This book presents the SIMILAR European research consortium in the field, the work under way and the great challenges posed by the development of the future multimodal interfaces. Lire la suite
Research has for many years concentrated on unimodal systems for human-computer interaction. Now, research systems are combining several input and output modalities, as in talking heads, in-car applications and games using computer vision, voice inpu
ACKNOWLEDGEMENT................................................................... 7
TABLE OF CONTENTS .................................................................... 9
CHAPTER 1: INTRODUCTION..................................................... 19
1.1. SIMILAR.................................................................................. 19
1.2. COMPUTER ASSISTED HUMAN ACTIVITIES ................................ 20
1.2.1. Image-guided surgery ....................................................... 22
1.2.2. Large Information Space visualization ............................. 23
1.2.3. Trans-modality for handicapped persons and car drivers 24
1.2.4. Edutainment ...................................................................... 25
1.3. SIMILAR PLATFORMS AND METHODOLOGY............................ 25
CHAPTER 2: FUSION AND FISSION........................................... 29
2.1. AUTHORS .................................................................................. 29
2.2. INTRODUCTION ......................................................................... 30
2.3. FUSION AND FISSION AT THE SIGNAL LEVEL............................. 31
2.3.1. SP for Human multimodal signals fusion-fission .............. 31
2.3.2. Fusion-fission in medical applications ............................. 33
2.3.3. Towards a Theoretical Framework................................... 35
2.3.4. Multimodal communications and distributed coding........ 36
2.4. FUSION AND FISSION FOR DESIGNING HCI................................ 36
2.4.1. Design of multimodal interaction and Fusion-Fission ..... 37
2.4.2. Context aware fusion and fission ...................................... 40
2.4.3. Fusion and fission in Natural Interaction Systems ........... 41
CHAPTER 3: OPENINTERFACE.................................................. 43
3.1. INTRODUCTION ......................................................................... 43
3.2. STATE OF THE ART: SOFTWARE PLATFORMS ............................ 44
3.2.1. Multimodal data fusion ..................................................... 44
3.2.2. Software Engineering: Component-based platforms ....... 45
3.2.3. Existing platforms/framework ........................................... 46
3.2.4. Conclusions: Component-based platforms........................ 49
3.3. GOALS....................................................................................... 50
3.4. FEATURES ................................................................................. 51
3.5. CONCEPTUAL ARCHITECTURE PROPOSAL ................................. 51
3.6. HOW IT WORKS.......................................................................... 53
3.7. EDITOR...................................................................................... 53
3.8. FUSION AND FISSIONMECHANISMS.......................................... 55
3.9. USERS........................................................................................ 58
3.10. POTENTIAL APPLICATIONS ...................................................... 58
3.11. CONCLUSIONS ......................................................................... 59
3.12. REFERENCES ........................................................................... 59
3.12.1. State-of-the-art ................................................................ 59
3.12.2. OpenInterface.................................................................. 61
CHAPTER 4: MEDICAL APPLICATIONS .................................. 63
4.1. INTRODUCTION ......................................................................... 63
4.2.MEDICAL STUDIO FRAMEWORK ............................................... 64
4.2.1. Platform Architecture........................................................ 64
4.2.2. GENERAL PURPOSE COMPONENTS............................ 67
4.2.3. PROCEDURE-SPECIFIC SCENARIOS........................... 69
4.3. OMICS DATA SUPPORT............................................................ 73
4.4. REFERENCES ............................................................................. 75
CHAPTER 5: BUILDING USABLE MULTIMODAL NIS .......... 77
5.1. INTRODUCTION ......................................................................... 77
5.2. STATE OF THE ART IN BRIEF ..................................................... 79
5.3. THE SIMILAR USABILITY SIG APPROACH.............................. 83
5.3.1. General objectives in brief ................................................ 83
5.3.2. A bottom-up approach....................................................... 85
5.4. APPLICATION DESCRIPTION STRUCTURE.................................. 86
5.4.1. Introduction....................................................................... 87
5.4.2. Application description ..................................................... 87
5.4.3. Technical issues................................................................. 91
5.4.4. Functionality ..................................................................... 94
5.4.5. Interface and usability....................................................... 97
5.4.6. Evaluation ....................................................................... 100
5.4.7. Conclusions..................................................................... 102
5.4.8. References ....................................................................... 103
5.5. NEXT STEPS ............................................................................ 103
5.6. REFERENCES ........................................................................... 105
CHAPTER 6: MULTIMODAL INTERFACES FOR PEOPLE WITH DISABILITIES.... 107
6.1. INTRODUCTION ....................................................................... 107
6.2.MODALITY REPLACEMENT IN MULTIMODAL INTERFACES .... 110
6.2.1. Multimodal Interfaces ..................................................... 110
6.2.2. Modality Replacement..................................................... 110
6.3.MAIN RESEARCH AREAS WITHIN SIMILAR .......................... 112
6.3.1. Haptic Applications for the Blind ................................... 113
6.3.2. Haptic Tool to Access Presentations............................... 113
6.3.3. Virtual Interactive Training Environments for the Blind 117
6.3.4. Sign Language Analysis .................................................. 120
6.3.5. Sign Language Synthesis................................................. 123
6.3.6. Cued Speech Recognition................................................ 125
6.4. THE DREAM SCENARIO............................................................ 126
6.5. CONCLUSIONS......................................................................... 128
6.6. REFERENCES ........................................................................... 129
CHAPTER 7: MIGRATORY MULTIMODAL UI...................... 133
7.1. PROCESS.................................................................................. 134
7.2. ARCHITECTURE....................................................................... 136
7.3. HIIS PROFILE .......................................................................... 138
CHAPTER 8: SIMILAR WORK ’04............................................. 143
1.1 INTEGRATION THROUGH ENTERFACE................................... 144
1.2 INTEGRATION THROUGH EXCHANGES AND TWINNINGS .......... 146
1.3 PUBLIC AWARENESS THROUGH SIMILAR WEBSITE................ 148
1.4 PUBLIC AWARENESS THROUGH THE SIMILAR NEWSLETTER . 149
1.5 PUBLIC AWARENESS THROUGH CONFERENCES........................ 150
1.6 PUBLIC AWARENESS THROUGH BOOKS AND PAPERS ............... 153
1.7 PUBLIC AWARENESS THROUGH BEST SUMMER SCHOOL........ 154
1.8 PUBLIC AWARENESS THROUGH A SOFTWARE CONTEST........... 155
1.9 SIG ON INFORMATION FUSION AND FISSION ............................ 157
Multimodal sources representation in a HCI context ............... 157
1.10 SIG ON USABILITY................................................................. 159
1.11 SIG ON CONTEXT AWARE ADAPTATION................................. 160
1.12 SIG ON MULTIMODAL ANALYSIS AND SYNTHESIS ................. 162
1.13 SIG ON MEDICAL APPLICATIONS............................................ 163
1.14 SIG ON DISABILITY APPLICATIONS ........................................ 164
1.15 SIG ON EDUTAINMENT APPLICATIONS................................... 165
Virtual sculpturing .................................................................... 166
Artistic performance using 3D Body Tracking.......................... 167
Pointing interaction................................................................... 168
Multimodal Speaker Identification............................................ 170
Surveillance and assistance in learning environments ............. 170
1.16 COMMUNICATION BETWEEN PARTNERS................................. 171
1.17 SUBMISSION OF EUROPEAN RESEARCH PROJECTS ................. 173
CHAPTER 9: INTRODUCTION................................................... 177
9.1. THE “10-10-10”....................................................................... 177
9.2. INTERVIEWS ............................................................................ 178
CHAPTER 10: TEN MAJOR ACHIEVEMENTS ....................... 179
10.1. RELIABILITY-ORDERED CASCADE......................................... 179
10.2.MUTUAL INFORMATION IN MULTIMODAL SP........................ 180
10.2.1. Mutual information ....................................................... 180
10.2.2. Mutual information in multimodal signal processing ... 181
10.3.MULTIMODAL EMOTION DETECTION .................................... 182
10.3.1. Introduction................................................................... 182
10.3.2. Achievements................................................................. 183
10.3.3. Future research work .................................................... 184
10.4.MULTIMODAL BIOMETRICS................................................... 184
10.4.1. Introduction................................................................... 184
10.4.2. Different Fusion Strategies ........................................... 185
10.5.MULTIMODAL MEDICAL IMAGE REGISTRATION.................... 188
10.5.1. Image registration ......................................................... 188
10.5.2. Multimodal medical image registration ........................ 189
10.6. ICARE .................................................................................. 190
10.6.1. Introduction: The CARE properties ............................. 190
10.6.2. ICARE: What is it?....................................................... 192
10.6.3. Elementary Components ............................................... 194
10.6.4. Composition Components ............................................. 195
10.6.5. ICARE Platform ............................................................ 197
10.7. CAMELEON............................................................................ 199
10.8.MODALITY THEORY.............................................................. 202
10.8.1. MULTIMODALITY ....................................................... 206
10.9. USIXML................................................................................ 208
10.10. AMODEUS MODEL FOR DIALOGUE CONTROLLER............. 211
10.11. REFERENCES ....................................................................... 213
Reliability ordered cascade....................................................... 213
Multimodal emotion detection (prosody + facial) .................... 214
Mutual information in multimodal SP....................................... 214
Multimodal biometrics .............................................................. 214
Multimodal medical image registration.................................... 214
ICARE ....................................................................................... 214
CAMELEON.............................................................................. 215
Modality theory ......................................................................... 216
UsiXML ..................................................................................... 216
AMODEUS................................................................................ 216
CHAPTER 11: 10 MAJOR PRACTICAL OUTCOMES............ 217
11.1. IMMERSIVE ENVIRONMENT................................................... 217
11.1.1. Introduction................................................................... 217
11.1.2. The CAVE...................................................................... 218
11.1.3. Other immersive platforms............................................ 218
11.2. AIRPLANE COCKPIT............................................................... 219
11.3. CAR APPLICATION................................................................. 220
11.4. VTK-ITK MULTIMODAL MEDICAL IMAGING PLATFORMS.... 221
11.4.1. The Visualization ToolKit (VTK) .................................. 221
11.4.2. The Segmentation & Registration ToolKit (ITK) .......... 222
11.4.3. Multimodal platforms.................................................... 224
11.5. AUGMENTED REALITY IN SURGERY...................................... 226
11.5.1. Augmented reality ......................................................... 226
11.5.2. AR and surgery................. ............................................ 226
11.6.MULTIMODAL MOBILE AUGMENTED REALITY...................... 227
11.6.1. Definition....................................................................... 227
11.6.2. Applications................................................................... 228
11.7. NICE DEMO........................................................................... 229
11.7.1. The NICE Project .......................................................... 230
11.7.2. The Multimodal Scenario .............................................. 230
11.8. FAME: CONTEXT-AWARE DISTRIBUTED USER INTERFACES 232
11.8.1. What is it?...................................................................... 232
11.8.2. How does it work?......................................................... 232
11.8.3. What is it used for?........................................................ 233
11.9. CONCURTASKTREES............................................................. 234
11.9.1. What is it?...................................................................... 234
11.9.2. Applications................................................................... 236
11.10. GRAFIXML......................................................................... 237
11.11. REFERENCES ....................................................................... 238
Immersive environment ............................................................. 238
Airplane cockpit ........................................................................ 238
Car applications........................................................................ 239
VTK-ITK platforms for 3D multimodal medical imaging ......... 239
Augmented reality in surgical operating theatres ..................... 239
Multimodal mobile augmented reality ...................................... 239
NICE demo ................................................................................ 240
FAME........................................................................................ 240
ConcurTaskTree ........................................................................ 240
GrafiXML .................................................................................. 240
CHAPTER 12: 10 MAJOR CHALLENGES ................................ 241
12.1. SOCIAL INTERACTIONS.......................................................... 241
12.2. SOFTWARE ARCHITECTURE REFERENCE MODEL .................. 242
12.3.MIX OF ARCHITECTURAL STYLES.......................................... 243
12.4. SOFTWARE COMPONENT DESCRIPTION ................................. 243
12.5. POLYMORPHIC USER INTERFACES......................................... 243
12.6. GENERICNESS OF MODEL, METHODS, AND TOOLS................. 243
12.7. SCALABILITY......................................................................... 244
12.8. REFERENCE GLOSSARY......................................................... 244
12.9. GENERIC CONTACTLESS MULTIMODAL INTERFACES ............ 246
12.10. SECURITY/PRIVACY IN CONTEXT-SENSITIVE MULTIMODAL APPLICATIONS.......... 246
12.11. REFERENCES ....................................................................... 247
CHAPTER 13: INTERVIEWING ................................................. 249
13.1. QUESTIONNAIRE ................................................................... 249
13.2. INDUSTRY ............................................................................. 250
13.2.1. Xavier Marichal (Alterface, Belgium)........................... 250
13.2.2. Frederic Kaplan (Sony, France) ................................... 252
13.2.3. Stéphane Chatty and Stéphane Sire (Intuilab, France). 253
13.2.4. Robin Springer (Computer Talk, USA) ......................... 261
13.3. ACADEMICS .......................................................................... 269
13.3.1. Human-Computer Interaction....................................... 269
13.3.2. Context-aware adaptation............................................. 273
13.3.3. Usability ........................................................................ 275
13.3.4. Information fusion & fission ......................................... 285
13.3.5. Edutainment .................................................................. 298
13.3.6. Medical.......................................................................... 304
GLOSSARY ..................................................................................... 313
FLAGS. ........................................................................................... 313
TERMS AND DEFINITIONS............................................................... 313
REFERENCES.................................................................................. 346