CN104200422A - Expert system for remote sensing image processing - Google Patents
Expert system for remote sensing image processing Download PDFInfo
- Publication number
- CN104200422A CN104200422A CN201410432141.0A CN201410432141A CN104200422A CN 104200422 A CN104200422 A CN 104200422A CN 201410432141 A CN201410432141 A CN 201410432141A CN 104200422 A CN104200422 A CN 104200422A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- remote sensing
- expert
- sensing image
- management system
- 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.)
- Withdrawn
Links
Abstract
The invention provides an expert system for remote sensing image processing. The expert system for remote sensing image processing comprises a user interface, a system interface, an inference machine, knowledge bases, a management system of the knowledge bases, a database, a database management system, a knowledge obtaining mechanism and an interpretation mechanism. The expert system earnestly and scientifically conclude and summarize and establish the knowledge bases by simulating visual interpretation experiences of a human expert, then quotes the knowledge bases to classify remote sensing data, utilizes a mode recognition method to obtain multiple characteristics of ground feature, provides evidence for remote sensing image interpretation, meanwhile applies an artificial intelligence technology, applies experiences and methods of the remote sensing image interpretation expert, simulates specific thinking process of remote sensing image visual interpretation, and performs remote sensing image interpretation to enable the computer interpretation level to reach the expert level.
Description
Technical field
The present invention relates to technical field of image processing, relate in particular to a kind of expert system for remote sensing image processing.
Background technology
Being on the increase by type of airplane and quantity along with remote sensing satellite and remote sensing in recent years, remote-sensing geology basic data is also multiplied with surprising rapidity, in the face of numerous and jumbled like this remote-sensing geology basic data, how to process a difficult problem of pendulum in face of scientific research personnel beyond doubt.Use traditional manual sorting analysis, speed and quality cannot guarantee.These data of the processing of accurate quick particularly image data have become a problem in the urgent need to address.
Summary of the invention
The defect and the deficiency that for solving prior art, exist, the invention provides a kind of expert system for remote sensing image processing.
Technical scheme of the present invention is:
An expert system for remote sensing image processing, is characterized in that, described expert system comprises user interface, system interface, inference machine, knowledge base and management system thereof, database and management system thereof, knowledge obtaining mechanism and decipher mechanism, wherein,
User interface: described user interface is the interface connecting between expert system and expert or user, is comprised of batch processing and corresponding hardware, for completing input and output work;
System interface: described system interface is data processing and mutual interface platform, and described system interface connects respectively knowledge obtaining mechanism, inference machine, interpretative structural modeling and user interface;
Decipher mechanism: connect described database and management system thereof, for answering user the enquirement to system, follow the tracks of and record reasoning process, resulting conclusion is made explanations, when exporting decipher result to user, not only will list rule used, and precedence coherent, that be triggered according to rule is listed;
Inference machine: for simulating expert's thought process, control, coordinate whole system and according to the data of current input, utilize the knowledge in knowledge base and management system thereof, carry out progressively reasoning by certain inference method and control strategy, until deal with problems;
Knowledge obtaining mechanism: for knowledge is input to knowledge base, set up well behaved knowledge base, realize user or expert to the expansion of knowledge base and modification, the consistance of maintenance knowledge and integrality, knowledge obtaining mechanism is a kind of knowledge editor.
Database and management system thereof: the general the most original GIS data that include the information such as geophysics, geology, boat magnetic of using in remote-sensing geology; Database is managed by data base management system (DBMS), and the method for expressing method for expressing general and knowledge of data is consistent; Database and management system thereof are being deposited original data message, the data in operational process, the data of operation result;
Knowledge base and management system thereof: knowledge base, for storing the expertise of Solve problems, comprises principle knowledge, relevant facts etc.
Described inference machine comprises inference method and control strategy two parts.
Described inference method is divided into Accurate Reasoning and inexact reasoning, and described control strategy mainly refers to the control of inference direction and the selection strategy of inference rule.
In described knowledge base, the quality and quantity of contained knowledge is the performance that determines expert system.
Described knowledge base management system is responsible for the knowledge in knowledge base to organize, retrieve maintenance, and described knowledge base management system comprises interpret tag storehouse, image feature storehouse, 3, decipher example storehouse word bank.
Described knowledge base and management system thereof comprise interpret tag storehouse, image feature storehouse, decipher example storehouse.
In whole remote sensing image processing geology expert system, the processing of data and mutual OO programmed method and the interactive form manifestation mode of adopting, database adopts relevant database.
Technique effect of the present invention:
The invention provides a kind of expert system for remote sensing image processing by simulating human expert's visual interpretation experience, after conscientiously scientifically concluding, summing up, set up knowledge base, then quoting these knowledge bases classifies to remotely-sensed data, it utilizes mode identification method to obtain atural object various features, for explaining remote sensing images, produce evidence, while using artificial intellectual technology, use remote sensing images to explain expert's experience and method, the concrete thinking process of simulation remote sensing images visual interpretation, carries out remote sensing image interpretation.Can think that remote sensing images expert system gives computing machine by remote sensing domain expert's special knowledge, by these knowledge, practical problems be carried out to reasoning, analysis, make the decipher level of computing machine reach expert level.
Accompanying drawing explanation
Fig. 1 represents the general structure of expert system.
Fig. 2 is forward reasoning process flow diagram.
Fig. 3 is backward reasoning process flow diagram.
Embodiment
Below in conjunction with accompanying drawing, embodiments of the invention are described further.
Fig. 1 represents the general structure of expert system.As shown in Figure 1, expert system generally all comprises user interface, system interface, inference machine, knowledge base and management system thereof, database and management system thereof, knowledge obtaining mechanism, these seven parts of decipher mechanism, and the general structure of expert system as shown in Figure 1.
(1) user interface: user interface is the interface between expert system and expert or user, is comprised of batch processing and corresponding hardware, for completing input and output work.In input/output procedure, need to carry out the conversion of internal representation form and external representation form.
(2) system interface: system interface is data processing and mutual bridge.
(3) decipher mechanism: for remote-sensing geology image processing system outbalance, can answer user the enquirement to system, follow the tracks of and record reasoning process, resulting conclusion is made explanations, when exporting decipher result to user, not only will list rule used, and precedence coherent, that be triggered according to rule is listed.To strengthen the transparency of expert system.
(4) inference machine: be " thinking " mechanism of expert system, one of core of expert system.Its task is simulation expert's thought process, controls, coordinates whole system and according to the data of current input, utilize the knowledge in knowledge base, carries out progressively reasoning, until deal with problems by certain inference method and control strategy.It comprises inference method and control strategy two parts.Inference method is divided into Accurate Reasoning and inexact reasoning.Control strategy mainly refers to the control of inference direction and the selection strategy of inference rule.
(5) knowledge obtaining mechanism: knowledge obtaining mechanism is to obtain the mechanism of knowledge in expert system, its basic task is that knowledge is input in knowledge base, set up well behaved knowledge base, realize user or expert to the expansion of knowledge base and modification, the consistance of maintenance knowledge and integrality, knowledge obtaining mechanism is a kind of knowledge editor.
(6) database and management system thereof: the general the most original GIS data that include the information such as geophysics, geology, boat magnetic of using in remote-sensing geology.Database is managed by data base management system (DBMS), and the method for expressing method for expressing general and knowledge of data is consistent.Database and management system thereof are being deposited original data message, the data in operational process, and the data of operation result, this and knowledge base have a great difference.
(7) knowledge base and management system thereof: knowledge base, for storing the expertise of Solve problems, comprises principle knowledge, relevant facts etc.Knowledge base provides Solve problems required knowledge for inference machine, so in knowledge base, the quality and quantity of contained knowledge is the key factor that determines expert system performance.Knowledge base is abundanter, and problem-solving ability is just stronger.Knowledge base and management system thereof comprise interpret tag storehouse, image feature storehouse, decipher example storehouse.
Fig. 2 is forward reasoning process flow diagram.So-called reasoning just refers to is released the thought process of another judgement by known judgement by certain strategy.In general, reasoning comprises two kinds of judgements: a kind of is known judgement, and it comprises the knowledge relevant with Solve problems grasped and about the known fact of problem; Another kind is the new judgement of being released by known judgement, i.e. the conclusion of reasoning.In expert system, reasoning is realized by program, is called inference machine.
Knowledge-based inference process matter of utmost importance to be solved is: under each state, how to control selection and the utilization of knowledge, adopt which kind of Inferential Control.When a high efficiency inference machine of design, control strategy has influence on the efficiency of system.Conventional RBES has forward reasoning, backward reasoning and forward and reverse mixed inference.It is main that the reasoning process of remote-sensing geology image processing expert system generally adopts forward reasoning, and backward reasoning is auxiliary positive and negative combination inference strategy.
Forward reasoning system is from one group of fact, attempts over and over again all available rules, and adds new fact in this process, until obtain the termination condition that comprises target formula, is called again data drive control strategy.Its basic process is: from the fact, find out with rule-based knowledge base in the fact that matches of precondition of rule, if the match is successful, this rule is triggered, thereby produce new conclusion, using new conclusion as the new fact, proceed coupling, until the conclusion drawing can not be mated again.
Fig. 3 is backward reasoning process flow diagram.Backward reasoning system centre thought is first to put forward hypothesis, after look for evidence.Be exactly first to suppose that a target exists specifically, then in knowledge base, search its corresponding knowledge evidence, verify whether the prerequisite of this hypothesis exists.This process belongs to the process of a recurrence in computer science, is depth-first search strategy.If that is: the known fact in this prerequisite and factbase matches, or by being met with user's the means such as mutual, hypothesis is set up.If do not mated, using regular prerequisite as a new sub-goal, repeat above-mentioned reasoning process, until all sub-goals are proved to be existence.If sub-goal can not be verified, hypothesis does not exist, and reasoning failure, need to propose hypothesis again.
Knowledge base management system is responsible for the knowledge in knowledge base to organize, retrieve maintenance etc.This module comprises interpret tag storehouse, image feature storehouse, 3, decipher example storehouse word bank.It is the basis of whole remote sensing robotization decipher system.Its function quality is one of key issue of expert system success or not, and it has determined whether this system can be trusted by user.
Image feature storehouse
Characteristics of remote sensing image is to consist of the pixel that represents a certain atural object type of subject on representative remote sensing image, can reflect intuitively spectral signature and the textural characteristics of different types of ground objects.By the foundation of characteristics of remote sensing image search library, decipher personnel can be according to verifying the conditions such as the natural and geographical factors such as landform, landforms in region and sensor type, imaging season, from system, automatically retrieve the image sample under corresponding conditions, by contrasting with the achievement of submitting to, thereby the accuracy of investigation achievement is made to objective judgement.
Interpret tag storehouse
Remote sensing image interpret tag also claims interpretation key element, and it can directly reflect differentiation terrestrial object information, separate translator and utilize these signs on image, to identify character, type or the situation of atural object or phenomenon, so it is significant for remote sensing image data decipher.
Decipher example storehouse
In decipher process, with reference to existing data and map, be very necessary, this just needs knowledge base system to set up decipher example storehouse, facilitates the contrast of image information.As judge will be by the contrast between known geologic body, structure etc. and remote sensing image when remote-sensing geology body becomes ore deposit situation, according to the reflectance spectrum of master stratum, lithology on remote sensing images and the characteristic feature analysis of formation, different according to complicated geology degree, set up respectively the remote sensing interpret tag such as stratum, magmatite and structure of different times, and then add in decipher example storehouse.
The processing of data
In whole remote sensing image processing geology expert system, the processing of data and comparatively difficult alternately, needs the relevant knowledge of a large amount of computer graphicss, and adopts OO programmed method and interactive form manifestation mode.Various data acquisitions also need primary study by which type of data structure storage in database.Need to deposit the database of the attribute of a large amount of images, figure, data, think herein and preferably adopt the relevant database of current comparative maturity, the inference machine of reconciling database and knowledge base just can be simulated expert's thought process better like this, control whole system and according to the data of current input, utilize the knowledge in knowledge base, by certain inference method and control strategy, carry out progressively reasoning, until deal with problems.In addition, when decipher personnel specifically process remote sensing images, the interactive form guide that can be provided by knowledge base is carried out decipher to image information, can carry out to VectorLayer the operation such as editor, interpolation, deletion of element.This makes the hommization more of whole data handling procedure, standardization.
It should be pointed out that the above embodiment can make the invention of those skilled in the art's comprehend, but do not limit the present invention in any way creation.Therefore, although this instructions and embodiment have been described in detail to the invention,, it will be appreciated by those skilled in the art that still and can modify or be equal to replacement the invention; And all do not depart from technical scheme and the improvement thereof of the spirit and scope of the present invention, it is all encompassed in the middle of the protection domain of the invention patent.
Claims (7)
1. for an expert system for remote sensing image processing, it is characterized in that, described expert system comprises user interface, system interface, inference machine, knowledge base and management system thereof, database and management system thereof, knowledge obtaining mechanism and decipher mechanism, wherein,
User interface: described user interface is the interface connecting between expert system and expert or user, is comprised of batch processing and corresponding hardware, for completing input and output work;
System interface: described system interface is data processing and mutual interface platform, and described system interface connects respectively knowledge obtaining mechanism, inference machine, interpretative structural modeling and user interface;
Decipher mechanism: connect described database and management system thereof, for answering user the enquirement to system, follow the tracks of and record reasoning process, resulting conclusion is made explanations, when exporting decipher result to user, not only will list rule used, and precedence coherent, that be triggered according to rule is listed;
Inference machine: for simulating expert's thought process, control, coordinate whole system and according to the data of current input, utilize the knowledge in knowledge base and management system thereof, carry out progressively reasoning by certain inference method and control strategy, until deal with problems;
Knowledge obtaining mechanism: for knowledge is input to knowledge base, set up well behaved knowledge base, realize user or expert to the expansion of knowledge base and modification, the consistance of maintenance knowledge and integrality, knowledge obtaining mechanism is a kind of knowledge editor.
Database and management system thereof: the general the most original GIS data that include the information such as geophysics, geology, boat magnetic of using in remote-sensing geology; Database is managed by data base management system (DBMS), and the method for expressing method for expressing general and knowledge of data is consistent; Database and management system thereof are being deposited original data message, the data in operational process, the data of operation result;
Knowledge base and management system thereof: knowledge base, for storing the expertise of Solve problems, comprises principle knowledge, relevant facts etc.
2. a kind of expert system for remote sensing image processing according to claim 1, is characterized in that, described inference machine comprises inference method and control strategy two parts.
3. a kind of expert system for remote sensing image processing according to claim 2, is characterized in that, described inference method is divided into Accurate Reasoning and inexact reasoning, and described control strategy mainly refers to the control of inference direction and the selection strategy of inference rule.
4. a kind of expert system for remote sensing image processing according to claim 1, is characterized in that, in described knowledge base, the quality and quantity of contained knowledge is the performance that determines expert system.
5. a kind of expert system for remote sensing image processing according to claim 1, it is characterized in that, described knowledge base management system is responsible for the knowledge in knowledge base to organize, retrieve maintenance, described knowledge base management system comprises interpret tag storehouse, image feature storehouse, 3, decipher example storehouse word bank.
6. a kind of expert system for remote sensing image processing according to claim 1, is characterized in that, described knowledge base and management system thereof comprise interpret tag storehouse, image feature storehouse, decipher example storehouse.
7. a kind of expert system for remote sensing image processing according to claim 1, it is characterized in that, in whole remote sensing image processing geology expert system, the processing of data and mutual OO programmed method and the interactive form manifestation mode of adopting, database adopts relevant database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410432141.0A CN104200422A (en) | 2014-08-28 | 2014-08-28 | Expert system for remote sensing image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410432141.0A CN104200422A (en) | 2014-08-28 | 2014-08-28 | Expert system for remote sensing image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104200422A true CN104200422A (en) | 2014-12-10 |
Family
ID=52085708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410432141.0A Withdrawn CN104200422A (en) | 2014-08-28 | 2014-08-28 | Expert system for remote sensing image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104200422A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104951778A (en) * | 2015-07-24 | 2015-09-30 | 上海华旌科技有限公司 | Face recognition expert system based on semantic network |
| CN105046221A (en) * | 2015-07-10 | 2015-11-11 | 北京全景天地科技有限公司 | Image engineering intelligent interpretation method |
| CN105160022A (en) * | 2015-09-29 | 2015-12-16 | 北京全景天地科技有限公司 | Cloud image mining and interpretation system |
| CN106210450A (en) * | 2016-07-20 | 2016-12-07 | 罗轶 | Video display artificial intelligence based on SLAM |
| CN106777002A (en) * | 2016-12-07 | 2017-05-31 | 华北理工大学 | A kind of medical knowledge base system based on data mining |
| CN107169618A (en) * | 2017-03-23 | 2017-09-15 | 北京国电通网络技术有限公司 | A kind of power communication security risk assessment system |
| CN109522329A (en) * | 2018-09-30 | 2019-03-26 | 蓝库时代(北京)科技有限公司 | A kind of marketing communication analysis method based on artificial intelligence |
| CN110716995A (en) * | 2019-04-24 | 2020-01-21 | 中国科学院地理科学与资源研究所 | Electronic map reading method and device based on network geographic information system |
| CN111126028A (en) * | 2019-12-30 | 2020-05-08 | 中国联合网络通信集团有限公司 | Data processing method, device and equipment |
-
2014
- 2014-08-28 CN CN201410432141.0A patent/CN104200422A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046221A (en) * | 2015-07-10 | 2015-11-11 | 北京全景天地科技有限公司 | Image engineering intelligent interpretation method |
| CN104951778A (en) * | 2015-07-24 | 2015-09-30 | 上海华旌科技有限公司 | Face recognition expert system based on semantic network |
| CN105160022A (en) * | 2015-09-29 | 2015-12-16 | 北京全景天地科技有限公司 | Cloud image mining and interpretation system |
| CN106210450A (en) * | 2016-07-20 | 2016-12-07 | 罗轶 | Video display artificial intelligence based on SLAM |
| CN106210450B (en) * | 2016-07-20 | 2019-01-11 | 罗轶 | A kind of multichannel multi-angle of view big data video clipping method |
| CN106777002A (en) * | 2016-12-07 | 2017-05-31 | 华北理工大学 | A kind of medical knowledge base system based on data mining |
| CN106777002B (en) * | 2016-12-07 | 2020-10-30 | 华北理工大学 | Medical knowledge base system based on data mining |
| CN107169618A (en) * | 2017-03-23 | 2017-09-15 | 北京国电通网络技术有限公司 | A kind of power communication security risk assessment system |
| CN109522329A (en) * | 2018-09-30 | 2019-03-26 | 蓝库时代(北京)科技有限公司 | A kind of marketing communication analysis method based on artificial intelligence |
| CN110716995A (en) * | 2019-04-24 | 2020-01-21 | 中国科学院地理科学与资源研究所 | Electronic map reading method and device based on network geographic information system |
| CN111126028A (en) * | 2019-12-30 | 2020-05-08 | 中国联合网络通信集团有限公司 | Data processing method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200422A (en) | Expert system for remote sensing image processing | |
| Lehtola et al. | Digital twin of a city: Review of technology serving city needs | |
| Yu et al. | Prediction of highway tunnel pavement performance based on digital twin and multiple time series stacking | |
| US20200115066A1 (en) | Machine learning on big data in avionics | |
| CN108921200A (en) | Method, apparatus, equipment and medium for classifying to Driving Scene data | |
| Bianchi et al. | COCO-bridge: Structural detail data set for bridge inspections | |
| CN110383298A (en) | Data efficient intensified learning for continuous control task | |
| CN107423747A (en) | A kind of conspicuousness object detection method based on depth convolutional network | |
| CN114998744B (en) | Agricultural machinery track field dividing method and device based on motion and vision dual-feature fusion | |
| de la Rosa et al. | On the classical and nonclassical symmetries of a generalized Gardner equation | |
| Wang et al. | Finite-time active disturbance rejection control for marine diesel engine | |
| Cao et al. | A grey wolf optimizer–cellular automata integrated model for urban growth simulation and optimization | |
| CN115578693A (en) | Construction safety early warning method and device based on significance neural network model | |
| Fang et al. | Routing UAVs in landslides Monitoring: A neural network heuristic for team orienteering with mandatory visits | |
| Choi et al. | System integration of GIS and a rule-based expert system for urban mapping | |
| Carbonera et al. | Visual interpretation of events in petroleum geology | |
| CN115358477A (en) | Random generation system for battle scenario and application thereof | |
| Abdollahzadeh et al. | Safe Landing Zones Detection for UAVs Using Deep Regression | |
| Wang et al. | Mountainous village relocation planning with 3D GIS virtual imaging space model and neural network | |
| Yu | A model study based on social network relational dimensions and structural dimensions | |
| Gray | Cognitive modeling for cognitive engineering | |
| Lu et al. | An efficient annotation method for big data sets of high-resolution earth observation images | |
| CN113341461B (en) | Earthquake velocity prediction method, earthquake velocity prediction device and server | |
| Chomiak-Orsa et al. | Open Data for simulation to determine the efficient management of parking spaces in Smart City | |
| Vozenilek | ARTIFICIAL INTELLIGENCE FOR GEOSPATIAL APPLICATIONS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C04 | Withdrawal of patent application after publication (patent law 2001) | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| CB03 | Change of inventor or designer information |
Inventor after: Han Zaiman Inventor before: Deng Xin |
|
| COR | Change of bibliographic data | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20160725 Address after: 533899, the Guangxi Zhuang Autonomous Region, Baise, Jingxi Jing Zhen Town East Road, a residential area No. 18 Applicant after: Jingxi Xiumei Biancheng Agricultural Science and Technology Co., Ltd. Address before: 13 No. 530200 the Guangxi Zhuang Autonomous Region Nanning Qingxiu District five Avenue Applicant before: Deng Xin |
|
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20141210 |