CN108090898A - The satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary - Google Patents
The satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary Download PDFInfo
- Publication number
- CN108090898A CN108090898A CN201711380350.5A CN201711380350A CN108090898A CN 108090898 A CN108090898 A CN 108090898A CN 201711380350 A CN201711380350 A CN 201711380350A CN 108090898 A CN108090898 A CN 108090898A
- Authority
- CN
- China
- Prior art keywords
- terrestrial reference
- dictionary
- image
- typical case
- typical
- 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
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/513—Sparse representations
Abstract
The invention discloses a kind of satellite remote sensing images typical case's terrestrial reference detection methods represented based on dictionary, comprise the following steps S1, selected landmark region, generate the typical terrestrial reference database of the landmark region；S2, Image Acquisition is carried out to landmark region, is matched the image of acquisition with the typical terrestrial reference database that S1 is obtained using dictionary method for expressing, obtain testing result.Different weather situation is contained in typical case's terrestrial reference database, different time, different illumination, typical landmark image information of the different background when complicated day under environment, therefore adaptability of the present invention is good, and typical terrestrial reference detection during for complicated day under environment can obtain good detection result.The dictionary method for expressing includes rarefaction representation and is represented with cooperateing with, and design synthesis typical case terrestrial reference storehouse of the present invention and dictionary method for expressing carry out satellite remote sensing images typical case's terrestrial reference detection, and detection result and stability are good.
Description
Technical field
The present invention relates to remote sensing technology fields, and in particular to a kind of satellite remote sensing images typical case's terrestrial reference represented based on dictionary
Detection method.
Background technology
Confessed one's crime since an artificial earth satellite successful launch, satellite image data since its acquisition is rapid, cost is relatively low and
Without geographical restrictions the advantages of, has obtained extensively in multiple fields such as space exploration, meteorology, resource investigation, navigation, communication and investigations
General application.Passing of satelline satellite borne sensor obtains ground, air, the image in space, by being carried out to satellite image at analysis
Reason, completes corresponding function.Satellite image analyzing and processing application in, wherein the geometric correction of satellite image, based on satellite
The technologies such as Satellite Orbit Determination, the image-guidance of remote sensing images are the important applications in satellite image data processing procedure, are also simultaneously
Satellite image data application study and the technical foundation of product development.How to realize that satellite remote sensing images typical case's terrestrial reference detection is to defend
One of crucial research contents of the geometric correction of star chart picture, the Satellite Orbit Determination based on image, image-guidance etc..
In practical applications, satellite image is since there are image errors so that characters of ground object included in image exists
Deformation, along in image influence of noise, optical sensor be imaged when optical system point diffusion phenomena and satellite image
In domain containing cloud sector characters of ground object is blocked, these can all have an impact the precision of terrestrial reference detection in satellite image.By defending
Average cloud amount in star chart picture is larger, in addition terrestrial reference is influenced very big, different illumination conditions hypograph by weather and sunshine condition etc.
Feature may change.In addition, characters of ground object has phenomena such as distortion, offset in satellite image, sensor also has noise,
These can all cause characters of ground object information in satellite image to lose either invalid acquisition and then cause erroneous matching or reduce ground
Target matching precision, therefore, traditional terrestrial reference detection method can not reach preferable detection result.
The content of the invention
It is an object of the invention to provide it is a kind of based on dictionary represent satellite remote sensing images typical case's terrestrial reference detection method, with
The defects of traditional satellite image typical case's terrestrial reference detection is overcome not to be suitable for the efficient detection under complex environment.
To achieve the above object, the present invention uses following technical scheme：
Based on satellite remote sensing images typical case's terrestrial reference detection method that dictionary represents, comprise the following steps：
S1, selected landmark region generate the typical terrestrial reference database of the landmark region；
S2, Image Acquisition is carried out to landmark region, the typical case for the image of acquisition and S1 being obtained using dictionary method for expressing
Landmark data storehouse is matched, and obtains testing result.
Further, step S1 is specifically included：
S11, Image Acquisition is carried out to selected landmark region, obtains prior image and the terrestrial reference area of the landmark region
The geographic coordinate information in domain；
S12, feature extraction is carried out to the prior image of the landmark region；
S13, the typical terrestrial reference database for generating the landmark region, typical case's terrestrial reference database are believed including prior image
Breath, characteristic information and geographical location information.
Further, prior image described in step S11 includes different weather situation, different time, different illumination or not
With the image information under background.
Further, the step S2 is specifically included：
S21, the realtime graphic for gathering landmark region, and carry out image preprocessing；
S22, feature extraction is carried out to pretreated image；
S23, the typical terrestrial reference database progress for representing to obtain the image of acquisition and S1 using rarefaction representation or collaboration
Match somebody with somebody, obtain testing result.
Further, the rarefaction representation described in step S23 is specially：
S231, typical terrestrial reference database is set as dictionary D, the realtime graphic of step S2 acquisitions is set to test sample y, then hasIn formula, λ1For regular parameter, α is sparse coefficient to be estimated；
S232, sparse coefficient α is solved；
The product of each atom and sparse coefficient α in S233, Dictionary of Computing D obtains the estimate of realtime graphic y；
Two norms of the residual error of the estimate D α of S234, calculating test sample y and dictionary, i.e. Res=| | y-D α | |,
Selected threshold δ, if | | y-D α | | ＜ δ, realtime graphic and terrestrial reference storehouse successful match.
Further, orthogonal matching pursuit algorithm or synchronous orthogonal matching pursuit algorithm or non-thread are passed through in step S232
Property orthogonal matching pursuit algorithm solve sparse coefficient α.
Further, described in step S23 collaboration expression be specially：
S231, typical terrestrial reference database is set as dictionary D, the realtime graphic of step S2 acquisitions is set to test sample y, then hasIn formula, λ2For regular parameter, α is sparse coefficient to be estimated；
S232, sparse coefficient α is solved；
The product of each atom and sparse coefficient α in S233, Dictionary of Computing D obtains the estimate of realtime graphic y；
S234, two norms for calculating test sample y and the residual error of the estimate D α of each atom, i.e. Res=| | y-D
α | |, selected threshold δ, if | | y-D α | | ＜ δ, realtime graphic and terrestrial reference storehouse successful match.
Further, sparse coefficient α, i.e. α are solved by least square method in step S232(CR)=(DTD+λ2I)-1DTY,
In formula, DTRepresent the transposed matrix of D, I represents unit matrix.
After adopting the above technical scheme, the present invention has the following advantages that compared with background technology：
The present invention adapts to, for the typical terrestrial reference detection under the complex situations such as complex background, noise jamming, illumination variation
It can obtain good detection result；
The present invention is represented using the dictionary of typical terrestrial reference storehouse, since the robustness of typical terrestrial reference storehouse is good, comprising various multiple
Miscellaneous situation, therefore its detection result stability is good.
Description of the drawings
Fig. 1 is overall flow schematic diagram of the present invention；
Fig. 2 is the flow diagram of the typical terrestrial reference database of present invention generation；
The image of acquisition and typical terrestrial reference database are carried out matched flow by Fig. 3 for the present invention using dictionary method for expressing
Schematic diagram.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to the accompanying drawings and embodiments, it is right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Embodiment
Refering to what is shown in Fig. 1, the invention discloses a kind of satellite remote sensing images typical case terrestrial reference detection sides represented based on dictionary
Method comprises the following steps：
S1, selected landmark region generate the typical terrestrial reference database of the landmark region；
S2, Image Acquisition is carried out to landmark region, the typical case for the image of acquisition and S1 being obtained using dictionary method for expressing
Landmark data storehouse is matched, and obtains testing result.
Refering to what is shown in Fig. 2, step S1 (step is processed offline part) is specifically included：
S11, Image Acquisition is carried out to selected landmark region using satellite or unmanned plane, obtains the priori of the landmark region
Image and the geographic coordinate information of the landmark region；
S12, feature extraction is carried out to the prior image of the landmark region；
S13, the typical terrestrial reference database for generating the landmark region, typical case's terrestrial reference database are believed including prior image
Breath, characteristic information and geographical location information.
Typical terrestrial reference database is by typically target template image data and landmark attributes data in sensor observation area
Composition, is the matched important component of satellite image terrestrial reference.The factors such as precision, size, the type of terrestrial reference template image are direct
It is related to the matched precision of terrestrial reference and efficiency, when the terrestrial reference negligible amounts in terrestrial reference template database, with satellite image success
The terrestrial reference that matching obtains the effective offset parameter of image is on the low side, can also influence the precision of image geometry positioning, image-guidance etc..
Therefore, the landmark region chosen in step S11 should have abundant, apparent characteristics of image and be not easy to obscure, such as
There is obvious characteristic with skyscraper, viaduct, river, reservoir dam and airport etc. and be difficult to the remote sensing ground replicated control
Point.
Landmark attributes data mainly include 4 aspect contents：1) sky of the geographical location information, i.e. control point at control point is described
Between coordinate；2) some necessary auxiliary informations of geographical coordinate, such as used coordinate system, projection pattern, ellipsoidal parameter are described
Deng；3) auxiliary information of description control point image, such as the type of sensor, wave band, picture altitude, image resolution ratio；4) control
The feature description that system point is chosen, such as the intersection of road or bridge central point, these information can be as the subsidiary conditions of inquiry.
Meanwhile to reduce influence of the complex background to detection result, the adaptability of detection is improved, described in step S11 first
Testing image includes the image information under different weather situation, different time, different illumination or different background.
Refering to what is shown in Fig. 3, the step S2 is specifically included：
S21, the realtime graphic for gathering landmark region, and carry out image preprocessing；
Satellite image is since there are image errors so that characters of ground object included in image is there are deformation, along with figure
As in influence of noise, optical sensor imaging when optical system point diffusion phenomena and satellite image in domain containing cloud sector over the ground
Object feature is blocked, these can all have an impact the matched precision of terrestrial reference in satellite image.Therefore, it is necessary to distant to what is collected
Feel image and carry out data prediction, such as image denoising, image rectification and registering processing.
S22, feature extraction is carried out to pretreated image；Feature extraction namely image is converted accordingly, carried
Image information is taken, such as HOG features, Rough features, SIFT feature can be chosen according to the actual conditions of detection object.
S23, represent that (i.e. rarefaction representation or collaboration represents) obtains the image of acquisition and S1 typically using dictionary
Mark database is matched, and obtains testing result.
Wherein, Image Acquisition is carried out to landmark region using satellite in step S21, while step S1 is obtained typically
Database purchase is marked into the memory of satellite.Due to being influenced be subject to environment, sensor and platform interference etc., what satellite obtained
Image data can be there are noise and various forms of interference, in order to ensure the quality of subsequent operation and performance, so in step S2
It needs to carry out pretreatment operation to image.
In step S23, represent that detection criteria is based on dictionary：Test sample can be by the sample approximately linear table that marks
Show, weight coefficient is to pass through l0Norm or l1Norm punishment constraint (being known as rarefaction representation) or l2Norm punishment constraint (referred to as cooperates with
It represents).
Specifically, sparse representation model is selected still to cooperate with expression model, it need to be according to dictionary feature and scale (institute in dictionary
Number containing atom) etc. factors determine.Only have the corresponding expression coefficient of a small amount of atom in sparse representation model, in dictionary to be not zero
(i.e.：Only a small amount of atom pair expression contributes), suitable for dictionary larger (being usually complete dictionary) or dictionary atom
Each stronger situation of the opposite sex.Most atoms are corresponding in collaboration represents model, in dictionary represents that coefficient is not zero
(i.e.：Most atoms contribute expression), the different property unobvious of atom suitable for dictionary scale is smaller or dictionary
Situation.
The rarefaction representation (Sparse Representation, SR) is specially：
S231, typical terrestrial reference database is set as dictionary D, the realtime graphic of step S2 acquisitions is set to test sample y, then hasIn formula, λ1For regular parameter, α is sparse coefficient to be estimated, and α is a column vector,
SR represents rarefaction representation, | | | |2Represent 2- norms, i.e. vector field homoemorphism or length, | | | |1Represent 1- norms, i.e., vectorial each atom
The sum of absolute value.
S232, sparse coefficient α is solved；
The product of each atom and sparse coefficient α in S233, Dictionary of Computing D obtains the estimate of realtime graphic y；
Two norms of the residual error of the estimate D α of S234, calculating test sample y and dictionary, i.e. Res=| | y-D α | |,
Suitable threshold value δ is chosen, if | | y-D α | | ＜ δ, realtime graphic and terrestrial reference storehouse successful match.
Threshold selection method：Suitable threshold value is chosen by testing, i.e., with the image of some Given informations (including positive sample
And negative sample, the positive sample want matched landmark image, and the negative sample is not matched landmark image) it goes to use dictionary
It is indicated, by experiment, choosing one can be by the effectively separated threshold value of positive negative sample.
Wherein, orthogonal matching pursuit algorithm (OMP) or synchronous orthogonal matching pursuit algorithm (SOMP) are passed through in step S232
Or non-linear orthogonal matching pursuit algorithm (Kernel-OMP, KOMP) solves sparse coefficient α.
Collaboration described in step S23 represents that (Cooperative Representation, CR) is specially：
S231, typical terrestrial reference database is set as dictionary D, the realtime graphic of step S2 acquisitions is set to test sample y, then hasIn formula, λ2For regular parameter, α is sparse coefficient to be estimated, and α is a column vector；
CR represents collaboration and represents,Represent square of square, i.e. vector field homoemorphism of the 2- norms of vector；
Sparse coefficient α is solved by least square method in S232, step S232, then has α(CR)=(DTD+λ2I)-1DTy；Formula
In, CR represents collaboration and represents, DTThe transposed matrix of representing matrix D, I represent unit matrix；
The product of each atom and sparse coefficient α in S233, Dictionary of Computing D obtains the estimate of realtime graphic y；
S234, two norms for calculating test sample y and the residual error of the estimate D α of each atom, i.e. Res=| | y-D
α | |, suitable threshold value δ is chosen, if | | y-D α | | ＜ δ, realtime graphic and terrestrial reference storehouse successful match.
Threshold selection method：Suitable threshold value is chosen by testing, i.e., with the image of some Given informations (including positive sample
And negative sample, the positive sample want matched landmark image, and the negative sample is not matched landmark image) it goes to use dictionary
It is indicated, by experiment, choosing one can be by the effectively separated threshold value of positive negative sample.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
Subject to.
Claims (8)
1. the satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary, which is characterized in that comprise the following steps：
S1, selected landmark region generate the typical terrestrial reference database of the landmark region；
S2, Image Acquisition is carried out to landmark region, the typical terrestrial reference for the image of acquisition and S1 being obtained using dictionary method for expressing
Database is matched, and obtains testing result.
2. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as described in claim 1, feature
It is, step S1 is specifically included：
S11, Image Acquisition is carried out to selected landmark region, obtains prior image and the landmark region of the landmark region
Geographic coordinate information；
S12, feature extraction is carried out to the prior image of the landmark region；
S13, the typical terrestrial reference database for generating the landmark region, typical case's terrestrial reference database include prior image information, spy
Reference ceases and geographical location information.
3. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as claimed in claim 2, feature
It is：Prior image described in step S11 includes the figure under different weather situation, different time, different illumination or different background
Picture.
4. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as described in claim 1, feature
It is, the step S2 is specifically included：
S21, the realtime graphic for gathering landmark region, and carry out image preprocessing；
S22, feature extraction is carried out to pretreated image；
S23, represent to match the image of acquisition with the typical terrestrial reference database that S1 is obtained using rarefaction representation or collaboration, obtain
Take testing result.
5. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as claimed in claim 4, feature
It is, the rarefaction representation described in step S23 is specially：
S231, typical terrestrial reference database is set as dictionary D, the realtime graphic of step S2 acquisitions is set to test sample y, then hasIn formula, λ1For regular parameter, α is sparse coefficient to be estimated；
S232, sparse coefficient α is solved；
The product of each atom and sparse coefficient α in S233, Dictionary of Computing D obtains the estimate of realtime graphic y；
Two norms of the residual error of the estimate D α of S234, calculating test sample y and dictionary, i.e. Res=| | y-D α | |, it chooses
Threshold value δ, if | | y-D α | | ＜ δ, realtime graphic and terrestrial reference storehouse successful match.
6. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as claimed in claim 5, feature
It is：It is chased after in step S232 by orthogonal matching pursuit algorithm or the matching of synchronous orthogonal matching pursuit algorithm or non-linear orthogonal
Track Algorithm for Solving sparse coefficient α.
7. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as claimed in claim 4, feature
It is, the collaboration expression described in step S23 is specially：
S231, typical terrestrial reference database is set as dictionary D, the realtime graphic of step S2 acquisitions is set to test sample y, then hasIn formula, λ2For regular parameter, α is sparse coefficient to be estimated；
S232, sparse coefficient α is solved；
The product of each atom and sparse coefficient α in S233, Dictionary of Computing D obtains the estimate of realtime graphic y；
S234, two norms for calculating test sample y and the residual error of the estimate D α of each atom, i.e. Res=| | y-D α | |,
Selected threshold δ, if | | y-D α | | ＜ δ, realtime graphic and terrestrial reference storehouse successful match.
8. a kind of satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary as claimed in claim 7, feature
It is：Sparse coefficient α, i.e. α are solved by least square method in step S232(CR)=(DTD+λ2I)-1DTY, in formula, DTRepresent D
Transposed matrix, I represent unit matrix.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711380350.5A CN108090898B (en) | 2017-12-20 | 2017-12-20 | Dictionary representation-based satellite remote sensing image typical landmark detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711380350.5A CN108090898B (en) | 2017-12-20 | 2017-12-20 | Dictionary representation-based satellite remote sensing image typical landmark detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108090898A true CN108090898A (en) | 2018-05-29 |
| CN108090898B CN108090898B (en) | 2020-11-10 |
Family
ID=62177404
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711380350.5A Active CN108090898B (en) | 2017-12-20 | 2017-12-20 | Dictionary representation-based satellite remote sensing image typical landmark detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108090898B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375205A (en) * | 2018-09-28 | 2019-02-22 | 清华大学 | Multiple types unmanned plane scene recognition method dictionary-based learning and device |
| CN109614998A (en) * | 2018-11-29 | 2019-04-12 | 北京航天自动控制研究所 | Landmark database preparation method based on deep learning |
| CN114022784A (en) * | 2021-11-09 | 2022-02-08 | 中国人民解放军61646部队 | Method and device for screening landmark control points |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200478A (en) * | 2014-09-12 | 2014-12-10 | 广东财经大学 | Low-resolution touch screen image defect detection method based on sparse representation |
| CN105631478A (en) * | 2015-12-25 | 2016-06-01 | 天津科技大学 | Plant classification method based on sparse expression dictionary learning |
| CN107133260A (en) * | 2017-03-22 | 2017-09-05 | 新奥特（北京）视频技术有限公司 | The matching and recognition method and device of a kind of landmark image |
-
2017
- 2017-12-20 CN CN201711380350.5A patent/CN108090898B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104200478A (en) * | 2014-09-12 | 2014-12-10 | 广东财经大学 | Low-resolution touch screen image defect detection method based on sparse representation |
| CN105631478A (en) * | 2015-12-25 | 2016-06-01 | 天津科技大学 | Plant classification method based on sparse expression dictionary learning |
| CN107133260A (en) * | 2017-03-22 | 2017-09-05 | 新奥特（北京）视频技术有限公司 | The matching and recognition method and device of a kind of landmark image |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109375205A (en) * | 2018-09-28 | 2019-02-22 | 清华大学 | Multiple types unmanned plane scene recognition method dictionary-based learning and device |
| CN109614998A (en) * | 2018-11-29 | 2019-04-12 | 北京航天自动控制研究所 | Landmark database preparation method based on deep learning |
| CN114022784A (en) * | 2021-11-09 | 2022-02-08 | 中国人民解放军61646部队 | Method and device for screening landmark control points |
| CN114022784B (en) * | 2021-11-09 | 2022-04-19 | 中国人民解放军61646部队 | Method and device for screening landmark control points |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108090898B (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Oh et al. | Automated bias-compensation of rational polynomial coefficients of high resolution satellite imagery based on topographic maps | |
| CN106056605B (en) | A kind of in-orbit high precision image localization method based on images match | |
| Teo et al. | DEM-aided block adjustment for satellite images with weak convergence geometry | |
| Liu et al. | Comparative analysis of fractional vegetation cover estimation based on multi-sensor data in a semi-arid sandy area | |
| CN108090898A (en) | The satellite remote sensing images typical case's terrestrial reference detection method represented based on dictionary | |
| CN103093459A (en) | Assisting image matching method by means of airborne lidar point cloud data | |
| Huang et al. | High-efficiency determination of coastline by combination of tidal level and coastal zone DEM from UAV tilt photogrammetry | |
| Wang et al. | Large-scale orthorectification of GF-3 SAR images without ground control points for China’s land area | |
| CN108364279A (en) | Determine the method that stationary orbit remote sensing satellite is directed toward deviation | |
| Zhang et al. | UAV‐derived imagery for vegetation structure estimation in rangelands: validation and application | |
| Zhu et al. | An efficient and effective approach for georeferencing AVHRR and GaoFen-1 imageries using inland water bodies | |
| Qiao et al. | Assessment of geo-positioning capability of high resolution satellite imagery for densely populated high buildings in metropolitan areas | |
| LEE et al. | Analysis of cropland spectral properties and vegetation index using UAV | |
| Lu et al. | Estimation of Transformation Parameters Between Centre‐Line Vector Road Maps and High Resolution Satellite Images | |
| Kumar et al. | Data input in GIS | |
| Wang et al. | Retrieving individual tree heights from a point cloud generated with optical imagery from an unmanned aerial vehicle (UAV) | |
| Wang et al. | Comparison of change detection accuracy based on VHR images corresponding to the fusion estimation indexes | |
| CN109583484A (en) | A kind of three classes sea area landmark point automatically selecting method | |
| Yanan et al. | DEM extraction and accuracy assessment based on ZY-3 stereo images | |
| Zhang et al. | Registration of CBERS-02B satellite imagery in quick GIS updating | |
| El Sagheer et al. | Building Automated Navigation System for River Nile in Egypt Using Remote Sensing and GIS Techniques | |
| Dybkjaer | Algorithm Theoretical Basis Document for OSI SAF Medium Resolution Sea Ice Drift Product | |
| Cai et al. | Multispectral image and fullcolor remote sensing image processing technology | |
| Sattar et al. | The development of geoinformatics based framework to quantify gully erosion | |
| Naimark et al. | Vision-Aided Navigation for Aerial Platforms |
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 |