Multi-dimensional heterogeneous information fusion identification method based on Copula theory

A heterogeneous information, fusion recognition technology, applied in the field of information fusion, can solve the problems of few feature layers, failure to study multi-dimensional combination characteristics, etc.

Active Publication Date: 2022-01-07
SICHUAN UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] 2. Failure to study target multidimensional combination characteristics
However, the above-mentioned multi-source or even all-source info

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-dimensional heterogeneous information fusion identification method based on Copula theory
  • Multi-dimensional heterogeneous information fusion identification method based on Copula theory
  • Multi-dimensional heterogeneous information fusion identification method based on Copula theory

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0111] Such as figure 1 As shown, a multi-dimensional heterogeneous information fusion recognition method based on Copula theory is proposed. This method is based on the space-time registration of sensor observation data, and constructs an innovative abstract mathematical space that can incorporate different types of heterogeneous information—full-dimensional signal space, and realize the unified representation of the heterogeneous data of the three sensors (radar, infrared, visible light).

[0112] First, the heterogeneous information registration part.

[0113] The space-time registration of sensor observation data in "different time and space" mainly includes two aspects:

[0114] (1) Spatial registration based on the transformation equation of the earth coordinate system and the sensor coordinate system;

[0115] When performing spatial registration, the earth coordinate system and the sensor coordinate system are mainly considered.

[0116] 1) Geodetic coordinate system

example

[0293] Example: The test target is a 1:40 all-metal scale model of ship A and ship B (the length of the ship is 4 meters and 3 meters respectively), and the actual data of the target is collected by using three sensors: infrared, visible light and millimeter wave radar. It validates the abstract mathematical space construction technology that can incorporate different types of heterogeneous information;

[0294] (1) Take all the real experimental data of the two ships as sample data for identification calculation, and the identification results are as follows:

[0295] Table 3 Identification results of real experimental data

[0296]

[0297] (2) We will randomly generate 10,000 sets of data from the Copula joint distribution F1 and F2 as sample data for identification and calculation. The identification results are as follows:

[0298] Table 4 Generating sample data recognition results

[0299]

[0300] The above results show that the combined feature detection method ba

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a multi-dimensional heterogeneous information fusion identification method based on a Copula theory, and belongs to the technical field of information fusion. The method comprises the following steps: carrying out spatial registration based on a geodetic coordinate system and a sensor coordinate system transformation equation; after space registration is completed, completing time registration of interpolation and extrapolation, curve fitting and data interpolation; constructing a full-dimensional signal space; in a full-dimensional signal space which can be incorporated into different heterogeneous information, using a Copula function to establish connection of edge distribution of each single-dimensional data, recovering correlativity among feature data of each dimension, and inverting high-dimensional combination features of a target. According to the combined feature detection method based on Copula combined distribution, the combined recognition accuracy of the target is higher than that of a single feature detection method under each edge distribution, and the advantages of combined detection are embodied.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Owner SICHUAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products