Publications
Detailed Information
Operation of an Intelligent Space with Heterogeneous Sensors : 이종 센서들을 이용한 지능형 공간의 운용
DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 이범희 | - |
dc.contributor.author | Doojin Kim | - |
dc.date.accessioned | 2017-07-13T07:06:19Z | - |
dc.date.available | 2017-07-13T07:06:19Z | - |
dc.date.issued | 2014-08 | - |
dc.identifier.other | 000000021843 | - |
dc.identifier.uri | https://hdl.handle.net/10371/119039 | - |
dc.description | 학위논문 (박사)-- 서울대학교 대학원 : 전기·컴퓨터공학부, 2014. 8. 이범희. | - |
dc.description.abstract | A new approach of multi-sensor operation is presented in an intelligent space, which is based on heterogeneous multiple vision sensors and robots mounted with an infrared (IR) sensor. The intelligent space system is a system that exists in task space of robots, helps missions of the robots, and can self-control the robots in a particular situation. The conventional intelligent space consists of solely static cameras. However, the adoption of multiple heterogeneous sensors and an operation technique for the sensors are required in order to extend the ability of intelligent space.
First, this dissertation presents the sub-systems for each sensor group in the proposed intelligent space. The vision sensors consist of two groups: static (fixed) cameras and dynamic (pan-tilt) cameras. Each sub-system can detect and track the robots. The sub-system using static cameras localize the robot within a high degree of accuracy. In this system, a handoff method is proposed using the world-to-pixel transformation in order to interwork among the multiple static cameras. The sub-system using dynamic cameras is designed to have various views without losing the robot in view. In this system, a handoff method is proposed using the predictive positions of the robot, relationship among cameras, and relationship between the robot and the camera in order to interwork among the multiple dynamic cameras. The robots system localizes itself using an IR sensor and IR tags. The IR sensor can localize the robot even if illumination of the environment is low. For robust tracking, a sensor selection method is proposed using the advantages of these sensors under environmental change of the task space. For the selection method, we define interface protocol among the sub-systems, sensor priority, and selection criteria. The proposed method is adequate for a real-time system, which has a low computational cost than sensor fusion methods. Performance of each sensor group is verified through various experiments. In addition, multi-sensor operation using the proposed sensor selection method is experimentally verified in the environment with an occlusion and low-illumination setting. | - |
dc.description.tableofcontents | Abstracts i
Contents iii List of Figures vii List of Tables xv Chapter 1 Introduction 1 1.1 Background and Motivation 1 1.2 Related Work 4 1.3 Contributions 7 1.4 Organization 10 Chapter 2 Overview of Intelligent Space 11 2.1 Original Concept of Intelligent Space 11 2.2 Related Research 13 2.3 Problem Statement and Objective 16 Chpater 3 Architecture of a Proposed Intelligent Space 18 3.1 Hardware Architecture 19 3.2.1 Metallic Structure 20 3.2.2 Static Cameras 22 3.2.3 Dynamic Cameras 24 3.2.4 Infrared (IR) Camera and Passive IR Tags 27 3.2.5 Mobile Robots 28 3.2 Software Architecture 31 Chpater 4 Localization and Tracking of Mobile Robots in a Proposed Intelligent Space 36 4.1 Localization and Tracking with an IR Sensor Mounted on Robots 36 4.1.1 Deployment of IR Tags 36 4.1.2 Localization and Tracking Using an IR Sensor 38 4.2 Localization and Tracking with Multiple Dynamic Cameras 41 4.2.1 Localization and Tracking based on the Geometry between a Robot and a Single Dynamic Camera 41 4.2.2 Proposed Predictive Handoff among Dynamic Cameras 45 4.3 Localization and Tracking with Multiple Static Cameras 53 4.3.1 Preprocess for Static Cameras 53 4.3.2 Marker-based Localization and Tracking of Multiple Robots 58 4.3.3 Proposed Reprojection-based Handoff among Static Cameras 67 Chpater 5 Operation with Heterogeneous Sensor Groups 72 5.1 Interface Protocol among Sensor Groups 72 5.2 Sensor Selection for an Operation Using Heterogeneous Sensors 84 5.3 Proposed Operation with Static Cameras and Dynamic cameras 87 5.4 Proposed Operation with the iSpace and Robots 90 Chapter 6 Experimental Results 94 6.1 Experimental Setup 94 6.2 Experimental Results of Localization 95 6.2.1 Results using Static Cameras and Dynamic Cameras 95 6.2.2 Results using the IR Sensor 102 6.3 Experimental Results of Tracking 104 6.3.1 Results using Static and Dynamic Cameras 104 6.3.2 Results using the IR Sensor 108 6.4 Experimental Results using Heterogeneous Sensors 111 6.4.1 Results in Environment with Occlusion 111 6.4.2 Results in Low-illumination Environment 115 6.5 Discussion 118 Chapter 7 Conclusions 120 Bibliography 125 | - |
dc.format | application/pdf | - |
dc.format.extent | 17441391 bytes | - |
dc.format.medium | application/pdf | - |
dc.language.iso | en | - |
dc.publisher | 서울대학교 대학원 | - |
dc.subject | intelligent space | - |
dc.subject | sensor selection | - |
dc.subject | heterogeneous sensors | - |
dc.subject | camera handoff | - |
dc.subject | multiple camera tracking | - |
dc.subject.ddc | 621 | - |
dc.title | Operation of an Intelligent Space with Heterogeneous Sensors | - |
dc.title.alternative | 이종 센서들을 이용한 지능형 공간의 운용 | - |
dc.type | Thesis | - |
dc.contributor.AlternativeAuthor | 김두진 | - |
dc.description.degree | Doctor | - |
dc.citation.pages | xvii, 137 | - |
dc.contributor.affiliation | 공과대학 전기·컴퓨터공학부 | - |
dc.date.awarded | 2014-08 | - |
- Appears in Collections:
- Files in This Item:
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.