CN107730496A - A kind of multi-temporal remote sensing image building change detecting method based on image blocks - Google Patents
A kind of multi-temporal remote sensing image building change detecting method based on image blocks Download PDFInfo
- Publication number
- CN107730496A CN107730496A CN201711016143.1A CN201711016143A CN107730496A CN 107730496 A CN107730496 A CN 107730496A CN 201711016143 A CN201711016143 A CN 201711016143A CN 107730496 A CN107730496 A CN 107730496A
- Authority
- CN
- China
- Prior art keywords
- building
- change
- region
- phase
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 48
- 238000012360 testing method Methods 0.000 claims abstract description 29
- 238000004445 quantitative analysis Methods 0.000 claims abstract description 7
- 239000012491 analyte Substances 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 14
- 238000011160 research Methods 0.000 description 9
- 238000002474 experimental method Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000003595 spectral effect Effects 0.000 description 4
- 235000013399 edible fruits Nutrition 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012372 quality testing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012800 visualization 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G06T5/70—
-
- 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
Abstract
The invention discloses a kind of multi-temporal remote sensing image building change detecting method based on image blocks, this method inputs the thick result of building analyte detection of different phases first, each testing result length and width are distinguished into N deciles, ratio is made to the building number of pixels in two phase the same areas of front and rear arbitrary time span, the building change in the region is divided into by " significantly increasing ", " being basically unchanged " and " substantially reducing " three kinds of changing patteries based on threshold value, then the changing pattern in each region is marked on latter phase image, exports testing result.In addition, the present invention can also make the quantitative analysis of area change based on ratio shared by the two phase floor area of buildings of front and rear arbitrary time span.The present invention can consider contextual information, overcome the noise of high score image, effectively realize the fast automatic change detection of building, and fully excavate the changing pattern of building, can be issued to comparatively ideal precision in building testing result in general condition.
Description
Technical field
The invention belongs to technical field of image processing, is related to a kind of remote sensing image building change detecting method, specifically relates to
A kind of and multi-temporal remote sensing image building change detecting method based on image blocks.
Background technology
Remote sensing is one of important means of earth observation.With such as IKONOS, Quick Bird, WorldView,
The lift-off of the High Resolution Remote Sensing Satellites such as GeoEye and high score two, the spatial resolution and temporal resolution of remote sensing image all obtain
To being obviously improved.The data source of high score remote sensing image is increasingly wider, renewal is more and more faster.Disaster prison based on remote sensing technology
The application such as survey, urban sprawl, urban planning and land management is significant to country and society.In these applications, one
Important step is exactly timely acquisition change information.
Remote sensing image change detection purpose be identify change species and corresponding geographical position and evaluate change essence
Degree.The construction zone that multi-temporal remote sensing image changes, often examined with city variation monitoring described above, the architecture against regulations
Survey, the application such as geography information quickly updates, Natural calamity monitoring or emergency response it is relevant.Therefore, research is based on multi-temporal remote sensing
The building change of image detects and to analyze its changing pattern significant.
The method of remote sensing image change detection is various.In general it can be divided into and directly compare, converted from original image, base
In classification, based on machine learning and sophisticated method this five major classes method.However, these methods are still difficult to meet that high score image becomes
Change the demand of detection in a particular application.In short, the problem of main and deficiency include:
(1) traditional change detecting method is based on spectral information more, is not suitable for high score image.
Direct comparison method, from original image conversion, based on classification etc. change detecting method mostly towards middle low resolution
Remote sensing image, based on spectral information.Different time obtain remote sensing image by space, spectrum and when equal condition influenceed,
By radiate, the condition such as air is influenceed, bring difficulty to high accuracy change detection.In addition, high-resolution remote sensing image is general
Only four near-infrared, red, green and blue wave bands, and spatial information enriches more than middle low resolution image, it is poor inside similar atural object
Different increase, difference is not notable between different atural objects.Traditional detection method based on spectral information is caused to be applied to high score image
Substantial amounts of false-alarm and false dismissal can be caused.
(2) most of high-precision change detection algorithm is also more remote apart from practical application at present.
The geo-information product production unit such as Bureau of Surveying and Mapping, geography information center often realizes atural object using artificial delineate at present
The method that classification is changed detection generation thematic map again, although precision is high, time-consuming, labor intensive is more, efficiency is low;Supervision
Study tends to obtain the result of high-precision target identification and change detection, but generally requires the substantial amounts of training sample of artificial collection
This, and the training for carrying out model is consumed a longer time, while the generalization ability of different models is different, it is difficult to find while be applied to
The high precision test model of all kinds of detection zones.Therefore, although these methods can obtain degree of precision under certain condition at present,
But also have apart from the automation application of reality more remote.
(3) mass data is faced, lacks simple, fast and effectively change detecting method.
In recent years, with the lift-off of a large amount of business high score satellites and the popularization of Multiple Source Sensor platform, a certain area is obtained
Multidate multi-source high score image in short time interval is no longer difficult.In face of the mass remote sensing data of daily TB levels, described in (2)
Certain methods it is more complicated, time-consuming, and traditional change detecting method is mostly based on spectral information, is not particularly suited for balloon score
According to.Therefore, it is still a huge challenge using change detection algorithms quick, simple, efficient, suitable for high performance environments.
(4) city local scale and following change detection Research Significance are great, but it is effectively theoretical to lack system at present
Method.
With the rapid development of social economy, Urbanization in China is accelerated.Thus bring traffic congestion, break rules and regulations to build
Build, removal municipal administration a series of problems, such as.A kind of important hand of the remote sensing as fields such as urban planning, geographical data bank renewals
Section, can carry out effective application.However, current research is mostly based on this overall yardstick of city, it is intended to study urban sprawl or
Land use change survey.Carried out based on high score image the city slight change detection of block and following yardstick research and method compared with
It is few.However, these researchs have significant application value in fields such as architecture against regulations detection, urban planning, construction area monitorings.
(5) many algorithms of change detection at present, it is also very limited to the analysis mining of change and its essence.
Common change detection algorithm generally can be divided into two major classes, i.e., only detects to change and detect change type.Mesh
Preceding existing method is in the majority to detect to change, and the analysis, especially quantitative analysis to change are also weaker.On the other hand, when long
The mutation analysis research of sequence remote sensing image generally requires to study the changing pattern of certain object, and current research first detects respectively mostly
The target of individual phase carries out terrain classification, then is manually compared, and intelligence degree is relatively low, and easily mix it is subjective because
Element.To sum up, the algorithm requirements that analysis mining can be carried out to change and its essence are big.
To sum up, study based on high score image, the quick change detection side of building high accuracy of changing pattern can be analysed in depth
Method, there is important research and application value.
The content of the invention:
In order to solve the above-mentioned technical problem, the invention provides a kind of multi-temporal remote sensing image building based on image blocks
Change detecting method.
The technical solution adopted in the present invention is:A kind of multi-temporal remote sensing image building change detection based on image blocks
Method, it is characterised in that the building change detection of front and rear two phase comprises the following steps:
Step A1:By the length of the building testing result of the same area A of reading former and later two phases and wide N etc. respectively
Point, 2*N*N identical image blocks are divided into, obtain the subregion of N*N formed objects;
Step A2:To each sub-regions, the sum of all pixels that building is judged in former and later two phases is counted respectively, and
Calculate its ratio R with region A sum of all pixelsT1And RT2;
Step A3:According to change threshold T, the T > 1 of setting, judged according to following rule;
IfThen region A buildings occupied area significantly increases, and is judged to " significantly increasing " pattern, changes;
IfThen region A buildings occupied area substantially reduces, and is judged to " substantially reducing " pattern, changes;
IfThen region A buildings occupied area is held essentially constant, and is judged to " being basically unchanged " pattern, does not have
Change;
Step A4:According to the detection of step 3 and judged result, corresponding region is marked on the remote sensing image of latter phase,
Export testing result.
For the data of any two phase, except the change for exporting adjacent front and rear two phases one by one according to above step detects knot
Outside fruit, following operate can be also carried out:
(1) data of any two phase are selected, according to above step, detects and exports the building in random time span
Result of variations.
(2) based on building in each phase in the pixel ratio shared by the region, the quantitative analysis region is at this
Between building situation of change in span, can use and draw the expression of the method for visualizing such as line chart.
Advantage of this approach is that:
(1) detection is changed based on image blocks, can effectively overcomes the noise of high score image building extraction result, robust
Property is strong, and accuracy of detection is substantially better than traditional change detecting method.It is not suitable for high score image for traditional change detecting method to provide
A solution.
(2) automatic detection goes out the situation of change of certain region building, and the quantitative analysis region can be realized sometime
Building situation of change in section, effectively excavates change information.
(3) detection speed is fast.For one kilometer of sub-meter grade remote sensing image of circumference, detection time was at 1 second or so.Meanwhile
This method is based on image blocks, can accelerate under parallel computation environment, and changing fast automatic detecting for a wide range of building provides
A kind of effective ways.
(4) towards high score image and the scope of settable each image blocks, it can be effectively used for urban planning, city locally becomes
Change the applications such as monitoring, geographical data bank renewal.
The present invention has the advantages that:
(1) production unit for geo-information product provides a kind of fast and efficiently remote sensing image building change inspection
Survey method.Manpower and production time can effectively be saved.
(2) be deeply excavate change essence, realize quantitative description region change provide a kind of Research Thinking and
Implementation method.
Brief description of the drawings
Fig. 1 is that the building of front and rear two phase of the embodiment of the present invention changes overhaul flow chart;
Fig. 2 is that the building of the multidate of the embodiment of the present invention changes overhaul flow chart;
Fig. 3 is the visualization mutation analysis exemplary plot of the embodiment of the present invention;
Fig. 4 is the data source of three groups of experiments of the embodiment of the present invention, wherein (a) is photographed on 2008, (b) is photographed on 2010 years;
Fig. 5 is three pieces of experiment sample area essential information schematic diagrames of the embodiment of the present invention;
Fig. 6 is three groups of test blocks building quality testing as this method input of 2008 and 2010 of the embodiment of the present invention
Thick result schematic diagram is surveyed, wherein (a) is first piece of test block building thick result schematic diagram of analyte detection in 2008, (b) is first piece
The test block building thick result schematic diagram of analyte detection in 2010, (c) are that second piece of test block building thick result of analyte detection in 2008 is shown
It is intended to, (d) is second piece of test block building thick result schematic diagram of analyte detection in 2010, and (e) is that the 3rd piece of test block is built for 2008 years
The thick result schematic diagram of analyte detection is built, (f) is the 3rd piece of test block building thick result schematic diagram of analyte detection in 2010;
Fig. 7 is that the building of three groups of test blocks of the embodiment of the present invention changes testing result schematic diagram, wherein (a) is sample area
One convolution network method result schematic diagram, (b) are this method result schematic diagram of sample area one, and (c) is the convolutional network method of sample area two
Result schematic diagram, (d) are this method result schematic diagram of sample area two, and (e) is the convolutional network methods and resultses schematic diagram of sample area three, (f)
For this method result schematic diagram of sample area three.
Embodiment
Understand for the ease of those of ordinary skill in the art and implement the present invention, below in conjunction with the accompanying drawings and embodiment is to this hair
It is bright to be described in further detail, it will be appreciated that implementation example described herein is merely to illustrate and explain the present invention, not
For limiting the present invention.
The present invention is changed detection based on image blocks, and the floor area of building change in each region is divided into and " significantly increased
It is more ", " being basically unchanged " and " substantially reducing " these three changing patteries, thick result is detected as inputting using high score image building,
Two parameters of window isodisperse N and change threshold T are set, detection is changed based on image blocks, exports these three changing patteries
Corresponding image blocks.
Relevant this method realizes step, and for simplicity, two phases realizes step, Zhi Houzai before and after only discussing first
Expand to the situation of multidate.The building change detecting step (referring to accompanying drawing 1) of front and rear two phase is as follows:
(1) by the length of the building testing result of the same area A of reading former and later two phases and wide N deciles respectively, draw
It is divided into 2*N*N identical image blocks.That is, region A is divided into the subregion of N*N formed objects.
(2) to each sub-regions, the sum of all pixels that building is judged in former and later two phases is counted respectively, and calculate
Its ratio R with region A sum of all pixelsT1And RT2。
(3) according to the change threshold T (T > 1) of setting, judged according to following rule:
IfThen region A buildings occupied area significantly increases, and is judged to " significantly increasing " pattern, changes;
IfThen region A buildings occupied area substantially reduces, and is judged to " substantially reducing " pattern, changes;
IfThen region A buildings occupied area is held essentially constant, and is judged to " being basically unchanged " pattern, does not have
Change.
(4) detection and judged result more than, corresponding region, output detection are marked on the remote sensing image of latter phase
As a result.
For the data of any two phase, except the change for exporting adjacent front and rear two phases one by one according to above step detects knot
Fruit (referring to accompanying drawing 2) outside, can also carry out following operate:
(1) data of any two phase are selected, according to above step, detects and exports the building in random time span
Result of variations.
(2) based on building in each phase in the pixel ratio shared by the A of region, quantitative analysis region A is in this time
Building situation of change in span, it can use and draw the method for visualizing such as line chart expression (accompanying drawing 3).
Below based on three groups of experiments and a case, change detection illustrates with the operation analyzed to more than.
The multispectral image of bird soon in the two scape optical valleys south area in accompanying drawing 4 is shot in Augusts, 2008 and 2010 12 respectively
Month, spatial resolution is 2.4 meters.Three pieces of regions for having significantly building change are chosen as testing sample area, as shown in Figure 5.Experiment
The Main change in region one and three is that building increases;Experimental Area two is because village changes city in latter phase while occurs building
Thing is built to increase and the changing pattern of reduction.
The building testing result obtained using morphology building index is respectively as shown in six width subgraphs in accompanying drawing 6
(subgraph (a), (b) are respectively first piece of test block testing result of 2008 and 2010 years;(c), (d) is respectively second piece of reality
Test area 2008 and the testing result of 2010;(e), (f) is respectively the 3rd piece of test block detection knot of 2008 and 2010 years
Fruit).The result of this three Kuai Yang areas building extraction is general, if based on traditional change detecting method to the building in this three pieces of regions
Thing extraction result is changed detection, due to much noise present in extraction result, change detection band can be given substantial amounts of empty
Alert and false dismissal.This change detecting method also proposed to this patent brings very big challenge.
From depth convolutional network and this method expansion contrast experiment.Visio of this method based on OpenCV3.1.0
Studio2015 programming realizations.Change testing result as shown in Figure 7.Actually whether occurred based on the image blocks for identifying change
Change to calculate recall ratio, precision ratio and overall accuracy respectively.Corresponding accuracy of detection and time used are respectively such as Tables 1 and 2 institute
Show.
As can be seen that this method in accuracy of detection and is superior to depth convolutional network on the calculating time.
More test result indicates that, the algorithm value is suggested as follows:
(1) change threshold take 3 and more than, and no more than 5;
(2) window isodisperse ensures each window length of side between 130 meters to 200 meters.
Now easily there is more satisfactory testing result.
Each region each method accuracy of detection (%) and this method parameter value in 1 three groups of experiments of table
Time (unit used in each region each method in 2 three groups of experiments of table:Second)
Experimental Area | Depth convolutional network | This method |
Sample area one | 2.32 | 1.13 |
Sample area two | 2.34 | 1.13 |
Sample area three | 2.29 | 1.09 |
Existing four scape is shot in the remote sensing image of the areal of 2000,2004,2008 and 2012 respectively.It is right
Wherein a certain piece of region, is operated according to algorithm above, is obtained the region 2004 and is with the ratio between component shared by building in 2000
0.5,2008 year with building in 2004 shared by the ratio between component for 1.8,2012 with building in 2008 shared by the ratio between component be
1.2.So it is hereby achieved that:
(1) 2008 year with building in 2000 shared by the ratio between component be 0.9;
(2) 2012 years with building in 2000 shared by the ratio between component be 1.08;
(3) 2012 years with building in 2004 shared by the ratio between component be 2.16.
Three conclusions of the above may be interpreted as, region building in 2000 to 2008 this 8 years time scale
It is basically unchanged, building significantly increased in 2004 to 2012 this 8 years time scale, at 2000 to 2012
Building is basically unchanged in this 12 years time scale.
It can draw out the region in whole time series according to the ratio of three above different time sections and build number
Change curve, so as to quantitative analysis.
The main innovation of this method is:
(1) some region of floor area of building situation of change is divided into " significantly increasing ", " being basically unchanged " and " significantly subtracted
It is few " these three changing patteries, the change detection of certain region building is regarded as that these three changing patteries are identified.
(2) when carrying out more based on the image blocks obtained by remote sensing image grid partition, setting change threshold and window size
The change detection of phase building.
(3) each phase testing result of the same area can form one group of high dimension vector, it is easy to from the quantitative angle analysis area
Domain building is in the sometime situation of change in sequence.
It should be appreciated that the part that this specification does not elaborate belongs to prior art.
It should be appreciated that the above-mentioned description for preferred embodiment is more detailed, therefore can not be considered to this
The limitation of invention patent protection scope, one of ordinary skill in the art are not departing from power of the present invention under the enlightenment of the present invention
Profit is required under protected ambit, can also be made replacement or deformation, be each fallen within protection scope of the present invention, this hair
It is bright scope is claimed to be determined by the appended claims.
Claims (2)
- A kind of 1. multi-temporal remote sensing image building change detecting method based on image blocks, it is characterised in that front and rear two phase Building change detection comprise the following steps:Step A1:By the length of the building testing result of the same area A of reading former and later two phases and wide N deciles respectively, draw It is divided into 2*N*N identical image blocks, obtains the subregion of N*N formed objects;Step A2:To each sub-regions, the sum of all pixels that building is judged in former and later two phases is counted respectively, and calculate Its ratio R with region A sum of all pixelsT1And RT2;Step A3:According to change threshold T, the T > 1 of setting, judged according to following rule;IfThen region A buildings occupied area significantly increases, and is judged to " significantly increasing " pattern, changes;IfThen region A buildings occupied area substantially reduces, and is judged to " substantially reducing " pattern, changes;IfThen region A buildings occupied area is held essentially constant, and is judged to " being basically unchanged " pattern, is not changed;Step A4:According to the detection of step 3 and judged result, corresponding region is marked on the remote sensing image of latter phase, is exported Testing result.
- A kind of 2. multi-temporal remote sensing image building change detecting method based on image blocks, it is characterised in that any two phase Building change detection comprise the following steps:Step B2:The data of any two phase are selected, according to the building change detecting method of front and rear two phase, detects and exports Building result of variations in random time span;Step B2:Based on building in each phase in the pixel ratio shared by the A of region, quantitative analysis region A is in this time Building situation of change in span.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711016143.1A CN107730496A (en) | 2017-10-26 | 2017-10-26 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711016143.1A CN107730496A (en) | 2017-10-26 | 2017-10-26 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107730496A true CN107730496A (en) | 2018-02-23 |
Family
ID=61214009
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711016143.1A Pending CN107730496A (en) | 2017-10-26 | 2017-10-26 | A kind of multi-temporal remote sensing image building change detecting method based on image blocks |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107730496A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108776772A (en) * | 2018-05-02 | 2018-11-09 | 北京佳格天地科技有限公司 | Across the time building variation detection modeling method of one kind and detection device, method and storage medium |
CN110136170A (en) * | 2019-05-13 | 2019-08-16 | 武汉大学 | A kind of remote sensing image building change detecting method based on convolutional neural networks |
CN111323768A (en) * | 2020-02-26 | 2020-06-23 | 北京佳格天地科技有限公司 | Building change identification method, device, terminal and storage medium |
CN111582194A (en) * | 2020-05-12 | 2020-08-25 | 吉林大学 | Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network |
CN111738144A (en) * | 2020-06-19 | 2020-10-02 | 中国水利水电科学研究院 | Surface water product generation method and system based on Google Earth Engine cloud platform |
CN111798415A (en) * | 2020-06-16 | 2020-10-20 | 中设设计集团股份有限公司 | Method and device for monitoring buildings in expressway control area and storage medium |
CN116957883A (en) * | 2023-07-25 | 2023-10-27 | 南京智绘星图信息科技有限公司 | Construction land use control method based on data analysis |
CN117333530A (en) * | 2023-12-01 | 2024-01-02 | 四川农业大学 | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101751674A (en) * | 2010-01-08 | 2010-06-23 | 西安电子科技大学 | Change detection method of remote sensing image based on Graph-cut and general gauss model (GGM) |
CN101937079A (en) * | 2010-06-29 | 2011-01-05 | 中国农业大学 | Remote sensing image variation detection method based on region similarity |
CN102213593A (en) * | 2011-04-08 | 2011-10-12 | 东南大学 | Method for rapidly acquiring abnormal land |
CN102967850A (en) * | 2011-09-02 | 2013-03-13 | 吴立新 | Disaster remote sensing automatic identification method based on multi-scale grid and fractal dimensional changes |
CN103077515A (en) * | 2012-12-29 | 2013-05-01 | 北方工业大学 | Multi-spectral image building change detection method |
CN105447208A (en) * | 2016-02-01 | 2016-03-30 | 福建师范大学 | Automatic urban geographical database updating method for buildings |
CN106372612A (en) * | 2016-09-09 | 2017-02-01 | 河海大学 | Multi-temporal remote sensing image change detection method combining FCM with MRF model |
CN106384352A (en) * | 2016-09-09 | 2017-02-08 | 河海大学 | Multi-temporal remote sensing image change detection method based on fusion strategy and FCM |
CN106650571A (en) * | 2016-09-09 | 2017-05-10 | 河海大学 | Multi-temporal remote sensing image change detection method based on adaptive chi-squared transform (CST) |
CN107248172A (en) * | 2016-09-27 | 2017-10-13 | 中国交通通信信息中心 | A kind of remote sensing image variation detection method based on CVA and samples selection |
-
2017
- 2017-10-26 CN CN201711016143.1A patent/CN107730496A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101751674A (en) * | 2010-01-08 | 2010-06-23 | 西安电子科技大学 | Change detection method of remote sensing image based on Graph-cut and general gauss model (GGM) |
CN101937079A (en) * | 2010-06-29 | 2011-01-05 | 中国农业大学 | Remote sensing image variation detection method based on region similarity |
CN102213593A (en) * | 2011-04-08 | 2011-10-12 | 东南大学 | Method for rapidly acquiring abnormal land |
CN102967850A (en) * | 2011-09-02 | 2013-03-13 | 吴立新 | Disaster remote sensing automatic identification method based on multi-scale grid and fractal dimensional changes |
CN103077515A (en) * | 2012-12-29 | 2013-05-01 | 北方工业大学 | Multi-spectral image building change detection method |
CN105447208A (en) * | 2016-02-01 | 2016-03-30 | 福建师范大学 | Automatic urban geographical database updating method for buildings |
CN106372612A (en) * | 2016-09-09 | 2017-02-01 | 河海大学 | Multi-temporal remote sensing image change detection method combining FCM with MRF model |
CN106384352A (en) * | 2016-09-09 | 2017-02-08 | 河海大学 | Multi-temporal remote sensing image change detection method based on fusion strategy and FCM |
CN106650571A (en) * | 2016-09-09 | 2017-05-10 | 河海大学 | Multi-temporal remote sensing image change detection method based on adaptive chi-squared transform (CST) |
CN107248172A (en) * | 2016-09-27 | 2017-10-13 | 中国交通通信信息中心 | A kind of remote sensing image variation detection method based on CVA and samples selection |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108776772B (en) * | 2018-05-02 | 2022-02-08 | 北京佳格天地科技有限公司 | Cross-time building change detection modeling method, detection device, method and storage medium |
CN108776772A (en) * | 2018-05-02 | 2018-11-09 | 北京佳格天地科技有限公司 | Across the time building variation detection modeling method of one kind and detection device, method and storage medium |
CN110136170A (en) * | 2019-05-13 | 2019-08-16 | 武汉大学 | A kind of remote sensing image building change detecting method based on convolutional neural networks |
CN111323768B (en) * | 2020-02-26 | 2023-12-12 | 北京佳格天地科技有限公司 | Building change identification method, device, terminal and storage medium |
CN111323768A (en) * | 2020-02-26 | 2020-06-23 | 北京佳格天地科技有限公司 | Building change identification method, device, terminal and storage medium |
CN111582194A (en) * | 2020-05-12 | 2020-08-25 | 吉林大学 | Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network |
CN111582194B (en) * | 2020-05-12 | 2022-03-29 | 吉林大学 | Multi-temporal high-resolution remote sensing image building extraction method based on multi-feature LSTM network |
CN111798415A (en) * | 2020-06-16 | 2020-10-20 | 中设设计集团股份有限公司 | Method and device for monitoring buildings in expressway control area and storage medium |
CN111738144A (en) * | 2020-06-19 | 2020-10-02 | 中国水利水电科学研究院 | Surface water product generation method and system based on Google Earth Engine cloud platform |
CN116957883A (en) * | 2023-07-25 | 2023-10-27 | 南京智绘星图信息科技有限公司 | Construction land use control method based on data analysis |
CN116957883B (en) * | 2023-07-25 | 2024-04-05 | 南京智绘星图信息科技有限公司 | Construction land use control method based on data analysis |
CN117333530A (en) * | 2023-12-01 | 2024-01-02 | 四川农业大学 | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building |
CN117333530B (en) * | 2023-12-01 | 2024-02-06 | 四川农业大学 | Quantitative analysis method for change trend of Tibetan Qiang traditional aggregation building |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107730496A (en) | A kind of multi-temporal remote sensing image building change detecting method based on image blocks | |
Yang et al. | Spatiotemporal evolution of urban agglomerations in four major bay areas of US, China and Japan from 1987 to 2017: Evidence from remote sensing images | |
Feng et al. | Spatiotemporal variation of landscape patterns and their spatial determinants in Shanghai, China | |
Jochem et al. | Identifying residential neighbourhood types from settlement points in a machine learning approach | |
CN110472661B (en) | Automatic change detection method and system based on historical background and current remote sensing image | |
CN111062368B (en) | City update region monitoring method based on Landsat time sequence remote sensing image | |
CN103345566B (en) | Based on the geochemical anomaly discrimination and evaluation method of Geological Connotation | |
Falahatkar et al. | Integration of remote sensing data and GIS for prediction of land cover map | |
CN104899562A (en) | Texture segmentation and fusion based radar remote-sensing image artificial building recognition algorithm | |
Kucsicsa et al. | Urban growth in the Bucharest metropolitan area: Spatial and temporal assessment using logistic regression | |
Gervasoni et al. | Convolutional neural networks for disaggregated population mapping using open data | |
Lu et al. | Regional assessment of pan-Pacific urban environments over 25 years using annual gap free Landsat data | |
Hoang et al. | Remote sensing–based urban green space detection using marine predators algorithm optimized machine learning approach | |
Kausika et al. | GeoAI for detection of solar photovoltaic installations in the Netherlands | |
Abriha et al. | Smaller is better? Unduly nice accuracy assessments in roof detection using remote sensing data with machine learning and k-fold cross-validation | |
Triantakonstantis et al. | A spatially heterogeneous expert based (SHEB) urban growth model using model regionalization | |
CN113901348A (en) | Oncomelania snail distribution influence factor identification and prediction method based on mathematical model | |
Aithal et al. | Prediction of spatial patterns of urban dynamics in Pune, India | |
Liu et al. | Landslide detection with Mask R-CNN using complex background enhancement based on multi-scale samples | |
Long et al. | Mapping parcel-level urban areas for a large geographical area | |
Yang et al. | Urban roads network detection from high resolution remote sensing | |
Chuangchang et al. | Modelling urban growth over time using grid-digitized method with variance inflation factors applied to spatial correlation | |
Gan et al. | A random forest based method for urban object classification using lidar data and aerial imagery | |
Zhang et al. | Semantic segmentation method accelerated quantitative analysis of the spatial characteristics of traditional villages | |
CN107133360B (en) | Construction method of large-scale remote sensing image feature point library |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180223 |