CN106971396A - Ice sheet freeze thawing detection method based on super-pixel - Google Patents
Ice sheet freeze thawing detection method based on super-pixel Download PDFInfo
- Publication number
- CN106971396A CN106971396A CN201710140706.1A CN201710140706A CN106971396A CN 106971396 A CN106971396 A CN 106971396A CN 201710140706 A CN201710140706 A CN 201710140706A CN 106971396 A CN106971396 A CN 106971396A
- Authority
- CN
- China
- Prior art keywords
- pixel
- super
- detection method
- seed point
- gray
- 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
Classifications
-
- 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
- G06T2207/10044—Radar image
-
- 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
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of ice sheet freeze thawing detection method based on super-pixel, comprises the following steps：Super-pixel segmentation step, carries out mean filter processing and super-pixel segmentation to the data of synthetic aperture radar of acquisition, forms cluster areas；Region merging technique step based on gray scale, is merged according to gray scale to the cluster areas, forms most like gray areas；And the region merging technique step based on texture, region merging technique is carried out again to the most like gray areas with reference to texture information.The present invention is handled image in super-pixel rank, and combines the texture information progress image segmentation of image, and faster, precision is higher for splitting speed compared with conventional region growing, watershed algorithm.
Description
Technical field
The present invention relates to polar region change detection field, and in particular to a kind of ice sheet freeze thawing detection method based on super-pixel.
Background technology
Aspect On Study of Antarctic Ice Cap is the maximum glacier of earth surface and freshwater resources, and Aspect On Study of Antarctic Ice Cap freeze thawing is in control earth surface and greatly
Play an important roll in terms of gas heat exchange, earth's surface solar radiative absorption, to reflecting and controlling Global climate change state to have
It is significant.Because Aspect On Study of Antarctic Ice Cap area coverage is very big, and special geographical position and harsh climate environment cause reality
The investigation on ground is difficult to realize, thus is utilized as the space remote sensing represented once the master for occurring turning into observation polar region with satellite sensor
Want means.
The method for carrying out polar ice sheet freeze thawing detection using multiband passive microwave data has a lot, and a class is to be based on threshold
Value, it is believed that the bright temperature of single channel or multichannel bright temperature combination will have thawing when reaching some specific value；Another kind of is base
In edge detection algorithm, it is believed that melt when bright temperature changes most fast and occur.Utilize the detection method and microwave radiation of microwave scatterometer
The detection method of meter is compared, and general idea is the same, has researcher to change using multichannel backscattering coefficient and between the morning and evening, and
Backscattering coefficient judges accumulated snow or melting with the change of winter reference value.In general, the method behaviour based on threshold value
Make simple, but the sensor of low spatial resolution can only roughly carry out freeze thawing detection, lack for ice sheet freeze thawing details
Description, threshold value depends on limited observation data, there is certain limitation.
Being currently based on the method for the freeze thawing detection of image segmentation mainly has：Normal image dividing method such as region growing and point
Water ridge method.Conventional fractionation method is normally based on pixel scale, more sensitive to noise, easily produces cavity and over-segmentation.
Although the influence of noise can be reduced by filtering operation, for high-resolution image, the problem of existing is inefficiency.
The content of the invention
In order to solve the above problems, the present invention discloses a kind of ice sheet freeze thawing detection method based on super-pixel, including following
Step：Super-pixel segmentation step, carries out mean filter processing and super-pixel segmentation to the data of synthetic aperture radar of acquisition, is formed
Cluster areas；Region merging technique step based on gray scale, is merged according to gray scale to the cluster areas, forms most like gray scale
Region；And the region merging technique step based on texture, region is carried out again to the most like gray areas with reference to texture information
Merge.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, the super-pixel segmentation step includes
Following steps：Seed point setting steps, seed point is set according to expected super-pixel number；Local Clustering step, with the seed
Local Clustering is carried out centered on point.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, the super-pixel segmentation step is also wrapped
Include following steps：Eliminate area and cross zonule step, adjacency matrix is set up to the Local Clustering result, area is less than given
The region of threshold value merges with adjacent area.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, the time interval of the seed point is
Wherein, m, n are respectively the line number and columns of image, and k is super-pixel number.
The present invention the ice sheet freeze thawing detection method based on super-pixel in, be preferably, the Local Clustering step include with
Lower step：Allocation step, the pixel in search 2S centered on seed point regions, pixel is assigned to away from its nearest seed
Point region；Iterative step, takes the average of cluster areas pixel value as new seed point, is given if the offset of new seed point is more than
Determine threshold value, then clustered again using new seed point as cluster centre, if the offset of new seed point is less than given threshold value, clustered
Terminate.
The present invention the ice sheet freeze thawing detection method based on super-pixel in, be preferably, the pixel away from seed point away from
From being expressed as
D=d1+md2
Wherein,
Wherein, a, b, l refer respectively to the value of reddish yellow primary colors in the color of pixel, xk,ykRespectively seed point is horizontal
Ordinate, xi,yiRespectively pixel transverse and longitudinal coordinate, m is color distance and the weights of space length.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, greatest iteration in the iterative step
Number of times is 10.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, the region merging technique based on gray scale
Step comprises the following steps：The average for calculating each area pixel gray scale is used as the gray value of super-pixel；And by hierarchical clustering
Method, is merged using most like gray scale as criterion.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, the region merging technique based on texture
Step comprises the following steps：The textural characteristics of the most like gray areas are calculated by calculation procedure；Sequence step, is pressed
Gray value size is ranked up to the most like gray areas；And combining step, by gray scale adjacent area, with most like line
Manage and merged for criterion.
In the ice sheet freeze thawing detection method based on super-pixel of the present invention, it is preferably, the calculation procedure includes following step
Suddenly：Grey level quantization step, carries out grey level quantization by the most like gray areas, 16 grades is changed to by original 256 grades；Symbiosis
Gray level co-occurrence matrixes on matrix construction step, tectonic level, vertical, diagonal, back-diagonal four direction；And homogeney
Calculation procedure, is calculated as follows homogeney：
Wherein i, j are respectively two adjacent pixel gray scales, and p (i, j) is i, the probability that j occurs simultaneously.
The ice sheet freeze thawing detection method based on super-pixel of the present invention is handled image in super-pixel rank, and is tied
The texture information for closing image carries out image segmentation, compared with conventional region growing, watershed algorithm splitting speed faster, precision
It is higher.
Brief description of the drawings
Fig. 1 is the flow chart of the ice sheet freeze thawing detection method based on super-pixel；
Fig. 2 is the flow chart of super-pixel segmentation step；
Fig. 3 is the flow chart of Local Clustering step；
Fig. 4 is the flow chart of another embodiment of super-pixel segmentation step；
Fig. 5 is the flow chart of the region merging technique step based on gray scale；
Fig. 6 is the flow chart of the region merging technique step based on texture；
Fig. 7 is the flow chart of textural characteristics calculation procedure；
Fig. 8 is the figure in each stage for representing the ice sheet freeze thawing detection method based on super-pixel：(a) Local Clustering, (b) is tiny
Region merges with adjacent area, and (c) is merged based on gray scale, and (d) combines the design sketch that texture merges, and (e) segmentation result border.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it will be appreciated that described herein
Specific embodiment only to explain the present invention, is not intended to limit the present invention.Described embodiment is only the present invention one
Divide embodiment, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making
The all other embodiment obtained under the premise of creative work, belongs to the scope of protection of the invention.
Fig. 1 is the flow chart of the ice sheet freeze thawing detection method based on super-pixel.As shown in figure 1, the ice sheet based on super-pixel
Freeze thawing detection method includes super-pixel segmentation step S1, the region merging technique step S2 based on gray scale and the region merging technique based on texture
Step S3.
Specifically, in super-pixel segmentation step S1, synthetic aperture radar (SAR) data to acquisition carry out average filter
Ripple processing, carries out super-pixel segmentation.Figure 2 illustrates the flow chart of super-pixel segmentation step.As shown in Fig. 2 super-pixel point
Cutting step S1 includes seed point setting steps S11 and local sorting procedure S12.Super-pixel segmentation step is directed to below in conjunction with Fig. 2
It is described in detail.
First, in seed point setting steps S11, seed point is set according to expected super-pixel number.Seed point interval can
To be expressed as following formula,
Wherein, S is that m, n are respectively the line number and columns of image, and k is super-pixel number.
Next, in Local Clustering step S12, Local Clustering is carried out centered on seed point.For more specifically, such as
Shown in Fig. 3, step S121 is allocated first, and the pixel in the 2S regions searched for centered on seed point distributes pixel
To away from its nearest seed point region.Distance can be calculated using equation below
D=d1+md2
Wherein,
In formula, a, b, l refers respectively to the face of the value of reddish yellow primary colors in the color of pixel, pixel and seed point
Aberration is different bigger, then d1Value it is bigger, the color distortion of pixel and seed point is smaller, then d1Value it is smaller.
xk,ykRespectively seed point transverse and longitudinal coordinate, xi,yiRespectively pixel transverse and longitudinal coordinate, m is color distance and space
The weights of distance.
Then, in iterative step S122, the average of cluster areas pixel value is taken as new seed point, if new seed point
Offset be more than given threshold value, then clustered again using new seed point as cluster centre, if the offset of new seed point is less than
Given threshold value, then cluster and terminate.It is further preferred that to prevent from not restraining, it is 10 to take maximum iteration.Show in Fig. 8 (a)
Go out and completed the design sketch after Local Clustering step.The present invention, by group pixels, is formed using the similarity of feature between pixel
Super-pixel, the rank of super-pixel is far smaller than pixel scale, and image is split based on super-pixel, substantially increases image segmentation effect
Rate.
Preferably, as shown in figure 4, super-pixel segmentation step S1, which also includes elimination area, crosses zonule step S13, to cluster
As a result adjacency matrix is set up, the region that area is less than given threshold value is merged with adjacent area.So as to ensure the premise of precision
Lower raising arithmetic speed.Shown in Fig. 8 (b) and complete to eliminate the design sketch that area is crossed after the step of zonule.
Next, the region merging technique step S2 based on gray scale is described in detail with reference to Fig. 5.As shown in figure 5, existing first
In step S21, the average of each cluster areas pixel grey scale is calculated as the gray value of super-pixel, then, in step S22,
By hierarchical clustering method, merged using most like gray scale as criterion.Show that completing the region based on gray scale closes in Fig. 8 (c)
And the design sketch after step.
Rely solely on gradation of image and be difficult to accurate segmentation to SAR image.Contain abundant texture letter in SAR image
Breath, therefore, further merges with reference to texture information on the basis of the region merging technique step S2 based on gray scale, is accurately divided
Cut result.The flow chart of the region merging technique step S3 based on texture is shown in Fig. 6.As shown in fig. 6, the region based on texture is closed
And step S3 further specifically includes calculation procedure S31, sequence step S32 and combining step S33.
In calculation procedure S31, the textural characteristics of most like gray areas are calculated.More specifically, such as Fig. 7
It is shown, including：
Grey level quantization step S311, carries out grey level quantization by the most like gray areas, is changed to by original 256 grades
16 grades；
Gray level co-occurrence matrixes on co-occurrence matrix constitution step S312, construction four direction, this four direction is water respectively
Flat, vertical, diagonal, back-diagonal；
Homogeney calculation procedure S313, is calculated as follows homogeney
Wherein i, j are respectively two adjacent pixel gray scales, and p (i, j) is i, the probability that j occurs simultaneously.
In sequence step S32, most like gray areas is ranked up by gray value size；In combining step S33,
By gray scale adjacent area, merged using most like texture as criterion.Respectively illustrated in Fig. 8 (d) and Fig. 8 (e) and complete base
In the design sketch after the region merging technique step of texture and segmentation result border.
The ice sheet freeze thawing detection method based on super-pixel of the present invention, is handled image in super-pixel rank, and
Image segmentation is carried out with reference to the texture information of image, splitting speed is faster, smart compared with conventional region growing, watershed algorithm
Du Genggao.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, the change or replacement that can be readily occurred in, all should
It is included within the scope of the present invention.
Claims (10)
1. a kind of ice sheet freeze thawing detection method based on super-pixel, it is characterised in that
Comprise the following steps：
Super-pixel segmentation step, carries out mean filter processing and super-pixel segmentation to the data of synthetic aperture radar of acquisition, is formed
Cluster areas；
Region merging technique step based on gray scale, is merged according to gray scale to the cluster areas, forms most like gray areas；
And
Region merging technique step based on texture, region merging technique is carried out with reference to texture information again to the most like gray areas.
2. the ice sheet freeze thawing detection method according to claim 1 based on super-pixel, it is characterised in that
The super-pixel segmentation step comprises the following steps：
Seed point setting steps, seed point is set according to expected super-pixel number；And
Local Clustering step, carries out Local Clustering centered on the seed point.
3. the ice sheet freeze thawing detection method according to claim 2 based on super-pixel, it is characterised in that
The super-pixel segmentation step also includes：Eliminate area and cross zonule step, the Local Clustering result is set up and abutted
Matrix, the region that area is less than given threshold value is merged with adjacent area.
4. the ice sheet freeze thawing detection method according to claim 2 based on super-pixel, it is characterised in that
The time interval of the seed point is
Wherein, m, n are respectively the line number and columns of image, and k is super-pixel number.
5. the ice sheet freeze thawing detection method according to claim 4 based on super-pixel, it is characterised in that
The Local Clustering step comprises the following steps：
Allocation step, the pixel in search 2S centered on seed point regions, pixel is assigned to away from its nearest seed point
Region, forms cluster areas；And
Iterative step, takes the average of the cluster areas pixel value as new seed point, if the offset of new seed point is more than
Given threshold value, then cluster again using new seed point as cluster centre, if the offset of new seed point is less than given threshold value, gathers
Class terminates.
6. the ice sheet freeze thawing detection method according to claim 5 based on super-pixel, it is characterised in that
Distance of the pixel away from seed point is expressed as
D=d1+md2
Wherein,
In formula, a, b, l refers to the value of reddish yellow primary colors in the color of pixel, x respectivelyk,ykRespectively seed point transverse and longitudinal coordinate,
xi,yiRespectively pixel transverse and longitudinal coordinate, m is color distance and the weights of space length.
7. the ice sheet freeze thawing detection method according to claim 5 based on super-pixel, it is characterised in that
Maximum iteration is 10 in the iterative step.
8. the ice sheet freeze thawing detection method according to claim 1 based on super-pixel, it is characterised in that
The region merging technique step based on gray scale comprises the following steps：
The average for calculating each area pixel gray scale is used as the gray value of super-pixel；And
By hierarchical clustering method, merged using most like gray scale as criterion.
9. the ice sheet freeze thawing detection method according to claim 1 based on super-pixel, it is characterised in that
The region merging technique step based on texture comprises the following steps：
The textural characteristics of the most like gray areas are calculated by calculation procedure；
Sequence step, is ranked up by gray value size to the most like gray areas；And
Combining step, gray scale adjacent area is merged using most like texture as criterion.
10. the ice sheet freeze thawing detection method according to claim 9 based on super-pixel, it is characterised in that
The calculation procedure comprises the following steps：
Grey level quantization step, carries out grey level quantization by the most like gray areas, 16 grades is changed to by original 256 grades；
Gray level co-occurrence matrixes on co-occurrence matrix constitution step, tectonic level, vertical, diagonal, back-diagonal four direction；With
And
Homogeney calculation procedure, is calculated as follows homogeney
Wherein i, j are respectively two adjacent pixel gray scales, and p (i, j) is i, the probability that j occurs simultaneously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710140706.1A CN106971396A (en) | 2017-03-10 | 2017-03-10 | Ice sheet freeze thawing detection method based on super-pixel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710140706.1A CN106971396A (en) | 2017-03-10 | 2017-03-10 | Ice sheet freeze thawing detection method based on super-pixel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106971396A true CN106971396A (en) | 2017-07-21 |
Family
ID=59328784
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710140706.1A Pending CN106971396A (en) | 2017-03-10 | 2017-03-10 | Ice sheet freeze thawing detection method based on super-pixel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106971396A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359533A (en) * | 2018-09-12 | 2019-02-19 | 浙江海洋大学 | A kind of tidal saltmarsh method based on multiband remote sensing image |
| CN109741340A (en) * | 2018-12-16 | 2019-05-10 | 北京工业大学 | Ice sheet radar image ice sheet based on FCN-ASPP network refines dividing method |
| CN109829423A (en) * | 2019-01-18 | 2019-05-31 | 电子科技大学 | A kind of icing lake infrared imaging detection method |
| CN110570352A (en) * | 2019-08-26 | 2019-12-13 | 腾讯科技（深圳）有限公司 | image labeling method, device and system and cell labeling method |
| CN111709483A (en) * | 2020-06-18 | 2020-09-25 | 山东财经大学 | Multi-feature-based super-pixel clustering method and equipment |
| CN111914674A (en) * | 2020-07-09 | 2020-11-10 | 中国科学院地理科学与资源研究所 | Object-pixel-based ice and snow automatic extraction method and device and electronic equipment |
| CN113240694A (en) * | 2021-05-31 | 2021-08-10 | 中国科学院空天信息创新研究院 | Polar ice cover freeze-thaw detection method and device and computer readable storage medium |
| CN114373283A (en) * | 2022-03-22 | 2022-04-19 | 中国科学院、水利部成都山地灾害与环境研究所 | Early warning method for burst disaster of ice-disintegrating type tillite lake |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567726A (en) * | 2010-12-13 | 2012-07-11 | 北京师范大学 | Technology for automatically extracting floating ice in polar ice sheet edge regions |
| CN102567963A (en) * | 2011-11-10 | 2012-07-11 | 西安电子科技大学 | Quantum multi-target clustering-based remote sensing image segmentation method |
| CN104408458A (en) * | 2014-12-09 | 2015-03-11 | 西安电子科技大学 | Ray completion region graph and characteristic learning-based SAR (synthetic aperture radar) image segmentation method |
| CN104794688A (en) * | 2015-03-12 | 2015-07-22 | 北京航空航天大学 | Single image defogging method and device based on depth information separation sky region |
| CN106340020A (en) * | 2015-07-10 | 2017-01-18 | 阿里巴巴集团控股有限公司 | Super-pixel segmentation method and device |
-
2017
- 2017-03-10 CN CN201710140706.1A patent/CN106971396A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567726A (en) * | 2010-12-13 | 2012-07-11 | 北京师范大学 | Technology for automatically extracting floating ice in polar ice sheet edge regions |
| CN102567963A (en) * | 2011-11-10 | 2012-07-11 | 西安电子科技大学 | Quantum multi-target clustering-based remote sensing image segmentation method |
| CN104408458A (en) * | 2014-12-09 | 2015-03-11 | 西安电子科技大学 | Ray completion region graph and characteristic learning-based SAR (synthetic aperture radar) image segmentation method |
| CN104794688A (en) * | 2015-03-12 | 2015-07-22 | 北京航空航天大学 | Single image defogging method and device based on depth information separation sky region |
| CN106340020A (en) * | 2015-07-10 | 2017-01-18 | 阿里巴巴集团控股有限公司 | Super-pixel segmentation method and device |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359533A (en) * | 2018-09-12 | 2019-02-19 | 浙江海洋大学 | A kind of tidal saltmarsh method based on multiband remote sensing image |
| CN109741340A (en) * | 2018-12-16 | 2019-05-10 | 北京工业大学 | Ice sheet radar image ice sheet based on FCN-ASPP network refines dividing method |
| CN109741340B (en) * | 2018-12-16 | 2020-10-16 | 北京工业大学 | Ice cover radar image ice layer refined segmentation method based on FCN-ASPP network |
| CN109829423A (en) * | 2019-01-18 | 2019-05-31 | 电子科技大学 | A kind of icing lake infrared imaging detection method |
| CN109829423B (en) * | 2019-01-18 | 2023-03-07 | 电子科技大学 | Infrared imaging detection method for frozen lake |
| CN110570352A (en) * | 2019-08-26 | 2019-12-13 | 腾讯科技（深圳）有限公司 | image labeling method, device and system and cell labeling method |
| CN111709483A (en) * | 2020-06-18 | 2020-09-25 | 山东财经大学 | Multi-feature-based super-pixel clustering method and equipment |
| CN111914674A (en) * | 2020-07-09 | 2020-11-10 | 中国科学院地理科学与资源研究所 | Object-pixel-based ice and snow automatic extraction method and device and electronic equipment |
| CN113240694A (en) * | 2021-05-31 | 2021-08-10 | 中国科学院空天信息创新研究院 | Polar ice cover freeze-thaw detection method and device and computer readable storage medium |
| CN113240694B (en) * | 2021-05-31 | 2024-01-05 | 中国科学院空天信息创新研究院 | Polar ice cover freeze thawing detection method, device and computer readable storage medium |
| CN114373283A (en) * | 2022-03-22 | 2022-04-19 | 中国科学院、水利部成都山地灾害与环境研究所 | Early warning method for burst disaster of ice-disintegrating type tillite lake |
| CN114373283B (en) * | 2022-03-22 | 2022-06-21 | 中国科学院、水利部成都山地灾害与环境研究所 | Early warning method for burst disaster of ice-disintegrating type tillite lake |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106971396A (en) | Ice sheet freeze thawing detection method based on super-pixel | |
| Li et al. | Identifying asphalt pavement distress using UAV LiDAR point cloud data and random forest classification | |
| Sahebjalal et al. | Analysis of land use-land covers changes using normalized difference vegetation index (NDVI) differencing and classification methods | |
| CN101840581B (en) | Method for extracting profile of building from satellite remote sensing image | |
| CN103578110B (en) | Multiband high-resolution remote sensing image dividing method based on gray level co-occurrence matrixes | |
| CN107016677A (en) | A kind of cloud atlas dividing method based on FCN and CNN | |
| Qin et al. | Object-based land cover change detection for cross-sensor images | |
| CN108830844B (en) | Facility vegetable extraction method based on multi-temporal high-resolution remote sensing image | |
| CN107784657A (en) | A kind of unmanned aerial vehicle remote sensing image partition method based on color space classification | |
| CN102063720B (en) | Treelets-based method for detecting remote sensing image changes | |
| CN106548141A (en) | A kind of object-oriented farmland information extraction method based on the triangulation network | |
| CN104899562A (en) | Texture segmentation and fusion based radar remote-sensing image artificial building recognition algorithm | |
| CN102184423B (en) | Full-automatic method for precisely extracting regional impervious surface remote sensing information | |
| CN110334623B (en) | Method for extracting collapsing information based on Sentinel-2A satellite remote sensing image | |
| CN102129566A (en) | Method for identifying rainstorm cloud cluster based on stationary meteorological satellite | |
| CN105139375A (en) | Satellite image cloud detection method combined with global DEM and stereo vision | |
| CN102073867A (en) | Sorting method and device for remote sensing images | |
| CN102567726A (en) | Technology for automatically extracting floating ice in polar ice sheet edge regions | |
| CN105894006A (en) | Space-time probability model rice remote sensing recognition method | |
| CN101561882A (en) | Sub-pixel spatial mapping method based on spatial correlation | |
| Sun et al. | Deep learning for check dam area extraction with optical images and digital elevation model: A case study in the hilly and gully regions of the Loess Plateau, China | |
| CN110175638B (en) | Raise dust source monitoring method | |
| Zhao et al. | Quantifying urban vegetation coverage change with a linear spectral mixing model: A case study in Xi’an, China | |
| CN109543729A (en) | Time series data land cover classification method based on characteristic parameter cluster | |
| Sun et al. | Check dam extraction from remote sensing images using deep learning and geospatial analysis: A case study in the Yanhe River Basin of the Loess Plateau, China |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170721 |