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

Ground moving target micro-tremor signal characteristic extraction based on sparse decomposition

A sparse decomposition and signal feature technology, which is applied in the field of feature extraction of micro-Doppler signals, can solve the problems of insufficient feature extraction of micro-Doppler signals and unsatisfactory actual recognition effect, so as to reduce the number of searches, improve efficiency, background Effects with little effect of noise

Inactive Publication Date: 2013-11-27
SICHUAN UNIV
View PDF1 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In order to solve the problems of insufficient feature extraction and unsatisfactory actual recognition effect of micro-Doppler signals interfered by noise in actual situations, the present invention proposes a feature extraction method for ground moving targets based on sparse decomposition

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
  • Ground moving target micro-tremor signal characteristic extraction based on sparse decomposition
  • Ground moving target micro-tremor signal characteristic extraction based on sparse decomposition
  • Ground moving target micro-tremor signal characteristic extraction based on sparse decomposition

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0027] Specific implementation mode 1: Combination figure 1 To describe this embodiment, this embodiment includes the following specific steps:

[0028] Step 1: Establish an over-complete signal atomic library corresponding to the target signal. The corresponding atom library is established according to the specific signal, and the atoms are normalized to obtain the corresponding atom library of the signal.

[0029] Step 2: Combine the optimized genetic algorithm with sparse decomposition, search for a series of best matching sparse atoms in the genetic space mapped from the atom search space, and decompose the signal until the decomposition stop condition is met. According to the theory of signal decomposition, the original signal after decomposition can be expressed in the form of formula (1)

[0030] (1)

[0031] In formula (2) Is the residual value after decomposition when the signal is decomposed to the mth time. From a theoretical analysis, when m approaches infinity, the r...

specific Embodiment approach 2

[0033] Specific embodiment two: this mode is a specific description of step one in the first embodiment. The over-complete signal atom library in this method is to establish the corresponding atom library according to the signal characteristics, and the atom library is constructed by the method of formula (2).

[0034] (2)

[0035] Where It is a Gaussian window function, γ=(s,u,v,w) is a time-frequency parameter, s, u, v, w represent the scale, displacement, frequency, and phase of the atom, respectively.

[0036] Among them, the prior value is extracted by sampling and estimation of the target signal, and the amplitude fluctuation range of the target signal [a min ,a max ] As the variation range of the atomic scale s, the position of the target signal is moved by the interval [d min ,d max ] As the variation range of the atomic displacement u, and discretize the variation amplitude. Through this improvement, the search space range of the atom library is related to the sp...

specific Embodiment approach 3

[0037] Specific implementation mode 3: This mode is a specific description of combining the optimized genetic algorithm and sparse decomposition in specific implementation mode 1 to decompose the signal.

[0038] Step 1: Map the solution space of the sparse decomposition to the genetic space, create the initial population Initial_Group, that is, define a parameter group to be optimized, so as to convert the search for the most matching atom in the dictionary into the search for the most suitable atom in the population, and Find the initial most suitable individual g in the first generation population.

[0039] Step 2: Use mutation probability p for optimal individual g m Change the value of the feature in the vector group to achieve the purpose of generating (N-1) / 4 new individuals.

[0040] Step 3: For all individuals except the best adapted individual g, select 2 individuals each time to compare their fitness and keep the individuals with high fitness; repeat the selection process ...

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 realizing the characteristic extraction of a ground moving target micro-tremor signal based on a sparse decomposition theory, and problems of the long running time of a sparse decomposition algorithm, many occupied resources, a long process of searching a most matched atom, and the insufficient characteristic extraction and a high dimensional decomposition parameter of a signal caused by noise interference in an actual environment can be solved. The concrete method comprises the following steps: (1) establishing an over-complete atom dictionary corresponding to a target signal, taking the scale, the displacement, the frequency, the amplitude and the projection value of an atom as change parameters and carrying out parameter discretization, setting the change range of the parameters according to the characteristics of the target signal and the prior knowledge, and carrying out normalization on the atom to obtain a characteristic atom library corresponding to the micro-tremor signal; (2) combining an optimized genetic algorithm (GA) with MP sparse decomposition, searching an atom with sparse parameter in an efficient and adaptive way, and obtaining a series of atomic parameters which describe signal characteristics; and (3) carrying out PCA principal component analysis to carry out vector dimensionality reduction on the obtained atom and extracting an effective component to be a final characteristic. By applying the method, the amount of calculation of a sparse decomposition algorithm can be effectively reduced, the algorithm speed and resource consumption are raised, and the characteristic can be effectively applied to the later target identification.

Description

technical field [0001] The invention provides a feature extraction algorithm based on sparse decomposition, and in particular relates to the feature extraction of micro-Doppler signals of ground moving targets. Background technique [0002] The monitoring and identification of ground moving targets is an important part of battlefield target monitoring and border defense; ground moving targets usually refer to various types of mobile equipment (such as motor trucks, armored vehicles, etc.), and various human motion states (such as crawling, walking, running, etc.). They can disperse and have strong concealment. They can hide in bunkers or camouflage to avoid detection and tracking. [0003] The micro-motion signal is a signal obtained by using the micro-Doppler effect to describe the micro-motion characteristics of a moving object and using micro-Doppler modulation on the radar echo. This type of signal contains micro-motion information that can be used to describe the micr...

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
IPC IPC(8): G06K9/46G06N3/12
Inventor 李智阳佑虹任和
Owner SICHUAN 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