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

Low-altitude sound target comprehensive identification method and device based on multi-dimensional feature space

A technology of multi-dimensional features and recognition methods, applied in speech recognition, speech analysis, instruments, etc., can solve problems such as incompleteness, and achieve the effect of reducing the false alarm rate of detection and improving the target recognition rate

Pending Publication Date: 2020-11-20
THE THIRD RES INST OF CHINA ELECTRONICS TECH GRP CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, only extracting these features is incomplete for describing target characteristics, because there are often large similarities in time-frequency characteristics between targets and environmental disturbances, such as helicopter targets and certain types of cars have similar line spectrum features, fighter jets Interference sources such as trucks have wide-spectrum characteristics, resulting in more false alarms

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
  • Low-altitude sound target comprehensive identification method and device based on multi-dimensional feature space
  • Low-altitude sound target comprehensive identification method and device based on multi-dimensional feature space
  • Low-altitude sound target comprehensive identification method and device based on multi-dimensional feature space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] A comprehensive recognition method for low-altitude acoustic targets based on multi-dimensional feature space

[0048] Such as figure 1 As shown, a method for comprehensive recognition of low-altitude acoustic targets based on multi-dimensional feature space includes the following steps:

[0049] Step 1: Acquire signals through a multi-channel acoustic sensor array.

[0050] The sampling frequency is 1024Hz, and the signal is divided into frames using a short time window with a 1s long overlap rate of 50%.

[0051] Step 2: Analyze and calculate the collected signals to obtain multi-dimensional feature vectors including time-frequency features, spatial features and harmonic features.

[0052] Time-frequency features and harmonic features are obtained through analysis and calculation of single-channel signals; spatial features are obtained through analysis and calculation of multi-channel signals.

[0053] (1) Time-frequency characteristics

[0054] The signal is obta...

Embodiment 2

[0113] A low-altitude acoustic target comprehensive recognition device based on multi-dimensional feature space

[0114] Such as Figure 4 As shown, a low-altitude acoustic target comprehensive recognition device based on multi-dimensional feature space, including:

[0115] A multi-channel sound sensor array, the multi-channel sound sensor array is used to collect sound signals;

[0116] A sound signal analysis and calculation unit, the sound signal analysis and calculation unit is used to analyze and calculate the collected signal to obtain a multi-dimensional feature vector including time-frequency features, spatial features and harmonic features;

[0117] A target recognition unit, the target recognition unit includes a target classification model, and inputs the multi-dimensional feature vector into the target classification model to perform target recognition;

[0118] A display unit, the display unit is used to display the target recognition result.

[0119] In the se...

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 relates to a low-altitude sound target comprehensive identification method and device based on a multi-dimensional feature space. Signals are collected through a multi-channel sound sensor array; the acquired signals are analyzed and calculated to obtain a multi-dimensional feature vector including time-frequency features, spatial features and harmonic features; and the multi-dimensional feature vector is inputted into a target classification model to carry out target identification. The method can effectively improve the target identification rate.

Description

technical field [0001] The invention relates to a method and device for comprehensive recognition of low-altitude acoustic targets based on multi-dimensional feature space. Background technique [0002] Using acoustic sensors to passively receive low-altitude moving targets (such as helicopters, fighter jets, etc.) radiated noise signals, and using methods such as array signal processing and pattern recognition, the target's orientation, attributes, and motion status can be obtained. Acoustic detection is free from electromagnetic interference, good concealment, and strong survivability; sound waves have diffraction characteristics, and are not limited by visibility and visibility conditions. , it can accurately detect low-altitude concealed targets; using target noise to extract voiceprint features can realize accurate identification of target types and models. [0003] Acoustic target recognition technology includes two stages: acoustic signal feature extraction and class...

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): G10L25/03G10L25/27G10L25/51G10L15/14G10L15/08
CPCG10L25/03G10L25/27G10L25/51G10L15/08G10L15/142
Inventor 杨立学王志峰周印龙袁彦
Owner THE THIRD RES INST OF CHINA ELECTRONICS TECH GRP CORP
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