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

Method for extracting stable spectrum characteristics of solid matter

An extraction method and technology of solid matter, applied in the field of target recognition, can solve problems such as natural ground object changes and spectrum changes, and achieve the effect of strong anti-noise ability

Active Publication Date: 2011-02-16
HUAZHONG UNIV OF SCI & TECH
View PDF0 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

So far, there are still some problems in using spectrum for target recognition: (1) The spectrum will change with the temperature of the target body; (2) The spectrum of natural objects will change with time and geographical environment

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
  • Method for extracting stable spectrum characteristics of solid matter
  • Method for extracting stable spectrum characteristics of solid matter
  • Method for extracting stable spectrum characteristics of solid matter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The invariant feature of the present invention refers to the unique spectral feature related to the target that can be acquired under the condition of multi-spectral and hyper-spectral detection sensors, and the spectral feature remains unchanged under different environmental conditions.

[0038] The preliminary work of spectrum-based target recognition and detection is to establish a spectrum-based database from the spectrum data of the target. Among them, there are several sources of spectral data: 1. Public spectral databases, such as the 0.2-3.0 μm USGS spectral database established by the US Geological Survey USGS for remote sensing exploration of mineral resources; The 0.4-25 μm ASTER spectral database established by ground objects and artificial targets, etc. 2. Experimental equipment collects data, such as infrared spectrum data collected by infrared Fourier spectrometer.

[0039] The processing flow of the present invention is as image 3 As shown, specifical...

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 provides a method for extracting stable spectrum characteristics of a solid matter, comprising the steps of: firstly, carrying out multiscale decomposition on spectrum data, then carrying out regional division on the topography under all the scales respectively, carrying out local binary coding on each region so as to complete the expression on shape trends for the spectrum data, then generating a regional characteristic histogram according to the binary coding of each region, sequentially connecting all the regional characteristic histograms of all the regions under the same scale so as to form a spatial enhanced histogram, and finally carrying out weighting and calculating on the obtained spatial enhanced histograms of different scales to obtain a spectrum characteristic vector. The invention is used for extracting the stable intrinsic spectrum characteristics of solid materials under different conditions, has robustness resistant to condition changes and excellent separating capacity, and provides support for spectrum based target identification under complex conditions.

Description

technical field [0001] The invention belongs to the field of target identification, and in particular relates to a spectral feature extraction method, which is especially suitable for solid substances. Background technique [0002] Conventional detection methods generally use a single-spectrum imaging detection method to collect target / background energy in a wider spectrum. At this time, the target is often submerged in the complex background clutter or concealed by interference, camouflage, etc., and appears as a target signal Very weak, low signal-to-noise ratio and signal-to-clutter ratio. However, the inherent physical and chemical properties and structure of the target are quite different from the background, interference, camouflage, etc., so its features will be more obvious on some spectral lines or narrower spectral bands, that is, on these spectral lines or narrower In the narrow spectrum, the signal-to-noise ratio and signal-to-noise ratio of the target are highe...

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): G06K9/46
Inventor 张天序颜露新郑珍珠杨卫东方正孙协昌张伟刘翔燕边小勇徐利成王娟付平高慧杰
Owner HUAZHONG UNIV OF SCI & TECH
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