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

Time-frequency domain sparse reconstruction-based radar pedestrian detection method

A sparse reconstruction and pedestrian detection technology, applied in the field of radar signal processing and target recognition, can solve the problem of low radar detection rate, improve search accuracy, reduce multi-component aliasing, and easily extract features

Active Publication Date: 2019-06-21
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF14 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Realized the separation of multi-component time-frequency domain aliasing, solved the conditional constraints of time-frequency images on motion feature detection and the problem of low detection rate of radar under complex environmental noise conditions, has good generalization ability, and is convenient for engineering implementation

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
  • Time-frequency domain sparse reconstruction-based radar pedestrian detection method
  • Time-frequency domain sparse reconstruction-based radar pedestrian detection method
  • Time-frequency domain sparse reconstruction-based radar pedestrian detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] Definition of Abbreviations and Key Terms

[0062] FFT (Fast Fourier Transform, Fast Fourier Transform)

[0063] CFAR (constant false alarm rate, constant false alarm)

[0064] PRI (pulse repetition period, pulse repetition period)

[0065] OMP (Orthogonal Matching Pursuit, Orthogonal Matching Pursuit)

[0066] SVM (Support Vector Machine, support vector machine)

[0067] The invention proposes a radar pedestrian detection system based on time-frequency domain sparse reconstruction. When a person moves forward, the torso and limbs will swing regularly, that is, the micro-movement of the target presents a micro-Doppler effect in the radar signal. The pedestrian detection system of the present invention is completed by studying the Doppler shift of the radar echo and its phase change law, and combining the sparse signal processing technology.

[0068] In order to make the object, technical solution and advantages of the present invention clearer, the present inventio...

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 belongs to the field of radar signal processing and target recognition technologies and provides a time-frequency domain sparse reconstruction-based radar pedestrian detection method. The invention aims to solve the problems of the conditional constraints of time-frequency images on motion feature detection and the low detection rate of a radar under complex environmental noise conditions. According to the main technical schemes of the invention, the method includes the following steps that: step 1, as a data acquisition device, a radar can obtain A / D sampling data, and the A / D sampling data can be adopted as radar signals S(t) to be identified; step 2, two-dimensional FFT is performed on the A / D sampling data, so that distance dimension-speed dimension frequency-domain dataS(f) can be obtained; step 3, CFAR detection is performed so as to acquire the motion parameters of a moving target, and at the same time, a range gate where the moving target is located is obtained;step 4, the data Sn(f) of the range gate where the moving target is located are extracted, and sparse reconstruction processing is performed; step 5, feature extraction is performed on reconstructed moving target signals; and step 6, the category of the target is judged through a target decision making device.

Description

technical field [0001] The invention belongs to the technical field of radar signal processing and target recognition. More specifically, the invention relates to a radar pedestrian detection system based on time-frequency domain sparse reconstruction, which can be used for radar target recognition processing in complex environments. Background technique [0002] Pedestrian detection technology has broad application prospects in automotive assisted driving, intelligent monitoring, intelligent transportation, and home service robots. At the same time, pedestrian detection does not exist in isolation, it is closely related to issues such as pedestrian tracking, behavior analysis, gesture recognition, scene segmentation, etc., and has high scientific research value and commercial value. [0003] As a non-contact life detection technology, radar is less affected by light and has high detection accuracy. It can detect and locate targets all day, all weather, and at a long distanc...

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): G01S7/41
Inventor 王章静余月琴缪显涵汪呈智杨伦龙吴兆亮
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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