CN106384340A - Remote sensing space-time image downscaling fusion method - Google Patents
Remote sensing space-time image downscaling fusion method Download PDFInfo
- Publication number
- CN106384340A CN106384340A CN201610749655.8A CN201610749655A CN106384340A CN 106384340 A CN106384340 A CN 106384340A CN 201610749655 A CN201610749655 A CN 201610749655A CN 106384340 A CN106384340 A CN 106384340A
- Authority
- CN
- China
- Prior art keywords
- spatial resolution
- resolution image
- pixel
- early stage
- 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.)
- Granted
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 16
- VMXUWOKSQNHOCA-UKTHLTGXSA-N ranitidine Chemical compound [O-][N+](=O)\C=C(/NC)NCCSCC1=CC=C(CN(C)C)O1 VMXUWOKSQNHOCA-UKTHLTGXSA-N 0.000 claims description 25
- 230000009467 reduction Effects 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 21
- 230000003595 spectral effect Effects 0.000 claims description 8
- 239000000284 extract Substances 0.000 claims description 4
- 238000002156 mixing Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 241000894007 species Species 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000013626 chemical specie Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4053—Scaling of whole images or parts thereof, e.g. expanding or contracting based on super-resolution, i.e. the output image resolution being higher than the sensor resolution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a remote sensing space-time image downscaling fusion method, which comprises the steps of A, extracting variation values of corresponding pixels from an early low spatial resolution image to a late low spatial resolution image, and acquiring surface classification map of the high spatial resolution from an early high spatial resolution image; B, traversing low resolution pixel units on the scale of the low spatial resolution image, solving a least square solution of a system of linear equations of a pixel unit set of each pixel unit to act as a surface feature category variation value of the high spatial resolution; and C, adding the variation value calculated in the step B to data of the early high spatial resolution image by referring to component spatial distribution conditions within a target pixel spatial range of the late low spatial resolution image so as to complete reconstruction of the late high spatial resolution image. The remote sensing space-time image downscaling fusion method provided by the invention improves the upper limit of a downscaling fusion method in number of solved mixed pixel components.
Description
Technical field
The present invention relates to the digital image processing techniques field in photogrammetry and remote sensing section, particularly to one kind for
The method that the different spatial resolutions remote sensing image of different times carries out image co-registration.
Background technology
Due to the remote sensing images of the same area be difficult to continual persistently obtain, therefore, using this region different time sections,
Without the specified resolution image that the remote sensing image fusion of spatial resolution goes out different time sections be field of remote sensing image processing just
One of important directions in research, its importance and rationale can be found in following document:
Zhou Qiming. multi-temporal remote sensing image change-detection summarizes [J]. the geography information world, 2011 (02):28-33.;
Chen J,Lu M,Chen X,et al.A spectral gradient difference based
approach for land cover change detection[J].ISPRS Journal of Photogrammetry
and Remote Sensing,2013,85(2):1-12.;
Xie Dengfeng, Zhang Jinshui, Pan Yaozhong, wait .Landsat8 and MODIS to construct the high-spatial and temporal resolution data identification autumn
Grain crop [J]. remote sensing journal, 2015,19 (5):791-805.;
Chen X,Yang D,Chen J,et al.An improved automated land cover updating
approach by integrating with downscaled NDVI time series data[J].Remote
Sensing Letters,2015,6(1):29-38.;
At present, typically will be single to the fusion treatment of many time periods and the Hi-spatial resolution remote sensing image of single time
The high spatial resolution image of time carries out temporal-spatial fusion with the low spatial resolution image of multiple different times, when generating multiple
Between high spatial resolution image, specific example can be found in following document:
Shi Yuechan, Yang Guijun, Li Xinchuan, etc. merge the method pair that multi- source Remote Sensing Data data generates high-spatial and temporal resolution data
Than [J]. infrared and millimeter wave journal, 2015,34 (1):92-99.;
Sun Peijun, Zhang Jinshui, Pan Yaozhong, etc. build temporal-spatial fusion model and carry out Oryza sativa L. remote sensing recognition [J]. remote sensing journal,
2016,20(2):328-343.;
The process of remote sensing images temporal-spatial fusion is actual to be exactly by dividing the spectral information of yardstick thick in low-resolution image
NO emissions reduction process on solution spectral information of smart yardstick in high-definition picture, concrete application case can be found in following document:
Wu Mingquan, Niu Zheng, Wang Changyao. extract Monitoring of Paddy Rice Plant Area [J] using remotely-sensed data temporal-spatial fusion technology. agriculture work
Journey journal, 2010,26 (Supp.2):48-52.
Wu Mingquan, Wang Jie, Niu Zheng, etc. merge MODIS and Landsat data genaration high time resolution Landsat data
[J]. infrared and millimeter wave journal, 2012,31 (1):80-84.
Boschetti L,Roy D P,Justice C O,et al.MODIS–Landsat fusion for large
area 30m burned area mapping[J].Remote Sensing of Environment,2015,161:27-42.
Hwang T,Song C,Bolstad P V,et al.Downscaling real-time vegetation
dynamics by fusing multi-temporal MODIS and Landsat NDVI in topographically
complex terrain[J].Remote Sensing of Environment,2011,115(10):2499-2512.
Ha W,Gowda P H,Howell T A.Downscaling of Land Surface Temperature
Maps in the Texas High Plains with the TsHARP Method[J].GIScience&Remote
Sensing,2011,48(4):583-599.
As described in above-mentioned document, existing remote sensing images temporal-spatial fusion technology, be typically with goal pels be
Center, sets up, by delimiting various sizes of window, the equation group calculating, therefore, when atural object classification and group in remote sensing images
When one-tenth form is more complicated, easily cause the equation group that resolving set up that underdetermined problem occurs, thus cannot successful NO emissions reduction so that
Blending algorithm can the atural object categorical measure of NO emissions reduction be restricted.
Content of the invention
The technical problem to be solved in the present invention is to provide a kind of remote sensing space-time image NO emissions reduction fusion method, to reduce or to keep away
Exempt from problem noted earlier.
For solving above-mentioned technical problem, the invention provides a kind of remote sensing space-time image NO emissions reduction fusion method, it passes through
Early stage low spatial resolution image and later stage low spatial resolution image are analyzed obtain delta data, thus using early stage
High spatial resolution image obtains later stage high spatial resolution image, and it comprises the steps:
Step A, extracts described early stage low spatial resolution image to described later stage low spatial resolution shadow using differential technique
The changing value of the corresponding pixel of picture, and the Surface classification of high spatial resolution is obtained by described early stage high spatial resolution image
Figure;
Step B, on low spatial resolution yardstick, according to the described early stage high spatial resolution image F1 of step A acquisition
Surface classification figure and described early stage low spatial resolution image R1 to described later stage low spatial resolution image R2 corresponding picture
The changing value of unit, travels through low resolution picture element unit, each pixel unit is handled as follows:In with this pixel unit being
The heart, builds picture element unit set to the pixel unit of its neighborhood according to the atural object classification in periphery pixel spatial dimension along helical,
According to linear spectral mixture model, resolve the least square solution of this picture element unit set system of linear equations, as high-space resolution
The atural object classification changing value of rate;
Step C, the terrain classification figure of the described early stage high spatial resolution image obtaining by step A, after described
Component Space distribution situation in the goal pels spatial dimension of phase low spatial resolution image, the change that step B is calculated
Value is added in the data of described early stage high spatial resolution image, you can complete the weight of described later stage high spatial resolution image
Build process.
Preferably, in step, using non-supervised classification, obtain the ground of described early stage high spatial resolution image
Table sort figure.
Preferably, in stepb, described helical is Archimedes spiral.
;A kind of remote sensing space-time image NO emissions reduction fusion method provided by the present invention, by the structure of the resolving equation group of pixel
Mode of building is replaced the window form of traditional planar by the helical form of wire, and targetedly construction resolves pixel set, from
And effectively improve fusion method can NO emissions reduction number of components the upper limit.
Brief description
The following drawings is only intended to, in doing schematic illustration and explanation to the present invention, not delimit the scope of the invention.Wherein,
Fig. 1 is the schematic diagram of the remote sensing images with isolated atural object area;
Fig. 2 is a kind of schematic diagram of the pixel set of window form in isolated atural object area of Fig. 1;
Fig. 3 is a kind of remote sensing space-time image NO emissions reduction fusion method of a specific embodiment according to the present invention to figure
1 isolated atural object area carries out the principle schematic of pixel process.
Specific embodiment
In order to be more clearly understood to the technical characteristic of the present invention, purpose and effect, now comparison brief description this
Bright specific embodiment.
As described in background, remote sensing space-time image NO emissions reduction method is the Pixel domain in low spatial resolution image
On yardstick, by the Surface classification figure of high spatial resolution, resolve pixel set by building by pixel, and resolve this pixel collection
The system of linear equations closing, by the numerical value NO emissions reduction of the spectral information of low spatial resolution pixel to corresponding high-space resolution
On rate pixel.Require according to resolving system of linear equations, the number of the effective equation in equation group should be not less than the individual of unknown number
Number.When equation number is equal to unknown number, belongs to well-posed problem, have unique solution;When equation number is less than unknown number, belongs to and owe surely to ask
Topic, no unique solution;When equation number is more than unknown number, belongs to overdetermined problem, no solve, now, available least square method is asked
Optimal solution.
Based in the resolving equation group building mode of window form, window refers to the square centered on NO emissions reduction pixel to tradition
Shape region.When building pixel set using window form, the pixel being currently ready for NO emissions reduction is referred to as goal pels, will drop
Other pixels in yardstick pixel set are referred to as feature pixel.By the size of window, obtain other pixels in goal pels neighborhood
As feature pixel.Fig. 1 is the schematic diagram of the remote sensing images with isolated atural object area;Fig. 2 is the one kind in the isolated atural object area of Fig. 1
The schematic diagram of the pixel set of window form;Referring to shown in Fig. 1-2, in Fig. 1, wire illustrates the position in isolated atural object area, Fig. 2
For isolating the enlarged diagram in atural object area, shown in Figure 2, in order to calculate the value of 3*3 window center various places species not (component),
Need to set up using other pixels in its window and resolve pixel set.And for isolated atural object area such in Fig. 1, by its picture
The equation group that unit's set draws, unknown number number (number of components) can be more than equation number (i.e. low spatial resolution pixel number),
Result in underdetermined problem it is impossible to successful NO emissions reduction.
The pixel set building mode of legacy windows form is not due to shaping with respect to the atural object classification of goal pels and group
Formula, therefore, easily cause resolving equation group occur underdetermined problem, also allow for blending algorithm can NO emissions reduction atural object categorical measure
It is restricted.
Adverse effect NO emissions reduction fusion method being caused for the defect overcoming legacy windows form building mode, the present invention
Provide a kind of remote sensing space-time image NO emissions reduction fusion method, it passes through to early stage low spatial resolution image R1 and later stage low latitude
Between resolution image R2 be analyzed obtain delta data, thus using early stage high spatial resolution image F1 obtain later stage high-altitude
Between resolution image F2, it comprises the steps:
Step A, extracts described early stage low spatial resolution image R1 to described later stage low spatial resolution using differential technique
The changing value of the corresponding pixel of image R2, and the earth's surface of high spatial resolution is obtained by described early stage high spatial resolution image F1
Classification chart;
The different times of the equal resolution to same geographical position remote sensing image (as described early stage low spatial differentiate
Rate image R1 and described later stage low spatial resolution image R2) when being studied, available linear spectral mixture model, by each
Pixel changing value is expressed as the line that various change of component value in this pixel (class) is with component proportion (abundance) in pixel
Property combination.
Linear spectral mixture model formula is as follows:
Wherein R is the pixel value of low spatial resolution yardstick remote sensing image, and r is corresponding high-altitude in the range of low spatial resolution
Between resolution image component meansigma methodss, f be component proportion in the range of low spatial resolution, n be pixel in component sum,
ε is residual error.
Due to described early stage low spatial resolution image R1 and described later stage low spatial resolution image R2 pixel value with
The mathematical formulae of its internal composition all can be utilized above-mentioned formula obtain, therefore ask described early stage low spatial resolution image R1 and
During difference (i.e. the changing value) of the same correspondence position pixel of described later stage low spatial resolution image R2, ε can be eliminated.
Therefore, the same position of described early stage low spatial resolution image R1 and described later stage low spatial resolution image R2
The changing value Δ R of goal pels (utilizes differential technique:R2 R1 obtains), available equation below represents:
Wherein, Δ t represents from described early stage low spatial resolution image R1 to described later stage low spatial resolution image R2
The time of experience, Δ r represents the changing value of component in this time period.
On computers, it is also with non-supervised classification K-means method, obtain described early stage high-space resolution
The Surface classification figure of rate image F1, that is to say acquisition atural object classification information, thus can be used as atural object classification during subsequent processes
Parameter.Described early stage low spatial resolution image R1 and described later stage low spatial resolution image R2 is inputted computer, you can
Obtain the changing value of each corresponding low spatial resolution pixel and the change of component value of high spatial resolution using above-mentioned formula
Between corresponding mathematical relationship.
Step B, on low spatial resolution yardstick, according to the described early stage high spatial resolution image F1 of step A acquisition
Surface classification figure and described early stage low spatial resolution image R1 to described later stage low spatial resolution image R2 corresponding picture
The changing value of unit, travels through low resolution picture element unit, each pixel unit is handled as follows:In with this pixel unit being
The heart, builds picture element unit set to the pixel unit of its neighborhood according to the atural object classification in periphery pixel spatial dimension along helical,
According to linear spectral mixture model, resolve the least square solution of this picture element unit set system of linear equations, as high-space resolution
The atural object classification changing value of rate;
What described helical preferably employed is Archimedes spiral (i.e. constant velocity spiral), in low spatial resolution yardstick (for example
10m resolution) on, each low spatial resolution picture element unit corresponding can be according to the ground of described early stage high spatial resolution image F1
Table sort figure knows the atural object classification comprising (for example when the resolution of described early stage high spatial resolution image F1 is 1m, then
Each low spatial resolution picture element unit corresponding, can be from the corresponding region location of described early stage high spatial resolution image F1
Atural object classification is known in the pixel of 10*10), therefore, can be low according to described early stage low spatial resolution image R1 and described later stage
The difference (i.e. changing value) of the same correspondence position pixel of spatial resolution image R2 travels through to picture element unit, thus setting up
Equation group set.For example, when goal pels unit inclusively species other 1,2,3, then choose successively along described helical and comprise atural object
The picture element unit of classification 1,2,3, and the picture element unit comprising classification 1,2, the picture element unit comprising classification 2,3 and comprise class
Other 1,3 picture element unit;So it is achieved with enough equation group.
The maximum advantage of the present invention is, in the NO emissions reduction to goal pels, can turn round and look at along Archimedes spiral track
And the space variance to pixel;Possesses the resolving equation group of atural object classification any effective scale of structure that according to target pixel comprises
Ability.Fig. 3 is a kind of remote sensing space-time image NO emissions reduction fusion method of a specific embodiment according to the present invention to Fig. 1
Isolated atural object area carry out the principle schematic of pixel process, as shown in figure 3, in object area in isolation, along spiral path, permissible
Sequence through the atural object of peripheral neighborhood, by the chemical species of center pel, construction feature pixel set effectively.In spiral path
On (at least ensure that the pixel number that the pixel set building comprises is more than or equal to target when traversing sufficient amount of effective pixel
Number of components in pixel), you can NO emissions reduction resolving is carried out to goal pels.
Step C, the terrain classification figure of the described early stage high spatial resolution image F1 obtaining by step A, with reference to described
Component Space distribution situation in the goal pels spatial dimension of later stage low spatial resolution image R2, step B is calculated
Changing value is added in the data of described early stage high spatial resolution image F1, you can complete described later stage high spatial resolution shadow
Process of reconstruction as F2.
Specifically, during the data rebuilding described later stage high spatial resolution image F2, with reference to the described later stage
Component Space distribution situation in the goal pels spatial dimension of low spatial resolution image R2, the meter as described in step B
Calculation process, the change of component value of all categories within the pixel unit of low spatial resolution yardstick as unknown number, according to linear light
Spectrum mixed model, by one equation of each pixel unit, to the pixel unit chosen in step B, builds system of linear equations, utilizes
Restrictive method of least square resolves equation group, thus the corresponding high-altitude of pixel unit of low spatial resolution yardstick can be calculated
Between resolution change of component value, then refer again to described early stage high spatial resolution image F1 and the Surface classification in step A
The other distribution of in figure various places species, on the basis of the pixel value of described early stage high spatial resolution image F1, adds the group solving
Divide changing value, you can calculate and obtain described later stage high spatial resolution image F2.
A kind of remote sensing space-time image NO emissions reduction fusion method provided by the present invention, will resolve the structural model of model construction
Develop into the helical pattern of wire from the window scheme of planar, thus resolving pixel set can targetedly be constructed, improve
NO emissions reduction fusion method resolves the upper limit of mixed pixel number of components.
It will be appreciated by those skilled in the art that although the present invention is to be described according to the mode of multiple embodiments,
It is that not each embodiment only comprises an independent technical scheme.For the sake of in description, so narration is just for the sake of understanding,
Description should be understood by those skilled in the art as an entirety, and by involved technical scheme in each embodiment
Regard as and can be mutually combined into the mode of different embodiments to understand protection scope of the present invention.
The foregoing is only the schematic specific embodiment of the present invention, be not limited to the scope of the present invention.Any
Those skilled in the art, the equivalent variations made on the premise of the design without departing from the present invention and principle, modification and combination,
The scope of protection of the invention all should be belonged to.
Claims (3)
1. a kind of remote sensing space-time image NO emissions reduction fusion method, it passes through to early stage low spatial resolution image and later stage low spatial
Resolution image is analyzed obtaining delta data, thus obtaining later stage high-space resolution using early stage high spatial resolution image
Rate image, it comprises the steps:
Step A, extracts described early stage low spatial resolution image to described later stage low spatial resolution image using differential technique
The changing value of corresponding pixel, and the Surface classification figure of high spatial resolution is obtained by described early stage high spatial resolution image;
Step B, on low spatial resolution yardstick, the ground of the described early stage high spatial resolution image F1 being obtained according to step A
The corresponding pixel of table sort figure and described early stage low spatial resolution image R1 to described later stage low spatial resolution image R2
Changing value, travels through low resolution picture element unit, each pixel unit is handled as follows:Centered on this pixel unit, edge
Helical builds picture element unit set to the pixel unit of its neighborhood according to the atural object classification in periphery pixel spatial dimension, according to line
Property spectral mixing model, resolves the least square solution of this picture element unit set system of linear equations, as the ground of high spatial resolution
The other changing value of species.
Step C, the terrain classification figure of the described early stage high spatial resolution image obtaining by step A is low with reference to the described later stage
Component Space distribution situation in the goal pels spatial dimension of spatial resolution image, the changing value that step B is calculated adds
Enter in the data of described early stage high spatial resolution image, you can complete the reconstruction of described later stage high spatial resolution image
Journey.
2. method according to claim 1 it is characterised in that in step, using non-supervised classification, to described
Early stage high spatial resolution image is classified, and obtains the Surface classification figure of described early stage high spatial resolution image.
3. it is characterised in that in stepb, described helical is Archimedes spiral to the method according to claim 1-2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610749655.8A CN106384340B (en) | 2016-08-29 | 2016-08-29 | A kind of remote sensing space-time image NO emissions reduction fusion method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610749655.8A CN106384340B (en) | 2016-08-29 | 2016-08-29 | A kind of remote sensing space-time image NO emissions reduction fusion method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106384340A true CN106384340A (en) | 2017-02-08 |
CN106384340B CN106384340B (en) | 2019-01-01 |
Family
ID=57917017
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610749655.8A Active CN106384340B (en) | 2016-08-29 | 2016-08-29 | A kind of remote sensing space-time image NO emissions reduction fusion method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106384340B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109523498A (en) * | 2018-11-06 | 2019-03-26 | 南京农业大学 | A kind of remote sensing image space-time fusion method towards field scale crop growth monitoring |
CN110706188A (en) * | 2019-09-23 | 2020-01-17 | 北京航天宏图信息技术股份有限公司 | Image fusion method and device, electronic equipment and storage medium |
CN112017135A (en) * | 2020-07-13 | 2020-12-01 | 香港理工大学深圳研究院 | Method, system and equipment for spatial-temporal fusion of remote sensing image data |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103177431A (en) * | 2012-12-26 | 2013-06-26 | 中国科学院遥感与数字地球研究所 | Method of spatial-temporal fusion for multi-source remote sensing data |
CN104715467A (en) * | 2015-03-06 | 2015-06-17 | 中国科学院遥感与数字地球研究所 | Improved multi-source remote sensing data space-time fusion method |
CN104933397A (en) * | 2014-03-18 | 2015-09-23 | 元智大学 | Image description and image recognition method thereof |
US20160019422A1 (en) * | 2008-04-17 | 2016-01-21 | Biometricore, Inc. | Computationally Efficient Feature Extraction and Matching Iris Recognition |
-
2016
- 2016-08-29 CN CN201610749655.8A patent/CN106384340B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160019422A1 (en) * | 2008-04-17 | 2016-01-21 | Biometricore, Inc. | Computationally Efficient Feature Extraction and Matching Iris Recognition |
CN103177431A (en) * | 2012-12-26 | 2013-06-26 | 中国科学院遥感与数字地球研究所 | Method of spatial-temporal fusion for multi-source remote sensing data |
CN104933397A (en) * | 2014-03-18 | 2015-09-23 | 元智大学 | Image description and image recognition method thereof |
CN104715467A (en) * | 2015-03-06 | 2015-06-17 | 中国科学院遥感与数字地球研究所 | Improved multi-source remote sensing data space-time fusion method |
Non-Patent Citations (4)
Title |
---|
CHUNHUA DENG 等: "Recognizing the Formations of CVBG Based on Multiviewpoint Context", 《IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS》 * |
DAVIDE PICCINI 等: "Spiral Phyllotaxis: The Natural Way to Construct a 3D Radial Trajectory in MRI", 《MEDICAL DEVICES AND SENSORS》 * |
杨敏: "基于对数螺旋线边缘拟合的SAR图像漩涡信息提取方法", 《雷达学报》 * |
蔡志林: "螺旋线状搜索的快速块匹配纹理合成", 《计算机工程与设计》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109523498A (en) * | 2018-11-06 | 2019-03-26 | 南京农业大学 | A kind of remote sensing image space-time fusion method towards field scale crop growth monitoring |
CN109523498B (en) * | 2018-11-06 | 2020-04-07 | 南京农业大学 | Remote sensing image space-time fusion method for field scale crop growth monitoring |
CN110706188A (en) * | 2019-09-23 | 2020-01-17 | 北京航天宏图信息技术股份有限公司 | Image fusion method and device, electronic equipment and storage medium |
CN112017135A (en) * | 2020-07-13 | 2020-12-01 | 香港理工大学深圳研究院 | Method, system and equipment for spatial-temporal fusion of remote sensing image data |
CN112017135B (en) * | 2020-07-13 | 2021-09-21 | 香港理工大学深圳研究院 | Method, system and equipment for spatial-temporal fusion of remote sensing image data |
Also Published As
Publication number | Publication date |
---|---|
CN106384340B (en) | 2019-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Diek et al. | Barest pixel composite for agricultural areas using landsat time series | |
Li et al. | A 30-year (1984–2013) record of annual urban dynamics of Beijing City derived from Landsat data | |
Agudo et al. | The potential of drones and sensors to enhance detection of archaeological cropmarks: A comparative study between multi-spectral and thermal imagery | |
O’Neil-Dunne et al. | A versatile, production-oriented approach to high-resolution tree-canopy mapping in urban and suburban landscapes using GEOBIA and data fusion | |
CN102609726B (en) | Method for classifying remote sensing images blended with high-space high-temporal-resolution data by object oriented technology | |
Lehnert et al. | Mapping local climate zones and their applications in European urban environments: A systematic literature review and future development trends | |
Yu et al. | Study of the seasonal effect of building shadows on urban land surface temperatures based on remote sensing data | |
Ahmad | Detection of change in vegetation cover using multi-spectral and multi-temporal information for District Sargodha, Pakistan | |
Spada et al. | Multi-temporal image analysis for fluvial morphological characterization with application to Albanian rivers | |
CN106468658B (en) | A kind of MODIS remote-sensing monitoring method of eutrophic lake algocyan | |
WO2019147440A1 (en) | Crop boundary detection in images | |
Verhoeven | Are we there yet? A review and assessment of archaeological passive airborne optical imaging approaches in the light of landscape archaeology | |
Weber et al. | Hyperspectral imagery for environmental urban planning | |
Carbonneau et al. | UAV‐based training for fully fuzzy classification of Sentinel‐2 fluvial scenes | |
Brooke et al. | Mapping heterogeneous buried archaeological features using multisensor data from unmanned aerial vehicles | |
Argyrou et al. | A review of artificial intelligence and remote sensing for archaeological research | |
Goodarzi Mehr et al. | Using the mixture-tuned matched filtering method for lithological mapping with Landsat TM5 images | |
Ji et al. | Comparison of different multispectral sensors for photosynthetic and non-photosynthetic vegetation-fraction retrieval | |
Domínguez-Beisiegel et al. | Analysis and mapping of the spectral characteristics of fractional green cover in saline wetlands (NE Spain) using field and remote sensing data | |
Zhang et al. | Spatial domain bridge transfer: An automated paddy rice mapping method with no training data required and decreased image inputs for the large cloudy area | |
CN106384340A (en) | Remote sensing space-time image downscaling fusion method | |
Proença et al. | Potential of high-resolution Pléiades imagery to monitor salt marsh evolution after Spartina invasion | |
Jilge et al. | Detecting unknown artificial urban surface materials based on spectral dissimilarity analysis | |
Zi–chen et al. | Comparison of the backpropagation network and the random forest algorithm based on sampling distribution effects consideration for estimating nonphotosynthetic vegetation cover | |
Yang et al. | Mapping plant diversity based on combined SENTINEL-1/2 data—opportunities for subtropical mountainous forests |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |