CN107895370A - A kind of saddle point extracting method based on contour - Google Patents
A kind of saddle point extracting method based on contour Download PDFInfo
- Publication number
- CN107895370A CN107895370A CN201711226158.0A CN201711226158A CN107895370A CN 107895370 A CN107895370 A CN 107895370A CN 201711226158 A CN201711226158 A CN 201711226158A CN 107895370 A CN107895370 A CN 107895370A
- Authority
- CN
- China
- Prior art keywords
- contour
- mrow
- msub
- point
- saddle point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 239000000284 extract Substances 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 229910010888 LiIn Inorganic materials 0.000 claims description 3
- 239000004020 conductor Substances 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 238000012946 outsourcing Methods 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007373 indentation Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 235000014347 soups Nutrition 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Abstract
The invention discloses a kind of saddle point extracting method based on contour, this method includes:(1) contour line data of topographic map is read, therefrom extracts mountain top point;(2) according to the mountain top of extraction point, TIN is built;(3) every a line of TIN is directed to, filters out two intersecting therewith contours arranged side by side;(4) two contours arranged side by side corresponding to each edge are based on, extract saddle point, generate saddle point figure layer.Execution efficiency of the present invention is higher, is lacked by the interference of landform noise, and extraction effect is good, is consistent with actual landform.
Description
Technical field
The invention belongs to geographical information technology application field, and in particular to a kind of saddle point extraction side based on contour
Method.
Background technology
The topography and landform character point such as saddle point and mountain top point, ridge point together constitutes the basic framework of landform.Saddle point
Because its special physiognomy morphological character becomes the pass that mountain road can select to pass through when crossing over mountain after mountain, have to traffic lines
Important control action.
Saddle point how is automatically and quickly calibrated, there is important Research Significance.Method at present, it is mainly based upon DEM
Data carry out the extraction of saddle point.Traditional saddle point calibration algorithm mainly realized by mobile analysis window, in the window heart point
Two mutually orthogonal directions on, direction is depression, and another direction is projection, then may determine that the point is saddle
Point.Although this algorithm speed is fast, due to being limited by window size, extracts and more noise in result be present, accuracy compared with
Difference.Open dimension etc. and (Zhang Wei, soup Guoan, Yang of making pottery, wait saddle point extraction improved method [J] mapping sections of the based on DEM runoff concentration simulations
Learn, 2011,36 (1):A kind of improved saddle point extracting method 158-160.) is proposed based on DEM runoff concentration simulation models,
Though the accuracy of this method extraction saddle point greatly improves, can be produced using basin divide and positive form overlapping some broken
Ridge line, error is brought to the extraction of saddle point.
Defined according to geography, saddle point refers between adjacent two hilltop in the indentation position of the shape of a saddle.Thus may be used
Know, the identification feature of saddle mainly includes:(1) between adjacent two hilltop;(2) it is in the shape of a saddle;(3) indentation position.In addition,
(Wu Fan, grain defend contour Representation of topological spatial relations [J] Wuhan University Journals that people takes features of terrain into account to Wu Fan etc.:Engineering
Version, 2006,39 (3):The spy in region present in saddle point 140-144.) has been annotated from the topological transitiveness of contour
Sign, i.e. a region include the contour of two tool coordinations.Therefore, geography definition of the present invention from saddle point,
For contour line data, the methods of being extracted with mountain top point, build TIN, contour lines recognition arranged side by side based on mountain top point, formed a kind of
Efficiently, the saddle point extracting method of high quality.
The content of the invention
Goal of the invention:A kind of the problem of present invention exists for prior art, there is provided saddle point extraction based on contour
Method.
Technical scheme:Saddle point extracting method of the present invention based on contour includes:
(1) contour line data of topographic map is read, therefrom extracts mountain top point;
(2) according to the mountain top of extraction point, TIN is built;
(3) every a line of TIN is directed to, filters out two intersecting therewith contours arranged side by side;
(4) two contours arranged side by side corresponding to each edge are based on, extract saddle point, generate saddle point figure layer.
Further, step (3) specifically includes:
(3-1) is directed to a line l of TINi, carry out intersecting processing with contour, and will have intersecting pass therewith
The elevation of the contour of system, element numerals information, are spatially sequentially sequentially stored into queue LiIn;
(3-2) presses elevation order from small to large, to queue LiMiddle element is resequenced;
(3-3) traversal queue Li, search is informed against abuts elements, contour as arranged side by side to two with identical elevation;
(3-4) repeats (3-1) and arrives (3-3), until obtaining the contour arranged side by side of each edge of TIN.
Further, step (4) specifically includes:
(4-1) is directed to a line l of TINiCorresponding two contour e arranged side by sidei1、ei2, obtain two it is contour
Closest 2 points on line, p is designated asi1、pi2;
(4-2) travels through the contour line data of topographic map, and e is removed if wherein existingi1、ei2Contour in addition and line segment (pi1,
pi2) intersecting, then step (4-4) is performed, if in the absence of execution step (4-3);
(4-3) calculates line segment (pi1,pi2) midpoint pi, midpoint piAs saddle point;
(4-4) returns to execution (4-1) and arrives (4-3), until each edge of TIN is all by alignment processing;
(4-5) is according to obtained saddle point generation saddle point figure layer.
Wherein, the calculation formula of distance between two points is in the step (4-1):
In formula, (x1,y1) for wherein on a contour any point coordinate, (x2,y2) it is any on another contour
The coordinate of point.
Wherein, step (4-3) middle conductor (pi1,pi2) midpoint piCalculation formula be:
Wherein, (xpi,ypi) it is midpoint piCoordinate, (xpi1,ypi1)(xpi2,ypi2) it is respectively line segment starting point and terminal pi1,
pi2Coordinate.
Beneficial effect:Compared with prior art, its remarkable advantage is the present invention:The inventive method execution efficiency is higher, by
The interference of landform noise is lacked, and extraction effect is good, is consistent with actual landform.
Brief description of the drawings
Fig. 1 is the experimental data figure used in embodiment;
Fig. 2 is the schematic flow sheet of the inventive method;
Fig. 3 is the mountain top point schematic diagram of the present embodiment extraction;
Fig. 4 is the schematic diagram of the TIN formed in the present embodiment;
Fig. 5 is the saddle point schematic diagram extracted in the present embodiment, and black is saddle point.
Embodiment
Technical solution of the present invention is described in detail below, the experimental data of this example is using 1:25000 dusk
Terrain data (Fig. 1) in the terrain and geologic map of Yunling area.Have that independent mountain peak is multiple in area, mountain peak relative relief 50m-
Between 150m.Below in conjunction with the accompanying drawings, and by describing a specific embodiment, to further illustrate.
As shown in Fig. 2 in the present embodiment, saddle point extracting method comprises the following steps:
(1) contour line data of topographic map is read, therefrom extracts mountain top point.
Wherein, the contour line data of shp forms is specially read, the method for extraction mountain top point is specially:
A, non-closed contour line chart layer and closed contour face figure layer are generated according to original wire contour map layer;Specifically
Including:For original wire contour map layer, non-closed contour therein is extracted, and generate non-closed contour line chart layer;
For original wire contour map layer, closed contour therein is extracted, and is converted to closed contour face figure layer.
B, from each closed contour in the figure layer of closed contour face, extraction Due South is upwards apart from key element outsourcing square
A nearest point of the midpoint of shape, as the node for representing the closed contour, form set of node.
Specifically include:
B-1, a closed contour l is read from the figure layer of closed contour facei;
B-2, based on below equation, the midpoint c of computational element outsourcing rectangle;
In formula, xc,ycFor midpoint c coordinate, xmax、xmin、ymax、yminX directions and y directions for key element outsourcing rectangle
Coordinate range information;
B-3, obtain the upward closed contour l of Due SouthiAbscissa and the immediate point p of midpoint c abscissas, as generation
Table closed contour liNode;
B-4, circulation perform step B-1 to B-3, are saved until obtaining in the figure layer of closed contour face corresponding to each contour
Point, it is stored in set of node P.
C, using corresponded in set of node contour have comprising and the point of syntople build syntople figure, and according to neighbour
Connect graph of a relation and extract mountain top point.
Specifically include:
C-1, with corresponded in directed edge connecting node collection P contour have comprising and syntople point, form adjacent close
System figure G;
C-2, it will abut against the side chain rejecting that terminal elevation in graph of a relation G is less than starting point elevation;
Contour where the tail node of each side chain in C-3, the syntople figure G for obtaining step C-2, as mountain top position
Put the contour at place;
C-4, the contour for mountain top opening position, its center of mass point is extracted as mountain top point.
D, for corresponded in set of node contour not comprising or syntople point, based on non-closed contour line chart
Layer, selects mountain top point.
Specifically include:
D-1, for corresponded in set of node P contour not comprising or syntople point, obtain contour l where itt
On any point pr;
D-2, a is calculated using below equation, and with prCentered on point, the length of side be that a builds square key element R;
A=k*d
In formula, d is the substantially spacing between two adjoining contours, and k is amplification coefficient, and its span is (2,3);
D-3, extracted and contour l from non-closed contour line chart layertElevation differ a contour interval and with just
Contour l intersecting square key element Ra;
If D-4, contour laHeight value be less than contour ltHeight value, then contour laWhere the point of mountain top etc.
High line;Otherwise, contour laThe contour where the point of mountain valley;
D-5, the contour for mountain top opening position, its center of mass point is extracted as mountain top point.
E, all mountain top points extracted are generated into mountain top point figure layer, extraction result is as shown in Figure 3.
(2) according to the mountain top of extraction point, TIN is built.It is as shown in Figure 4 to build result.
(3) every a line of TIN is directed to, filters out two intersecting therewith contours arranged side by side.Specific bag
Include:
(3-1) is directed to a line l of TINi, carry out intersecting processing with contour, and will have intersecting pass therewith
The elevation of the contour of system, element numerals information, are spatially sequentially sequentially stored into queue LiIn.
For example, in the present embodiment, L1Include 6 elements altogether, its element numerals, height value be respectively (10,300), (12,
300), (19,350), (20,350), (23,400), (24,450).
(3-2) presses elevation order from small to large, to queue LiMiddle element is resequenced.
For example, L1After sequence result for (10,300), (12,300), (19,350), (20,350), (23,400), (24,
450)}。
(3-3) traversal queue Li, search is informed against abuts elements, contour as arranged side by side to two with identical elevation.
In the present embodiment, from L1In the two contours arranged side by side numberings that search out be respectively:10,12.This two contours point
It is not designated as:e11、e12。
(3-4) repeats (3-1) and arrives (3-3), until obtaining the contour arranged side by side of each edge of TIN.
(4) two contours arranged side by side corresponding to each edge are based on, extract saddle point, generate saddle point figure layer.Specifically include:
(4-1) is directed to a line l of TINiCorresponding two contour e arranged side by sidei1、ei2, obtain two it is contour
Closest 2 points on line, p is designated asi1、pi2。
In the present embodiment, 2 points are respectively:p11(401713.52504707419,3273057.1557612987), p12
(401219.66235632286,3272805.9475572747)。
(4-2) travels through the contour line data of topographic map, and e is removed if wherein existingi1、ei2Contour in addition and line segment (pi1,
pi2) intersecting, then step (4-4) is performed, if in the absence of execution step (4-3);
In the present embodiment, in the absence of with line segment (p11,p12) intersecting contour, then perform step (4-3)
(4-3) calculates line segment (pi1,pi2) midpoint pi, midpoint piAs saddle point.
In the present embodiment, p1Coordinate result of calculation is:(401802.11915109842,3272906.4302647519).
(4-4) returns to execution (4-1) and arrives (4-3), until each edge of TIN is all by alignment processing;
(4-5) is according to obtained saddle point generation saddle point figure layer.In the present embodiment, 7 saddle points are extracted altogether, are extracted
As a result tie shown in Fig. 5.
Above disclosed is only a kind of preferred embodiment of the present invention, it is impossible to the right model of the present invention is limited with this
Enclose, therefore the equivalent variations made according to the claims in the present invention, still belong to the scope that the present invention is covered.
Claims (5)
1. a kind of saddle point extracting method based on contour, it is characterised in that this method includes:
(1) contour line data of topographic map is read, therefrom extracts mountain top point;
(2) according to the mountain top of extraction point, TIN is built;
(3) every a line of TIN is directed to, filters out two intersecting therewith contours arranged side by side;
(4) two contours arranged side by side corresponding to each edge are based on, extract saddle point, generate saddle point figure layer.
2. the saddle point extracting method according to claim 1 based on contour, it is characterised in that:Step (3) is specifically wrapped
Include:
(3-1) is directed to a line l of TINi, carry out intersecting processing with contour, and will have overlapping relation therewith
The elevation of contour, element numerals information, are spatially sequentially sequentially stored into queue LiIn;
(3-2) presses elevation order from small to large, to queue LiMiddle element is resequenced;
(3-3) traversal queue Li, search is informed against abuts elements, contour as arranged side by side to two with identical elevation;
(3-4) repeats (3-1) and arrives (3-3), until obtaining the contour arranged side by side of each edge of TIN.
3. the saddle point extracting method according to claim 1 based on contour, it is characterised in that:Step (4) is specifically wrapped
Include:
(4-1) is directed to a line l of TINiCorresponding two contour e arranged side by sidei1、ei2, obtain on two contours
Closest 2 points, are designated as pi1、pi2;
(4-2) travels through the contour line data of topographic map, and e is removed if wherein existingi1、ei2Contour in addition and line segment (pi1,pi2) phase
Hand over, then perform step (4-4), if in the absence of execution step (4-3);
(4-3) calculates line segment (pi1,pi2) midpoint pi, midpoint piAs saddle point;
(4-4) returns to execution (4-1) and arrives (4-3), until each edge of TIN is all by alignment processing;
(4-5) is according to obtained saddle point generation saddle point figure layer.
4. the saddle point extracting method according to claim 3 based on contour, it is characterised in that:The step (4-1)
The calculation formula of middle distance between two points is:
<mrow>
<mi>d</mi>
<mo>=</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
<mo>-</mo>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
</mrow>
In formula, (x1,y1) for wherein on a contour any point coordinate, (x2,y2) it is any point on another contour
Coordinate.
5. the saddle point extracting method according to claim 3 based on contour, it is characterised in that:The step (4-3)
Middle conductor (pi1,pi2) midpoint piCalculation formula be:
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<msub>
<mi>x</mi>
<mrow>
<mi>p</mi>
<mi>i</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>p</mi>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>x</mi>
<mrow>
<mi>p</mi>
<mi>i</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</mfrac>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>y</mi>
<mrow>
<mi>p</mi>
<mi>i</mi>
</mrow>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mo>(</mo>
<msub>
<mi>y</mi>
<mrow>
<mi>p</mi>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>y</mi>
<mrow>
<mi>p</mi>
<mi>i</mi>
<mn>2</mn>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</mfrac>
</mtd>
</mtr>
</mtable>
</mfenced>
Wherein, (xpi,ypi) it is midpoint piCoordinate, (xpi1,ypi1)(xpi2,ypi2) it is respectively line segment starting point and terminal pi1,pi2Sit
Mark.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711226158.0A CN107895370B (en) | 2017-11-29 | 2017-11-29 | Saddle point extraction method based on contour line |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711226158.0A CN107895370B (en) | 2017-11-29 | 2017-11-29 | Saddle point extraction method based on contour line |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107895370A true CN107895370A (en) | 2018-04-10 |
CN107895370B CN107895370B (en) | 2020-05-15 |
Family
ID=61806646
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711226158.0A Active CN107895370B (en) | 2017-11-29 | 2017-11-29 | Saddle point extraction method based on contour line |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107895370B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109242930A (en) * | 2018-11-02 | 2019-01-18 | 中国石油大学(华东) | A kind of elevational point for digital adventure appearance and contour spatial logic relationship detection method |
CN109739942A (en) * | 2018-12-14 | 2019-05-10 | 南京泛在地理信息产业研究院有限公司 | A kind of saddle point extracting method based on contour line model |
CN110569871A (en) * | 2019-07-30 | 2019-12-13 | 西安建筑科技大学 | saddle point identification method based on deep convolutional neural network |
CN113343916A (en) * | 2021-06-30 | 2021-09-03 | 上海申瑞继保电气有限公司 | Method for extracting device features in transformer substation device image |
CN114723911A (en) * | 2022-06-09 | 2022-07-08 | 自然资源部第二海洋研究所 | Seabed geographic entity boundary automatic identification method based on D-P algorithm and optimal path |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103226845A (en) * | 2013-03-18 | 2013-07-31 | 北京市测绘设计研究院 | TIN-based earth surface refinement processing method and system |
CN107067446A (en) * | 2017-01-19 | 2017-08-18 | 中国测绘科学研究院 | A kind of contour proximity relations judges and direction automatic adjusting method |
-
2017
- 2017-11-29 CN CN201711226158.0A patent/CN107895370B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103226845A (en) * | 2013-03-18 | 2013-07-31 | 北京市测绘设计研究院 | TIN-based earth surface refinement processing method and system |
CN107067446A (en) * | 2017-01-19 | 2017-08-18 | 中国测绘科学研究院 | A kind of contour proximity relations judges and direction automatic adjusting method |
Non-Patent Citations (5)
Title |
---|
刘颖: "空间图形的表达、识别与综合", 《中国优秀博硕士学位论文全文数据库(博士) 基础科学辑》 * |
吴凡等: "顾及地形特征的等高线拓扑空间关系表达", 《武汉大学学报( 工学版)》 * |
孔月萍等: "利用拓扑关系快速提取鞍部点", 《计算机工程与应用》 * |
张宇军: "基于DEM骨架特征点线的地貌自动综合研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
杨族桥: "DEM多尺度表达研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109242930A (en) * | 2018-11-02 | 2019-01-18 | 中国石油大学(华东) | A kind of elevational point for digital adventure appearance and contour spatial logic relationship detection method |
CN109739942A (en) * | 2018-12-14 | 2019-05-10 | 南京泛在地理信息产业研究院有限公司 | A kind of saddle point extracting method based on contour line model |
CN109739942B (en) * | 2018-12-14 | 2020-10-16 | 南京泛在地理信息产业研究院有限公司 | Saddle point extraction method based on contour line model |
CN110569871A (en) * | 2019-07-30 | 2019-12-13 | 西安建筑科技大学 | saddle point identification method based on deep convolutional neural network |
CN113343916A (en) * | 2021-06-30 | 2021-09-03 | 上海申瑞继保电气有限公司 | Method for extracting device features in transformer substation device image |
CN113343916B (en) * | 2021-06-30 | 2024-02-09 | 上海申瑞继保电气有限公司 | Method for extracting equipment characteristics in substation equipment image |
CN114723911A (en) * | 2022-06-09 | 2022-07-08 | 自然资源部第二海洋研究所 | Seabed geographic entity boundary automatic identification method based on D-P algorithm and optimal path |
Also Published As
Publication number | Publication date |
---|---|
CN107895370B (en) | 2020-05-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107895370A (en) | A kind of saddle point extracting method based on contour | |
CN107392925B (en) | Remote sensing image ground object classification method based on super-pixel coding and convolutional neural network | |
CN101901343B (en) | Remote sensing image road extracting method based on stereo constraint | |
CN110348445A (en) | A kind of example dividing method merging empty convolution sum marginal information | |
CN106557579A (en) | A kind of vehicle model searching system and method based on convolutional neural networks | |
CN107146280A (en) | A kind of point cloud building method for reconstructing based on cutting | |
CN105869173A (en) | Stereoscopic vision saliency detection method | |
CN105374033A (en) | SAR image segmentation method based on ridgelet deconvolution network and sparse classification | |
CN101303729B (en) | Novel method for detecting fingerprint singularity | |
CN101639947A (en) | Image-based plant three-dimensional shape measurement and reconstruction method and system | |
CN104573685A (en) | Natural scene text detecting method based on extraction of linear structures | |
CN110688958A (en) | Intersection identification method based on GoogleLeNet neural network | |
CN107944437B (en) | A kind of Face detection method based on neural network and integral image | |
CN110008602B (en) | Road network selection method considering multi-feature coordination under large scale | |
CN105956544B (en) | A method of it extracts the remote sensing image road intersection based on structure index feature | |
CN106611423A (en) | SAR image segmentation method based on ridge wave filter and deconvolution structural model | |
CN107679539A (en) | A kind of single convolutional neural networks local message wild based on local sensing and global information integration method | |
CN110458797A (en) | A kind of conspicuousness object detecting method based on depth map filter | |
CN109800713A (en) | The remote sensing images cloud detection method of optic increased based on region | |
CN106530334A (en) | Complex image registration method and complex image registration system of airborne interferometric synthetic aperture radar | |
CN106355607A (en) | Wide-baseline color image template matching method | |
CN103226825B (en) | Based on the method for detecting change of remote sensing image of low-rank sparse model | |
CN110503113A (en) | A kind of saliency object detection method restored based on low-rank matrix | |
CN112116709B (en) | Terrain characteristic line processing method for improving terrain expression precision | |
CN103310456B (en) | Multidate/multi-modal remote sensing image registration method based on Gaussian-Hermite square |
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 |