CN111178160B - Method and device for determining urban ground feature coverage information - Google Patents

Method and device for determining urban ground feature coverage information Download PDF

Info

Publication number
CN111178160B
CN111178160B CN201911266180.7A CN201911266180A CN111178160B CN 111178160 B CN111178160 B CN 111178160B CN 201911266180 A CN201911266180 A CN 201911266180A CN 111178160 B CN111178160 B CN 111178160B
Authority
CN
China
Prior art keywords
spectral
spectrum
spectral data
data
correlation coefficient
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
Application number
CN201911266180.7A
Other languages
Chinese (zh)
Other versions
CN111178160A (en
Inventor
邓应彬
许剑辉
胡泓达
陈仁容
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Institute of Geography of GDAS
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Original Assignee
Guangzhou Institute of Geography of GDAS
Southern Marine Science and Engineering Guangdong Laboratory Guangzhou
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Institute of Geography of GDAS, Southern Marine Science and Engineering Guangdong Laboratory Guangzhou filed Critical Guangzhou Institute of Geography of GDAS
Priority to CN201911266180.7A priority Critical patent/CN111178160B/en
Publication of CN111178160A publication Critical patent/CN111178160A/en
Application granted granted Critical
Publication of CN111178160B publication Critical patent/CN111178160B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/176—Urban or other man-made structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/13—Satellite images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Astronomy & Astrophysics (AREA)
  • Remote Sensing (AREA)
  • Geophysics And Detection Of Objects (AREA)

Abstract

The invention relates to a method and a device for determining urban ground cover information, wherein a similarity value between every two spectral data in a group of spectral data corresponding to a first ground cover type is obtained according to a plurality of groups of spectral data corresponding to a plurality of first ground cover types of a region to be researched, the first ground cover type is subdivided by comparing the similarity value between the two spectral data with a set threshold value, and ground cover information in the research region is accurately identified according to the subdivided ground cover type. Compared with the prior art, the method can accurately identify the ground surface coverage information in the research area, and provide accurate and reliable basic data for the researches of urban fine management, urban micro-ecology, urban ecological space structure and the like.

Description

Method and device for determining urban ground feature coverage information
Technical Field
The invention relates to the technical field of geographic information, in particular to a method and a device for determining urban ground object coverage information.
Background
The impervious surface is an artificial earth surface characteristic that water cannot permeate into soil through the impervious surface, and mainly comprises buildings such as roads, parking lots, squares, roofs and the like. The distribution and the coverage degree of the impervious surface can reflect the township degree and the ecological environment change degree of the area, and have very important significance on the evaluation of urban ecological environment, the monitoring and the management of the urban process and the like.
However, since the urban impervious surface often contains a plurality of building materials, the existing classification identification technology cannot accurately identify specific urban ground cover information.
Disclosure of Invention
The embodiment of the application provides a method and a device for determining urban ground object coverage information, which can accurately identify specific urban ground object coverage information. The technical scheme is as follows:
in a first aspect, an embodiment of the present application provides a method for determining urban land cover information, including the following steps:
dividing the impervious surface of the area to be researched into a plurality of first ground object covering types according to the material components of the impervious surface of the area to be researched;
acquiring a plurality of groups of spectral data respectively corresponding to the plurality of first ground object coverage types;
acquiring a correlation coefficient, a spectral angle and a spectral distance between every two spectral data in a group of spectral data corresponding to a first ground object coverage type;
obtaining a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle and the spectral distance;
if the similarity value between the two spectral data is larger than a set threshold value, subdividing the ground features corresponding to the two spectral data into two different subdivided ground feature coverage types from a first ground feature coverage type, and if the similarity value between the two spectral data is smaller than the set threshold value, merging the ground features corresponding to the two spectral data into the same subdivided ground feature coverage type;
and determining the earth surface coverage information in the research area according to the subdivided earth object coverage types.
Optionally, the step of dividing the watertight surface of the area to be studied into a plurality of first ground cover types includes:
and dividing the impervious surface of the area to be researched into metal, asphalt cement, plastic rubber and masonry according to the material components of the impervious surface of the area to be researched.
Optionally, the method for determining urban ground object coverage information further includes the following steps:
and acquiring the optimal classification threshold of the spectrums of the plurality of ground object coverage types based on a decision tree algorithm to serve as a set threshold.
Optionally, the step of obtaining a correlation coefficient, a spectrum angle, and a spectrum distance between every two pieces of spectrum data in a group of spectrum data corresponding to the first feature coverage type specifically includes:
the correlation coefficient of the two spectral data was calculated according to the following formula:
Figure BDA0002312913830000021
wherein N is the total number of wave bands of the spectrum, x i And y i Spectral values of two spectral data of the ith waveband respectively,
Figure BDA0002312913830000022
and &>
Figure BDA0002312913830000023
The spectrum mean value of the two spectrum data is shown, and P is a correlation coefficient of the two spectrum data;
the spectral angle a of any two spectral data is calculated according to the following formula:
Figure BDA0002312913830000024
wherein A is the spectrum angle of any two spectrum data;
the spectral distance D of any two spectral data is calculated according to the following formula:
Figure BDA0002312913830000025
where D is the spectral distance of any two spectral data.
Optionally, the step of obtaining a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle, and the spectral distance specifically includes:
normalizing the correlation coefficient according to the following formula:
Figure BDA0002312913830000026
wherein PN is the normalized correlation coefficient, P i Is a correlation coefficient, P, of two spectral data min Is the minimum value, P, of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground cover type max The maximum value of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
the spectral angles are normalized according to the following formula:
Figure BDA0002312913830000027
wherein AN is the normalized spectral angle, A i Spectral angle for two spectral data, A min Is the minimum value in the spectrum angle between any two spectrum data in the corresponding spectrum data of the ground object coverage type, A max The maximum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type is obtained;
the spectral distances are normalized according to the following formula:
Figure BDA0002312913830000031
wherein DN is the normalized spectral distance, D i Spectral distance, D, for two spectral data min Is the minimum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground cover type, D max The maximum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
a similarity value between the two spectral data is calculated according to the following formula:
SI＝(1-PN)+AN+DN
wherein, SI is a similarity value between two spectrum data, PN is a normalized correlation coefficient, AN is a normalized spectrum angle and a normalized spectrum distance, and DN is a normalized spectrum distance.
In a second aspect, an embodiment of the present application provides an urban land cover information determining apparatus, including:
the first classification module is used for dividing the impervious surface of the area to be researched into a plurality of first ground object covering types according to the material composition of the impervious surface of the area to be researched;
the spectral data acquisition module is used for acquiring a plurality of groups of spectral data corresponding to the plurality of first ground object coverage types respectively;
the parameter calculation module is used for acquiring a correlation coefficient, a spectrum angle and a spectrum distance between every two pieces of spectrum data in a group of spectrum data corresponding to the first ground object coverage type;
the similarity value calculation module is used for acquiring a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle and the spectral distance;
the second classification module is used for subdividing the ground features corresponding to the two spectral data into two different subdivided ground feature coverage types from the first ground feature coverage type if the similarity value between the two spectral data is larger than a set threshold value, and merging the ground features corresponding to the two spectral data into the same subdivided ground feature coverage type if the similarity value between the two spectral data is smaller than the set threshold value;
and the earth surface coverage information acquisition module is used for determining earth surface coverage information in the research area according to the subdivided earth object coverage types.
Optionally, the first classification module divides the impervious surface of the area to be researched into metal, asphalt cement, plastic rubber and masonry according to the material composition of the impervious surface of the area to be researched.
Optionally, the device for determining urban ground cover information further includes:
and the threshold acquisition module is used for acquiring the optimal classification threshold of the spectrums of the ground object coverage types based on a decision tree algorithm to serve as a set threshold.
Optionally, the parameter calculating module includes:
a correlation coefficient calculating unit, configured to calculate a correlation coefficient of any two spectral data according to the following formula:
Figure BDA0002312913830000041
wherein N is the total number of wave bands of the spectrum, x i And y i Spectral values of two spectral data of the ith waveband respectively,
Figure BDA0002312913830000042
and &>
Figure BDA0002312913830000043
The spectrum mean value of the two spectrum data is shown, and P is a correlation coefficient of the two spectrum data;
a spectral angle calculation unit for calculating a spectral angle a of any two spectral data according to the following formula:
Figure BDA0002312913830000044
wherein A is the spectrum angle of any two spectrum data;
the spectral distance calculating unit is used for calculating the spectral distance D of any two spectral data according to the following formula:
Figure BDA0002312913830000045
where D is the spectral distance of any two spectral data.
Optionally, the similarity value calculating module includes:
a correlation coefficient normalization unit, configured to normalize the correlation coefficient according to the following formula:
Figure BDA0002312913830000046
wherein PN is the normalized correlation coefficient, P i Is a correlation coefficient, P, of two spectral data min Is the minimum value, P, of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground cover type max The maximum value of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
a spectrum angle normalization unit, configured to normalize the spectrum angle according to the following formula:
Figure BDA0002312913830000047
wherein AN is the normalized spectral angle, A i Spectral angle for two spectral data, A min Is the minimum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type, A max The maximum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type is obtained;
a spectral distance normalization unit, configured to normalize the spectral distance according to the following formula:
Figure BDA0002312913830000051
wherein DN is the normalized spectral distance, D i Spectral distance, D, for two spectral data min Is the minimum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground cover type, D max The maximum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
a similarity value calculation unit for calculating a similarity value between the two spectral data according to the following formula:
SI＝(1-PN)+AN+DN
wherein, SI is a similarity value between two spectrum data, PN is a normalized correlation coefficient, AN is a normalized spectrum angle and a normalized spectrum distance, and DN is a normalized spectrum distance.
In the embodiment of the application, according to a plurality of groups of spectral data corresponding to a plurality of first ground cover types of a region to be researched, a similarity value between every two spectral data in a group of spectral data corresponding to the first ground cover type is obtained, the similarity value between the two spectral data is compared with a set threshold value, the first ground cover type is subdivided, a finer ground cover type is obtained, ground cover information in the research region is accurately identified according to the subdivided ground cover type, and accurate and reliable basic data are provided for researches such as fine city management, micro-ecology of cities, ecological spatial structure of cities and the like.
For a better understanding and practice, the present invention is described in detail below with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart of a method for determining urban terrain coverage information in an exemplary embodiment of the invention;
FIG. 2 is a flowchart of step S3 in an exemplary embodiment of the invention;
FIG. 3 is a flowchart of step S4 in an exemplary embodiment of the invention;
fig. 4 is a schematic structural diagram of a city expansion prediction apparatus according to an exemplary embodiment of the present invention;
FIG. 5 is a schematic diagram of the structure of the parameter calculation module 3 according to an exemplary embodiment of the present invention;
fig. 6 is a schematic structural diagram of the similarity value calculation module 4 according to an exemplary embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.
It should be understood that the embodiments described are only a few embodiments of the present application, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present application without any creative effort belong to the protection scope of the embodiments in the present application.
The terminology used in the embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the embodiments of the present application. As used in the examples of this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application, as detailed in the claims that follow. In the description of the present application, it is to be understood that the terms "first," "second," "third," and the like are used solely to distinguish one from another and are not necessarily used to describe a particular order or sequence, nor are they to be construed as indicating or implying relative importance. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art as appropriate.
In addition, in the description of the present application, "a number" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated object, indicating that there may be three relationships, for example, a and/or B, which may indicate: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
Referring to fig. 1, the present invention provides a method for determining urban land cover information, which includes the following steps:
step S1: the impervious surface of the area to be studied is divided into a plurality of first ground cover types according to the material composition of the impervious surface of the area to be studied.
The research area is a set land surface area, and in the embodiment of the application, the research area mainly refers to an urban area.
The impervious surface is an artificial earth surface characteristic through which water cannot permeate into soil, and mainly comprises buildings such as roads, parking lots, squares, roofs and the like. The impervious surface mainly comprises metal, asphalt cement, plastic rubber, masonry and other materials.
The ground cover type refers to the land utilization or cover type of the research area, and can be classified according to the Chinese land utilization classification or the American land utilization/cover classification system.
Step S2: and acquiring a plurality of groups of spectral data respectively corresponding to the plurality of first ground object coverage types.
In one example, the spectral data may be spectral values for a plurality of wavelength bands, the spectral values reflecting the reflectance of the measurement color surface for light of each wavelength of the visible spectrum. The spectral data can be obtained by field measurement, and can also be obtained by measuring a waterproof surface material of a corresponding material in a laboratory.
And step S3: and acquiring a correlation coefficient, a spectral angle and a spectral distance between every two spectral data in a set of spectral data corresponding to the first ground object coverage type.
The correlation coefficient is a quantity for researching the linear correlation degree between two groups of variables, and the spectrum angle can be used for estimating the similarity between the image element spectrum and the end member component (end member) spectrum in the sample or the mixed image element, thereby realizing the classification of the spectrum.
And step S4: and acquiring a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle and the spectral distance.
Step S5: if the similarity value between the two spectral data is larger than a set threshold value, the ground features corresponding to the two spectral data are subdivided into two different subdivided ground feature coverage types from the first ground feature coverage type, and if the similarity value between the two spectral data is smaller than the set threshold value, the ground features corresponding to the two spectral data are combined into the same subdivided ground feature coverage type.
For the metal impervious surface, the subdivided ground object covering types can be a blue steel roof, a white steel roof and an aluminum alloy roof; for the asphalt cement impervious surface, the subdivided ground object coverage types can be new asphalt, old asphalt, new cement and old cement; for the plastic rubber impervious surface, the subdivided ground object covering type can be plastic and plastic; for masonry type impervious surfaces, the finely divided ground covering type may be brick and stone.
The set threshold can be set manually, or based on a decision tree algorithm, the optimal classification threshold of the spectra of the plurality of ground object coverage types is obtained according to the existing training sample and is used as the set threshold.
By comparing the similarity value between the two spectral data with a set threshold value, the spectral data with larger similarity value is subdivided, and the spectral data with smaller similarity value is merged, so that the spectral data classification speed can be effectively improved.
Step S6: and determining the earth surface coverage information in the research area according to the subdivided earth coverage type.
According to the subdivided ground object coverage types, the ground surface coverage types contained in the research area can be determined, and further, ground surface coverage information such as probabilities of various ground surface coverage types in the research area can be determined by combining the remote sensing images or other geographic information.
In the embodiment of the application, according to a plurality of groups of spectral data corresponding to a plurality of first terrain coverage types of a to-be-researched area respectively, a similarity value between every two spectral data in a group of spectral data corresponding to the first terrain coverage types is obtained, the similarity value between the two spectral data is compared with a set threshold value, the first terrain coverage types are subdivided, finer ground coverage types are obtained, ground surface coverage information in the research area is accurately identified according to the subdivided terrain coverage types, and accurate and reliable basic data are provided for researches such as city fine management, city micro-ecology and city ecological space structure.
Referring to fig. 2, in an exemplary embodiment, the step of acquiring a correlation coefficient, a spectrum angle and a spectrum distance between every two spectrum data in a set of spectrum data corresponding to the first feature coverage type specifically includes:
step S301: the correlation coefficient of the two spectral data was calculated according to the following formula:
Figure BDA0002312913830000071
wherein N is the total number of wave bands of the spectrum, x i And y i Respectively, the spectral values of any two spectral data in the ith waveband,
Figure BDA0002312913830000081
and &>
Figure BDA0002312913830000082
Is the spectral mean of the two spectral data, and P is the correlation coefficient of the two spectral data.
Step S302: the spectral angle a of the two spectral data is calculated according to the following formula:
Figure BDA0002312913830000083
wherein A is the spectrum angle of any two spectrum data;
step S303: the spectral distance D of the two spectral data is calculated according to the following formula:
Figure BDA0002312913830000084
where D is the spectral distance of any two spectral data.
Referring to fig. 3, in an exemplary embodiment, the step of obtaining a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle, and the spectral distance specifically includes:
step S401: normalizing the correlation coefficient according to the following formula:
Figure BDA0002312913830000085
wherein PN is the normalized correlation coefficient, P i Is a correlation coefficient, P, of two spectral data min Is the minimum value, P, in the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type max And the feature coverage type corresponds to the maximum value in the correlation coefficient between any two spectral data in the spectral data.
Step S402: the spectral angles are normalized according to the following formula:
Figure BDA0002312913830000086
wherein AN is the normalized spectral angle, A i Spectral angle, A, for two spectral data min Is the minimum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type, A max The feature coverage type corresponds to a maximum in a spectral angle between any two of the spectral data.
Step S403: normalizing the spectral distance according to the following formula:
Figure BDA0002312913830000087
wherein DN is the normalized spectral distance, D i Spectral distance, D, for two spectral data min Is the minimum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground object coverage type, D max The feature coverage type corresponds to a maximum in a spectral distance between any two spectral data in the spectral data.
Step S404: a similarity value between the two spectral data is calculated according to the following formula:
SI＝(1-PN)+AN+DN
wherein, SI is a similarity value between two spectrum data, PN is a normalized correlation coefficient, AN is a normalized spectrum angle and spectrum distance, and DN is a normalized spectrum distance.
And each correlation coefficient, each spectral angle and each spectral distance are normalized and converted into a numerical value between 0 and 1, so that the calculation and judgment of similar values are facilitated.
Referring to fig. 4, the present invention further provides an apparatus for determining urban ground feature coverage information, including:
the first classification module 1 is used for dividing the impervious surface of the area to be researched into a plurality of first ground object covering types according to the material components of the impervious surface of the area to be researched;
the spectral data acquisition module 2 is used for acquiring a plurality of groups of spectral data corresponding to the plurality of first ground object coverage types respectively;
the parameter calculation module 3 is configured to obtain a correlation coefficient, a spectrum angle and a spectrum distance between every two pieces of spectrum data in a set of spectrum data corresponding to the first feature coverage type;
the similarity value calculation module 4 is used for obtaining a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle and the spectral distance;
the second classification module 5 is configured to, if the similarity value between the two pieces of spectral data is greater than a set threshold, subdivide the feature corresponding to the two pieces of spectral data from the first feature coverage type into two different subdivided feature coverage types, and if the similarity value between the two pieces of spectral data is less than the set threshold, merge the features corresponding to the two pieces of spectral data into the same subdivided feature coverage type;
and the earth surface coverage information acquisition module 6 is used for determining earth surface coverage information in the research area according to the subdivided earth covering type.
In one example, the first classification module 1 classifies the watertight surface of the area to be studied as metal, asphalt cement, plastic rubber, masonry, according to the material composition of the watertight surface of the area to be studied.
In an exemplary embodiment, the urban feature coverage information determining apparatus further includes:
and the threshold acquisition module is used for acquiring the optimal classification threshold of the spectrums of the ground object coverage types based on a decision tree algorithm to serve as a set threshold.
In an exemplary embodiment, the parameter calculation module 3 includes:
a correlation coefficient calculating unit 301, configured to calculate a correlation coefficient of any two spectral data according to the following formula:
Figure BDA0002312913830000101
wherein N is the total number of wave bands of the spectrum, x i And y i The spectral values of the two spectral data of the ith waveband,
Figure BDA0002312913830000102
and &>
Figure BDA0002312913830000103
The spectrum mean value of the two spectrum data is shown, and P is a correlation coefficient of the two spectrum data;
a spectrum angle calculating unit 302, configured to calculate a spectrum angle a of any two spectrum data according to the following formula:
Figure BDA0002312913830000104
wherein A is the spectrum angle of any two spectrum data;
a spectral distance calculating unit 303, configured to calculate a spectral distance D between any two spectral data according to the following formula:
Figure BDA0002312913830000105
where D is the spectral distance of any two spectral data.
In an exemplary embodiment, the similarity value calculation module 4 includes:
a correlation coefficient normalization unit 401, configured to normalize the correlation coefficient according to the following formula:
Figure BDA0002312913830000106
wherein PN is the normalized correlation coefficient, P i Is a correlation coefficient, P, of two spectral data min Is the minimum value, P, of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground cover type max The maximum value of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
a spectrum angle normalization unit 402, configured to normalize the spectrum angle according to the following formula:
Figure BDA0002312913830000107
wherein AN is the normalized spectral angle, A i Spectral angle for two spectral data, A min Is the minimum value in the spectrum angle between any two spectrum data in the corresponding spectrum data of the ground object coverage type, A max The maximum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type is obtained;
a spectral distance normalization unit 403, configured to normalize the spectral distance according to the following formula:
Figure BDA0002312913830000111
wherein DN is the normalized spectral distance, D i Spectral distance, D, for two spectral data min Corresponding to any two spectrums in the spectrum data for the ground object coverage typeMinimum in spectral distance between data, D max The maximum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
a similarity value calculation unit 404, configured to calculate a similarity value between the two spectral data according to the following formula:
SI＝(1-PN)+AN+DN
wherein, SI is a similarity value between two spectrum data, PN is a normalized correlation coefficient, AN is a normalized spectrum angle and a normalized spectrum distance, and DN is a normalized spectrum distance.
The invention can subdivide the coverage types of the artificial ground features of the cities from a fine scale, more accurately embody the coverage information of the urban ground surfaces and provide richer basic information for urban managers.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.

Claims (8)

1. A method for determining urban ground object coverage information is characterized by comprising the following steps:
dividing the impervious surface of the area to be researched into a plurality of first ground object covering types according to the material components of the impervious surface of the area to be researched; wherein the first ground cover type comprises metal, asphalt cement, plastic rubber, and masonry;
acquiring a plurality of groups of spectral data respectively corresponding to the plurality of first ground object coverage types;
acquiring a correlation coefficient, a spectrum angle and a spectrum distance between every two spectrum data in a group of spectrum data corresponding to the first ground object coverage type;
normalizing the correlation coefficient, the spectrum angle and the spectrum distance to obtain a normalized correlation coefficient, a normalized spectrum angle and a normalized spectrum distance;
according to the normalized correlation coefficient, the normalized spectral angle and the normalized spectral distance, obtaining a similarity value between every two spectral data in the set of spectral data according to the following formula:
SI＝(1-PN)+AN+DN
wherein, SI is a similarity value between two spectral data, PN is a normalized correlation coefficient, AN is a normalized spectral angle and a normalized spectral distance, and DN is a normalized spectral distance;
if the similarity value between the two spectral data is larger than a set threshold value, subdividing the ground features corresponding to the two spectral data into two different subdivided ground feature coverage types from a first ground feature coverage type, and if the similarity value between the two spectral data is smaller than the set threshold value, merging the ground features corresponding to the two spectral data into the same subdivided ground feature coverage type; and determining the earth surface coverage information in the research area according to the subdivided earth object coverage types.
2. The urban feature coverage information determination method according to claim 1, wherein the urban feature coverage information determination method further comprises the steps of:
and acquiring the optimal classification threshold of the spectrums of the plurality of first ground object coverage types based on a decision tree algorithm to serve as a set threshold.
3. The urban terrain coverage information determination method according to claim 1, wherein the step of obtaining the correlation coefficient, the spectral angle and the spectral distance between every two spectral data in the set of spectral data corresponding to the first terrain coverage type specifically comprises:
the correlation coefficient of the two spectral data was calculated according to the following formula:
Figure FDA0003960678020000011
wherein N is the total number of wave bands of the spectrum, x i And y i Of two spectral data in the i-th bandThe value of the spectrum of the light is,
Figure FDA0003960678020000012
and &>
Figure FDA0003960678020000013
The spectrum mean value of the two spectrum data is obtained, and P is a correlation coefficient of the two spectrum data;
the spectral angle a of any two spectral data is calculated according to the following formula:
Figure FDA0003960678020000021
wherein A is the spectrum angle of any two spectrum data;
calculating the spectral distance D of any two spectral data according to the following formula:
Figure FDA0003960678020000022
where D is the spectral distance of any two spectral data.
4. The urban terrain coverage information determination method according to claim 1,
the step of normalizing the correlation coefficient, the spectral angle and the spectral distance specifically comprises:
normalizing the correlation coefficient according to the following formula:
Figure FDA0003960678020000023
wherein PN is the normalized correlation coefficient, P i Is a correlation coefficient, P, of two spectral data min Is the minimum value, P, of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground cover type max The maximum value of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
the spectral angles are normalized according to the following formula:
Figure FDA0003960678020000024
wherein AN is the normalized spectral angle, A i Spectral angle, A, for two spectral data min Is the minimum value in the spectrum angle between any two spectrum data in the corresponding spectrum data of the ground object coverage type, A max The maximum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type is obtained;
the spectral distances are normalized according to the following formula:
Figure FDA0003960678020000025
wherein DN is the normalized spectral distance, D i Spectral distance, D, for two spectral data min Is the minimum value in the spectral distance between any two spectral data in the spectral data corresponding to the ground object coverage type, D max And the ground cover type corresponds to the maximum value in the spectral distance between any two spectral data in the spectral data.
5. An urban feature coverage information determination device, comprising:
the first classification module is used for dividing the impervious surface of the area to be researched into a plurality of first ground object covering types according to the material composition of the impervious surface of the area to be researched; wherein the first type of terrain covering comprises metal, asphalt cement, plastic rubber, and masonry;
the spectral data acquisition module is used for acquiring a plurality of groups of spectral data respectively corresponding to the plurality of first ground object coverage types;
the parameter calculation module is used for acquiring a correlation coefficient, a spectrum angle and a spectrum distance between every two pieces of spectrum data in a group of spectrum data corresponding to the first ground object coverage type;
the similarity value calculation module is used for acquiring a similarity value between every two spectral data in the set of spectral data according to the correlation coefficient, the spectral angle and the spectral distance;
the similarity value calculation module includes:
a correlation coefficient normalization unit for normalizing the correlation coefficient;
a spectrum angle normalization unit for normalizing the spectrum angle;
the spectrum distance normalization unit is used for normalizing the spectrum distance;
a similarity value calculation unit for calculating a similarity value between the two spectral data according to the following formula:
SI＝(1-PN)+AN+DN
wherein, SI is a similarity value between two spectral data, PN is a normalized correlation coefficient, AN is a normalized spectral angle and spectral distance, and DN is a normalized spectral distance;
the second classification module is used for subdividing the ground features corresponding to the two spectral data into two different subdivided ground feature coverage types from the first ground feature coverage type if the similarity value between the two spectral data is larger than a set threshold value, and merging the ground features corresponding to the two spectral data into the same subdivided ground feature coverage type if the similarity value between the two spectral data is smaller than the set threshold value;
and the earth surface coverage information acquisition module is used for determining earth surface coverage information in the research area according to the subdivided earth object coverage types.
6. The urban feature coverage information determination device according to claim 5, wherein said urban feature coverage information determination device further comprises:
and the threshold acquisition module is used for acquiring the optimal classification threshold of the spectrums of the first ground object coverage types based on a decision tree algorithm to serve as a set threshold.
7. The urban feature coverage information determination device according to claim 5, wherein the parameter calculation module comprises:
a correlation coefficient calculating unit, configured to calculate a correlation coefficient of any two spectral data according to the following formula:
Figure FDA0003960678020000041
wherein N is the total number of wave bands of the spectrum, x i And y i Spectral values of two spectral data of the ith waveband respectively,
Figure FDA0003960678020000042
and &>
Figure FDA0003960678020000043
The spectrum mean value of the two spectrum data is shown, and P is a correlation coefficient of the two spectrum data;
a spectral angle calculation unit for calculating a spectral angle a of any two spectral data according to the following formula:
Figure FDA0003960678020000044
wherein A is the spectrum angle of any two spectrum data;
the spectral distance calculating unit is used for calculating the spectral distance D of any two spectral data according to the following formula:
Figure FDA0003960678020000045
where D is the spectral distance of any two spectral data.
8. The urban feature coverage information determination device according to claim 5, wherein:
the correlation coefficient normalization unit is configured to normalize the correlation coefficient according to the following formula:
Figure FDA0003960678020000046
wherein PN is the normalized correlation coefficient, P i Is a correlation coefficient, P, of two spectral data min Is the minimum value, P, in the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type max The maximum value of the correlation coefficient between any two spectral data in the spectral data corresponding to the ground object coverage type is obtained;
the spectrum angle normalization unit is used for normalizing the spectrum angle according to the following formula:
Figure FDA0003960678020000047
wherein AN is the normalized spectral angle, A i Spectral angle, A, for two spectral data min Is the minimum value in the spectrum angle between any two spectrum data in the corresponding spectrum data of the ground object coverage type, A max The maximum value in the spectrum angle between any two spectrum data in the spectrum data corresponding to the ground object coverage type is obtained;
the spectrum distance normalization unit is used for normalizing the spectrum distance according to the following formula:
Figure FDA0003960678020000051
wherein DN is the normalized spectral distance, D i Spectral distance, D, for two spectral data min Corresponding to any two spectral data for the ground cover typeMinimum in spectral distance between spectral data, D max And the ground cover type corresponds to the maximum value in the spectral distance between any two spectral data in the spectral data.
CN201911266180.7A 2019-12-11 2019-12-11 Method and device for determining urban ground feature coverage information Active CN111178160B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911266180.7A CN111178160B (en) 2019-12-11 2019-12-11 Method and device for determining urban ground feature coverage information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911266180.7A CN111178160B (en) 2019-12-11 2019-12-11 Method and device for determining urban ground feature coverage information

Publications (2)

Publication Number Publication Date
CN111178160A CN111178160A (en) 2020-05-19
CN111178160B true CN111178160B (en) 2023-03-28

Family

ID=70653833

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911266180.7A Active CN111178160B (en) 2019-12-11 2019-12-11 Method and device for determining urban ground feature coverage information

Country Status (1)

Country Link
CN (1) CN111178160B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408941A (en) * 2008-10-20 2009-04-15 中国科学院遥感应用研究所 Method for multi-dimension segmentation of remote sensing image and representation of segmentation result hierarchical structure

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4228745B2 (en) * 2003-03-28 2009-02-25 株式会社日立製作所 Multispectral image analysis device
CN104751166B (en) * 2013-12-30 2018-04-13 中国科学院深圳先进技术研究院 Remote Image Classification based on spectral modeling and Euclidean distance
CN103729651A (en) * 2014-01-17 2014-04-16 重庆大学 Hyperspectral remote sensing image classification method based on manifold neighbor measurement through local spectral angles
JP6303764B2 (en) * 2014-04-23 2018-04-04 日本電気株式会社 Data fusion device, land cover classification system, method and program
CN104463203B (en) * 2014-12-03 2018-01-12 复旦大学 High-spectrum remote sensing semisupervised classification method based on the scoring of atural object classification degree of membership
CN105608473B (en) * 2015-12-31 2019-01-15 中国资源卫星应用中心 A kind of high-precision land cover classification method based on high-resolution satellite image

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101408941A (en) * 2008-10-20 2009-04-15 中国科学院遥感应用研究所 Method for multi-dimension segmentation of remote sensing image and representation of segmentation result hierarchical structure

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
基于机载成像光谱数据的宜兴市土地利用/土地覆盖分类方法对比研究;张定祥等;《地理科学》;20040428(第02期);第66-71页 *

Also Published As

Publication number Publication date
CN111178160A (en) 2020-05-19

Similar Documents

Publication Publication Date Title
CN110678737B (en) Device and method for analyzing an object
Herold et al. Spectrometry for urban area remote sensing—Development and analysis of a spectral library from 350 to 2400 nm
Heiden et al. Urban structure type characterization using hyperspectral remote sensing and height information
Couteron et al. Predicting tropical forest stand structure parameters from Fourier transform of very high‐resolution remotely sensed canopy images
González-Jorge et al. Monitoring biological crusts in civil engineering structures using intensity data from terrestrial laser scanners
Meroño et al. Recognition of materials and damage on historical buildings using digital image classification
CN108319923A (en) A kind of cloud Shadow recognition method and system
Pan et al. Mapping asphalt pavement aging and condition using multiple endmember spectral mixture analysis in Beijing, China
CN114066876B (en) Construction waste change detection method based on classification result and CVA-SGD method
Heldens et al. Integration of remote sensing based surface information into a three-dimensional microclimate model
Kaloustian et al. Local climate zones and annual surface thermal response in a Mediterranean city
Hidayati et al. A comparative study of various indices for extraction urban impervious surface of Landsat 8 OLI
Lemp et al. Improvements of roof surface classification using hyperspectral and laser scanning data
JPWO2018146279A5 (en)
Ben-Dor Imaging spectrometry for urban applications
CN111178160B (en) Method and device for determining urban ground feature coverage information
Teppati Losè et al. New developments in lidar UAS surveys. Performance analyses and validation of the DJI Zenmuse L1
CN109598310B (en) Multi-factor sensitive facility identification method
Falcone et al. Mapping impervious surface type and sub‐pixel abundance using hyperion hyperspectral imagery
Heldens et al. Supporting urban micro climate modelling with airborne hyperspectral data
Asad et al. Use of remote sensing for urban impervious surfaces: a case study of Lahore
Fiumi Evaluation of MIVIS hyperspectral data for mapping covering materials
Nagyváradi et al. Monitoring the changes of suburban settlement by remote sensing
Vorovencii The assessment of the impact on the environment of the limestone quarries using satellite images
Zahradník et al. Flat roof classification and leaks detections by Deep Learning

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