음성, 영상, 먼지 센서를 활용한 1인 가구 이상 행동 패턴 탐지 = Abnormal Behavior Pattern Identifications of One-person Households using Audio, Vision, and Dust Sensors

다국어 초록 (Multilingual Abstract)

The number of one person households has grown steadily over the recent past and the population of lonely and unnoticed death are also observed. The phenomenon of one person households has been occurred. In the dark side of society, the remarkable number of lonely and unnoticed death are reported among different age-groups. We propose an unusual event detection method which may give a remarkable solution to reduce the number of the death rete for people dying alone and remaining undiscovered for a long period of time. The unusual event detection method we suggested to identify abnormal user behavior in their lives using vision pattern, audio pattern, and dust pattern algorithms. Individually proposed pattern algorithms have disadvantages of not being able to detect when they leave the coverage area. We utilized a fusion method to improve the accuracy performance of each pattern algorithm and evaluated the technique with multiple user behavior patterns in indoor areas.

국문 초록 (Abstract)

최근 1인 가구가 다양한 연령대에서 증가하고 있으며 무연고자의 사망도 점차 증가한다. 1인 가구의 무연고사의 경우 주위에 돌봐줄 사람이 없어 많이 발생하며 최근에는 노인뿐만 아니라 다양한 연령대에서 발생한다. 우리는 혼자 사는 사람의 이상 징후를 탐지하고자 홈 CCTV를 이용한 영상 패턴 알고리즘과 음성을 인식하는 음성 패턴 알고리즘, 움직임 및 요리 등에서 발생하는 먼지를 탐지하는 센서로 먼지 패턴 알고리즘을 연구 및 개발하였다. 개별적으로 제안된 패턴 알고리즘은 탐지 영역을 벗어나게 되면 탐지하지 못하는 단점이 존재한다. 개별 패턴 알고리즘의 성능을 향상시키기 위해 융합 방식을 연구했으며, 다수의 사용자 행동 패턴을 분석하여 그 성능을 검증하였다.

참고문헌 (Reference)

1 노진호, "사물인터넷기반 미세먼지 측정 시스템 구현" 한국정보통신학회 21 (21): 829-835, 2017

2 News 뉴스, "기동민 "고독사 증가 추세…무연고 사망자 6년간 1만여건""

3 연합뉴스, "‘나 혼자 산다' 1인가구 562만명…17년새2.5배로 늘어"

4 연합뉴스, "‘1인 노인가구 증가' 무연고 사망 4년새179％ 증가"

5 Junho Ahn, "my Black Box: Black box Mobile Cloud Systems for Personalized Unusual Event Detection"

6 Jun-Hak Heo, "Proposal and Implementation of High-Speed Intelligent Algorithm on Omni-directional Video" 569-572, 2018

7 정주호, "Intelligent User Pattern Recognition based on Vision, Audio and Activity for Abnormal Event Detections of Single Households" 한국컴퓨터정보학회 24 (24): 59-66, 2019

8 Sei Chang, "Fine Dust Measuring System based on Arduino and Raspberry Pi Application Development &Analysis" 2016

9 Sei Chang, "Fine Dust Measuring System based on Arduino and Raspberry Pi Application Development &Analysis" 2017

10 Jaeyeol Choi, "Development of Potable Sensor Device for Measuring Particulate Matters Concentration using Arduino" 407-409, 2017

11 Kwang-Hee Park, "Development of CCTV Image Deep Learning Method for Smart River and Inundation Identification" Graduate School of Busan University 2018

12 MoonEuiseong, "Detection Drone by using Yolo" The Korean Institute of Information Scientists and Engineers 2315-2317, 2018

13 Jin-Hwan Kim, "An Object Tracking System Using an Omni-Directional Camera" 781-782, 2008

14 이현성, "A study on designing a speech/non-speech classification algorithm" Graduate School of Hanyang University 2017

15 Sun-Eung Kim, "A Study on the Single Camera Based 3-D Fall Detection for Outdoor Environment" Graduate School of Korea University 2018

16 Sang Young Jo, "A Study on Development and Real-Time Implementation of Voice Recognition Algorithm" 18 (18): 250-258, 2015