1. A map expression method for water traffic multi-source data fusion is characterized by comprising the following steps:

s1, collecting the spatial geographic data on the water by using a plurality of sensors, storing the spatial geographic data in the form of points, lines, surfaces and attribute tables, and performing attribute preprocessing such as classification and grading on various data;

s2, transmitting the preprocessed data to a fusion network, performing certain distributed fusion calculation, and concentrating the preprocessed data to a fusion center to complete feature extraction, data association and fusion calculation, including analysis, supplement, accept and reject, modification and decision calculation of observation results of multiple sensors, and generating a fusion calculation result;

s3, constructing a water traffic information database, extracting and filtering the processed data, and storing the data in the water traffic information database;

s4, matching and integrating the data stored in the water traffic information database with the data in the public map database, generating a three-dimensional map from the data by virtue of a plurality of processors, and identifying corresponding positions;

and S5, updating the data collected by the sensors according to the set time interval, and processing and storing the updated data in the water traffic information database again to perform subsequent generation and updating on the map.

2. The map expression method for multi-source data fusion of water traffic according to claim 1, wherein the preprocessing method in step S1 is to set classification and classification by using an attribute coding method, and define data codes as required, so that the data codes can meet the symbolization requirements of various map products, and the batch visual conversion of symbols corresponding to points, lines and planes can be realized to meet the requirements of map expression.

3. The map representation method for multi-source data fusion of water traffic according to claim 2, wherein the data fusion in step S2 using Bayes comprises the following steps:

A. the sensors 1, 2.. m obtain an observed value of an observed object on water, and there are n possible assumed events about the observed object, and the n assumed events must be independent of each other and form a complete set;

B. each sensor obtains a judgment according to the observed value thereof, selects a hypothetical event related to the observed object, and knows that the actually occurring event is E according to the classification algorithm established by the sensor k_rIs judged as an event E under the condition of (1)_rHas a probability of P_k(E_d|E_r) (k 1, 2.. said., m), for each sensor, all P_k(E_d|E_r) Form an nA matrix of x n, so there are m such matrices for m sensors;

C. fusing the judgment obtained by each sensor according to the formula 2-2 to obtain an updated joint probability p (E)_r|E_d1,E_d2,E_d3,...,E_dk,...E_dm)，

In the formula, E_dk(k ═ 1,2, 3.., m) is the result of determination by the kth sensor

Since the assumptions are independent of each other, equations 2-3 are obtained

D. Once the joint probability distribution P (E) is obtained_r|E_d1,E_d2,E_d3,...,E_dk,...E_dm) Various candidate events are evaluated according to the distribution function to find the optimal choice.

4. The map expression method for multi-source data fusion of water traffic according to claim 1, wherein in step S3, for the characteristics of each data element, detailed design of operation mode is required, and a specific operation instruction is formed, so that a tool batch process is adopted as much as possible, thereby improving efficiency and quality.

5. The method for mapping multi-source data fusion of water traffic according to claim 4, wherein the operation mode comprises the following steps:

(1) matching the water areas by utilizing the attribute classification of the overwater watershed in the map database of the public edition, completely matching the water areas consistently, and directly assigning codes according to classification;

(2) for the rest water areas, the central line is widened, the matching is carried out again, a temporary code 'A' is recorded in the matching result, the data recorded as the 'A' are sequentially interpreted according to a water body basin code table, the generated redundant data are removed, and the FeatureTD code is assigned according to the level;

(3) and (3) artificially manufacturing the water area lacking after matching according to the latest image (under a scale of 1: 500), processing the intersection according to the original technical standard, and adding a corresponding element code in FeatureTD.

6. The method for mapping multi-source data fusion in water traffic according to claim 1, wherein the method for identifying the three-dimensional map in step S4 includes: and determining azimuth information of the current position based on the sensor device, and matching the azimuth information with the position information, the place name information and the azimuth information in the water traffic information database to identify the position in a corresponding position in the map.

Background

With the development demand of society and the progress of technology, maps are expanded from traditional paper media to different carriers such as electronics, internet, mobile terminals and the like, and the contents and forms of map expression are greatly enriched.

Map information is widely applied to various industries along with the development of electronic and information technology, and the displayed information is not only natural geographic information, but also business information, service information and the like. However, information acquisition in the inland river transportation industry is limited in the traditional manual experience teaching mode, few computer assistance is available, and the existing information acquisition and display mode cannot meet the development of the inland river transportation industry. Inland waterway transportation has the advantages of large transportation amount, low cost, long transportation distance and the like. The navigation channel is the most important component in waterway transportation, inland navigation channel resources in China are very rich, but the navigation channel information display direction has the defects of low efficiency, untimely updating, lack of transverse and longitudinal research, asymmetric information and the like, so that a related flow and a matching technology need to be established, effective fusion and rapid extraction of various original data are realized, various drawing requirements can be met, a rapid channel between data and map drawing is unblocked, and the informatization drawing level is improved.

Therefore, a map expression method for water traffic multi-source data fusion is provided to solve the problems.

Disclosure of Invention

The invention aims to solve the defects in the prior art, and provides a map expression method for water traffic multi-source data fusion.

In order to achieve the purpose, the invention adopts the following technical scheme:

a map expression method for water traffic multi-source data fusion comprises the following steps:

s1, collecting the spatial geographic data on the water by using a plurality of sensors, storing the spatial geographic data in the form of points, lines, surfaces and attribute tables, and performing attribute preprocessing such as classification and grading on various data;

s2, transmitting the preprocessed data to a fusion network, performing certain distributed fusion calculation, and concentrating the preprocessed data to a fusion center to complete feature extraction, data association and fusion calculation, including analysis, supplement, accept and reject, modification and decision calculation of observation results of multiple sensors, and generating a fusion calculation result;

s3, constructing a water traffic information database, extracting and filtering the processed data, and storing the data in the water traffic information database;

s4, matching and integrating the data stored in the water traffic information database with the data in the public map database, generating a three-dimensional map from the data by virtue of a plurality of processors, and identifying corresponding positions;

and S5, updating the data collected by the sensors according to the set time interval, and processing and storing the updated data in the water traffic information database again to perform subsequent generation and updating on the map.

In the above map expression method for multi-source data fusion of water traffic, the preprocessing method in step S1 is to set data codes in a classified and hierarchical manner by using attribute codes, and define the data codes as required, so that the data codes can meet the symbolization requirements of various map products, and the batch visual conversion of symbols corresponding to points, lines and planes can be realized to meet the requirements of map expression.

In the above map expression method for multi-source data fusion of water traffic, the data fusion using Bayes in step S2 includes the following steps:

A. the sensors 1, 2.. m obtain an observed value of an observed object on water, and there are n possible assumed events about the observed object, and the n assumed events must be independent of each other and form a complete set;

B. each sensor obtains a judgment according to the observed value thereof, selects a hypothetical event related to the observed object, and knows that the actually occurring event is E according to the classification algorithm established by the sensor k_rIs judged as an event E under the condition of (1)_rHas a probability of P_k(E_d|E_r) (k 1, 2.. said., m), for each sensor, all P_k(E_d|E_r) An n × n matrix is formed, so that m such matrices are common to m sensors;

C. obtaining an updated union by fusing the judgment obtained by each sensor according to the formula 2-2Resultant probability p (E)_r|E_d1,E_d2,E_d3,...,E_dk,...E_dm)，

In the formula, E_dk(k ═ 1,2, 3.., m) is the result of determination by the kth sensor

Since the assumptions are independent of each other, equations 2-3 are obtained

D. Once the joint probability distribution P (E) is obtained_r|E_d1,E_d2,E_d3,...,E_dk,...E_dm) Various candidate events are evaluated according to the distribution function to find the optimal choice.

In the above map expression method for multi-source data fusion of water traffic, in step S3, for the features of each data element, detailed design of operation mode is required, a specific operation instruction is formed, and the method adopts instrumental batch processing as much as possible, thereby improving efficiency and quality.

In the above map expression method for multi-source data fusion of water traffic, the operation method comprises the following steps:

(1) matching the water areas by utilizing the attribute classification of the overwater watershed in the map database of the public edition, completely matching the water areas consistently, and directly assigning codes according to classification;

(2) for the rest water areas, the central line is widened, the matching is carried out again, a temporary code 'A' is recorded in the matching result, the data recorded as the 'A' are sequentially interpreted according to a water body basin code table, the generated redundant data are removed, and the FeatureTD code is assigned according to the level;

(3) and (3) artificially manufacturing the water area lacking after matching according to the latest image (under a scale of 1: 500), processing the intersection according to the original technical standard, and adding a corresponding element code in FeatureTD.

In the above map expression method for multi-source data fusion of water traffic, the method for identifying a three-dimensional map in step S4 includes: and determining azimuth information of the current position based on the sensor device, and matching the azimuth information with the position information, the place name information and the azimuth information in the water traffic information database to identify the position in a corresponding position in the map.

Compared with the prior art, the map expression method for the water traffic multi-source data fusion has the advantages that:

1. the invention adopts an attribute coding mode to classify and grade, defines the data codes according to requirements, can meet the symbolization requirements of various map products, and can realize the batch visual transformation of the symbols corresponding to points, lines and surfaces so as to meet the requirements of map expression.

2. The method adopts a multi-source data fusion mode to perform fusion processing on the water traffic data, constructs the water traffic information database, extracts and filters the processed data, and stores the processed data into the water traffic information database, thereby being beneficial to the generation and the update of the map in the follow-up process.

Drawings

FIG. 1 is a block diagram of a map expression method for multi-source data fusion of water traffic according to the present invention;

fig. 2 is a block diagram of an operation mode and a method of the map expression method for water traffic multi-source data fusion provided by the invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.

Examples

Referring to fig. 1-2, a map expression method for water traffic multi-source data fusion comprises the following steps:

s1, collecting the spatial geographic data on the water by using a plurality of sensors, storing the spatial geographic data in the form of points, lines, surfaces and attribute tables, and performing attribute preprocessing such as classification and grading on various data;

s2, transmitting the preprocessed data to a fusion network, performing certain distributed fusion calculation, and concentrating the preprocessed data to a fusion center to complete feature extraction, data association and fusion calculation, including analysis, supplement, accept and reject, modification and decision calculation of observation results of multiple sensors, and generating a fusion calculation result;

s3, constructing a water traffic information database, extracting and filtering the processed data, and storing the data in the water traffic information database;

s4, matching and integrating the data stored in the water traffic information database with the data in the public map database, generating a three-dimensional map from the data by virtue of a plurality of processors, and identifying corresponding positions;

and S5, updating the data collected by the sensors according to the set time interval, and processing and storing the updated data in the water traffic information database again to perform subsequent generation and updating on the map.

The preprocessing method in step S1 is to set the data codes in a classified and hierarchical manner by using attribute codes, and define the data codes as required, so that the data codes can meet the symbolization requirements of various map products, and the batch visual conversion of symbols corresponding to points, lines and planes can be realized to meet the requirements of map expression.

In step S2, data fusion is performed using Bayes, including the following steps:

A. the sensors 1, 2.. m obtain an observed value of an observed object on water, and there are n possible assumed events about the observed object, and the n assumed events must be independent of each other and form a complete set;

B. each sensor obtains a judgment according to the observed value thereof, selects a hypothetical event related to the observed object, and knows that the actually occurring event is E according to the classification algorithm established by the sensor k_rIs judged as an event E under the condition of (1)_rHas a probability of P_k(E_d|E_r) (k 1, 2.. said., m), for eachFor each sensor, all P_k(E_d|E_r) An n × n matrix is formed, so that m such matrices are common to m sensors;

C. fusing the judgment obtained by each sensor according to the formula 2-2 to obtain an updated joint probability p (E)_r|E_d1,E_d2,E_d3,...,E_dk,...E_dm)，

In the formula, E_dk(k ═ 1,2, 3.., m) is the result of determination by the kth sensor

Since the assumptions are independent of each other, equations 2-3 are obtained

D. Once the joint probability distribution P (E) is obtained_r|Ed1,Ed2,E_d3,...,E_dk,...E_dm) Various candidate events are evaluated according to the distribution function to find the optimal choice.

In step S3, for the features of each data element, detailed design of operation mode is required, a specific operation instruction is formed, and batch processing with tools is adopted as much as possible, so as to improve efficiency and quality.

Further, the operation mode comprises the following steps:

(1) matching the water areas by utilizing the attribute classification of the overwater watershed in the map database of the public edition, completely matching the water areas consistently, and directly assigning codes according to classification;

(2) for the rest water areas, the central line is widened, the matching is carried out again, a temporary code 'A' is recorded in the matching result, the data recorded as the 'A' are sequentially interpreted according to a water body basin code table, the generated redundant data are removed, and the FeatureTD code is assigned according to the level;

(3) and (3) artificially manufacturing the water area lacking after matching according to the latest image (under a scale of 1: 500), processing the intersection according to the original technical standard, and adding a corresponding element code in FeatureTD.

Through the steps, more than 80% of the water areas can be subjected to batch classification assignment, less than 20% of the water areas are left to be subjected to manual intervention, the task requirement can be completed quickly, and meanwhile, the consistency of the water area line and the water area surface can be guaranteed.

The method for identifying the three-dimensional map in step S4 includes: the method comprises the steps of determining azimuth information of a current position based on sensor equipment, and matching the azimuth information with position information, place name information and azimuth information in a water traffic information database to identify the position at a corresponding position in a map, specifically, in the map generation, relating to a plurality of data sources, wherein due to different operation requirements and periods, after attribute consistency is solved, the data may have non-uniformity in aspects such as graphs and topological relations, and therefore when data are integrated at an early stage, the problems are processed together, and a target data set meets drawing requirements.

The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.