-feature fusion as claimed in claim 4, wherein the building height calculation for complex scene can use a combination of multiple data sources to determine the elevation of the building floor and the shadow feature line endpoint using local DEM elevation model to facilitate correction of the detected shadow length.
6. The method for building height estimation by multi-feature fusion according to claim 1, wherein the building height estimation is realized by geometric calculation according to the length of the building shadow;
the method is specifically divided into two types:
1) the sun and the satellite are positioned on different sides;
2) the sun and the satellite are positioned at the same side;
these two cases are explained below separately:
when the sun and the satellite are positioned on different sides, the difference between the azimuth angle of the sun and the azimuth angle of the satellite is more than 180 degrees, at the moment, the satellite can observe all shadow areas of the building, and at the moment, the shadow and the height of the building are in the following relationship:
H＝L×tan(ω)
wherein H is the building height, L is the shadow length, and omega is the solar altitude;
using the known building height, a series of K's are calculatediCalculating the height of the building by taking the average value of K as tan (omega);
when the sun and the satellite are positioned at the same side, namely the difference between the satellite azimuth angle and the sun azimuth angle is 0-180 degrees, the relationship between the building height and the length of the visible shadow is as follows:
wherein H is the building height, L2Is the length of the visible shadow of the satellite, omega is the solar altitude, beta is the solar azimuth, alpha is the satellite azimuth,
Is a building azimuth.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110682573.7A CN113408419A (en) | 2021-06-18 | 2021-06-18 | Method for measuring and calculating building height by utilizing multi-feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110682573.7A CN113408419A (en) | 2021-06-18 | 2021-06-18 | Method for measuring and calculating building height by utilizing multi-feature fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113408419A true CN113408419A (en) | 2021-09-17 |
Family
ID=77681700
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110682573.7A Pending CN113408419A (en) | 2021-06-18 | 2021-06-18 | Method for measuring and calculating building height by utilizing multi-feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113408419A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679441A (en) * | 2017-02-14 | 2018-02-09 | 郑州大学 | Method based on multi-temporal remote sensing image shadow extraction City Building height |
-
2021
- 2021-06-18 CN CN202110682573.7A patent/CN113408419A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107679441A (en) * | 2017-02-14 | 2018-02-09 | 郑州大学 | Method based on multi-temporal remote sensing image shadow extraction City Building height |
Non-Patent Citations (2)
| Title |
|---|
| 王永刚等: "利用角点最近距离统计平均法计算建筑物阴影长度", 《国土资源遥感》, no. 3, pages 33 - 36 * |
| 陈冲: "基于高分影像阴影的多场景建筑物高度反演研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》, no. 1, pages 2 - 4 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109416413B (en) | Solar energy forecast | |
| US11995886B2 (en) | Large-scale environment-modeling with geometric optimization | |
| CN108197583B (en) | Building change detection method based on graph cut optimization and image structure characteristics | |
| CN111047695B (en) | Method for extracting height spatial information and contour line of urban group | |
| CN107610164B (en) | High-resolution four-number image registration method based on multi-feature mixing | |
| CN107895376A (en) | Based on the solar panel recognition methods for improving Canny operators and contour area threshold value | |
| CN108596103A (en) | High resolution ratio satellite remote-sensing image building extracting method based on optimal spectrum Index selection | |
| CN102622738B (en) | Method for recovering spectral information of hill shade area of Landsat thematic mapper/enhanced thematic mapper plus (TM/ETM+) image | |
| CN104751478A (en) | Object-oriented building change detection method based on multi-feature fusion | |
| CN111062991A (en) | Method and device for positioning inspection target of photovoltaic scene and readable storage medium | |
| CN106294705A (en) | A kind of batch remote sensing image preprocess method | |
| CN101980294A (en) | Remote sensing image-based method for detecting ice flood of Yellow River | |
| Dai et al. | Road extraction from high-resolution satellite images based on multiple descriptors | |
| WO2024109419A1 (en) | Elevation information-fused processing method for remote sensing images | |
| CN103871072A (en) | Method for automatic extraction of orthoimage embedding line based on projection digital elevation models | |
| CN114549998A (en) | Satellite image-based anti-interference evaluation method for photovoltaic potential of roof | |
| CN113409332B (en) | Building plane segmentation method based on three-dimensional point cloud | |
| CN114639023A (en) | Roof photovoltaic potential evaluation method based on machine learning | |
| CN113724400A (en) | Oblique photography-oriented multi-attribute fusion building point cloud extraction method | |
| CN112561981A (en) | Photogrammetry point cloud filtering method fusing image information | |
| CN110276270B (en) | High-resolution remote sensing image building area extraction method | |
| CN115294482B (en) | Edible fungus yield estimation method based on unmanned aerial vehicle remote sensing image | |
| CN113408419A (en) | Method for measuring and calculating building height by utilizing multi-feature fusion | |
| CN116468873A (en) | Building model reconstruction method based on airborne TomoSAR point cloud | |
| CN114596490A (en) | Hilly land feature line extraction method and hilly land DEM (digital elevation model) fine production method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |