Cited 0 time in webofscience Cited 0 time in scopus

Intelligent Video Surveillance: Behavioral Detection of Falls Based on Double-Layer Support Vector Machine

Intelligent Video Surveillance: Behavioral Detection of Falls Based on Double-Layer Support Vector Machine
Translated Title
지능형 비디오 감시: 3D 관절 데이터를 사용한 DLSVM 기반의 낙상사고 감지
Yoon, Hee Jung
DGIST Authors
Yoon, Hee Jung; Son, Sang Hyuk; Park, Tae Joon
Son, Sang Hyuk
Park, Tae Joon
Issue Date
Available Date
Degree Date
2013. 2
activity detectionbehavior recognitionfall detectionvideo surveillancesupport vector machine
The elderly population is expected to more than triple by 2050 in the United States alone. This indicates the growing need of medical innovations that are expected to deliver convenient, user-friendly, and intelligent health care in the home. In particular, the use of computer vision and artificial intelligence offers a new promising solution to analyze human behavior and detect unusual events. We propose a novel method to detect unintentional falls, which are one of the greatest risks for seniors living alone. Our approach is based on a machine learning technique, in which we use a human skeletal joint data from a Red Green Blue Depth (RGBD) sensor, Kinect. To the best of our knowledge, this is the first fall detection research utilizing machine learning mechanism with joint information. After building a solid definition of various types of falls, the system is trained using Support Vector Machine (SVM) in two separate layers, which we call Double Layer SVM (DLSVM). Our evaluation results show that our proposed system can efficiently detect different types of falls facing various directions from the camera and is capable of accurately distinguishing an actual fall versus a fall-like behavior. ⓒ 2013 DGIST
Table Of Contents
Ⅰ. INTRODUCTION 10 -- Ⅱ. BACKGROUND – CURRENT FALL DETECTION APPROACHES 11 -- 1. Accelerometer 11 -- 2. Floor Vibration 12 -- 3. Video Based Fall Detection 12 -- III. SYSTEM OVERVIEW – INTELLIGENT FALL DETECTION SYSTEM 13 -- 1. Kinect 14 -- 2. Architecture 14 -- IV. FALL BEHAVIOR 16 -- 1. Types of Falls 16 -- 2. Skeletal Joints 16 -- 3. Body Shape Features and Motion Sequence 17 -- 3.1 Body Shape Features 17 -- 3.2 Motion Sequence 18 -- V. BEHAVIOR CLASSIFCATION BY MACHINE LEARNING ALGORITHM 18 -- 1. Support Vector Machine 18 -- 2. Double Layer Support Vector Machine for Fall Detection 20 -- VI. EVALUATION 24 -- 1. Visualization of Joint Data 24 -- 2. Accuracy of First Layer of DLSVM 24 -- 3. Performance Evaluation 25 -- VII. RELATED WORK 28 -- VIII. CONCLUSIONS AND FUTURE WORK 31 -- REFERENCES 32 -- 요약문 35 -- Acknowledgement 36 -- Curriculum Vitae 37
Information and Communication Engineering
Related Researcher
  • Author Son, Sang Hyuk RTCPS(Real-Time Cyber-Physical Systems) Lab
  • Research Interests Real-time system; Wireless sensor network; Cyber-physical system; Data and event service; Information security; 실시간 임베디드 시스템
Department of Information and Communication EngineeringThesesMaster

qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.