CN107463775B - Vegetation based on more Indices variation tendencies is lost whereabouts recognition methods - Google Patents
Vegetation based on more Indices variation tendencies is lost whereabouts recognition methods Download PDFInfo
- Publication number
- CN107463775B CN107463775B CN201710605772.1A CN201710605772A CN107463775B CN 107463775 B CN107463775 B CN 107463775B CN 201710605772 A CN201710605772 A CN 201710605772A CN 107463775 B CN107463775 B CN 107463775B
- Authority
- CN
- China
- Prior art keywords
- vegetation
- index
- lost
- whereabouts
- indices
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Image Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of, and the vegetation based on more Indices variation tendencies is lost whereabouts recognition methods.This method calculates the vegetation index sequential similarity with the starting time over the years using JM distance, generate vegetation index sequential similarity track, Potential vegetation, which is extracted, according to vegetation index sequential similarity variable quantity is lost region, and then by vegetation index is remarkably decreased and impervious surface index significantly rises region, clearly region is lost for vegetation, on this basis, according to water body index, bare soil index variation tendency feature, finally judge that the different vegetation such as urbanization, famineization and wetland is lost whereabouts.This method determines coupling relationship region by sequential similarity variable quantity, and then judges that vegetation is lost whereabouts according to a variety of Indices, does not depend on manual intervention setting threshold value, has the characteristics that robustness is good, nicety of grading is high, the degree of automation and strong antijamming capability.
Description
Technical field
The present invention relates to remote sensing information process fields, and in particular to one kind is based on sequential similarity variable quantity and Indices
The vegetation of variation tendency is lost whereabouts automatic identifying method.
Background technique
Land use/covering variation is the interactive result of Man & Nature.Over nearest more than 30 years, with China's economic
It rapidly develops, land use/covering variation shows the distinguishing feature of following several respects: (1) urbanization, Elements of Urban Land Scale add
Play occupies high-quality cultivated land resource；(2) soil famine, on the one hand, after rural population transfer to city, leave arable land wasted phenomenon is serious；
On the other hand, arid and semiarid region of Northwest China, ecological environment is relatively fragile, although country puts into a large amount of manpower and material resources and implements three Norths
The engineering measures such as shelter-forest, but still not can avoid some some areas desertification.Fast real-time monitoring land use/covering variation
For ensuring that ecological safety, grain security etc. are all extremely important.Remote sensing technology plays in land use/covering variation monitoring
Increasingly important role.
Land use/covering variation remote sensing monitoring generallys use the variation monitoring method of double phases, passes through double phases first
Comparison identify region of variation, then again to region of variation carry out land use/cover type remote sensing information extract.This side
Method is disadvantageous in that repeatedly Land Use/Cover Classification error accumulation, data consistency over the years are relatively poor, it is difficult to real
Now automatic monitor for continuously of a wide range of many years.Carry out the continuous automatic prison of land use/covering variation based on many years remote sensing time series data
It surveys, it has also become the developing direction of land change scientific research.
Carry out land use/covering variation monitoring the relevant technologies currently based on timing remotely-sensed data, main sides focus on city
The hot fields such as cityization and forest interference.Variation monitoring technology based on timing remotely-sensed data helps to disclose multiple period soil
Ground utilization/covering dynamic change, can continue to monitor change procedure, be effectively prevented from the limitation of double Temporal variation monitoring technology
Property.It flourishes with land use/covering variation monitoring technology is carried out based on timing remotely-sensed data, the following aspects is still
Need further to be analysed in depth and inquire into: (1) it is waste to be turned to a kind of important land use/covering change procedure, although when very long
Between since attract attention, but make full use of the technical method of timing remotely-sensed data still rarely seen；(2) it is interfered with urbanization, forest
The timing remote sensing monitoring technique algorithm that monitoring is the theme is relatively complicated, and the degree of automation is to be improved；(3) it examines simultaneously at present
Consider a variety of land uses/covering change type change detecting method, is based on data driven mode, it is difficult to disclose it well more
Change procedure is opposite to lack geography meaning.
Summary of the invention
The present invention is proposed to be stood a kind of vegetation and is lost whereabouts automatic identifying method, can detect simultaneously vegetation urbanization, famineization with
And the loss whereabouts that wetland etc. is different, technical support tool is provided for a wide range of automatic detection coupling relationship.
The present invention is implemented with the following technical solutions: a kind of vegetation loss whereabouts knowledge based on more Indices variation tendencies
Other method, which comprises the steps of: step S01: vegetation index, impervious surface index, soil bareness are established and is referred to
Number, water body index time series data collection over the years；Step S02: calculating vegetation index sequential similarity by pixel year by year, establishes timing phase
Like property track；Step S03: being based on sequential similarity track, extracts vegetation index sequential similarity variable quantity；Step S04: it is based on
Vegetation index sequential similarity variable quantity obtains Potential vegetation and is lost region；Step S05: it calculates Indices variation over the years and becomes
Gesture；Step S06: being based on sequential similarity variable quantity and Indices variation tendency, establishes vegetation and is lost whereabouts differentiation flow chart；
Step S07: carrying out vegetation and be lost whereabouts automatic identification, obtains research area vegetation and is lost whereabouts distribution map.
Compared to the prior art, the invention has the following advantages:
(1) the vegetation index sequential similarity variable quantity that this special models fitting obtains using logic, can disclose plant well
It is lost the amplitude of variation of front and back, is conducive to the interference for eliminating individual time noises, preferably extraction vegetation is lost region of variation.
(2) a variety of Indices secular variation trend are comprehensively utilized, vegetation is formed and is lost different whereabouts remote-sensing monitoring methods
Frame system is compared with a certain vegetation loss type monitoring is only carried out merely, can preferably avoid different loss types
Mistake point accidentally divides phenomenon.
The variation tendency of (3) four big basic earth's surface cover types indicator vegetation can be lost variation whereabouts well, rely on ground
There is discipline background of science good geography to explain meaning.
(4) technical method established does not need that threshold value or human-computer interaction artificially is arranged, and method is clear, automatically
Change degree is high, in addition to Indices time series data, does not depend on other auxiliary datas, as a result reliable and stable.
Detailed description of the invention
Fig. 1 is the implementation flow chart of the embodiment of the present invention.
Fig. 2 urbanization is formed by 2001-2016 EVI, BCI, RIBS, LSWI time-sequence curve chart.
Fig. 3 desertification is formed by 2001-2016 EVI, BCI, RIBS, LSWI time-sequence curve chart.
Fig. 4 wetland is formed by 2001-2016 EVI, BCI, RIBS, LSWI time-sequence curve chart.
Fig. 5 vegetation index sequential similarity track 1.
Fig. 6 vegetation index sequential similarity track 2.
The schematic diagram of Fig. 7 acquisition sequential similarity variable quantity.
Fig. 8 vegetation is lost whereabouts decision rule.
Fig. 9 studies area vegetation and is lost whereabouts distribution map.
Specific embodiment
With reference to the accompanying drawing, technical solution of the present invention is specifically described.The following are specific embodiments of the present invention.
The present invention provides a kind of vegetation loss whereabouts recognition methods based on more Indices variation tendencies, as shown in Figure 1:
The many years time series data collection of research area's vegetation index, impervious surface index, soil bareness index, water body index is initially set up, so
It is determined afterwards based on vegetation index sequential similarity variable quantity and extracts coupling relationship region, and then combine the variation of a variety of Indices
Trend feature, automatic identification vegetation are lost whereabouts.
It further includes steps of
Step S01: vegetation index, impervious surface index, soil bareness index, water body index time series data over the years are established
Collection；
EVI, BCI, RIBS, LSWI are successively chosen, the Indices as characterization earth's surface elemental: vegetation index, no
Permeable facial index, soil bareness index, water body index.Within the scope of research area, 2001-2016 is successively established year by year by pixel
8 days maximums of EVI, BCI, RIBS, LSWI series Indices are combined to many years time series data collection.Utilize Whittaker
Smoother smoothing method is combined to more years time series data smoothing processings of EVI, BCI, RIBS, LSWI to original 8 days maximums, from
And obtain smooth 2001-2016 EVI in research area, when maximum was combined to many years in 8 days of BCI, RIBS, LSWI series Indices
Sequence data set is lost the basis of whereabouts identification as vegetation.According to a variety of different vegetation be lost whereabouts, as urbanization, famineization,
Wetland, selection is corresponding to refer to point, when being formed by 2001-2016 EVI, BCI, RIBS, LSWI Indices many years
Overture line chart is successively shown in Fig. 2, Fig. 3, Fig. 4.
Vegetation index: vegetation index is the factor for characterizing vegetation growth state and spacial distribution density.Common vegetation
Index has NDVI and EVI.NDVI is normalized differential vegetation index, and full name is Normalized Difference Vegetation
Index.EVI is enhancement mode meta file, and full name is Enhanced Vegetation Index.The calculation formula of EVI index
Are as follows:Wherein ρRedρBlue,ρNIRRespectively red spectral band, blue wave band and close
The reflectivity of infrared band.
Water body index: water body index is the index for characterizing Unified Surface Water Capacity or Humid Status.Common water body index Land
The calculation formula of SurfaceWater Index (LSWI) are as follows:Wherein ρSWIRIndicate that shortwave is red
The reflectivity of wave section.
Impervious surface index: the index of impervious surface index characterization urbanization degree.Common impervious surface index has life
Object physics index (Biophysical composition index, BCI), calculation formula are as follows:Wherein TC1、TC2、TC3First principal component, the second master respectively after K-T Transformation
Ingredient, third principal component；
Soil bareness index: normalization soil index (Ratio index for bright soil, RIBS) calculates public
Formula are as follows:Wherein In above-mentioned formula, NDSI is normalizing snow melting body index, and Green and SWIR1 are respectively
The green light band of MODIS image and the first short infrared wave band, NDSImax,NDSIminThe respectively maximum value of NDSI and minimum
Value, TC1max, TC1minRespectively TC1Maximum value and minimum value.MODIS data: Moderate Imaging Spectroradiomete data, full name
For Moderate Resolution Imaging Spectroradiometer.
Urbanization, famineization, wetland etc. refer to point, with the loss of vegetation, show becoming for vegetation index decline
Gesture.It shows as before vegetation is lost, the usual numerical value of vegetation index is higher and shows vegetation Phenological change in regular year
Feature, and after vegetation is lost generation, vegetation index shows lower level.The amplitude of variation of vegetation index can be vegetation
Whether generation, which is lost, provides reference frame.
Although different loss whereabouts, the common trait that vegetation index declines to a great extent, different vegetation stream are showed
It loses to showing different variation characteristics in the Indices many years time-sequence curve chart such as water body index, bare soil index.Such as:
In urbanization point, water body index is on a declining curve, and waterproof facial index, soil bareness index are in apparent ascendant trend
(see Fig. 2).And in vegetation famine point, water body index, soil bareness index show downward trend, and impervious surface only
Index shows ascendant trend (see Fig. 3).And in wetland point, impervious surface index, soil bareness index, water body index are equal
(see Fig. 4) in rising trend.Therefore, it can judge that different be lost of vegetation is gone according further to a variety of Indices variation tendencies
To.
Step S02: calculating vegetation index sequential similarity by pixel year by year, establishes sequential similarity track；
It is similar to the starting timing of time timing curve in 2001 to calculate annual vegetation index timing curve year by year by pixel
Property, the calculating of sequential similarity uses JM distance, to form 2002-2016 and 2001 year vegetation index sequential similarity rail
Mark.By taking stable vegetation point and vegetation are lost point (urbanization) as an example, it is formed by vegetation index sequential similarity track
See Fig. 5-6, compared to for stable vegetation region, the amplitude of variation that vegetation is lost vegetation index sequential similarity track in region is bright
It is aobvious to increase.It shows as before vegetation is lost generation, vegetation index sequential similarity is very high, and JM is apart from very little, as shown in Figure 5.And
After vegetation is lost generation, vegetation index sequential similarity weakens rapidly, and JM distance is also with increase, as shown in Figure 6.
Step S03: being based on sequential similarity track, extracts vegetation index sequential similarity variable quantity；
Based on 2001-2016 vegetation index sequential similarity track, using Logistic models fitting, when obtaining research
The pixel vegetation index sequential similarity variable quantity in section.The formula of Logistic model is as follows:
Wherein: f indicates that the sequential similarity (JM distance) in other times and the starting time 2001, independent variable x are the time,
It is indicated with the time.There are four parameters in Logistic model, and a, b, c, d are respectively provided with certain indicative significance.Wherein parameter a generation
Sequential similarity variable quantity in the table research period, variable quantity is bigger, and the degree for indicating variation is higher.Logistic model and
The corresponding meaning figure of its model parameter is shown in Fig. 7.
Within the scope of research area, it is based on sequential similarity track, calculates vegetation index sequential similarity variable quantity one by one, it is raw
Change spirogram at research area's vegetation index sequential similarity.
Step S04: being based on vegetation index sequential similarity variable quantity, obtains Potential vegetation and is lost region；
Sequential similarity variable quantity is bigger, and the tendency for indicating that vegetation is lost is more obvious.Therefore, when can be according to vegetation index
Sequence similitude variable quantity determines that Potential vegetation is lost region in research area.Assuming that vegetation index sequential similarity becomes in research area
Change amount M meets normal distribution N (μ, σ2), in given α significance, if M >=Q1-α, then the vegetation index of the pixel
Sequential similarity variable quantity significantly increases, it can be determined that the pixel belongs to Potential vegetation and is lost region.
Step S05: Indices variation tendency over the years is calculated
Using SenShi gradient method, 2001-2016 EVI, BCI, RIBS, LSWI timing curve are successively calculated by pixel
Many years general morphologictrend Q.As Q > 0, indicate the timing curve in certain ascendant trend；As Q < 0, the timing is indicated
Curve has certain downward trend.Based on Mann-Kendall method, further judge that the variation tendency of the timing curve is
It is no significant.According to significance test as a result, variation tendency is divided into three kinds of situations: (significant rise becomes significant positive trend
Gesture), without trend (constant) and significantly negative trend (significant downward trend).The corresponding 2001- of each pixel in area will be studied
EVI, BCI, RIBS, LSWI timing curve variation tendency testing result are successively saved in database within 2016.
Step S06: being based on sequential similarity variable quantity and Indices variation tendency, establishes vegetation and is lost whereabouts differentiation stream
Cheng Tu
In summary step establishes vegetation and is lost whereabouts differentiation flow chart (see Fig. 8).It is first depending on vegetation index timing phase
Like property variable quantity, the preliminary Potential vegetation that obtains is lost region, and then according to vegetation index, impervious surface index variation trend, mentions
Vegetation is taken to be lost region, the variation tendencies such as further comprehensive water body index, bare soil index determine that vegetation is lost whereabouts.
It is lost in regional scope in the Potential vegetation extracted according to vegetation index sequential similarity variable quantity, further by picture
Member judges whether vegetation index, impervious surface index are to be remarkably decreased trend, so that further clarifying Potential vegetation is lost area
Domain range.On this basis, it in conjunction with the variation tendency of water body index, bare soil index, obtains vegetation and is lost whereabouts: if water body refers to
Number, bare soil index show the trend of significantly rising, then it is wetland that vegetation, which is lost whereabouts,；If water body index, bare soil index
Significant downward trend is showed, then it is famineization that vegetation, which is lost whereabouts,；If water body index shows significant downward trend
And bare soil index shows significant ascendant trend, then it is urbanization that vegetation, which is lost whereabouts,.
Step S07: carrying out vegetation and be lost whereabouts automatic identification, obtains research area vegetation and is lost whereabouts distribution map
Whereabouts is lost according to the vegetation established and differentiates flow chart, judges whether vegetation is lost by pixel, if hair
Raw vegetation is lost, and then determines that it is lost whereabouts, ultimately generates research area vegetation and is lost whereabouts distribution map.According to the present embodiment
The method of offer, by taking Henan, China as an example, research area vegetation obtained is lost whereabouts distribution map and sees Fig. 9.
The above are preferred embodiments of the present invention, all any changes made according to the technical solution of the present invention, and generated function is made
When with range without departing from technical solution of the present invention, all belong to the scope of protection of the present invention.
Claims (8)
1. a kind of vegetation based on more Indices variation tendencies is lost whereabouts recognition methods, which is characterized in that including walking as follows
It is rapid:
Step S01: vegetation index, impervious surface index, soil bareness index, water body index time series data collection over the years are established；
Step S02: calculating vegetation index sequential similarity by pixel year by year, establishes sequential similarity track；
Step S03: being based on sequential similarity track, extracts vegetation index sequential similarity variable quantity；
Step S04: being based on vegetation index sequential similarity variable quantity, obtains Potential vegetation and is lost region；
Step S05: Indices variation tendency over the years is calculated；
Step S06: being based on sequential similarity variable quantity and Indices variation tendency, establishes vegetation and is lost whereabouts differentiation process
Figure；
Step S07: carrying out vegetation and be lost whereabouts automatic identification, obtains research area vegetation and is lost whereabouts distribution map.
2. the vegetation according to claim 1 based on more Indices variation tendencies is lost whereabouts recognition methods, feature
Be: S01 comprising the following specific steps
S011: successively choosing EVI, BCI, RIBS, LSWI, the Indices as characterization earth's surface elemental: vegetation index, no
Permeable facial index, soil bareness index, water body index；The calculation formula of EVI index are as follows:Wherein ρRed, ρBlue,ρNIRRespectively red spectral band, blue wave band and close red
The reflectivity of wave section；
Wherein TC1、TC2、TC3First principal component respectively after K-T Transformation,
Two principal components, third principal component；
WhereinNDSI is normalizing
Snow melting body index, NDSImax、NDSIminThe respectively maximum value of NDSI and minimum value, TC1max、TC1Min is respectively TC1Most
Big value and minimum value；Wherein ρSWIRIndicate the reflectivity of short infrared wave band；
S012: within the scope of research area, EVI, BCI, RIBS, LSWI series Indices in n are successively established year by year by pixel
8 days maximums be combined to many years time series data collection, using Whittaker Smoother smoothing method, original 8 days are maximized
Synthesize more years time series data smoothing processings of EVI, BCI, RIBS, LSWI, thus obtain research the smooth n in area in EVI, BCI,
8 days maximums of RIBS, LSWI series Indices are combined to many years time series data collection, and the base of whereabouts identification is lost as vegetation
Plinth；It is lost whereabouts according to a variety of different vegetation, selection is corresponding to refer to point, is formed by n EVI, BCI, RIBS, LSWI
Indices many years time-sequence curve chart.
3. the vegetation according to claim 1 based on more Indices variation tendencies is lost whereabouts recognition methods, feature
It is: in the step S02, is based on JM distance, calculates vegetation index timing curve over the years and research starting year period year by year
The sequential similarity of part, and then establish sequential similarity track.
4. the vegetation according to claim 1 based on more Indices variation tendencies is lost whereabouts recognition methods, feature
It is: in the step S03, is studied based on vegetation index sequential similarity track using Logistic models fitting
The pixel vegetation index sequential similarity variable quantity in period, the formula of Logistic model are as follows:Wherein: f indicates JM distance, and independent variable x is the time, is indicated with the time, and a was represented in the research period
Sequential similarity variable quantity, b are change type, and d is the JM distance before variation.
5. a kind of vegetation based on more Indices variation tendencies according to claim 1 is lost whereabouts recognition methods,
It is characterized in that: in the step S04, by the big region of vegetation index sequential similarity variable quantity, being determined as Potential vegetation stream
Lose region；Assuming that vegetation index sequential similarity variable quantity M meets normal distribution in research area, in given α significance
On, if M >=Q1-α, then the vegetation index sequential similarity variable quantity of the pixel significantly increases, and judges that the pixel belongs to potential plant
It is lost region.
6. a kind of vegetation based on more Indices variation tendencies according to claim 1 is lost whereabouts recognition methods,
It is characterized in that: in the step S05, being based on SenShi Slope Method and Mann-Kendall method, refer to by pixel detection vegetation
Number, impervious surface index, soil bareness index, water body index variation tendency over the years.
7. a kind of vegetation based on more Indices variation tendencies according to claim 1 is lost whereabouts recognition methods,
Be characterized in that: in the step S06, the Potential vegetation determined in step S04 is lost in region, is presented according to vegetation index
It is remarkably decreased trend, and the presentation of impervious surface index significantly rises trend, further clarifies Potential vegetation and be lost regional scope.
8. a kind of vegetation based on more Indices variation tendencies according to claim 1 is lost whereabouts recognition methods,
It is characterized in that: in the step S06, according to sequential similarity variable quantity and vegetation index, impervious surface index variation
Potential vegetation determined by trend is lost in range, according further to water body index, soil bareness index variation trend, judges to plant
By loss whereabouts；If water body index, soil bareness index show the trend of significantly rising, it is wetland that vegetation, which is lost whereabouts,
Change；If water body index, soil bareness index show significant downward trend, it is famineization that vegetation, which is lost whereabouts,；If
Water body index shows significant downward trend and soil bareness index shows significant ascendant trend, then vegetation is lost whereabouts
For urbanization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710605772.1A CN107463775B (en) | 2017-07-24 | 2017-07-24 | Vegetation based on more Indices variation tendencies is lost whereabouts recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710605772.1A CN107463775B (en) | 2017-07-24 | 2017-07-24 | Vegetation based on more Indices variation tendencies is lost whereabouts recognition methods |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107463775A CN107463775A (en) | 2017-12-12 |
| CN107463775B true CN107463775B (en) | 2019-11-12 |
Family
ID=60544356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710605772.1A Active CN107463775B (en) | 2017-07-24 | 2017-07-24 | Vegetation based on more Indices variation tendencies is lost whereabouts recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107463775B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875146B (en) * | 2018-05-28 | 2022-06-07 | 福州大学 | Method for detecting continuous change of earth surface coverage by considering change process |
| CN109446962B (en) * | 2018-10-19 | 2020-12-01 | 中国科学院地理科学与资源研究所 | Land cover annual change detection method and system |
| CN109840516B (en) * | 2019-03-06 | 2022-10-14 | 福州大学 | Water body change automatic identification method based on time sequence remote sensing image |
| CN111062368B (en) * | 2019-12-31 | 2020-09-11 | 中山大学 | City update region monitoring method based on Landsat time sequence remote sensing image |
| CN112116242B (en) * | 2020-09-17 | 2022-08-16 | 福州福大经纬信息科技有限公司 | Bare soil change identification method combining multiple remote sensing indexes |
| CN112801007B (en) * | 2021-02-07 | 2022-09-20 | 中国自然资源航空物探遥感中心 | Hot melt pond state identification method combining long time sequence data and machine learning algorithm |
| CN113592770B (en) * | 2021-06-23 | 2024-02-23 | 中国科学院南京地理与湖泊研究所 | Algal bloom remote sensing identification method for removing influence of aquatic weeds |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
| CN103063311A (en) * | 2012-12-24 | 2013-04-24 | 珠江水利委员会珠江水利科学研究院 | Nudity bed rock information extraction method based on soil index |
| CN103971027A (en) * | 2014-05-29 | 2014-08-06 | 福州大学 | Rice automatic mapping method based on ratio index of water body and vegetation index changes |
| CN106446555A (en) * | 2016-09-29 | 2017-02-22 | 福州大学 | Vegetation change occurrence time detection method based on time series similarity |
-
2017
- 2017-07-24 CN CN201710605772.1A patent/CN107463775B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
| CN103063311A (en) * | 2012-12-24 | 2013-04-24 | 珠江水利委员会珠江水利科学研究院 | Nudity bed rock information extraction method based on soil index |
| CN103971027A (en) * | 2014-05-29 | 2014-08-06 | 福州大学 | Rice automatic mapping method based on ratio index of water body and vegetation index changes |
| CN106446555A (en) * | 2016-09-29 | 2017-02-22 | 福州大学 | Vegetation change occurrence time detection method based on time series similarity |
Non-Patent Citations (1)
| Title |
|---|
| Changes in land surface temperatures and NDVI values over Europe between 1982 and 1999;Julien Y et al;《Remote Sens Environ》;20061231;第103卷(第1期);第43-55页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107463775A (en) | 2017-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463775B (en) | Vegetation based on more Indices variation tendencies is lost whereabouts recognition methods | |
| CN106650689B (en) | A kind of coastal cities time series Land-use extracting method | |
| Culvenor | TIDA: an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery | |
| Kuemmerle et al. | Cross-border comparison of land cover and landscape pattern in Eastern Europe using a hybrid classification technique | |
| CN108830844B (en) | Facility vegetable extraction method based on multi-temporal high-resolution remote sensing image | |
| HAO et al. | Early-season crop type mapping using 30-m reference time series | |
| Van Delm et al. | Classification and quantification of green in the expanding urban and semi-urban complex: Application of detailed field data and IKONOS-imagery | |
| Hidayati et al. | Developing an extraction method of urban built-up area based on remote sensing imagery transformation index | |
| Wang | A multi-scale approach for delineating individual tree crowns with very high resolution imagery | |
| CN106228545A (en) | A kind of automatic division method of figure of buddha class Tangka's concordance damaged area | |
| CN108537239A (en) | A kind of method of saliency target detection | |
| CN103679675A (en) | Remote sensing image fusion method oriented to water quality quantitative remote sensing application | |
| CN111091079A (en) | TLS-based method for measuring dominant single plant structural parameters of vegetation in alpine and fragile regions | |
| Wang et al. | Color-and texture-based image segmentation for improved forest delineation | |
| Berveglieri et al. | Identification of successional stages and cover changes of tropical forest based on digital surface model analysis | |
| Li et al. | Spatial and temporal patterns of wetland cover changes in East Kolkata Wetlands, India from 1972 to 2011 | |
| Dimyati et al. | Paddy field classification with MODIS-terra multi-temporal image transformation using phenological approach in Java Island | |
| Tuan et al. | Monitoring urban surface water bodies change using mndwi estimated from pan-sharpened optical satellite images | |
| Hua et al. | Image segmentation algorithm based on improved visual attention model and region growing | |
| Li et al. | Color and texture feature fusion using kernel PCA with application to object-based vegetation species classification | |
| Li et al. | Texture-Aware Self-Attention Model for Hyperspectral Tree Species Classification | |
| CN108629818A (en) | A kind of a wide range of impervious surface percentage variable quantity rapid drafting technology | |
| Ji et al. | Discriminating saltcedar (Tamarix ramosissima) from sparsely distributed cottonwood (Populus euphratica) using a summer season satellite image | |
| Ibaraki et al. | Image analysis for plants: basic procedures and techniques | |
| Liu et al. | The classification of airborne LiDAR building point clouds based on multi‐scale and multi‐level cloth simulation |
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 |