RU2612326C2 - Method of forming digital plan-scheme of agricultural facilities and system for realising said method - Google Patents

Abstract

FIELD: physics, computer science.

SUBSTANCE: invention includes the identification of objects in the field, based on the source of cartographic material, definition of a classification code, reception the metric information about these objects, the corresponding semantic information about the media in the file system, clarification of the location nature, size and quality of information, including the number of metric points and the characteristics of the object, the value of their code and the numerical values of these characteristics. Repeat the specified operations for each of the objects. At the same time in order to ensure the universality of the stored information, processing efficiency and reliability of the results, the vector design of source and reference information in the form of base layers is used, that have geographic and spatial reference, and stored in individual files, as well as the support data of the geometric nature and the geographic location of each object metric points on the Earth's sensing remote data, aggregating the layers information in accordance with the requirements to the output information - topic digital plan-scheme.

EFFECT: invention relates to computer science and can be used for satellite monitoring of the agricultural purpose objects to identify their condition, targeted processing of satellite images, obtained from different sources, using additional (ground) data, and the formation of problem-oriented digital plan-schemes areas of the earth surface.

7 cl, 3 dwg

Description

The technical result of the functioning of the knowledge base is to ensure the universality of the stored information, the speed of processing and the reliability of its results. This result is achieved through the use of quorum aggregation of source data sources (i.e., several sources are used in parallel: including representing data on the state of agricultural lands, including agricultural landfills and contours; soil fertility indicators of agricultural lands indicating the geographical coordinates of the location of agricultural landfills and contours; data on the use of agricultural land, pollution by heavy metals, pesticides, oil products mi, radionuclides and other pollutants; data on negative soil processes occurring on agricultural lands; data on agrochemical, reclamation, crop-technical and agrotechnological measures on agricultural lands; data on the distribution of agricultural crops on agricultural lands according to the results of ground surveys and observations, data remote sensing of the Earth; information on rights to real estate and land; soil survey materials; topographic maps and plans in graphic, digital, photographic and other forms, the accuracy and content of which provide the solution of target tasks; land monitoring data; official statistics on the availability and distribution of land within the boundaries of territorial entities). A well-known expert image processing system (OCAPI) (V. Clement, M. Thonnat, J. VanDenElst. Supervision of Perception Tasks for Autonomous Systems: The OCAPI Approach, INRIA Rapports de Recherche N2000, 1993, 28 p.). The system contains a module, which, together with the interface driver and the interface of the subprogram package, can function as an integrated environment designed for image processing. But this module contains only knowledge about how to manage an external software system in a general context.

Known methods for constructing knowledge bases for pattern recognition systems using computer technology, including with training (US 5159667, 10.27.1992; US 5748850, 05.05.1998; US 6577757, B1, 06/10/2003), but they solve particular problems, not related to the subject of this invention.

A known method of processing cartographic material (RU 2037776, G01C 11/00, 06/19/1995), which includes the identification of terrain objects on the original cartographic material, the removal of metric information about the objects in the form of an array of coordinates and the corresponding semantic symbolic information, recording the received information on a medium in file system. The disadvantage of this method is the lack of intelligent procedures for isolating problem-oriented information.

A known method and system for constructing image processing means (WO 01/67389 Al, G06T 1/00, 09/13/2001), which includes a knowledge base. This system is a multifunctional image analysis tool designed for application development, research and training. The disadvantage of this knowledge base is that it does not solve the problem of image analysis and recognition based on the automation of extracting information from images.

A known method (prototype) that provides the construction of a knowledge base for analysis and recognition of images (RU 2256224, G06K 9/66, 07/10/2005) with automation of the extraction of information from images, accumulating and using knowledge on analysis, recognition and interpretation of images. The technical result of the invention is achieved in that the knowledge base for analysis and recognition of images contains a central control unit for the processing and data transfer processes, a user interface, an external communication interface and a comprehensive subsystem of organized knowledge storage, which has a task module, a module for supporting planning, management and adoption processes solutions, module of algorithms, module of intermediate results of problem solving, module of reference and test images, module of extraction, structuring I and the records of new knowledge and the module of the thesaurus, glossary, bibliography and reference book. This knowledge base is characterized in that the central control unit for the processing and data transfer processes contains interconnected search and control subsystems; the modules that make up the integrated subsystem of organized knowledge storage are made in the form of autonomous relational databases.

The aim of the implementation of the proposed method is the construction of a complex of technical means of data processing, which provides the automated formation and replenishment of the knowledge base for analysis and recognition of images in the form of a search-oriented set of information arrays - task blocks based on various criteria. Each of these blocks is a structured description of the task of forming a specific type of DSP using a hierarchical classification of the tasks of analysis, processing and recognition of images and thesaurus for analysis, processing and recognition of images, as well as thematic mapping of agricultural objects.

The method of forming a digital plan of agricultural facilities is represented by algorithms of the basic procedures for its implementation.

1. The user enters the source data. The system analyzes the presented images (images) and extracts useful information about this image, which will be used when setting the problem and finding a solution (universal identifiers of agricultural objects, image formats, number of gradations of brightness, etc. signs).

2. The user creates an object corresponding to the formulation of a specific task, for which the maximum possible amount of data about the task is entered through the user interface. The information received at the 1st stage is taken into account.

3. A complex request is generated based on the object created by the user. The query conditions take into account the properties of the elements of the created DSP. For the properties of elements that reflect semantic content, the descriptors are preliminarily assigned (selected) using the domain thesaurus, which are included in the conditional part of the request.

4. A lot of descriptions of tasks (solutions) are formed containing algorithms (operators) of the solution. Descriptions are ranked according to the selected proximity measure.

5. The algorithm corresponding to the first of the ranked descriptions is selected.

6. Execution of the algorithm.

7. The resulting sample of task descriptions is analyzed. If the selection does not satisfy the user (the set is empty or there are too many descriptions), then changes are made to the problem statement and a new request is made.

8. Automated generation of a digital plan in the form of a specialized report.

The technical result formulated in the task of the present invention is achieved by the fact that the system for generating digital image plan-schemes contains a central control unit (CPU) for data processing and transmission, a user interface (PI), an external interface (VI) and a knowledge storage subsystem ( PCP). PCPI includes a task module (MOH) connected to a common information and control highway (IUM), a module for supporting planning processes (MPPR), management and decision making, an algorithm module (MA), an intermediate results module (MPR), problem solving, a reference module (ME) and test (MIT) images, a module for extracting, structuring and recording new knowledge (MNE) and a module for the thesaurus, glossary (MTG), bibliography and reference. The first input-output of the central data processing and transmission control unit is connected to the common information-control highway, the second input-output of which is connected to the user interface, and the third to the internal input-output of the external communication interface. The external input-output of the external communication interface is the input-output of the knowledge base for analysis and recognition of images with the ability to connect to the analysis and processing system.

At the same time, the CBU contains an interconnected associative search subsystem (PAP) and a central control device (CCU).

The system (see Fig. 1) contains a central control unit (CBU) 1 for data processing and transmission, a user interface (PI) 2, an external interface (VI) 3 and a knowledge storage subsystem (PCP) 4. User interface 2 is designed for user interaction with the knowledge base and serves for input, output and visualization of information.

The subsystem of PCP 4 includes those connected to a common information and control highway (UIM) 5: a task module (MOH) 6, a module for supporting planning, management and decision-making processes (MPPR) 7, an algorithm module (MA) 8, a module for intermediate decision results tasks (MPR) 9, module of reference and test images (MET) 10, module of the thesaurus, glossary (MTG) 11, bibliography and reference and module for extracting, structuring and recording new knowledge (MNE) 12.

The first input-output of the central control subsystem 1 is connected to the common information and control highway 5, the second input-output 13 of which is connected to the user interface 2. The third input-output is connected to the internal input-output of the external communication interface 14, whose external input-output 15 It is the input-output of the knowledge base for image analysis and recognition (BZAI) 16. This input-output 15 of interface 3 is intended for connection to image analysis and processing systems and exchanges data, in particular, it can be connected to an open system for automating the processing, analysis and recognition of images (RU 2242047, 12/10/2004).

The system (see Fig. 1) contains a central control unit (CBU) 1 for data processing and transmission, a user interface (PI) 2, an external interface (VI) 3 and a knowledge storage subsystem (PCP) 4. User interface 2 is designed for user interaction with the knowledge base and serves for input, output and visualization of information.

The subsystem of PCP 4 includes those connected to a common information and control highway (UIM) 5: a task module (MOH) 6, a module for supporting planning, management and decision-making processes (MPPR) 7, an algorithm module (MA) 8, a module for intermediate decision results tasks (MPR) 9, module of reference and test images (MET) 10, module of the thesaurus, glossary (MTG) 11, bibliography and reference and module for extracting, structuring and recording new knowledge (MNE) 12.

The first input-output of the central control subsystem 1 is connected to the common information and control highway 5, the second input-output 13 of which is connected to the user interface 2. The third input-output is connected to the internal input-output of the external communication interface 14, whose external input-output 15 It is the input-output of the knowledge base for image analysis and recognition (BZAI) 16. This input-output 15 of interface 3 is intended for connection to image analysis and processing systems and exchanges data, in particular, it can be connected to an open system for automating the processing, analysis and recognition of images (RU 2242047, 12/10/2004).

CBU 1 contains interconnected search PAP 17 and the control 18 of the subsystem.

The module of tasks МЗ 6, the module of support for planning, management and decision-making processes of MPPR 7, the module of algorithms MA 8, the module of intermediate results of solving problems of MPR 9, the module of reference and test images MET 10 and the module of thesaurus and glossary MTG 11 are made in the form of autonomous relational databases data (see Fig. 2).

Each of the autonomous relational databases of modules 6-11 contains one or more memory BP 17 blocks oriented to storing spreadsheets, a specialized controller K 18, and a communication block BS 19 with a common information-control trunk UIM 5. The first input-output 20 of block 19 communication is the input-output of the module, and the second input-output 21 is connected to a common input-output of the controller K 18. Information and control inputs and outputs 22 of the controller K 18 are connected respectively with the information control inputs and outputs of the memory unit BP 17.

The module for extracting, structuring, and recording new knowledge of MNZ 12 is also made in the form of an autonomous relational base, the structure of which is similar to that described above, is shown in FIG. 3. It contains a memory block of new knowledge BPNZ 23, focused on the storage of spreadsheets, and a specialized controller SK 24, a communication unit BS1 25 with a common information management highway UIM 5, a unit for checking the consistency of input knowledge BPN 26. The first input-output 27 of the block 25 communication is the input-output of the MNZ module 12, and the second input-output 28 is connected to the common input-output of the controller 24. Information and control inputs and outputs 29,30 of the controller SK 24 are associated with information and control inputs and outputs of the blocks 23 and 26.

The MOH 6 module of tasks contains knowledge about the classifications of problems of the formation of DSPs, knowledge of typical and solved problems (including the archive of existing DSPs) in the form of structured descriptions in a universal encoding, task blocks.

The support module for the planning, management and decision-making processes of MPPR 7 contains general information about solving problems using computer software, general and specialized knowledge on processing, analysis and recognition of images, contours and textures, knowledge about the application area, as well as decision rules of various types corresponding to the selected model for solving problems.

The MA 8 algorithm module contains knowledge about the image processing library used: information about the algorithms, their input parameters, results and methods for evaluating the quality of the algorithms.

The intermediate results module for solving MPR 9 problems is used to save and subsequently use the results of processing and recognition algorithms.

The module of reference and test images MET 10 is used for testing algorithms and training.

The MTG 11 module contains a thesaurus, glossary, bibliography and reference. The thesaurus and the glossary are used in the preparation of task descriptions, and are also the semantic base of the model used to solve problems. This module 11 also functions as a user guide "Help".

The module for extracting, structuring, and recording new knowledge of MNZ 12 is intended for introducing new task descriptions into the knowledge base, automated detection of dependencies, characteristics, and formalized expression of image properties, as well as checking the consistency of input knowledge with existing in the database.

Each of the modules consists of one or a group of knowledge base tables, a control subsystem (table controller) and can be connected (if it is functionally necessary) with the corresponding user interface. The table controller processes and exchanges data between knowledge base tables and the management subsystem

Problem Planning

1. In the search subsystem (PAP 17) according to the found description of a typical task, a query is generated to search for descriptions of (typical) subtasks.

2. The control subsystem (PU 18) through the controllers of the tables of descriptions of tasks and algorithms sends a request.

3. For each of the typical subtasks, a request is generated to search for descriptions of the constituent subtasks and other components.

4. Based on the results of a series of queries, a scheme (plan) for solving the problem is formed and displayed on user interface 2 (on the monitor screen in the editor window). The control subsystem 18 controls the algorithms included in the decision scheme for compatibility by input and output data types, and also assigns the initial values of the algorithm parameters.

5. The user adjusts the generated decision scheme and parameters of the algorithms. As a result, a program is formed, compiled on the macro language of the processing system, image analysis and the formation of the DSP.

6. The user compiles and runs the program for execution.

7. The user evaluates the results of solving the problem, if necessary, adjusts the solution scheme and parameters of the algorithms. Based on the results of the assessment, the user introduces new task descriptions into the knowledge base and checks the consistency of the entered knowledge already in the database.

Claims (7)

1. A method of forming a spatial-object representation of a territory with agricultural objects in the form of a digital plan diagram, including the identification of objects on the ground based on the original cartographic material, the definition of a classification code, the receipt of metric information about these objects, the corresponding semantic information about the medium in the file system , clarification of the nature of localization, size and quality information, including the number of metric points and characteristics of object, the value of their code and the numerical values of these characteristics, the repetition of these operations for each of the objects, characterized in that in order to ensure the universality of the stored information, the processing speed and the reliability of its results, vector design of the source and reference information in the form of base layers with geographical and spatial reference and recorded in separate files, as well as geometrical reference data and geographic reference of the metric points of each object according to remote sensing of the earth, aggregating layer information in accordance with the requirements for the output information - thematic digital plan. 2. The method according to p. 1, characterized in that to clarify information about agricultural facilities use additional thematic layers with qualitative characteristics of individual agricultural lands, including initial indicators of soil fertility, anthropogenic and natural-climatic effects on these indicators, as well as indicating the geographical coordinates of the placement of agricultural landfills and contours. 3. The method according to p. 2, characterized in that when forming thematic layers, to clarify information about objects simultaneously with remote sensing of the earth, use field data on the location of crops on the land according to the results of ground surveys and observations, as well as materials of soil surveys, topographic maps and plans in graphic, digital, photographic and other forms, the accuracy and content of which provide the solution to target tasks. 4. The method according to p. 3, characterized in that on the basis of information about the rights to real estate and land; official statistics of the availability and distribution of land within the boundaries of territorial entities, the set of lands and infrastructure used by a particular agricultural producer acts as an object of agricultural purpose. 5. The method according to p. 1, or 2, or 3, characterized in that the shape of its contour, topology, are used as signs of identifying the terrain object; the location of the "center of gravity" of the flat image bounded by this contour relative to the boundaries of the object; place in the meta-object, relative to the "centers of gravity" of neighboring objects; digital elevation model; texture inside the contour, soil type, vegetation cover, invariant characteristics; subsoil formations that affect the shape and texture within the contour. 6. A system supporting the implementation of the method according to paragraphs. 1-5, containing a central control unit for processing and data transfer processes, a user interface, an external communication interface, and a knowledge storage subsystem, the modules of which are made in the form of autonomous relational databases, characterized in that the knowledge storage subsystem includes connected to a common information control line task module, configured to accumulate and store information about task classifications, typical tasks and an archive of solved problems in the form of structured descriptions, blocks of dachas, a module for supporting planning, management and decision-making processes, with the ability to accumulate and store general information about solving problems using computer software, knowledge of image processing, analysis and recognition, the application area, as well as decision rules corresponding to the selected model problem solving, algorithm module, configured to accumulate and store information about the algorithms included in the image processing library, about input parameters, results and evaluation methods the quality of the algorithms, the module of intermediate results of solving problems, which is used to store and subsequently use the results of the processing and recognition algorithms, the module of reference and test images used for testing algorithms and training, the module for extracting, structuring and recording new knowledge, made with the possibility of introducing new descriptions of tasks in the knowledge base, automated detection of dependencies, characteristics and formalized expression of image properties, as well as checking n the inconsistency of the input knowledge with the one already available in the database, the thesaurus, glossary, bibliography and reference module used in compiling the task descriptions and being the semantic base of the problem solving model, while the first input-output of the central processing process control unit is connected to the common information and control line and data transmission, the second input-output of which is connected to the user interface, and the third - with the internal input-output of the external communication interface, the external input-output of which is an input home-exit knowledge base for analysis and recognition of images with the ability to connect to an analysis and image processing system. 7. The system according to claim 6, characterized in that the central control unit for the processing and data transmission processes contains an interconnected subsystem of associative search and a control subsystem, while the associative search subsystem is configured to search for solutions to a typical or similar problem, and the control subsystem is a control system algorithms included in the solution scheme for compatibility by types of input and output data and assignment of initial values of algorithm parameters.

Images