Ship type recognition method based on compactness measurement weighting

A technology of type recognition and compactness, applied to the recognition of patterns in signals, character and pattern recognition, instruments, etc.

Inactive Publication Date: 2016-04-06
HANGZHOU DIANZI UNIV +1
View PDF3 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of roughly classifying two types of ships, one-dimensional distance images of military ships and civilian ships, and propose a ship type recognition method based on compactness measure weighting

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
  • Ship type recognition method based on compactness measurement weighting
  • Ship type recognition method based on compactness measurement weighting
  • Ship type recognition method based on compactness measurement weighting

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] In the experiment, a set of measured data of radar one-dimensional range images under different targets and different attitude angles, HRRP of 5 civilian ship targets at different attitude angles, and HRRP of 5 military ship targets at different attitude angles were used. The traditional classification method only classifies and recognizes these 10 targets according to HRRP, and the result of discrimination is these 10 targets. However, in practical applications, the types of military ships and civilian ships are far more than these 10 types, so the traditional classification method has great limitations. Therefore, this experiment only recognizes two types of targets, military ships and civilian ships. However, due to the large differences in the shape, size and structure of different target individuals of the same type, this will lead to HRRP data of similar military ships or civilian ships. There are great differences in HRRP among different individuals in different ...

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 ship type recognition method based on compactness measurement weighting. A conventional method for target recognition based on one-dimensional distance image mainly carries out the extraction of the one-dimensional distance image, and carries out the direct weighted processing of the features with no reference to the compactness measurement of the features. The method firstly carries out the noise reduction and normalization of raw HRRP data, thereby solving a sensitivity problem of HRRP to amplitude. The method extracts a target region through estimating the starting and ending points of a ship, and carries out the preprocessing of HRRP data, thereby solving a translation problem of HRRP. The method solves a problem of HRRP attitude sensitivity to a certain extent through extracting invariant features of attitude. Because the compactness measurement of all extracted features is different, the method enables the extracted features to be multiplied by the compactness of all features according to the compactness measurement of sample features, reflects the difference of weights of different features in a process of classification and recognition, and then carries out the classification and recognition of testing samples through employing a nearest neighbor method.

Description

technical field [0001] The invention belongs to the field of radar one-dimensional range image target recognition, relates to a ship type identification method based on compactness measure weighting, and is suitable for the application technology research of ship target recognition based on radar one-dimensional range image. Background technique [0002] When the radar radial distance resolution is much smaller than the target size, the target echo occupies multiple range image units in the range direction, and the amplitude of each range unit on the one-dimensional range image (HRRP) is equal to all scattering from the range unit The coherent summation of the center echoes, while the scattering center reflects the target's size, geometry, material structure and other information. Therefore, the radar high-resolution one-dimensional range image can reflect the fine structure information of the target. Radar one-dimensional range image target recognition technology is mainly...

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): G06K9/00G06K9/62
CPCG06F2218/10G06F2218/04G06F2218/08G06F2218/12G06F18/21
Inventor 郭宝峰刘巧圆王刚孙同晶杨振赵鑫马腾
Owner HANGZHOU DIANZI 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

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