Title:
INTELLIGENT THROUGH-OBSTRUCTION 3D IMAGING SYSTEM USING UWB ELECTROMAGNETIC SENSING FOR OBJECT DETECTION
Document Type and Number:
WIPO Patent Application WO/2023/121410
Kind Code:
A1
Abstract:
Herein disclosed a system and method to utilize information from imaging sensor and UWB sensor to perform object recognition, object tracking, activity recognition, vital sign detection, and 3D image reconstruction through any obstruction. This proposed invention uses deep learning algorithm and neural network to perform feature extraction of image data and signal data, identify depth estimation, recognize object and track its activity, and construct a 3D model of the object even though the object is not visible or overlapped with other objects.
More Like This:
Inventors:
ADZAKA FIKRIANSYAH (ID)
FADLIL JUNAIDILLAH (ID)
SETIAWAN RICKY (ID)
HANIF MUHAMMAD ISHLAHUL (ID)
KARUNIANTO WISMA CHAERUL (ID)
FAKHRI DINAN (ID)
TRIWIBOWO IMMANUEL CATUR (ID)
S SUMARYANTO (ID)
FADLIL JUNAIDILLAH (ID)
SETIAWAN RICKY (ID)
HANIF MUHAMMAD ISHLAHUL (ID)
KARUNIANTO WISMA CHAERUL (ID)
FAKHRI DINAN (ID)
TRIWIBOWO IMMANUEL CATUR (ID)
S SUMARYANTO (ID)
Application Number:
PCT/KR2022/021243
Publication Date:
June 29, 2023
Filing Date:
December 23, 2022
Export Citation:
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06T17/00; A61B5/024; G06T5/00; G06T7/246; G06T7/593; G06T7/70; G06T15/06; G06V10/25
Foreign References:
| US20180211399A1 | 2018-07-26 | |||
| JP6482816B2 | 2019-03-13 | |||
| US20150146964A1 | 2015-05-28 | |||
| US20160078636A1 | 2016-03-17 |
Other References:
KIM JISU, LEE DEOKWOO: "Activity Recognition with Combination of Deeply Learned Visual Attention and Pose Estimation", APPLIED SCIENCES, vol. 11, no. 9, pages 4153, XP093074221, DOI: 10.3390/app11094153
Attorney, Agent or Firm:
LEE, Keon-Joo et al. (KR)
Download PDF: