東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

mmWave Radar Based Real-Time Human P...

Wang, Yijiang.

Linked to FindBook

Google Book

Amazon

博客來

mmWave Radar Based Real-Time Human Pose Construction.

Record Type:	Electronic resources : Monograph/item
Title/Author:	mmWave Radar Based Real-Time Human Pose Construction./
Author:	Wang, Yijiang.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	28 p.
Notes:	Source: Masters Abstracts International, Volume: 82-04.
Contained By:	Masters Abstracts International82-04.
Subject:	Computer science. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28090745
ISBN:	9798672198101

mmWave Radar Based Real-Time Human Pose Construction.
Wang, Yijiang.

mmWave Radar Based Real-Time Human Pose Construction. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 28 p.

Source: Masters Abstracts International, Volume: 82-04.

Thesis (M.S.)--State University of New York at Buffalo, 2020.

This item must not be sold to any third party vendors.

Recently, Millimeter wave (mmWave) FMCW radar sensors are popular in diverse application scenarios of Internet of things (IoT), especially in industrial and automobile scenarios. This type of sensors have specialty of providing the range, velocity, and angle of detected objects which may block by some materials in the line of sight, which makes they outperforms camera in some special scenarios. However, applying mmWave radar sensor on the human pose reconstruction task still lacks extensive research. So, this paper presents a real-time system based on TI automotive mmWave radar sensors that can estimate 3D pose of the human body from streaming Analog-to-Digital Converters (ADC) signal data. This system can capture ADC signal from TI AWR1843 radar sensor coupled with DCA1000 and convert it to points cloud array with classical radar signal processing algorithms. Then, points cloud will be fed into a deep learning model which extracts pose parameters of detected human body and constructs and renders the human pose in 3D skeleton form. The system performance achieves real-time level reconstruction of the 3D human pose within centimeter-level error and 300ms delay at 10fps.

ISBN: 9798672198101Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Human pose

mmWave Radar Based Real-Time Human Pose Construction.
LDR:02394nmm a2200421 4500 001 2276747
005 20210510091902.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798672198101
035 $a (MiAaPQ)AAI28090745
035 $a AAI28090745
040 $a MiAaPQ $c MiAaPQ
100 1 $a Wang, Yijiang. $3 3555041
245 1 0 $a mmWave Radar Based Real-Time Human Pose Construction.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 28 p.
500 $a Source: Masters Abstracts International, Volume: 82-04.
500 $a Advisor: Su, Lu.
502 $a Thesis (M.S.)--State University of New York at Buffalo, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Recently, Millimeter wave (mmWave) FMCW radar sensors are popular in diverse application scenarios of Internet of things (IoT), especially in industrial and automobile scenarios. This type of sensors have specialty of providing the range, velocity, and angle of detected objects which may block by some materials in the line of sight, which makes they outperforms camera in some special scenarios. However, applying mmWave radar sensor on the human pose reconstruction task still lacks extensive research. So, this paper presents a real-time system based on TI automotive mmWave radar sensors that can estimate 3D pose of the human body from streaming Analog-to-Digital Converters (ADC) signal data. This system can capture ADC signal from TI AWR1843 radar sensor coupled with DCA1000 and convert it to points cloud array with classical radar signal processing algorithms. Then, points cloud will be fed into a deep learning model which extracts pose parameters of detected human body and constructs and renders the human pose in 3D skeleton form. The system performance achieves real-time level reconstruction of the 3D human pose within centimeter-level error and 300ms delay at 10fps.
590 $a School code: 0656.
650 4 $a Computer science. $3 523869
650 4 $a Industrial engineering. $3 526216
650 4 $a Remote sensing. $3 535394
650 4 $a Automotive engineering. $3 2181195
650 4 $a Artificial intelligence. $3 516317
650 4 $a Information technology. $3 532993
653 $a Human pose
653 $a mmWave
653 $a Radar sensor
653 $a Internet of Things
653 $a 3D modeling
653 $a Analog-to-Digital Converters
690 $a 0984
690 $a 0489
690 $a 0800
690 $a 0546
690 $a 0799
690 $a 0540
710 2 $a State University of New York at Buffalo. $b Computer Science and Engineering. $3 1035503
773 0 $t Masters Abstracts International $g 82-04.
790 $a 0656
791 $a M.S.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28090745