公开(公告)号：US20230200672A1

公开(公告)日：2023-06-29

申请号：US18085817

申请日：2022-12-21

Applicant: Korea Electronics Technology Institute

Inventor： Sung Ho LEE ,  Min Geon SHIN ,  Yong Chul JUNG

IPC: A61B5/05 ,  A61B5/0205 ,  A61B5/00

CPC classification number: A61B5/05 ,  A61B5/0205 ,  A61B5/7203 ,  A61B5/7246 ,  A61B5/725 ,  A61B5/7257 ,  A61B5/024

Abstract: There is provided an FMCW radar target detection method for vital signal detection. A method for detecting vital signals by using radar selects a range bin where there are accurate vital signals by using a correlation between a phase change profile of an IF signal caused by a minute motion, and a target signal intensity change profile, so that accuracy of estimation of vital signals can be enhanced through exact tracking of a person (target). In addition, clutter may be exactly removed by utilizing a phase unwrapping technique which is adaptive to an upper body motion change compared to a 180-degree fixed phase unwrapping technique.

公开(公告)号：US20210158153A1

公开(公告)日：2021-05-27

申请号：US16952481

申请日：2020-11-19

Applicant: Korea Electronics Technology Institute

Inventor： Young Han LEE ,  Sung Ho LEE ,  Min Geon SHIN

IPC: G06N3/08 ,  G01S13/34 ,  G01S7/35

Abstract: A method and a system for processing an FMCW radar signal by using a lightweight deep learning network are provided. The data processing method using an AI model includes: converting n-dimensional data into a plurality of pieces of 2D data; inputting the plurality of pieces of 2D data into the AI model through different channels; and processing the plurality of pieces of 2D data inputted to the AI model by analyzing. Accordingly, an amount of computation and a memory usage can be reduced and characteristics of an object can be learned and inferred by the lightweight deep learning network.