DEEP LEARNING-BASED ABNORMAL BEHAVIOR DETECTION SYSTEM AND METHOD USING ANONYMIZED DATA

Title:

DEEP LEARNING-BASED ABNORMAL BEHAVIOR DETECTION SYSTEM AND METHOD USING ANONYMIZED DATA

Document Type and Number:

WIPO Patent Application WO/2022/119080

Kind Code:

A1

Abstract:

The present invention relates to a deep learning-based abnormal behavior detection system using anonymized data to sense abnormal behavior such as installing hidden cameras in a set area such as a bathroom. The present invention comprises: an anonymized image data generation unit for sensing the behavior of a subject in a set area, and generating image data in which personal information of the subject has been anonymized; and an abnormal behavior identification unit for categorizing the anonymized image data as normal or abnormal behavior data using a model trained with abnormal behaviors.

More Like This:

WO/2000/011858	DEVICE FOR PERSONAL SECURITY AND/OR VIGILANCE AND/OR ORIENTATION AND/OR HELP
JPH0564198	BURGLAR ALARM SYSTEM
JPH0821149	[Title of Invention] Security Monitoring System

Inventors:

HAN SOO YEON (KR)

Application Number:

PCT/KR2021/011583

Publication Date:

June 09, 2022

Filing Date:

August 30, 2021

Export Citation:

Click for automatic bibliography generation Help

Assignee:

UNIUNI CORP (KR)

International Classes:

G08B13/196; G08B5/22; G08B25/10; H04N7/18

Foreign References:

KR101845077B1	2018-04-03
KR20200103194A	2020-09-02
KR102016253B1	2019-08-29
KR20110028703A	2011-03-22
KR101194167B1	2012-10-24

Attorney, Agent or Firm:

HAEDAM IP GROUP (KR)

Download PDF:

View/Download PDF PDF Help

Previous Patent: CROSSROAD DANGER WARNING SYSTEM BASED ON SITUATION PREDICTION

Next Patent: PLATE COIL POWER GENERATION APPARATUS