Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Sequence aircraft target recognition method based on ELM and HMM

A technology of aircraft target and recognition method, which is applied in character and pattern recognition, computer parts, instruments, etc., and can solve the problems of low aircraft target recognition rate and changeable attitude

Inactive Publication Date: 2017-09-29
SOUTHEAST UNIV
View PDF1 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] Purpose of the invention: Aiming at the problems existing in the prior art, the present invention provides a sequence aircraft target recognition method based on ELM and HMM that can effectively solve the problem of low aircraft target recognition rate caused by attitude changes

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
  • Sequence aircraft target recognition method based on ELM and HMM
  • Sequence aircraft target recognition method based on ELM and HMM
  • Sequence aircraft target recognition method based on ELM and HMM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments.

[0045] A sequence aircraft target recognition method based on ELM and HMM. First, for the sequence of aircraft images, extract the profile of the aircraft target, and construct the profile local singular value features with translation, rotation, and scaling invariance; for the profile local singular value features, construct the corresponding SLFNs, and use the ELM algorithm with fast learning speed to train SLFNs; establish the corresponding HMM for the c-type aircraft in the training sample library, the state of each type of aircraft HMM is 7 of the aircraft's 360-degree flight attitude, and the observation value set is c There are 7c total states of the class aircraft, and the aircraft HMMs are initialized and trained to obtain c aircraft HMMs that have been trained; for the sequence of aircraft images to be recognized, firstly extract the l...

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 sequence aircraft target recognition method based on an ELM and an HMM. An aircraft target contour is extracted from a sequence aircraft image and a local contour singular value feature having translation, rotation, and zooming invariance properties is formed; on the basis of the local contour singular value feature, a corresponding SLFNs is constructed and the SLFNs is trained by using an ELM algorithm with a fast learning speed; a corresponding HMM is established for a c type of aircraft in a training sample base, seven types of 360-degree flight attitudes of the aircraft are provided in the HMM state of each type of aircraft and 7c states of the c type of aircraft are included in an observation value set, initialization and training are carried out on the aircraft HMM to obtain c trained aircraft HMMs; and a local contour singular value feature is extracted for a to-be-identified sequence aircraft image, a primary identification result is obtained by the trained SLFNs, and then similarity degrees of the sequence and the c aircraft HMMs are calculated and the aircraft type corresponding to the maximum value is used as a final identification result. Therefore, a problem of low aircraft target identification rate caused by an attitude changeable property can be solved.

Description

technical field [0001] The invention belongs to the technical field of automatic target recognition, in particular to a sequence aircraft target recognition method based on ELM and HMM. Background technique [0002] Automatic target recognition technology (Automatic Target Recognition, ATR) is one of the key factors to obtain battlefield control information. The ATR algorithm is mainly divided into two directions, one is the automatic target recognition algorithm based on template matching, and the other is the target recognition algorithm based on feature extraction. Aircraft target recognition, as one of the important fields of ATR, will occupy an extremely important position in modern warfare and future warfare. [0003] The template matching algorithm does not require the image to have a high contrast, and at the same time, it has incomparable advantages to other algorithms for tracking under partial occlusion of the target and complex background. Shao Dapei et al. (Sh...

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
CPCG06V20/41G06V20/46G06V2201/08G06F18/22
Inventor 李新德成杰
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com