CN104036507B - Light satellite based urban change area and evolution type rapid extraction method - Google Patents
Light satellite based urban change area and evolution type rapid extraction method Download PDFInfo
- Publication number
- CN104036507B CN104036507B CN201410262168.XA CN201410262168A CN104036507B CN 104036507 B CN104036507 B CN 104036507B CN 201410262168 A CN201410262168 A CN 201410262168A CN 104036507 B CN104036507 B CN 104036507B
- Authority
- CN
- China
- Prior art keywords
- type
- image
- urban
- differentiation
- evolution
- 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.)
- Expired - Fee Related
Links
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a light satellite based urban change area and evolution type rapid extraction method. Different years of light satellite images are obtained and data preprocessing is performed, the three years of images are selected, different urban evolution types of colors are set, rapid extraction of different urban evolution areas is implemented according to color discrimination, pseudo spectrum curves are built and urban evolution type spectrum libraries are established in the different evolution type areas, rapid extraction of urban change areas and evolution types is implemented, and an urban evolution type graph is drawn. According to the light satellite based urban change area and evolution type rapid extraction method, the rapid extraction of the urban change areas within a large range and the discrimination of the individual urban evolution types are implemented, the rapid and efficient effect is achieved, the scientific basis can be provided for governmental urbanization macroscopic planning, the market layout of consulting companies and transnational corporations and the like, and the market prospect is good.
Description
Technical field
The present invention relates to a kind of urban changes region based on light satellite and differentiation type rapid extracting method, belong to distant
Sense image procossing and area of pattern recognition.
Background technology
At present urban changes region is essentially with the analysis method developing type and applies conventional road resource satellite, first
Extract city, the Complicated Flow of rear change-detection.It is also limited to the letter of urban sprawl based on the urban study of light satellite image
Single analysis, or urban changes region is extracted by the method for some change-detection, algorithm is complicated, and efficiency is low, does not study
The rapid extraction in urban changes region and the discriminant analysiss of individual city evolvement type.
Content of the invention
In order to solve the deficiencies in the prior art, the invention provides a kind of urban changes region based on light satellite with drill
Become type rapid extracting method, by pseudo color composing, extract the pseudo- curve of spectrum, build the handss such as city evolvement type library of spectra
Section, it is achieved that the rapid extraction of interior city region of variation and the differentiation of individual city evolvement type on a large scale, has rapidly and efficiently
Advantage.
The present invention be employed technical scheme comprise that by its technical problem of solution:Provide a kind of city based on light satellite
Region of variation and differentiation type rapid extracting method, specifically include following steps:
(1) obtain the light satellite image of different year in same detection region;The described time at least includes Y1Time, Y2
Time and Y3Time;
(2) data prediction is carried out to light satellite image:
(201) radiation calibration:Relative detector calibration is carried out to urban lighting satellite image;
(202) go negative value:Image after step (201) radiation calibration carries out negative value and processes, by the value house less than 0
Abandon;
(203) Image registration:Light satellite image after negative value being gone to process through step (202) is according to geographical coordinate, right
Time data carries out registration;
(204) wave band synthesis:Image for each different year is considered as a wave band, according to time order and function order pair
Image carries out wave band synthesis, obtains a scape multiband image;
(3) setting develops the color of type, represents different types of evolution with different colours;
(4) pseudo color composing:Y is chosen through step (204) urban lighting satellite image after processing1Time, Y2Time
And Y3The image in time, wherein, Y1<Y2<Y3;Carry out pseudo color composing to the image in 3 times to show, wherein, Y1Time image
It is set to red channel, Y2Time image is set to green channel, Y3Time image is set to blue channel;
(5) discrimination standard set up according to step (3), interprets just by visual observation to the False color comp osite image of step (4)
Step judges to develop type, and detection zone is divided into non-development zone, stable region, development zone and blighted area;
(6) build the pseudo- curve of spectrum:Choose each pixel developing type area in detection zone respectively, extract this picture
Unit's DN value over the years, with the time as transverse axis, DN value be longitudinal axis construction DN value changes curve, the pseudo- light obtaining each differentiation type is set a song to music
Line;
(7) set up and develop type library of spectra:The color of the different types of evolution being arranged according to step (3), chooses each respectively
Develop the single pixel of type area or more than 2 pixels, be respectively directed to each differentiation type area and average, and construct and respectively drill
Become the pseudo- curve of spectrum of type, set up the differentiation type library of spectra being made up of the pseudo- curve of spectrum;
(8) rapid extraction in urban changes region:The differentiation type library of spectra set up according to step (7), using spectrum
Join algorithm, quickly identified to developing type, be that different types of evolution gives corresponding color, generate and develop type map, from
And so that urban changes region is shown in figure with developing type.
Further, in step (201), carry out relative detector calibration using below equation:
Y=c0+c1x+c2x2……(1)
Wherein, c0、c1And c2It is relative detector calibration parameter, provided by remote sensor production unit or Subscriber Unit, x represents
DN value, y represent relative detector calibration after DN value.
In step (202), go negative value using below equation:
yDN > 0=(xradiation> 0) × xradiation……(2)
Wherein, yDN > 0Represent the image after the negative value of place to go, xradiationRepresent the image after relative detector calibration.
Further, step (3) described city evolvement type decision standard is:Represent differentiation Class1 with black;With white
Represent and develop type 2;Represent differentiation type 3 with blue, cyan and green;Represent differentiation type 4 with yellow, redness and pink colour.
Further, quickly identified to developing type using following steps in step (8):
(801) obtain the light satellite resultant image that will carry out developing type identification;
(802) obtain the size of image, if the columns of its pixel and line number are respectively nSample and nLine, wave band number is
NBand, defines the independent variable i=0, j=0 of ranks change;
(803) line number judges, line number, when less than nLine, enters step 804, otherwise enters step 810;
(804) columns judges, columns, when less than nSample, enters step 806, otherwise enters step 805;
(805) columns resets j=0, and line number i increases by 1, return to step 803;
(806) obtain the pseudo- curve of spectrum at image (i, j) place;
(807) the pseudo- curve of spectrum that step 806 is obtained, is realized using Spectral matching algorithm and develops in type library of spectra
Pseudo- spectrum coupling;
(808) step 807 Spectral matching result is differentiated, obtains the differentiation type at step 806 (i, j) position,
And the type is given corresponding color;
(809) columns cumulative 1, enters step 804;
(810) travel through all row and columns, terminate quick identification to generate based on the Spectral matching developing type library of spectra
Differentiate and develop type map.
The present invention is had advantageous effect in that based on its technical scheme:
(1) present invention, avoiding the Complicated Flow of " first extracting, rear change-detection ", the plenty of time can be saved, meet number
Efficiently require according to processing;
(2) present invention passes through pseudo color composing, the means extracted the pseudo- curve of spectrum, build city evolvement type library of spectra,
Achieve the rapid extraction of interior city region of variation on a large scale and the differentiation of individual city evolvement type, have rapidly and efficiently is excellent
Point;
(3) present invention can carry out the offer such as market presence section for government's urbanization macro-plan, consulting firm, multinational corporationss
Learn foundation, there is good market prospect.
Brief description
Fig. 1 is the urban changes region and differentiation type rapid extracting method flow chart based on light satellite.
Fig. 2 is data prediction flow chart.
Fig. 3 is the city evolvement type schematic diagram using three primary colories definition, and wherein, A, B, C, D, E, F and G represent white respectively
Colour-stable area, blue development zone, cyan development zone, Green Development area, yellow blighted area, red blighted area and pink colour blighted area.
Fig. 4 is the pseudo- spectral curve in city evolvement type library of spectra.
Fig. 5 is that city evolvement type carries out quick identification process figure.
Fig. 6 is city evolvement type map.
Specific embodiment
The invention will be further described with reference to the accompanying drawings and examples.
The invention provides a kind of urban changes region based on light satellite and differentiation type rapid extracting method, reference
Fig. 1, specifically includes following steps:
(1) obtain the light satellite image of different year in same detection region;The described time at least includes Y1Time, Y2
Time and Y3Time;
(2) with reference to Fig. 2, by following steps, data prediction is carried out to light satellite image:
(201) using below equation, relative detector calibration is carried out to urban lighting satellite image:
Y=c0+c1x+c2x2……(1)
Wherein, c0、c1And c2It is relative detector calibration parameter, provided by remote sensor production unit or Subscriber Unit, x represents
DN value, y represent relative detector calibration after DN value;
(202) using below equation, the image after step (201) radiation calibration is carried out with negative value to process:
yDN > 0=(xradiation> 0) × xradiation……(2)
Wherein, yDN > 0Represent the image after the negative value of place to go, xradiationRepresent the image after relative detector calibration;
(203) Image registration:Light satellite image after negative value being gone to process through step (202) is according to geographical coordinate, right
Time data carries out registration;
(204) wave band synthesis:Image for each different year is considered as a wave band, according to time order and function order pair
Image carries out wave band synthesis, obtains a scape multiband image;
(3) with reference to Fig. 3, setting develops the color of type, represents different types of evolution using three primary colories, wherein:
Differentiation Class1 is non-development zone, is set to black, represents that light satellite DN value, close to 0, does not occur any for many years
The urban area of change;
Differentiation type 2 is stable region, is set to white, represents early stage, mid-term, later stage light satellite DN value all close to 60,
There is not the region of large change, represent Y here1、Y2And Y3The urban area of year all presence;
Differentiation type 3 is development zone, with following three kinds of colors setting:
Blue expression early stage did not change within this time period of mid-term, and the DN value of mid-term to post city region exists
It is continuously increased, be denoted here as Y1To Y2Year is not changed in, substantially in Y2To Y3Year expands the region for city;
Cyan represents that early stage is in state of development to mid-term, and mid-term to later stage is in steady statue, is denoted here as Y1
To Y2The urban area of year expansion, but in Y2To Y3Year keeps stable urban area;
Green represents the urban area expanded from early stage to mid-term and fail in mid-term to later stage, is denoted here as Y1
To Y2The urban area of year expansion, Y3The city gradually failed after year.
Develop type 4 and represent blighted area, with following three kinds of colors setting:
Yellow represents and is in steady statue from early stage to mid-term that the region gradually withered away after mid-term is denoted here as
Y1To Y2Year urban area is in steady statue, Y2To Y3Year, this city started to wither away;
Red expression is constantly in the urban area of decline from early stage to later stage, is denoted here as Y1The city that year exists
Region, in Y1To Y2Gradually wither away after year;
Pink colour represents and is in decay state from early stage to mid-term, mid-term to later stage is in state of development, is denoted here as
From Y1To Y2Year city starts to wither away, Y2To Y3Year city is in state of development again;
(4) pseudo color composing:Y is chosen through step (204) urban lighting satellite image after processing1Time, Y2Time
And Y3The image in time, wherein, Y1<Y2<Y3;Carry out pseudo color composing to the image in 3 times to show, wherein, Y1Time image
It is set to red channel, Y2Time image is set to green channel, Y3Time image is set to blue channel;
(5) color of the different types of evolution being arranged according to step (3), passes through to the False color comp osite image of step (4)
Visual interpretation preliminary judgement develops type, detection zone is divided into differentiation Class1, develops type 2, differentiation type 3 and drill
Become type 4, i.e. non-development zone, stable region, development zone and blighted area;
(6) build the pseudo- curve of spectrum:Choose each pixel developing type area in detection zone respectively, extract this picture
Unit's DN value over the years, with the time as transverse axis, DN value be longitudinal axis construction DN value changes curve, the pseudo- light obtaining each differentiation type is set a song to music
Line;
(7) set up and develop type library of spectra:The color of the different types of evolution being arranged according to step (3), chooses each respectively
Develop the single pixel of type area or more than 2 pixels, be respectively directed to each differentiation type area and average, and construct and respectively drill
Become the pseudo- curve of spectrum of type, set up the differentiation type library of spectra being made up of the pseudo- curve of spectrum;In city evolvement type library of spectra
The pseudo- curve of spectrum as shown in Figure 4;
(8) rapid extraction in urban changes region:The differentiation type library of spectra set up according to step (7), using spectrum
Join algorithm, quickly identified to developing type, be that different types of evolution gives corresponding color, generate and develop type map, from
And so that urban changes region is shown in figure with developing type;With reference to Fig. 5, specifically adopt following steps:
(801) obtain the light satellite resultant image that will carry out developing type identification;
(802) obtain the size of image, if the columns of its pixel and line number are respectively nSample and nLine, wave band number is
NBand, defines the independent variable i=0, j=0 of ranks change;
(803) line number judges, line number, when less than nLine, enters step 804, otherwise enters step 810;
(804) columns judges, columns, when less than nSample, enters step 806, otherwise enters step 805;
(805) columns resets j=0, and line number i increases by 1, return to step 803;
(806) according to developing type library of spectra, using Spectral matching algorithm, obtain the pseudo- curve of spectrum at image (i, j) place;
(807) the pseudo- curve of spectrum that step 806 is obtained, is realized using Spectral matching algorithm and develops in type library of spectra
Pseudo- spectrum coupling;
(808) step 807 Spectral matching result is differentiated, obtains the differentiation type at step 806 (i, j) position,
And the type is given corresponding color;
(809) columns cumulative 1, enters step 804;
(810) travel through all row and columns, terminate quick identification to generate based on the Spectral matching developing type library of spectra
Differentiate and develop type map, effect is as shown in Figure 6.
Claims (5)
1. the urban changes region based on light satellite and differentiation type rapid extracting method are it is characterised in that specifically include following
Step:
(1) obtain the light satellite image of different year in same detection region;The described time at least includes Y1Time, Y2Time
And Y3Time;
(2) by following steps, data prediction is carried out to light satellite image:
(201) radiation calibration:Relative detector calibration is carried out to urban lighting satellite image;
(202) go negative value:Image after step (201) radiation calibration is carried out with negative value process, the value less than 0 is given up;
(203) Image registration:The light satellite image after negative value process will be removed through step (202) according to geographical coordinate, to the time
Data carries out registration;
(204) wave band synthesis:The image of each different year is considered as a wave band, according to time order and function order, image is carried out
Wave band synthesizes, and obtains a scape multiband image;
(3) setting develops the color of type, represents different types of evolution with different colours;
(4) pseudo color composing:Y is chosen through step (204) urban lighting satellite image after processing1Time, Y2Time and Y3
The image in time, wherein, Y1<Y2<Y3;Carry out pseudo color composing to the image in 3 times to show, wherein, Y1Time image is arranged
For red channel, Y2Time image is set to green channel, Y3Time image is set to blue channel;
(5) color of the different types of evolution being arranged according to step (3), to the False color comp osite image of step (4) by visual observation
Interpretation preliminary judgement develops type, detection zone is divided into the region of different types of evolution;
(6) build the pseudo- curve of spectrum:Choose each pixel developing type area in detection zone respectively, extract this pixel and go through
Year DN value, with the time as transverse axis, DN value be the longitudinal axis construction DN value changes curve, obtain each differentiation type the pseudo- curve of spectrum;
(7) set up and develop type library of spectra:The color of the different types of evolution being arranged according to step (3), chooses each differentiation respectively
The single pixel of type area or more than 2 pixels, are respectively directed to each differentiation type area and average, and construct each differentiation class
The pseudo- curve of spectrum of type, sets up the differentiation type library of spectra being made up of the pseudo- curve of spectrum;
(8) rapid extraction in urban changes region:The differentiation type library of spectra set up according to step (7), is calculated using Spectral matching
Method, is quickly identified to developing type, is that different types of evolution gives corresponding color, generates and develop type map, so that
Urban changes region is shown in figure with developing type.
2. the urban changes region based on light satellite according to claim 1 and differentiation type rapid extracting method, its
It is characterised by:In step (201), carry out relative detector calibration using below equation:
Y=c0+c1x+c2x2……(1)
Wherein, c0、c1And c2It is relative detector calibration parameter, provided by remote sensor production unit or Subscriber Unit, x represents DN value,
Y represent relative detector calibration after DN value.
3. the urban changes region based on light satellite according to claim 1 and differentiation type rapid extracting method, its
It is characterised by:In step (202), go negative value using below equation:
yDN > 0=(xradiation> 0) × xradiation……(2)
Wherein, yDN > 0Represent the image after removing negative value, xradiationRepresent the image after relative detector calibration.
4. the urban changes region based on light satellite according to claim 1 and differentiation type rapid extracting method, its
It is characterised by:The described different colours of step (3) represent that different types of evolution is specially:
Represent differentiation Class1 with black;Represent differentiation type 2 with white;Represent differentiation type 3 with blue, cyan and green;With
Yellow, redness and pink colour represent differentiation type 4.
5. the urban changes region based on light satellite according to claim 1 and differentiation type rapid extracting method, its
It is characterised by:Quickly identified to developing type using following steps in step (8):
(801) obtain the light satellite resultant image that will carry out developing type identification;
(802) obtain the size of image, if the columns of its pixel and line number are respectively nSample and nLine, wave band number is
NBand, defines the independent variable i=0, j=0 of ranks change;
(803) line number judges, line number, when less than nLine, enters step 804, otherwise enters step 810;
(804) columns judges, columns, when less than nSample, enters step 806, otherwise enters step 805;
(805) columns resets j=0, and line number i increases by 1, return to step 803;
(806) obtain the pseudo- curve of spectrum at image (i, j) place;
(807) the pseudo- curve of spectrum that step 806 is obtained, is realized and the puppet developing in type library of spectra using Spectral matching algorithm
The coupling of spectrum;
(808) step 807 Spectral matching result is differentiated, obtain the differentiation type at step 806 (i, j) position, and will
The type gives corresponding color;
(809) columns cumulative 1, enters step 804;
(810) all row and columns have been traveled through, the Spectral matching terminating quick identification to generate based on developing type library of spectra differentiates
Develop type map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410262168.XA CN104036507B (en) | 2014-06-13 | 2014-06-13 | Light satellite based urban change area and evolution type rapid extraction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410262168.XA CN104036507B (en) | 2014-06-13 | 2014-06-13 | Light satellite based urban change area and evolution type rapid extraction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104036507A CN104036507A (en) | 2014-09-10 |
CN104036507B true CN104036507B (en) | 2017-02-15 |
Family
ID=51467266
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410262168.XA Expired - Fee Related CN104036507B (en) | 2014-06-13 | 2014-06-13 | Light satellite based urban change area and evolution type rapid extraction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104036507B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108052876A (en) * | 2017-11-28 | 2018-05-18 | 广东数相智能科技有限公司 | Regional development appraisal procedure and device based on image identification |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609711A (en) * | 2012-02-21 | 2012-07-25 | 核工业北京地质研究院 | Information extraction method applicable to hyperspectral image |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5738564B2 (en) * | 2010-09-30 | 2015-06-24 | オリンパス株式会社 | Image processing system |
-
2014
- 2014-06-13 CN CN201410262168.XA patent/CN104036507B/en not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609711A (en) * | 2012-02-21 | 2012-07-25 | 核工业北京地质研究院 | Information extraction method applicable to hyperspectral image |
Non-Patent Citations (3)
Title |
---|
Yueliang Ma et al..Remote sensing monitoring and driving force analysis of urban expansion in Guangzhou City, China.《Habitat International》.2010,第34卷(第2期),第228-235页. * |
基于遥感影像的城市土地利用变化检测研究;王勇;《城市勘测》;20121231(第6期);第96-99页 * |
宋妍 等.基于极大似然估计采样一致性准则的遥感影像配准参数解算方法研究.《测绘科学》.2011,第36卷(第1期),第51-54页. * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108052876A (en) * | 2017-11-28 | 2018-05-18 | 广东数相智能科技有限公司 | Regional development appraisal procedure and device based on image identification |
CN108052876B (en) * | 2017-11-28 | 2022-02-11 | 广东数相智能科技有限公司 | Regional development assessment method and device based on image recognition |
Also Published As
Publication number | Publication date |
---|---|
CN104036507A (en) | 2014-09-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108564109B (en) | Remote sensing image target detection method based on deep learning | |
CN111640159B (en) | Remote sensing image change detection method based on twin convolutional neural network | |
CN107292339B (en) | Unmanned aerial vehicle low-altitude remote sensing image high-resolution landform classification method based on feature fusion | |
CN109858450B (en) | Ten-meter-level spatial resolution remote sensing image town extraction method and system | |
CN105631880A (en) | Lane line segmentation method and apparatus | |
WO2018076138A1 (en) | Target detection method and apparatus based on large-scale high-resolution hyper-spectral image | |
CN111291826A (en) | Multi-source remote sensing image pixel-by-pixel classification method based on correlation fusion network | |
CN105868683A (en) | Channel logo identification method and apparatus | |
CN103489196A (en) | Moving object detection method based on codebook background modeling | |
Hosseinpoor et al. | Convolutional neural network for building extraction from high-resolution remote sensing images | |
CN107992856A (en) | High score remote sensing building effects detection method under City scenarios | |
CN109741337B (en) | Region merging watershed color remote sensing image segmentation method based on Lab color space | |
CN106875407A (en) | A kind of unmanned plane image crown canopy dividing method of combining form and marking of control | |
CN104036507B (en) | Light satellite based urban change area and evolution type rapid extraction method | |
CN112927252B (en) | Newly-added construction land monitoring method and device | |
CN104899558A (en) | Scene recognition and colorization processing method for vehicle-mounted infrared image | |
CN111046783A (en) | Slope geological disaster boundary extraction method for improving watershed algorithm | |
Xia et al. | An approach for road material identification by dual-stage convolutional networks | |
Huang et al. | A target fusion-based approach for classifying high spatial resolution imagery | |
CN110059704A (en) | A kind of rare-earth mining area remote sensing information intelligent extract method of visual attention model driving | |
CN111738201B (en) | Method and system for extracting remote sensing image of woodland based on region-of-interest network | |
CN113963265A (en) | Small sample small target rapid detection and identification method for complex remote sensing land environment | |
Moumtzidou et al. | Road passability estimation using deep neural networks and satellite image patches | |
CN103106655A (en) | Construction site unsupervised extraction method based on remote-sensing image | |
Swaine et al. | Operational pipeline for a global cloud-free mosaic and classification of sentinel-2 images |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170215 Termination date: 20170613 |
|
CF01 | Termination of patent right due to non-payment of annual fee |