CN103645517A - Comprehensive anomaly extraction method based on blind source separation technology and apparatus thereof - Google Patents
Comprehensive anomaly extraction method based on blind source separation technology and apparatus thereof Download PDFInfo
- Publication number
- CN103645517A CN103645517A CN201310661715.7A CN201310661715A CN103645517A CN 103645517 A CN103645517 A CN 103645517A CN 201310661715 A CN201310661715 A CN 201310661715A CN 103645517 A CN103645517 A CN 103645517A
- Authority
- CN
- China
- Prior art keywords
- component
- observation signal
- blind source
- extraction method
- geochemical
- 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
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A comprehensive anomaly extraction method based on a blind source separation technology is disclosed. The method comprises the following steps that based on geochemical element data exploration, an observation signal is determined; based on the observation signal, through an independent component analysis algorithm, a first component is determined, wherein the first component is the independent component with largest energy which is determined based on the independent component analysis algorithm; based on the first component, a geochemical anomaly is determined. By using the method of the invention, comprehensive anomaly information of the geochemical exploration can be accurately reflected so that a target prospecting area can be accurately predicted.
Description
Technical field
The present invention relates to geochemical prospecting field, relate in particular to a kind of comprehensive abnormal extraction method and device based on blind source separate technology.
Background technology
At exploration geochemistry, look in the process of ore deposit, the comprehensive abnormal extraction of geochemistry is extremely important, the formation of mineral resources has often been passed through complicated geological process, has been possessed good material base, be accompanied by migration, the enrichment of multiple element, the multielement that forms the existence of indication mineral products is abnormal---and comprehensively abnormal.
Problem that person pays close attention to that comprehensive abnormal extraction is Geochemical Exploration always, mostly comprehensive abnormal delineation is in the past to rely on the abnormal distribution situation of single element, by the abnormal fair drawing of relevant single element on a base map, utilize the overlapping situation of element, roughly draw a circle to approve out a scope, that draws a circle to approve out like this comprehensively can roughly reflect a mineralising scope in region extremely, for further looking for ore deposit to provide one to look for territory, mining area.In addition, also there are some mathematical methods to be applied to comprehensive abnormal extraction, such as, clustering methodology, factor analysis, principal component analysis (PCA) etc.
According to single element comprehensively extremely inevitably can there are some problems in concentrate situation delineation: such as, anomaly area is excessive and a scope just, cannot reflect concentration center; Comprehensive abnormal delineation varies with each individual, and can miss some significant abnormal informations, makes the comprehensive abnormal information determined inaccurate.
Summary of the invention
The problem that the present invention solves is that prior art cannot accurately be determined the problem of comprehensive abnormal information.
For addressing the above problem, technical solution of the present invention provides a kind of comprehensive abnormal extraction method based on blind source separate technology, and described method comprises:
Based on geochemical elements data, determine observation signal;
Based on described observation signal, by Independent Component Analysis Algorithm, determine the first component, described the first component is the isolated component based on the determined energy maximum of Independent Component Analysis Algorithm;
Based on described the first component, determine geochemical anomaly.
Optionally, described geochemical elements data are a plurality of single element data.
Optionally, described observation signal is multiple tracks observation signal.
Optionally, after determining observation signal, based on described observation signal, before determining the first component by Independent Component Analysis Algorithm, described observation signal is carried out to pre-service.
Optionally, described pre-service comprises described observation signal is gone at least one in average and albefaction.
Optionally, described opposition component analysis algorithm comprises any one in FastICA algorithm or JADE algorithm.
Optionally, describedly based on described the first component, determine that geochemical anomaly comprises:
Based on described the first component, determine target and change element combinations.
Optionally, described target groundization element combinations comprises the larger geochemical elements of described the first component impact.
Technical solution of the present invention also provides a kind of comprehensive abnormal extraction element based on blind source separate technology, and described device comprises:
The first determining unit, is suitable for determining observation signal based on geochemical elements data;
The second determining unit, is suitable for, based on described observation signal, by Independent Component Analysis Algorithm, determining the first component, described the first component is the isolated component based on the determined energy maximum of Independent Component Analysis Algorithm;
The 3rd determining unit, is suitable for determining geochemical anomaly based on described the first component
Compared with prior art, technical scheme of the present invention has the following advantages:
Based on existing single element geochemistry data, can determine corresponding observation signal, based on Independent Component Analysis Algorithm, can determine the corresponding isolated component of described observation signal, determine afterwards the isolated component (the first component) of energy maximum in the corresponding isolated component of described observation signal, and described the first component can reflect the comprehensive characteristics of geochemical elements, based on described the first component comprehensive abnormal information that accurately deterministic is visited, and then ore prediction and prospecting target area comparatively accurately.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the comprehensive abnormal extraction method based on blind source separate technology that provides of technical solution of the present invention;
Fig. 2 is the schematic flow sheet of the comprehensive abnormal extraction method based on blind source separate technology that provides of the embodiment of the present invention one;
Fig. 3 is the comprehensive abnormal results schematic diagram of detection that the embodiment of the present invention one provides;
Fig. 4 is the schematic flow sheet of the comprehensive abnormal extraction method based on blind source separate technology that provides of the embodiment of the present invention two;
Fig. 5 is the comprehensive abnormal results schematic diagram of detection that the embodiment of the present invention two provides.
Embodiment
In prior art, according to the single element situation that concentrates, draw a circle to approve comprehensive abnormal method, have the inaccurate problem of abnormal information, for addressing the above problem, technical solution of the present invention provides a kind of comprehensive abnormal extraction method based on blind source separate technology.In the method, in order comparatively accurately to determine comprehensive abnormal information, based on geochemical elements data, determine observation signal, and then based on Independent Component Analysis Algorithm, determine comprehensive abnormal.
The separation of blind source refers in the situation that not knowing input signal, only according to observation signal or output signal, carrys out recognition system, thereby isolates the isolated component of a plurality of signals, with this, recovers source signal (or signal source).
Independent component analysis (ICA, Independent Component Analysis) algorithm is in recent years by blind source separate technology (BSS, Blind Source Separation) a kind of new multi-dimensional signal disposal route that development comes is the developing forward position focus of signal processing technology.Its basic ideas are that the observation signal of multidimensional is set up to objective function according to adding up independently principle, by optimized algorithm, observation signal are decomposed into some independent components, thereby help to realize enhancing and the analysis of signal.ICA, from the higher order statistical characteristic of multidimensional observation data, extracts independent component wherein, thereby makes decomposition result have more practical significance, and ICA can guarantee the mutual independence between output component.
To some degree, ICA is the expansion of principal component analysis (PCA) (PCA, Principal Component Analysis), and the object of PCA is to reduce vectorial dimension, remove the correlativity between random vector, find out the larger vector of inherent energy implicit in original vector.But because PCA method only relates to the second-order statistics (only utilizing vectorial covariance matrix) of input data probability distributions function when the actual computation, so decomposite to obtain each principal component mutually orthogonal (also can say between each component uncorrelated).Viewpoint from mathematical statistics, most of important information of real data is often included in higher order statistical characteristic, ICA method often needs high-order statistic, namely at learning phase, need to use certain non-linear, in many situations, ICA can provide the more significant information than PCA, and ICA only could realize PCA when former data are Gaussian distribution.
A main difficulty that solves blind source separation problem is, does not know any information of source signal, does not also know the hybrid mode of source signal, but as long as hypothesis source signal be mutual statistical independently, just can apply Independent Component Analysis Algorithm and solve this problem.Independent component analysis is an effective way that solves blind source separation problem.
Technical solution of the present invention adopts the comprehensive abnormal extraction method based on blind source separate technology, and Fig. 1 is the schematic flow sheet of the comprehensive abnormal extraction method based on blind source separate technology that provides of technical solution of the present invention.
As shown in Figure 1, first perform step S101, based on geochemical elements data, determine observation signal.
Described geochemical elements data can be a plurality of single element data, shown in observation signal can be multiple tracks observation signal.
Execution step S102, based on described observation signal, determines the first component by Independent Component Analysis Algorithm.
Described the first component is the isolated component based on the determined energy maximum of Independent Component Analysis Algorithm.Described Independent Component Analysis Algorithm comprises any one in FastICA algorithm or JADE algorithm.
Execution step S103, determines geochemical anomaly based on described the first component.
Based on described the first component, determine target and change element combinations, described target groundization element combinations comprises the larger geochemical elements of described the first component impact.
For above-mentioned purpose of the present invention, feature and advantage can more be become apparent, below in conjunction with accompanying drawing, specific embodiments of the invention are described in detail.
embodiment mono-
In the present embodiment, adopt FastICA algorithm to carry out independent component analysis, based on independent component analysis result, determine geochemical anomaly.
FastICA algorithm, claim again Fixed point algorithm, independent component analysis method based on negentropy maximization criterion, the method relies on non-Gaussian and maximizes principle, by maximizing negentropy objective function, use that fixed-point iteration is theoretical to be found non-Gauss's maximal value and reach the optimum estimate of separation signal.This algorithm adopts Newton iterative to carry out batch processing to a large amount of sampled points of observation signal, and from observation signal, divide and measure an isolated component at every turn, be a kind of fast algorithm of independent component analysis.
Fig. 2 is the comprehensive abnormal extraction method based on blind source separate technology that the present embodiment provides, and as shown in Figure 2, first performs step S201, based on geochemical elements data, determines observation signal.
Described observation signal is multiple tracks observation signal, and each component of described observation signal is separate in statistics.
Step S202, carries out pre-service to described observation signal.
Generally, to the pre-service of data, be very necessary, because pre-service can be so that data complexity when carrying out engineering computing be simplified greatly, the result obtaining is also more accurate.Pre-service mainly comprises average and albefaction processing.
Data go average, go the process of average can be called centralization, go after the process of average completing data, in the algorithm of processing at signal, just can suppose that signal is zero-mean.
The albefaction of data, albefaction process itself is the process of a linear transformation, the meaning of this conversion is that the correlativity between new vector is removed.Can realize described albefaction process based on albefaction matrix, by described albefaction matrix, observation vector be applied to linear transformation and obtain.
Data are carried out to such processing and can make data more meet algorithm requirement, improve detection accuracy.
Step S203, determines objective function based on negentropy maximization.
Conventionally, the process of blind source separation realizes by objective function of optimization, and conventional objective function has Higher Order Cumulants, negentropy, mutual information and maximal possibility estimation etc.
Because the entropy of Gaussian distribution in having the probability density function of same covariance matrix is maximum, negentropy is the non-Gauss's of tolerance a sane criterion.Important character of negentropy is: for reversible linear transformation, remain unchanged, therefore can make it maximize, thereby determine objective function.
Negentropy maximization means the maximization component that solves non-Gauss, based on described negentropy maximization, determines objective function.
Step S204, asks the maximal value of objective function based on Newton iterative.
Step S205, determines separation matrix.
Maximal value based on the resulting objective function of step S205, can try to achieve separation matrix W.
Step S206, obtains separate component.
Based on formula Y=WX, obtain separate component, wherein, Y is described separate component, and X is observation signal, and W is determined separation matrix W in step S205.
Step S207, determines the first component.
Each separate component based on obtaining in step S206, determines the wherein isolated component of energy maximum, determines described the first component.
Step S208, determines geochemical anomaly based on described the first component.
Based on described the first component, can determine the association of mineralizing element that this component is corresponding, based on described association of mineralizing element, determine that the element based on described impact is larger can be determined geochemical anomaly on the larger element of described the first component impact.
Above-mentioned about FastICA algorithm part, only simply the committed step of this algorithm has been carried out to simple description, those skilled in the art can adopt detailed FastICA algorithm to implement the present embodiment, for FastICA algorithm, partly do not repeat them here.
Based on the described method of the present embodiment, actual mining area is detected and verified, at this, with the 1:20 ten thousand stream sediment survey's data to a certain mining area, be verified as example, as shown in Figure 3, the change that black lines obtains for forefathers process is visited comprehensive abnormal, the resulting comprehensive abnormal ranges of method providing based on the present embodiment and forefathers process the change obtaining and visit the comprehensive good fit that extremely has, can find out, the result of processing based on FastICA can carry out comprehensive extremely comparatively accurately determining, can some position, fine reflection ore deposit.
The fast convergence rate of FaseICA, there is certain accuracy guarantee, this algorithm can be more scientific removal element combinations between correlativity, because this algorithm is nonlinear algorithm, and geochemistry data has nonlinear characteristic equally, so can process geochemistry data based on FaseICA algorithm, further, the result based on FaseICA algorithm can be determined comprehensive abnormal comparatively accurately.
embodiment bis-
In the present embodiment, adopt joint approximate diagonalization method (JADE, the Joint Approximate Diagonalization of Eigen-matrices) algorithm of eigenmatrix to carry out independent component analysis, based on independent component analysis result, determine geochemical anomaly.
Fig. 4 is the comprehensive abnormal extraction method based on blind source separate technology that the present embodiment provides, and as shown in Figure 4, first performs step S401, based on geochemical elements data, determines observation signal.
Described observation signal is multiple tracks observation signal, and each component of described observation signal is separate in statistics.
Execution step S402, carries out pre-service to described observation signal.
In this step, complete and described observation signal is gone to the processing such as average, albefaction.
Describedly go average also can be called to be the zero-mean to described observation signal, by methods such as sane prewhitenings, to carry out albefaction processing, the data recording after described albefaction can being processed be albefaction data Z.
Perform step S403, based on described albefaction data Z, obtain the fourth order cumulant matrix Q of albefaction data.
Execution step S404, according to Givens, a rotation battle array V is found in rotation.
When asking for described rotation matrix V, make fourth order cumulant matrix Q diagonalization as much as possible, make criterion
minimum.
Execution step S405, obtains hybrid matrix B based on described rotation matrix.
Based on formula B=
obtain
described hybrid matrix B.
Step S406, obtains separate component.
Based on formula
obtain source signal, and then obtain separate component.Wherein
for described separate component, X is observation signal, and B is determined hybrid matrix W in step S405.
Step S407, determines the first component.
Each separate component based on obtaining in step S406, determines the wherein isolated component of energy maximum, determines described the first component.
Step S408, determines geochemical anomaly based on described the first component.
Based on described the first component, can determine the ore deposit element combinations that this component is corresponding, based on described association of mineralizing element, determine that the element based on described impact is larger can be determined geochemical anomaly on the larger element of described the first component impact.
Above-mentioned about JADE algorithm part, only simply the committed step of this algorithm has been carried out to simple description, those skilled in the art can adopt detailed JADE algorithm to implement the present embodiment, for JADE algorithm, partly do not repeat them here.
Based on the described method of the present embodiment, actual mining area is detected and verified, this equally with embodiment in 1:20 ten thousand stream sediment survey's data in a certain mining area be verified as example, as shown in Figure 5, the change that black lines obtains for forefathers process is visited comprehensive abnormal, the resulting comprehensive abnormal ranges of method providing based on the present embodiment and forefathers process the change obtaining and visit the comprehensive good fit that extremely has, can find out, the result of processing based on JADE can carry out comprehensive extremely comparatively accurately determining equally, can some position, fine reflection ore deposit.
JADE blind source separation algorithm is used for to Geochemistry element combinations definitely, and then determines in comprehensive abnormal method, can comparatively accurately determine comprehensive abnormal.
The comprehensive abnormal method of extracting based on blind source separate technology, can comparatively accurately extract distribution of mineralization elements feature and draw a circle to approve geochemical elements comprehensively abnormal, by finding out the detection in a certain mining area and checking in above-described embodiment, the actual of comprehensive abnormal extraction process result based on blind source separate technology and mining area becomes the ore deposit goodness of fit higher, substantially can more truly change the off-note of element, method provided by the invention has stronger applicability and validity aspect geochemical anomaly data processing with reflecting.
Although the present invention discloses as above, the present invention is not defined in this.Any those skilled in the art, without departing from the spirit and scope of the present invention, all can make various changes or modifications, so protection scope of the present invention should be as the criterion with claim limited range.
Claims (9)
1. the comprehensive abnormal extraction method based on blind source separate technology, is characterized in that, comprising:
Based on exploration geochemistry element data, determine observation signal;
Based on described observation signal, by Independent Component Analysis Algorithm, determine the first component, described the first component is the isolated component based on the determined energy maximum of Independent Component Analysis Algorithm;
Based on described the first component, determine geochemical anomaly.
2. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 1, is characterized in that, described geochemical elements data are a plurality of single element data.
3. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 1, is characterized in that, described observation signal is multiple tracks observation signal.
4. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 1, it is characterized in that, after determining observation signal, based on described observation signal, before determining the first component by Independent Component Analysis Algorithm, described observation signal is carried out to pre-service.
5. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 1, is characterized in that, described pre-service comprises goes at least one in average and albefaction to described observation signal.
6. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 1, is characterized in that, described Independent Component Analysis Algorithm comprises any one in FastICA algorithm or JADE algorithm.
7. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 1, is characterized in that, describedly based on described the first component, determines that geochemical anomaly comprises:
Based on described the first component, determine the combination of target geochemical elements.
8. the comprehensive abnormal extraction method based on blind source separate technology as claimed in claim 7, is characterized in that, described target groundization element combinations comprises the larger geochemical elements of described the first component impact.
9. the comprehensive abnormal extraction element based on blind source separate technology, is characterized in that, comprising:
The first determining unit, is suitable for determining observation signal based on geochemical elements data;
The second determining unit, is suitable for, based on described observation signal, by Independent Component Analysis Algorithm, determining the first component, described the first component is the isolated component based on the determined energy maximum of Independent Component Analysis Algorithm;
The 3rd determining unit, is suitable for determining geochemical anomaly based on described the first component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310661715.7A CN103645517A (en) | 2013-12-10 | 2013-12-10 | Comprehensive anomaly extraction method based on blind source separation technology and apparatus thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310661715.7A CN103645517A (en) | 2013-12-10 | 2013-12-10 | Comprehensive anomaly extraction method based on blind source separation technology and apparatus thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103645517A true CN103645517A (en) | 2014-03-19 |
Family
ID=50250765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310661715.7A Pending CN103645517A (en) | 2013-12-10 | 2013-12-10 | Comprehensive anomaly extraction method based on blind source separation technology and apparatus thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103645517A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954932A (en) * | 2014-04-29 | 2014-07-30 | 西安电子科技大学 | Blind extraction method based on signal cyclostationarity characteristics |
| CN108345048A (en) * | 2018-01-18 | 2018-07-31 | 中国科学院遥感与数字地球研究所 | A kind of geochemical elements exception source recourse method based on Alteration Information of Remote Sensing |
| CN111175608A (en) * | 2020-01-19 | 2020-05-19 | 上海电力大学 | Power distribution network harmonic responsibility quantitative division method based on accelerated independent component analysis |
| CN115101137A (en) * | 2022-06-28 | 2022-09-23 | 贵州逸宸未来科技有限公司 | Geochemical data analysis method based on deep learning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1421709A (en) * | 2001-11-29 | 2003-06-04 | 中国科学院长沙大地构造研究所 | Multielement optimizing control method for prospecting ore deposit |
| CN102539194A (en) * | 2010-12-29 | 2012-07-04 | 中国石油天然气集团公司 | Gradient geochemical exploration method |
-
2013
- 2013-12-10 CN CN201310661715.7A patent/CN103645517A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1421709A (en) * | 2001-11-29 | 2003-06-04 | 中国科学院长沙大地构造研究所 | Multielement optimizing control method for prospecting ore deposit |
| CN102539194A (en) * | 2010-12-29 | 2012-07-04 | 中国石油天然气集团公司 | Gradient geochemical exploration method |
Non-Patent Citations (8)
| Title |
|---|
| JEAN-FRANCOIS CARDOSO: "High-Order Constrasts for Independent Component Analysis", 《NEURAL COMPUTATION》 * |
| 敖东: "JADE算法反演地球化学元素组合的应用研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
| 柳炳利等: "FastICA反演地球化学成矿元素组合新探索", 《金属矿山》 * |
| 柳炳利等: "JADE在寻求地球化学成矿元素组合中的应用探索", 《物探化探计算技术》 * |
| 柳炳利等: "非线性地球化学矿化元素组合求异方法在西藏洞噶普矿区的应用", 《地学前缘（中国地质大学（北京）；北京大学）》 * |
| 陈聆: "地球化学矿致异常非线性分析方法研究", 《中国博士学位论文全文数据库 基础科学辑》 * |
| 陈聆等: "基于盲源分离理论的地球化学矿致异常识别研究", 《现代地质》 * |
| 陶中平等: "独立分量分析在地球化学异常圈定中的应用", 《国土资源科技管理》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103954932A (en) * | 2014-04-29 | 2014-07-30 | 西安电子科技大学 | Blind extraction method based on signal cyclostationarity characteristics |
| CN103954932B (en) * | 2014-04-29 | 2016-04-06 | 西安电子科技大学 | A kind of blind abstracting method based on signal cycle smooth performance |
| CN108345048A (en) * | 2018-01-18 | 2018-07-31 | 中国科学院遥感与数字地球研究所 | A kind of geochemical elements exception source recourse method based on Alteration Information of Remote Sensing |
| CN111175608A (en) * | 2020-01-19 | 2020-05-19 | 上海电力大学 | Power distribution network harmonic responsibility quantitative division method based on accelerated independent component analysis |
| CN115101137A (en) * | 2022-06-28 | 2022-09-23 | 贵州逸宸未来科技有限公司 | Geochemical data analysis method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Murtaza et al. | Determining the suitability and accuracy of various statistical algorithms for satellite data classification | |
| EP3443482B1 (en) | Classifying entities in digital maps using discrete non-trace positioning data | |
| CN102567994B (en) | Infrared small target detection method based on angular point gaussian characteristic analysis | |
| CN103645517A (en) | Comprehensive anomaly extraction method based on blind source separation technology and apparatus thereof | |
| CN105869146A (en) | Saliency fusion-based SAR image change detection method | |
| CN105354841A (en) | Fast matching method and system for remote sensing images | |
| CN111524117A (en) | Tunnel surface defect detection method based on characteristic pyramid network | |
| Yang et al. | A skeleton-based hierarchical method for detecting 3-D pole-like objects from mobile LiDAR point clouds | |
| Akbarzadeh et al. | Design and matlab simulation of Persian license plate recognition using neural network and image filtering for intelligent transportation systems | |
| CN102982345B (en) | Semi-automatic classification method for timing sequence remote sensing images based on continuous wavelet transforms | |
| CN114202539A (en) | Hyperspectral image anomaly detection method based on end-to-end RX | |
| CN103530612B (en) | Fast target detection method based on a small amount of sample | |
| Gal et al. | Tracking objects using PHD filter for USV autonomous capabilities | |
| Singh et al. | Shadow based building extraction from single satellite image | |
| Xiong et al. | Robust line detection of synthetic aperture radar images based on vector radon transformation | |
| Gu et al. | Rare signal component extraction based on kernel methods for anomaly detection in hyperspectral imagery | |
| Demir | VARIOUS BUILDING DETECTION METHODS WITH THE USE OF IMAGE AND LIDAR DATA. | |
| Yuan et al. | Image driven GPS trace analysis for road map inference | |
| Cui et al. | Linear mixture analysis for hyperspectral imagery in the presence of less prevalent materials | |
| Mawlood et al. | Prediction the groundwater depth using Kriging method and Bayesian Kalman filter approach in Erbil governorate | |
| CN110781803A (en) | Human body posture identification method based on extended Kalman filter | |
| Carrilho et al. | Quality assessment for automatic LiDAR data classification methods | |
| Bai et al. | Modeling high-resolution SAR images with generalized extreme value distribution | |
| Fang et al. | Automatic cloud and snow detection for GF-1 and PRSS-1 remote sensing images | |
| Lv et al. | Vehicle detection in synthetic aperture radar images with feature fusion-based sparse representation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140319 |