Method and apparatus for identifying behavior of target, and radar system

Patent metadata

Field	Value
Publication number	US-12044796-B2
Application number	US-202117188106-A
Country	US
Kind code	B2
Filing date	Mar 1, 2021
Priority date	Aug 30, 2019
Publication date	Jul 23, 2024
Grant date	Jul 23, 2024

Abstract

A method and apparatus for identifying behavior of a target, and a radar system applied to an automated driving scenario include receiving a radar echo signal from a target, processing the radar echo signal to obtain time-frequency domain data, processing the time-frequency domain data to obtain signal attribute feature data representing a first feature of a radar echo signal attribute and linear prediction coefficient (LPC) feature data representing a second feature of the radar echo signal, inputting the signal attribute feature data and the LPC feature data into a behavior identification model, and outputting behavior information of the target.

First claim

What is claimed is:

1. A method comprising:
receiving a radar echo signal from a target;
processing the radar echo signal to obtain time-frequency domain data;
processing the time-frequency domain data to obtain signal attribute feature data representing a first feature of a radar echo signal attribute, wherein the signal attribute feature data comprises one or more of a maximum frequency value corresponding to the time-frequency domain data, a standard deviation of amplitude value corresponding to the time-frequency domain data, a mean absolute error of amplitude value corresponding to the time-frequency domain data, an amplitude value quartile, an amplitude value interquartile range, and a spectral entropy;
processing the time-frequency domain data to obtain linear prediction coefficient (LPC) feature data representing a second feature of the radar echo signal, wherein processing the time-frequency domain data comprises:
re-arranging the time-frequency domain data to obtain a one-dimensional row vector; and
inputting the re-arranged time-frequency domain data into an LPC function to obtain the LPC feature data;
inputting the signal attribute feature data and the LPC feature data into a behavior identification model; and
obtaining, from an output of the behavior identification model, behavior information of the target.

2. The method of claim 1 , wherein before processing the time-frequency domain data, the method further comprises performing a dimension reduction on the time-frequency domain data.

3. The method of claim 2 , further comprising performing the dimension reduction on the time-frequency domain data based on a principal component analysis (PCA) algorithm.

4. The method of claim 1 , wherein the behavior identification model is a support-vector machines (SVM) classifier model.

5. The method of claim 1 , wherein the behavior identification model is a neural network model.

6. An apparatus comprising:
a receiver configured to receive a radar echo signal from a target;
a processor coupled to the receiver and configured to:
process the radar echo signal to obtain time-frequency domain data;
process the time-frequency domain data to obtain signal attribute feature data representing a first feature of a radar echo signal attribute, wherein the signal attribute feature data comprises one or more of a maximum frequency value corresponding to the time-frequency domain data, a standard deviation of amplitude value corresponding to the time-frequency domain data, a mean absolute error of amplitude value corresponding to the time-frequency domain data, an amplitude value quartile, an amplitude value interquartile range, and a spectral entropy;
process the time-frequency domain data to obtain linear prediction coefficient (LPC) feature data representing a second feature of the radar echo signal, wherein in a manner to process the time-frequency domain data, the processor is further configured to:
re-arrange the time-frequency domain data to obtain a one-dimensional row vector; and
input the re-arranged time-frequency domain data into an LPC function to obtain the LPC feature data;
input the signal attribute feature data and the LPC feature data into a behavior identification model; and
obtain, from an output of the behavior identification model, behavior information of the target.

7. The apparatus of claim 6 , wherein the processor is further configured to perform a dimension reduction on the time-frequency domain data.

8. The apparatus of claim 7 , wherein the processor is further configured to perform the dimension reduction on the time-frequency domain data based on a principal component analysis (PCA) algorithm.

9. The apparatus of claim 6 , wherein the behavior identification model is a support-vector machines (SVMs) classifier model.

10. The apparatus of claim 6 , wherein the behavior identification model is a neural network model.

11. A radar system comprising:
a signal transmitting apparatus configured to transmit a radar signal;
a signal receiving apparatus configured to receive a radar echo signal reflected from a target when the radar signal contacts the target; and
a signal processing apparatus coupled to the signal transmitting apparatus and the signal receiving apparatus and configured to:
process the radar echo signal to obtain time-frequency domain data;
process the time-frequency domain data to obtain signal attribute feature data representing a first feature of a radar echo signal attribute, wherein the signal attribute feature data comprises one or more of a maximum frequency value corresponding to the time-frequency domain data, a standard deviation of amplitude value corresponding to the time-frequency domain data, a mean absolute error of amplitude value corresponding to the time-frequency domain data, an amplitude value quartile, an amplitude value interquartile range, and a spectral entropy;
process the time-frequency domain data to obtain linear prediction coefficient (LPC) feature data representing a second feature of the radar echo signal, wherein in a manner to process the time-frequency domain data, the processor is further configured to:
re-arrange the time-frequency domain data to obtain a one-dimensional row vector; and
input the re-arranged time-frequency domain data into an LPC function to obtain the LPC feature data;
input the signal attribute feature data and the LPC feature data into a behavior identification model; and
obtain, from an output of the behavior identification model, behavior information of the target.

12. The radar system of claim 11 , wherein the signal processing apparatus is further configured to perform a dimension reduction on the time-frequency domain data based on a principal component analysis (PCA) algorithm.

13. The radar system of claim 11 , wherein the behavior identification model is a support-vector machines (SVM) classifier model.

14. The radar system of claim 11 , wherein the behavior identification model is a neural network model.

15. The radar system of claim 11 , wherein the signal processing apparatus is further configured to perform a dimension reduction on the time-frequency domain data.

16. A computer program product comprising computer-executable instructions stored on a non-transitory computer-readable storage medium that, when executed by a processor, cause an apparatus to:
receive a radar echo signal from a target;
process the radar echo signal to obtain time-frequency domain data;
process the time-frequency domain data to obtain signal attribute feature data representing a first feature of a radar echo signal attribute, wherein the signal attribute feature data comprises one or more of a maximum frequency value corresponding to the time-frequency domain data, a standard deviation of amplitude value corresponding to the time-frequency domain data, a mean absolute error of amplitude value corresponding to the time-frequency domain data, an amplitude value quartile, an amplitude value interquartile range, and a spectral entropy;
process the time-frequency domain data to obtain linear prediction coefficient (LPC) feature data representing a second feature of the radar echo signal, wherein in a manner to process the time-frequency domain data, the processor is further configured to:
re-arrange the time-frequency domain data to obtain a one-dimensional row vector; and
input the re-arranged time-frequency domain data into an LPC function to obtain the LPC feature data;
input the signal attribute feature data and the LPC feature data into a behavior identification model; and
obtain behavior i

Assignees

• Huawei Tech Co Ltd

Inventors

• Feng Xiangbing
• Yu Yueqin
• Peng Xueming
• Chen Qi

Classifications

• G01S7/417

  involving the use of neural networks · CPC title

• G01S7/352

  Receivers · CPC title

• G01S7/356

  involving particularities of FFT processing · CPC title

• G01S7/415 Primary

  Identification of targets based on measurements of movement associated with the target · CPC title

• G01S13/931

  of land vehicles · CPC title