CN117333530B - Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building - Google Patents
Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building Download PDFInfo
- Publication number
- CN117333530B CN117333530B CN202311633878.4A CN202311633878A CN117333530B CN 117333530 B CN117333530 B CN 117333530B CN 202311633878 A CN202311633878 A CN 202311633878A CN 117333530 B CN117333530 B CN 117333530B
- Authority
- CN
- China
- Prior art keywords
- building
- area
- tibetan
- traditional
- image
- 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
- 238000004220 aggregation Methods 0.000 title claims abstract description 49
- 230000002776 aggregation Effects 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000004445 quantitative analysis Methods 0.000 title claims abstract description 21
- 238000007635 classification algorithm Methods 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 20
- 239000000178 monomer Substances 0.000 claims description 18
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000011160 research Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 239000004576 sand Substances 0.000 claims description 4
- 238000013179 statistical model Methods 0.000 claims description 4
- 238000000137 annealing Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 claims description 3
- 230000000873 masking effect Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- 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
-
- 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
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a quantitative analysis method for a change trend of a Tibetan Qiang traditional aggregation building, which comprises the following steps: s1, acquiring a high-resolution SAR image of a Tibetan-Qiang traditional aggregation building, and extracting the image of the Tibetan-Qiang traditional aggregation building by using an SAR image classification algorithm of an improved MRF model to obtain a building image; s2, extracting geometric information of the building according to the building image to obtain accurate geometric information of the building; s3, setting an observation time period, obtaining accurate geometric information of the building in the traditional building of the Tibetan Qiang in the observation time period, and completing quantitative analysis of the change trend of the traditional building of the Tibetan Qiang.
Description
Technical Field
The invention relates to the field of quantitative analysis of digital images, in particular to a quantitative analysis method for a change trend of a Tibetan Qiang traditional aggregation building.
Background
The Tibetan Qiang traditional colony is an "active state" colony which is formed in a history period along with the continuous evolution of time and has historic continuity and vitality so far. It has a long and deep historical cultural background, a clustered form according to local conditions and an ancient and unique building style. Especially, the unique time diversity is presented in the aspect of building landscape, so that the original landscape is fully precious, and the method becomes a precious resource for researching and protecting regional landscape.
In the existing research, the qualitative research on the traditional aggregation building is rich, and the quantitative research is less. Macroscopic level building research is still a typed study of building in large areas of geography, building type, historic years. Quantitative studies of microscopic level aggregate building details are limited to studies of architectural aesthetic arts, structures, construction skills, materials, etc. in single or multiple villages. Building trend research is performed in a certain area in the absence of mesoscale.
The traditional aggregation development planning needs accurate and scientific guidance, three-dimensional information reflecting building features is accurately quantized and extracted, quantitative comparison analysis is carried out by utilizing high-resolution images in different time periods, aggregation building change trend in a selected area range can be obtained, and analysis results are visually presented. A set of method for providing scientific basis for planning decision based on data analysis and discrimination is formed.
Disclosure of Invention
Aiming at the defects in the prior art, the quantitative analysis method for the change trend of the Tibetan Notopterygium traditional aggregation building solves the problems that the prior art cannot quantitatively analyze building characteristics and lacks research on the change trend of the aggregation building.
In order to achieve the aim of the invention, the invention adopts the following technical scheme: a quantitative analysis method for the change trend of Tibetan Qiang traditional aggregation building comprises the following steps:
s1, acquiring a high-resolution SAR image of a Tibetan-Qiang traditional aggregation building, and extracting the image of the Tibetan-Qiang traditional aggregation building by using an SAR image classification algorithm of an improved MRF model to obtain a building image;
s2, extracting geometric information of the building according to the building image to obtain accurate geometric information of the building;
s3, setting an observation time period, and obtaining accurate geometric information of the building in the traditional building with the built-in Notopterygium in the observation time period, so as to finish quantitative analysis of the change trend of the traditional building with the built-in Notopterygium.
Further: the step S1 comprises the following sub-steps:
s11, acquiring a high-resolution SAR image of a Tibetan Notopterygium traditional aggregation building, and extracting the building by using an SAR image classification algorithm of an improved MRF model to obtain an initial building image;
s12, dividing a communication area with the same characteristics in the initial building image by using an area-based growth algorithm to obtain a separated building image;
s13, removing overlapping mask and shadow areas which do not belong to the building from the separated building image by adopting an object-oriented method based on shape characteristics, and obtaining the building image.
Further: the step S11 comprises the following sub-steps:
s111, acquiring a high-resolution SAR image of a Tibetan Notopterygium traditional aggregation building;
s112, dividing the high-resolution SAR image into three region types and marking;
the three zone types include a building zone, a shadow zone, and a background zone;
s113, respectively describing three region types by using a fisher distribution, estimating distribution parameters of the three region types by using a parameter estimation method based on Mellin transformation, and establishing a SAR image statistical model according to step parameters to interpret the marked SAR image;
s114, performing pixel-level classification on the interpreted SAR image by using an improved MRF model;
s115, utilizing an object-oriented method based on shape characteristics, distinguishing a building from a non-building from the SAR image after pixel-level classification according to the rule that overlapping and masking areas and shadow areas of the building appear in pairs, and extracting pixels classified into the building to obtain an initial building image.
Further: the step S2 comprises the following sub-steps:
s21, directly measuring the overlay mask and the shadow in the SAR image of the building according to the three-dimensional information features of the building contained in the overlay mask and the shadow formed in the imaging of the SAR image of the building, and obtaining a geometric model of the building according to a measurement result;
s22, determining shadows and overlay positions of the buildings in the geometric model through geometric mapping relations;
s23, describing the characteristics of the landing building through a matching degree function;
s24, optimizing a matching degree function through a simulated genetic annealing algorithm, and obtaining accurate building length, width and height information as accurate geometric information of a building when the matching degree function is increased and reaches a stable value.
Further: in the step S21, when the width of the building is greater than or equal to the height of the building, the shadow area, part of the roof scattering area and the overlap area of the building are all displayed in the SAR image, thereby obtaining the height of the buildingHAnd width ofWThe formula of (2) is:
wherein,W shadow AndW fold and mask Respectively represent the width of the shadow area and the overlap area of the building,θrepresenting radar incidence angle during SAR flight.
Further: in the step S21, when the width of the building is smaller than the height of the building, the building sequentially forms a covering area and a shadow area in the SAR image to obtain the height of the buildingHAnd width ofWThe formula of (2) is:
。
further: in S23, the formula of the matching degree function is:
wherein,Mis a geometric model of a building and is a model of the building,k 0 andk s matching weights of the overlay mask boundary and the shadow boundary respectively represent morphological expansion of the overlay mask boundary and the shadow boundary;ffor overlay and shadow boundary pictures after morphological dilation,C 0 a set of pixels of the resulting overlay mask boundary is mapped for the model,N（C 0 ) For the total number of pixels in the overlay mask boundary,C s a set of pixels of the resulting shadow boundary mapped for the model,N（C s ) Is the total number of pixels in the shadow boundary。
Further: the change trend of the Tibetan Notoptera traditional aggregation building in the S3 comprises a building monomer change trend and an aggregation building group change trend;
the building monomers comprise civil house buildings with the geometric shapes of 'field', 'sun', temple and official village buildings with the geometric shapes of 'mouth', 'L', and pillbox buildings with the geometric shapes of 'four corners', 'regular pentagon', 'regular octagon';
the aggregate building group comprises a plurality of regular building monomers with different sizes.
Further: the indexes of the change trend of the reaction building monomer are building geometric information and building area;
wherein, for the civil house building with the geometric form of 'field', 'sun', the temple with the geometric form of 'mouth', 'L', and the official village building, the building single area comprises the ground area, the wall elevation area and the roof area of the building, the area calculation formula is:
wherein,S civil house, official village and temple For the total area of a single residential building with a geometry of 'field', 'day' and a temple or a official village building with a geometry of 'mouth', 'L' in a certain research period,S 1 is the ground area of the building;S 2 the area of the vertical face of the building wall is measured;S 3 for the measured building roof area;
for the pillbox building with the geometric form of four corners, regular pentagons and regular octagons, the building area comprises the ground area, the wall elevation area and the roof area of the building, wherein the ground area and the roof area are split into regular rectangles, regular pentagons and regular octagons for calculation, the wall elevation area is split into the regular rectangles for calculation, and the calculation formula is as follows:
wherein,for the area of individual pillbox buildings within a study period,S 1,3 regular pentagon Is the area of a regular pentagon divided into the ground area and the roof area,S 1,3 regular octagon Is the area of a regular octagon divided by the ground area and the roof area,ais a regular pentagon with a side length,bthe side length of the regular octagon;
the area change trend of the building monomer is quantified by using the building change rate, and the calculation formula of the building change rate is as follows:
wherein,Kfor a rate of change of the area of a single building aggregate over a study period,U a andU b the area of the building at the beginning and end of the study period respectively,Tfor the study period.
Further: the variation trend of the aggregation building group is reflected by the compact trend of the building group area, the geometric shape of the building group and the distribution rule;
the compact trend of the aggregate building group and the building group geometry are reflected by a shape index, the shape index being calculated by the formula:
wherein,C n is the first to gathernThe length of the boundary of each building unit,S n is the first to gathernThe planar area of the individual building elements,nfor the quantity of building monomers in a building group,representing the average shape of the traditional building group of Tibet Qiang at a certain periodA shape index;
the distribution rule of the aggregation building group is based on the length-width ratio of the aggregation building groupTTo react, the calculation formula of the length-width ratio is as follows:
wherein,AandBthe long side and the short side of the smallest external rectangle of the building group are respectively formed.
Drawings
Fig. 1 is a flow chart of a quantitative analysis method of the change trend of the Tibetan qiang traditional aggregation building.
FIG. 2 is a schematic illustration of height and width calculations for a building having a width greater than or equal to its height.
FIG. 3 is a schematic illustration of height and width calculations for a building having a width less than or equal to its height.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and all the inventions which make use of the inventive concept are protected by the spirit and scope of the present invention as defined and defined in the appended claims to those skilled in the art.
As shown in fig. 1, in one embodiment of the present invention, a quantitative analysis method for a change trend of a Tibetan qiang traditional aggregation building is provided, which includes the following steps:
s1, acquiring a high-resolution SAR image of a Tibetan-Qiang traditional aggregation building, and extracting the image of the Tibetan-Qiang traditional aggregation building by using an SAR image classification algorithm of an improved MRF model to obtain a building image;
s2, extracting geometric information of the building according to the building image to obtain accurate geometric information of the building;
s3, setting an observation time period, and obtaining accurate geometric information of the building in the traditional building with the built-in Notopterygium in the observation time period, so as to finish quantitative analysis of the change trend of the traditional building with the built-in Notopterygium.
In one embodiment of the invention, the step S1 comprises the following substeps:
s11, acquiring a high-resolution SAR image of a Tibetan Notopterygium traditional aggregation building, and extracting the building by using an SAR image classification algorithm of an improved MRF model to obtain an initial building image;
s12, dividing a communication area with the same characteristics in the initial building image by using an area-based growth algorithm to obtain a separated building image;
s13, removing overlapping mask and shadow areas which do not belong to the building from the separated building image by adopting an object-oriented method based on shape characteristics, and obtaining the building image.
In one embodiment of the present invention, the step S11 includes the following substeps:
s111, acquiring a high-resolution SAR image of a Tibetan Notopterygium traditional aggregation building;
s112, dividing the high-resolution SAR image into three region types and marking;
the three zone types include a building zone, a shadow zone, and a background zone;
s113, respectively describing three region types by using a fisher distribution, estimating distribution parameters of the three region types by using a parameter estimation method based on Mellin transformation, and establishing a SAR image statistical model according to step parameters to interpret the marked SAR image;
wherein, the formula of the probability distribution density function of Fisher distribution is:
wherein,P fisher a probability distribution density function representing a Fisher distribution,uas a result of the random variable,LandMas a function of the shape parameter(s),μin order to be a weight parameter,is a Gamma function;
s114, performing pixel-level classification on the interpreted SAR image by using an improved MRF model;
in this embodiment, for defining a SAR image in two dimensions, it is considered as a two-dimensional random field, and according to parameters of the SAR image statistical model, these parameters include the relationships between the categories of building and non-building pixels and the neighboring pixels;
each pixel is allocated to a building or non-building category, a label corresponding to each pixel point of the SAR image forms a marking field, the label field is estimated by using a maximum posterior probability estimation algorithm according to a given observation SAR image and a gray value parameter corresponding to the given observation SAR image at a two-dimensional grid, and the posterior probability reaches the maximum value to determine the most suitable category;
the formula of the maximum posterior probability estimation algorithm is as follows:
wherein,Yin order to mark the field of view,P（Y |X）at a given marking fieldYLower observation imageXConditional probability of (2). The purpose of image classification is to estimate the marker field given the observed image XYTo make posterior probabilityP（Y |X）Reaching a maximum value;
the improved MRF model is represented using a random distribution of Gibbs fields, the formula of which is:
wherein,Zfor the normalization constant(s),Uas a function of the energy,U（y|x) The energy term is the sum of the likelihood energy term and the prior energy term of the neighborhood system;for likelihood energy term +.>Priori energy terms for the neighborhood system;
the prior energy term potential function formula is:
Cfor a set of neighborhood system groups,βis a classification parameter representing the influence of a neighborhood group on a pixel label;sandtpixel points in the same group;dandx s -x t is a pixel pointsAndtthe distance between them and the gray level difference,a c as a weight coefficient, inversely proportional to the distance of pixels in the neighborhood group and the gray level difference;
s115, utilizing an object-oriented method based on shape characteristics, distinguishing a building from a non-building from the SAR image after pixel-level classification according to the rule that overlapping and masking areas and shadow areas of the building appear in pairs, and extracting pixels classified into the building to obtain an initial building image.
In one embodiment of the invention, the step S2 comprises the following substeps:
s21, directly measuring the overlay mask and the shadow in the SAR image of the building according to the three-dimensional information features of the building contained in the overlay mask and the shadow formed in the imaging of the SAR image of the building, and obtaining a geometric model of the building according to a measurement result;
s22, determining shadows and overlay positions of the buildings in the geometric model through geometric mapping relations;
s23, describing the characteristics of the landing building through a matching degree function;
the matching degree function obtains the matching condition of the overlay mask and shadow positions obtained by mapping the geometric information of the aggregation building and the overlay mask and shadow positions actually detected, and the geometric information extraction problem is converted into the optimization problem of the matching degree function;
s24, optimizing a matching degree function through a simulated genetic annealing algorithm, and obtaining accurate building length, width and height information as accurate geometric information of a building when the matching degree function is increased and reaches a stable value.
In one embodiment of the present invention, as shown in fig. 2, in S21, when the width of the building is greater than or equal to the height thereof, the shadow area, part of the roof scattering area and the overlap area of the building are all presented in the SAR image, thereby obtaining the height of the buildingHAnd width ofWThe formula of (2) is:
wherein,W shadow AndW fold and mask Respectively represent the width of the shadow area and the overlap area of the building,θrepresenting radar incidence angle during SAR flight.
As shown in fig. 3, in one embodiment of the present invention, in S21, when the width of the building is smaller than the height thereof, the building sequentially forms a covering area and a shadow area in the SAR image to obtain the height of the buildingHAnd width ofWThe formula of (2) is:
。
in one embodiment of the present invention, in S23, the formula of the matching degree function is:
wherein,Mis a geometric model of a building and is a model of the building,k 0 andk s matching weights of the overlay mask boundary and the shadow boundary respectively represent morphological expansion of the overlay mask boundary and the shadow boundary;ffor overlay and shadow boundary pictures after morphological dilation,C 0 a set of pixels of the resulting overlay mask boundary is mapped for the model,N（C 0 ) For the total number of pixels in the overlay mask boundary,C s a set of pixels of the resulting shadow boundary mapped for the model,N（C s ) Is the total number of pixels in the shadow boundary; the landing building features are described through the matching function, the landing building features are converted into a comparable feature vector form, the matching results of the feature matching points are integrated, and finally an evaluation value of the matching degree is obtained. The matching condition of the overlay mask and shadow positions obtained by mapping the model and the actually detected overlay mask and shadow positions is described by using the function, and the larger the value of the matching degree function is, the higher the matching degree of the model is, and the closer the model parameters are to the real parameters of the building. When the function takes a maximum value, it indicates that there is a building that matches the model.
In one embodiment of the present invention, the change trend of the conventional collection building of the Tibetan Notoptera in S3 includes a building monomer change trend and a collection building group change trend;
the building monomers comprise civil house buildings with the geometric shapes of 'field', 'sun', temple and official village buildings with the geometric shapes of 'mouth', 'L', and pillbox buildings with the geometric shapes of 'four corners', 'regular pentagon', 'regular octagon';
the aggregate building group comprises a plurality of regular building monomers with different sizes.
In one embodiment of the invention, the index of the change trend of the reactive building monomer is the building geometric information and the building area;
wherein, for the civil house building with the geometric form of 'field', 'sun', the temple with the geometric form of 'mouth', 'L', and the official village building, the building single area comprises the ground area, the wall elevation area and the roof area of the building, the area calculation formula is:
wherein,S civil house, official village and temple For a single geometric form in a certain study period "The general area of the temple or the official village building with the shape of a mouth and an L is formed by the geometry,S 1 is the ground area of the building;S 2 the area of the vertical face of the building wall is measured;S 3 for the measured building roof area;
for the pillbox building with the geometric form of four corners, regular pentagons and regular octagons, the building area comprises the ground area, the wall elevation area and the roof area of the building, wherein the ground area and the roof area are split into regular rectangles, regular pentagons and regular octagons for calculation, the wall elevation area is split into the regular rectangles for calculation, and the calculation formula is as follows:
wherein,for the area of individual pillbox buildings within a study period,S 1,3 regular pentagon Is the area of a regular pentagon divided into the ground area and the roof area,S 1,3 regular octagon Is the area of a regular octagon divided by the ground area and the roof area,ais a regular pentagon with a side length,bthe side length of the regular octagon;
the area change trend of the building monomer is quantified by using the building change rate, and the calculation formula of the building change rate is as follows:
wherein,Kfor a rate of change of the area of a single building aggregate over a study period,U a andU b the area of the building at the beginning and end of the study period respectively,Tfor the study period.
In one embodiment of the invention, the trend of the aggregate group is reflected by a group area compactness trend, group geometry and distribution law;
the compact trend of the aggregate building group and the building group geometry are reflected by a shape index, the shape index being calculated by the formula:
wherein,C n is the first to gathernThe length of the boundary of each building unit,S n is the first to gathernThe planar area of the individual building elements,nfor the quantity of building monomers in a building group,mean shape index of Tibet Notoptera traditional aggregation building group in a certain period of time, when +.>A smaller time means that the compactness between the landing buildings is smaller, and the shape of the building group area becomes more irregular or more complex; when->When the index is increased, the compactness among the building clusters is increased, and the shape of the building group area is more regular and is more similar to a rectangle;
the distribution rule of the aggregation building group is based on the length-width ratio of the aggregation building groupTTo react, the calculation formula of the length-width ratio is as follows:
wherein,AandBthe long side and the short side of the smallest external rectangle of the building group are respectively formed; when the T value is large, the long and narrow degree of the distribution of the building group area is increased, if the long and narrow distribution of the building group area extends along the contour line, the change of the height difference of the distribution is not large, and if the long and narrow distribution of the building group area is perpendicular to the contour line, the change of the height difference of the building distribution is obvious; when T is smaller, the traditional aggregation and group-building balanced layout features are more prominent and the geography is shownThe factor restriction is small.
In the description of the present invention, it should be understood that the terms "center," "thickness," "upper," "lower," "horizontal," "top," "bottom," "inner," "outer," "radial," and the like indicate or are based on the orientation or positional relationship shown in the drawings, merely to facilitate description of the present invention and to simplify the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be configured and operated in a particular orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be interpreted as indicating or implying a relative importance or number of technical features indicated. Thus, a feature defined as "first," "second," "third," or the like, may explicitly or implicitly include one or more such feature.
Claims (8)
1. The quantitative analysis method for the change trend of the Tibetan Qiang traditional aggregation building is characterized by comprising the following steps of:
s1, acquiring a high-resolution SAR image of a Tibetan-Qiang traditional aggregation building, and extracting the image of the Tibetan-Qiang traditional aggregation building by using an SAR image classification algorithm of an improved MRF model to obtain a building image;
the step S1 comprises the following sub-steps:
s11, acquiring a high-resolution SAR image of a Tibetan Notopterygium traditional aggregation building, and extracting the building by using an SAR image classification algorithm of an improved MRF model to obtain an initial building image;
the step S11 comprises the following sub-steps:
s111, acquiring a high-resolution SAR image of a Tibetan Notopterygium traditional aggregation building;
s112, dividing the high-resolution SAR image into three region types and marking;
the three zone types include a building zone, a shadow zone, and a background zone;
s113, respectively describing three region types by using a fisher distribution, estimating distribution parameters of the three region types by using a parameter estimation method based on Mellin transformation, and establishing a SAR image statistical model according to step parameters to interpret the marked SAR image;
s114, performing pixel-level classification on the interpreted SAR image by using an improved MRF model;
the improved MRF model uses random distribution of Gibbs fieldsExpressed by the formula:
wherein,Z for the normalization constant(s),Uas a function of the energy,U（y|x) The energy term is the sum of the likelihood energy term and the prior energy term of the neighborhood system;for likelihood energy term +.>Priori energy terms for the neighborhood system;
the prior energy term potential function formula is:
wherein,Cfor a set of neighborhood system groups,βis a classification parameter representing the influence of a neighborhood group on a pixel label; sandtpixel points in the same group;dandx s -x t is a pixel pointsAndtthe distance between them and the gray level difference,a c distance and gray scale difference between the weight coefficient and the pixel in the neighborhood groupInversely proportional;
s115, distinguishing a building from a non-building from the SAR image after pixel-level classification by utilizing an object-oriented method based on shape characteristics and according to the rule that overlapping and masking areas and shadow areas of the building appear in pairs, extracting pixels classified into the building, and acquiring an initial building image;
s12, dividing a communication area with the same characteristics in the initial building image by using an area-based growth algorithm to obtain a separated building image;
s13, removing overlapping mask and shadow areas which do not belong to the building from the separated building image by adopting an object-oriented method based on shape characteristics, so as to obtain the building image;
s2, extracting geometric information of the building according to the building image to obtain accurate geometric information of the building;
s3, setting an observation time period, and obtaining accurate geometric information of the building in the traditional building with the built-in Notopterygium in the observation time period, so as to finish quantitative analysis of the change trend of the traditional building with the built-in Notopterygium.
2. The quantitative analysis method of the Tibetan qiang traditional aggregation building change trend according to claim 1, wherein the step S2 comprises the following sub-steps:
s21, directly measuring the overlay mask and the shadow in the SAR image of the building according to the three-dimensional information features of the building contained in the overlay mask and the shadow formed in the imaging of the SAR image of the building, and obtaining a geometric model of the building according to a measurement result;
s22, determining shadows and overlay positions of the buildings in the geometric model through geometric mapping relations;
s23, describing the characteristics of the landing building through a matching degree function;
s24, optimizing a matching degree function through a simulated genetic annealing algorithm, and obtaining accurate building length, width and height information as accurate geometric information of a building when the matching degree function is increased and reaches a stable value.
3. The quantitative analysis method for the change trend of the Tibetan notopterygium traditional aggregation building according to claim 2, wherein in the step S21, when the width of the building is greater than or equal to the height of the building, a shadow area, a part of a roof scattering area and a cover overlapping area of the building are all presented in an SAR image to obtain the height of the buildingHAnd width ofWThe formula of (2) is:
wherein,W shadow AndW fold and mask Respectively represent the width of the shadow area and the overlap area of the building,θrepresenting radar incidence angle during SAR flight.
4. The quantitative analysis method of the Tibetan Qiang traditional aggregation building variation trend according to claim 3, wherein in S21, when the width of the building is smaller than the height thereof, the building sequentially forms a covering area and a shadow area in the SAR image to obtain the height of the buildingHAnd width ofWThe formula of (2) is:
。
5. the quantitative analysis method of the Tibetan qiang traditional aggregation building change trend according to claim 2, wherein in S23, the formula of the matching degree function is:
wherein,Mis a geometric model of a building and is a model of the building,k 0 andk s matching weights of the overlay mask boundary and the shadow boundary respectively represent morphological expansion of the overlay mask boundary and the shadow boundary;ffor overlay and shadow boundary pictures after morphological dilation,C 0 mapping for the modelThe resulting set of pixels of the overlay mask boundary,N（C 0 ) For the total number of pixels in the overlay mask boundary,C s a set of pixels of the resulting shadow boundary mapped for the model,N（C s ) Is the total number of pixels in the shadow boundary.
6. The quantitative analysis method of the change trend of the Tibetan qiang traditional aggregation building according to claim 1, wherein the change trend of the Tibetan qiang traditional aggregation building in S3 comprises a building monomer change trend and an aggregation building group change trend;
the building monomers comprise civil house buildings with the geometric shapes of 'field', 'sun', temple and official village buildings with the geometric shapes of 'mouth', 'L', and pillbox buildings with the geometric shapes of 'four corners', 'regular pentagon', 'regular octagon';
the aggregate building group comprises a plurality of regular building monomers with different sizes.
7. The quantitative analysis method of the change trend of the Tibetan Qiang traditional colony building according to claim 6, wherein the indexes of the change trend of the reaction building monomers are building geometric information and building area;
wherein, for the civil house building with the geometric form of 'field', 'sun', the temple with the geometric form of 'mouth', 'L', and the official village building, the building single area comprises the ground area, the wall elevation area and the roof area of the building, the area calculation formula is:
wherein,S civil house, official village and temple For the total area of a single residential building with a geometry of 'field', 'day' and a temple or a official village building with a geometry of 'mouth', 'L' in a certain research period,S 1 is the ground area of the building;S 2 the area of the vertical face of the building wall is measured;S 3 for the measured building roof area;
for the pillbox building with the geometric form of four corners, regular pentagons and regular octagons, the building area comprises the ground area, the wall elevation area and the roof area of the building, wherein the ground area and the roof area are split into regular rectangles, regular pentagons and regular octagons for calculation, the wall elevation area is split into the regular rectangles for calculation, and the calculation formula is as follows:
wherein,for the area of individual pillbox buildings within a study period,S 1,3 regular pentagon Is the area of a regular pentagon divided into the ground area and the roof area,S 1,3 regular octagon Is the area of a regular octagon divided by the ground area and the roof area,ais a regular pentagon with a side length,bthe side length of the regular octagon;
the area change trend of the building monomer is quantified by using the building change rate, and the calculation formula of the building change rate is as follows:
wherein,Kfor a rate of change of the area of a single building aggregate over a study period,U a andU b the area of the building at the beginning and end of the study period respectively,Tfor the study period.
8. The quantitative analysis method of the Tibetan qiang traditional aggregation building variation trend according to claim 6, wherein the aggregation building group variation trend is reflected by a building group area compactness trend, a building group geometry and a distribution rule;
the compact trend of the aggregate building group and the building group geometry are reflected by a shape index, the shape index being calculated by the formula:
wherein,C n is the first to gathernThe length of the boundary of each building unit,is the first to gathernThe planar area of the individual building elements,nfor the number of building monomers in the building group, < +.>Representing the average shape index of the Tibetan Notopterygium traditional aggregation building group in a certain period;
the distribution rule of the aggregation building group is based on the length-width ratio of the aggregation building groupTTo react, the calculation formula of the length-width ratio is as follows:
wherein,AandBthe long side and the short side of the smallest external rectangle of the building group are respectively formed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311633878.4A CN117333530B (en) | 2023-12-01 | 2023-12-01 | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311633878.4A CN117333530B (en) | 2023-12-01 | 2023-12-01 | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117333530A CN117333530A (en) | 2024-01-02 |
| CN117333530B true CN117333530B (en) | 2024-02-06 |
Family
ID=89293918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311633878.4A Active CN117333530B (en) | 2023-12-01 | 2023-12-01 | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117333530B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473764A (en) * | 2013-09-03 | 2013-12-25 | 中国科学院深圳先进技术研究院 | Remote-sensing image target change detection method |
| CN104268879A (en) * | 2014-09-28 | 2015-01-07 | 民政部国家减灾中心 | Physical building quantity damage evaluation method based on remote sensing multi-spectral images |
| CN107730496A (en) * | 2017-10-26 | 2018-02-23 | 武汉大学 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
| CN108830203A (en) * | 2018-06-01 | 2018-11-16 | 中国科学院遥感与数字地球研究所 | A kind of building area extracting method and system based on SAR image |
| CN112132806A (en) * | 2020-09-22 | 2020-12-25 | 东南大学 | Method for extracting change region based on fuzzy space Markov random field |
| CN113822999A (en) * | 2021-09-22 | 2021-12-21 | 杭州趣村游文旅集团有限公司 | Building segmentation method of digital country three-dimensional model |
| CN115205678A (en) * | 2022-07-07 | 2022-10-18 | 中国电子科技集团公司第十四研究所 | SAR image building rapid extraction method |
| CN116580160A (en) * | 2023-07-12 | 2023-08-11 | 深圳大学 | Building monomer segmentation and structure reconstruction coupling processing method and related device |
| CN116597305A (en) * | 2023-04-28 | 2023-08-15 | 中国自然资源航空物探遥感中心 | Quantitative evaluation method and system for development dynamic change of open-pit mining area |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10521694B2 (en) * | 2016-09-09 | 2019-12-31 | The Chinese University Of Hong Kong | 3D building extraction apparatus, method and system |
-
2023
- 2023-12-01 CN CN202311633878.4A patent/CN117333530B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473764A (en) * | 2013-09-03 | 2013-12-25 | 中国科学院深圳先进技术研究院 | Remote-sensing image target change detection method |
| CN104268879A (en) * | 2014-09-28 | 2015-01-07 | 民政部国家减灾中心 | Physical building quantity damage evaluation method based on remote sensing multi-spectral images |
| CN107730496A (en) * | 2017-10-26 | 2018-02-23 | 武汉大学 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
| CN108830203A (en) * | 2018-06-01 | 2018-11-16 | 中国科学院遥感与数字地球研究所 | A kind of building area extracting method and system based on SAR image |
| CN112132806A (en) * | 2020-09-22 | 2020-12-25 | 东南大学 | Method for extracting change region based on fuzzy space Markov random field |
| CN113822999A (en) * | 2021-09-22 | 2021-12-21 | 杭州趣村游文旅集团有限公司 | Building segmentation method of digital country three-dimensional model |
| CN115205678A (en) * | 2022-07-07 | 2022-10-18 | 中国电子科技集团公司第十四研究所 | SAR image building rapid extraction method |
| CN116597305A (en) * | 2023-04-28 | 2023-08-15 | 中国自然资源航空物探遥感中心 | Quantitative evaluation method and system for development dynamic change of open-pit mining area |
| CN116580160A (en) * | 2023-07-12 | 2023-08-11 | 深圳大学 | Building monomer segmentation and structure reconstruction coupling processing method and related device |
Non-Patent Citations (8)
| Title |
|---|
| Classification of X-band High Resolution SAR Images over Urban Areas: Markovian Segmentation using Mellin Transform;Celine Tison等;《2003 2nd GRSS/ISPRS Joint Workshop on Remote Sensing and Data Fusion over Urban Areas》;第110-114页 * |
| Delineation of built-up land change from SAR stack by analysing the coefficient of variation;Mi Jiang等;《ISPRS Journal of Photogrammetry and Remote Sensing》;第169卷;第93-108页 * |
| 一种基于非参数密度估计和马尔可夫上下文的SAR图像分割算法;夏桂松等;《电子与信息学报》;第28卷(第12期);第2209-2213页 * |
| 基于MRF模型的SAR图像分割方法研究;李武周;《中国优秀硕士学位论文全文数据库 信息科技辑》(第03期);第I136-1011页 * |
| 基于MRF的SAR图像分类与变化检测应用研究;张斌;《中国博士学位论文全文数据库 信息科技辑》(第06期);第I136-49页 * |
| 基于多层马尔科夫随机场模型的变化检测;金永男等;《南京师范大学学报(工程技术版)》;第14卷(第3期);第84-88页 * |
| 面向对象的高分辨率遥感影像城区建筑物分级提取方法;陶超等;《测绘学报》;第39卷(第1期);第39-45页 * |
| 高分辨率SAR图像建筑物提取方法研究;赵凌君;《中国博士学位论文全文数据库 信息科技辑》(第04期);正文第108-144页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117333530A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Guan et al. | Integration of orthoimagery and lidar data for object-based urban thematic mapping using random forests | |
| Allouis et al. | Stem volume and above-ground biomass estimation of individual pine trees from LiDAR data: Contribution of full-waveform signals | |
| CN103632167B (en) | Monocular vision space recognition method under class ground gravitational field environment | |
| Yang et al. | Using nighttime light data to identify the structure of polycentric cities and evaluate urban centers | |
| CN112766184B (en) | Remote sensing target detection method based on multi-level feature selection convolutional neural network | |
| CN106485269B (en) | SAR image object detection method based on mixing statistical distribution and multi-part model | |
| WO2014054042A1 (en) | Device and method for detecting plantation rows | |
| CN110059713A (en) | Precipitation type identification method based on precipitation particle multi-feature parameters | |
| CN116030352B (en) | Long-time-sequence land utilization classification method integrating multi-scale segmentation and super-pixel segmentation | |
| CN102073867A (en) | Sorting method and device for remote sensing images | |
| CN111462919A (en) | Method and system for predicting insect-borne diseases based on sliding window time sequence model | |
| Wang et al. | A conformal regressor with random forests for tropical cyclone intensity estimation | |
| CN117333530B (en) | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building | |
| CN104077603B (en) | Outdoor scene monocular vision space recognition method in terrestrial gravity field environment | |
| CN117765006A (en) | Multi-level dense crown segmentation method based on unmanned aerial vehicle image and laser point cloud | |
| Sammartano et al. | High scale 3D modelling and orthophoto of curved masonries for a multipurpose representation, analysis and assessment | |
| CN115271557B (en) | Method for dividing priority protection space | |
| CN110276270B (en) | High-resolution remote sensing image building area extraction method | |
| CN112347926A (en) | High-resolution image urban village detection method based on building form distribution | |
| Engstrom et al. | Evaluating the Relationship between Contextual Features Derived from Very High Spatial Resolution Imagery and Urban Attributes: A Case Study in Sri Lanka | |
| CN114842356B (en) | High-resolution earth surface type sample automatic generation method, system and equipment | |
| CN106611425A (en) | Panchromatic remote sensing image segmentation method | |
| US20230186594A1 (en) | Information processing apparatus, information processing method, and non-transitory computer readable medium | |
| CN110276240A (en) | A kind of SAR image building wall window information extracting method | |
| Wang et al. | Simple building reconstruction from lidar data and aerial imagery |
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 |