Track fusion method based on neural network

A technology of track fusion and neural network, applied in the field of neural network, can solve problems such as unsatisfactory system fusion effect, achieve the effect of improving system fusion effect and reasonable weight distribution

Inactive Publication Date: 2020-08-25
UNIV OF ELECTRONICS SCI & TECH OF CHINA +1
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the weighted fusion system, the determination of the weight is the key, but the current weight distribution scheme makes the system fusion effect unsatisfactory

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
  • Track fusion method based on neural network
  • Track fusion method based on neural network
  • Track fusion method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] Embodiments of the present invention are described in detail below, examples of which are shown in the drawings, wherein the same or similar reference numerals designate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the figures are exemplary and are intended to explain the present invention and should not be construed as limiting the present invention.

[0028] see figure 1 and figure 2 , the present invention provides a neural network-based track fusion method, including:

[0029] S101. Acquire track data and perform preprocessing to obtain sample data.

[0030] Specifically, such as Figure 4 As shown in the data acquisition diagram provided, multiple sensors are used to collect the corresponding track data, and the track data is preprocessed and stored in the database to obtain enough sample data to facilitate subsequent construction The neural network model is trained. ...

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 discloses a track fusion method based on a neural network. The method comprises the following steps of using a plurality of sensors for obtaining corresponding track data, preprocessingthe data to obtain sample data; carrying out interactive multi-model filtering with the sample data to acquire corresponding state estimates; according to an input layer, three hidden layers and an output layer, creating a neural network model, sequentially inputting the sample data divided into the training set, the test set and the verification set into a search neural network model for model training, testing and verification; and then inputting any track data into the trained neural network model to obtain a weighted fusion result, carrying out interactive multi-model filtering again, andcarrying out one-step prediction on any single model at any moment until the fusion of all track data is completed, thereby improving the fusion effect of the system.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a neural network-based track fusion method. Background technique [0002] With the continuous advancement of science and technology, radar plays a huge role in various aspects such as ground, air, sea and space. Especially in the air and space, radar plays an irreplaceable role because the electromagnetic waves transmitted and received by radar have greater advantages than other media in air / vacuum. In terms of military use, early warning radar, search and warning radar, fire control radar, guidance radar and airborne radar are widely used in various environments, especially airborne radar is the most detailed and widely used, and its development is more rapid. Research on the detection and tracking of targets by airborne radars, spaceborne radars and near-space target detection radars, and achieve higher-precision target tracking capabilities through multi-radar track d...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08G01S7/41G01S13/60
CPCG06N3/08G01S13/60G01S7/418
Inventor 张可徐明明郭乐乐王志斌
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap