| Preface | p. vii |
| List of Contributors | p. xv |
| Intelligent Environments: Methods, Algorithms and Applications | p. 1 |
| Intelligent Environments | p. 1 |
| What Is An Intelligent Environment? | p. 2 |
| How Is An Intelligent Environment Built? | p. 2 |
| Technology for Intelligent Environments | p. 2 |
| Research Projects | p. 4 |
| Private Spaces | p. 4 |
| Public Spaces | p. 5 |
| Middleware | p. 7 |
| Chapter Themes in This Collection | p. 8 |
| Conclusion | p. 9 |
| References | p. 10 |
| A Pervasive Sensor System for Evidence-Based Nursing Care Support | p. 13 |
| Introduction | p. 13 |
| Evidence-Based Nursing Care Support | p. 14 |
| Background of the Project | p. 14 |
| Concept of Evidence-Based Nursing Care Support | p. 15 |
| Initial Goal of the Project: Falls Prevention | p. 16 |
| Second Goal of the Project: Obtaining ADL of Inhabitants | p. 17 |
| Related Work | p. 18 |
| Overview and Implementations of the System | p. 19 |
| Overview of the Evidence-Based Nursing Care Support System | p. 19 |
| System Implementations | p. 20 |
| Experiments and Analyses | p. 24 |
| Tracking a Wheelchair for Falls Prevention | p. 24 |
| Activity Transition Diagram: Transition of Activities in One Day | p. 25 |
| Quantitative Evaluation of Daily Activities | p. 26 |
| Probability of "Toilet" Activity | p. 28 |
| Discussion of the Experimental Results | p. 29 |
| Prospect of the Evidence-Based Nursing Care Support System | p. 30 |
| Conclusions | p. 31 |
| References | p. 32 |
| Anomalous Behavior Detection: Supporting Independent Living | p. 35 |
| Introduction | p. 35 |
| Related work | p. 36 |
| Methodology | p. 37 |
| Unsupervised Classification Techniques | p. 37 |
| Using HMM to Model Behavior | p. 38 |
| Experimental Setup and Data Collection | p. 39 |
| Noisy Data: Sources of Error | p. 40 |
| Learning activities | p. 40 |
| Experimental Results | p. 41 |
| Instance Class Annotation | p. 41 |
| Data Preprocessing | p. 41 |
| Models: Unsupervised Classification: Clustering and Allocation of Activities to Clusters | p. 43 |
| Behaviors: Discovering Patterns in Activities | p. 45 |
| Behaviors: Discovering Anomalous Patterns of Activity | p. 46 |
| Discussion | p. 48 |
| Conclusions | p. 49 |
| References | p. 49 |
| Sequential Pattern Mining for Cooking-Support Robot | p. 51 |
| Introduction | p. 51 |
| System Design | p. 53 |
| Inference from Series of Human Actions | p. 53 |
| Time Sequence Data Mining | p. 54 |
| Human Behavior Inference Algorithm | p. 54 |
| Activity Support of Human | p. 57 |
| Implementation | p. 59 |
| IC Tag System | p. 59 |
| Inference of Human's Next Action | p. 60 |
| Cooking Support Interface | p. 61 |
| Experimental Results | p. 63 |
| Conclusions | p. 65 |
| References | p. 66 |
| Robotic, Sensory and Problem-Solving Ingredients for the Future Home | p. 69 |
| Introduction | p. 69 |
| Components of the Multiagent System | p. 70 |
| The Robotic Platform Mobility Subsystem | p. 71 |
| The Interaction Manager | p. 73 |
| Environmental Sensors for People Tracking and Posture Recognition | p. 74 |
| Monitoring Activities of Daily Living | p. 76 |
| Schedule Representation and Execution Monitoring | p. 77 |
| Constraint Management in the RoboCare Context | p. 78 |
| From Constraint Violations to Verbal Interaction | p. 81 |
| Multiagent Coordination Infrastructure | p. 82 |
| Casting the MAC Problem to DCOP | p. 83 |
| Cooperatively Solving the MAC Problem | p. 86 |
| Conclusions | p. 87 |
| References | p. 88 |
| Ubiquitous Stereo Vision for Human Sensing | p. 91 |
| Introduction | p. 91 |
| Ubiquitous Stereo Vision | p. 93 |
| Concept of Ubiquitous Stereo Vision | p. 93 |
| Server-Client Model for USV | p. 93 |
| Real Utilization Cases | p. 94 |
| Hierarchical Utilization of 3D Data and Personal Recognition | p. 95 |
| Acquisition of 3D Range Information | p. 95 |
| Projection to Floor Plane | p. 96 |
| Recognition of Multiple Persons and Interface | p. 98 |
| Pose Recognition for Multiple People | p. 99 |
| Personal Identification | p. 100 |
| Interface for Space Control | p. 101 |
| Human Monitoring in Open Space (Safety Management Application) | p. 101 |
| Monitoring Railroad Crossing | p. 101 |
| Station Platform Edge Safety Management | p. 103 |
| Monitoring Huge Space | p. 104 |
| Conclusion and Future Work | p. 105 |
| References | p. 106 |
| Augmenting Professional Training, an Ambient Intelligence Approach | p. 109 |
| Introduction | p. 109 |
| Color Tracking of People | p. 112 |
| Counting People by Spatial Relationship Analysis | p. 113 |
| Simple People Counting Algorithm | p. 113 |
| Graphs of Blobs | p. 114 |
| Estimation of Distance Between Blobs | p. 116 |
| Temporal Pyramid for Distance Estimation | p. 117 |
| Probabilistic Estimation of Groupings | p. 119 |
| Grouping Blobs | p. 120 |
| Experimental Results | p. 121 |
| Conclusions | p. 124 |
| References | p. 124 |
| Stereo Omnidirectional System (SOS) and Its Applications | p. 127 |
| Introduction | p. 127 |
| System Configuration | p. 128 |
| Image integration | p. 131 |
| Generation of Stable Images at Arbitrary Rotation | p. 133 |
| An example Application: Intelligent Electric Wheelchair | p. 136 |
| Overview | p. 136 |
| System Configuration | p. 136 |
| Obstacle Detection | p. 138 |
| Gesture / Posture Detection | p. 140 |
| Conclusions | p. 140 |
| References | p. 140 |
| Video Analysis for Ambient Intelligence in Urban Environments | p. 143 |
| Introduction | p. 143 |
| Visual Data for Urban AmI | p. 144 |
| Video Surveillance in Urban Environment | p. 145 |
| The LAICA Project | p. 148 |
| Automatic Video Processing for People Tracking | p. 149 |
| People Detection and Tracking from Single Static Camera | p. 150 |
| People Detection and Tracking from Distributed Cameras | p. 152 |
| People Detection and Tracking from Moving Cameras | p. 154 |
| Privacy and Ethical Issues | p. 155 |
| References | p. 157 |
| From Monomodal to Multimodal: Affect Recognition Using Visual Modalities | p. 161 |
| Introduction | p. 161 |
| Organization of the Chapter | p. 163 |
| From Monomodal to Multimodal: Changes and Challenges | p. 164 |
| Background Research | p. 164 |
| Data Collection | p. 168 |
| Data Annotation | p. 169 |
| Synchrony/Asynchrony Between Modalities | p. 171 |
| Data Integration/Fusion | p. 172 |
| Information Complementarity/Redundancy | p. 174 |
| Information Content of Modalities | p. 176 |
| Monomodal Systems Recognizing Affective Face or Body Movement | p. 177 |
| Multimodal Systems Recognizing Affect from Face and Body Movement | p. 179 |
| Project 1: Multimodal Affect Analysis for Future Cars | p. 179 |
| Project 2: Emotion Analysis in Man-Machine Interaction Systems | p. 182 |
| Project 3: Multimodal Affect Recognition in Learning Environments | p. 183 |
| Project 4: FABO-Fusing Face and Body Gestures for Bimodal Emotion Recognition | p. 184 |
| Multimodal Affect Systems: The Future | p. 185 |
| References | p. 187 |
| Importance of Vision in Human-Robot Communication: Understanding Speech Using Robot Vision and Demonstrating Proper Actions to Human Vision | p. 191 |
| Introduction | p. 191 |
| Understanding Simplified Utterances Using Robot Vision | p. 193 |
| Inexplicit Utterances | p. 193 |
| Information Obtained by Vision | p. 194 |
| Language Processing | p. 195 |
| Vision Processing | p. 195 |
| Synchronization Between Speech and Vision | p. 197 |
| Experiments | p. 199 |
| Communicative Head Gestures for Museum Guide Robots | p. 200 |
| Observations from Guide-Visitor Interaction | p. 201 |
| Prototype Museum Guide Robot | p. 203 |
| Experiments at a Museum | p. 206 |
| Conclusion | p. 208 |
| References | p. 209 |
| Index | p. 211 |
| Table of Contents provided by Ingram. All Rights Reserved. |