RISK RECOGNITION METHOD FOR USE IN VIDEO SURVEILLANCE SYSTEM BASED ON HUMAN IDENTIFICATION

• US 20130188031A1
• Filed: 11/21/2012
• Published: 07/25/2013
• Est. Priority Date: 01/19/2012
• Status: Abandoned Application

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: PARK, So Hee, KO, Jong-Gook, YOO, Jang-Hee, CHOI, Jin-Woo
• Application Number:
  US13/684,090
• Publication Number:
  US 20130188031A1
• Time in Patent Office: Days
• US Class Current: 348/77
• CPC Class Codes: G06V 20/52 Surveillance or monitoring of activities, e.g. for recognising suspicious objects recognising microscopic objects G06V20/69
• CPC Class Codes: G06V 40/103 Static body considered as a whole, e.g. static pedestrian or occupant recognition
• CPC Class Codes: G08B 13/19613 Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion
• CPC Class Codes: G08B 13/19652 Systems using zones in a single scene defined for different treatment, e.g. outer zone gives pre-alarm, inner zone gives alarm
• CPC Class Codes: H04N 7/002 Special television systems not provided for by H04N7/007 - H04N7/18 still pictures via a television channel H04N1/00098
• CPC Class Codes: H04N 7/183 for receiving images from a single remote source

Abstract

A risk recognition method based on human identification is disclosed, which identifies a human being from a captured image, such that it can recognize a dangerous situation of each person. The risk recognition method includes detecting a person from photographed image information, and identifying the detected person, thereby generating identification information for each person; extracting access control information for each person using the identification information; analyzing the access control information simultaneously while tracking a movement path for each person, and determining whether a dangerous situation for each person occurs; and if the dangerous situation occurs, selectively warning of the dangerous situation of the person who causes the dangerous situation.

Claims

1. A risk recognition method based on human identification comprising:

detecting a person from photographed image information, and identifying the detected person, thereby generating identification information for each person;

extracting access control information for each person using the identification information;

analyzing the access control information simultaneously while tracking a movement path for each person, and determining whether a dangerous situation for each person occurs; and

if the dangerous situation occurs, selectively warning of the dangerous situation of the person who causes the dangerous situation.

2. The method according to claim 1, wherein the detecting and identifying of the person further includes:

identifying the person using radio frequency identification (RFID) information or electronic identification (ID) information.

3. The method according to claim 1, wherein the access control information includes at least one of a passage restriction time and a restricted zone for each person.

4. The method according to claim 3, wherein the determining of the dangerous situation includes at least one of determining whether a current time belongs to the restriction time, and determining whether a current position belongs to the restricted zone.

5. The method according to claim 1, wherein the identification information includes biological information.

6. The method according to claim 1, further comprising:

if the dangerous situation occurs, transmitting identification information of the person who causes the dangerous situation and the image information to a management system.