Contemporary man-machine interfaces are increasingly characterized by multimodality, nonintrusiveness, context-sensitivity, adaptivity, and teleoperability. The implementation of such properties relies on novel techniques in fields such as, e.g., computer vision, speech technology, trainable classifiers, robotics, and virtual reality. This book puts special emphasis on technological aspects of advanced interface implementation. Furthermore, it focuses on interface design and usability. For readers with a background in engineering and computer science, most chapters offer design guidelines and case studies, as well as a description of the functioning and limitations of the algorithms required for implementation. In addition, complementary code examples in C++ are given where appropriate. As a special feature, the book is accompanied by two easy-to-handle software development environments, which offer access to extensive public domain software for computer vision, classification, and virtual reality. These environments also provide real-time access to peripheral components like, e.g., webcams or microphones, enabling hands-on experimentation and testing.

Table of Contents

1 Introduction (Kraiss) 2 Non-intrusive Acquisition of Human Action (Canzler, Zieren) 2.1 Introduction 2.2 Hand Gesture Commands 2.3 Facial expressions commands 2.4 Examples 3 Sign Language Recognition (Bauer, Canzler, Kraiss, Zieren) 3.1 Introduction 3.2 Recognition of Isolated Signs 3.3 Recognition using manual and nonmanual features 3.4 Recognition of continuous sign language using subunits 4 Speech communication and multimodal interfaces (Rigoll) 4.1 Introduction 4.2 Speech recognition 4.3 Speech dialogs 4.4 Multimodal interaction 4.5 Emotions from speech and gesture 4.6 Exercises / Case studies 5 Supervision and Biometric Access (Haehnel, Fillbrandt, Schmidt) 5.1 Introduction 5.2 Tracking People 5.3 Multimodal Person Recognition 5.4 Signature Verification 6 Interacting in virtual and augmented reality (Kuhlen) 6.1 Introduction 6.2 3D User Interfaces: Output 6.3 3D User Interfaces: Input 6.4 Deformable Virtual Objects 6.5 Virtual humanoids, faces, and emotions 6.6 Implementing virtual environments 6.7 Implementing augmented reality 6.8 Case studies 7 Interactive and cooperative robot assistants (Dillmann) 7.1 Introduction 7.2 Advanced robotics hard- and software 7.3 Mobile and humanoid robots 7.4 Teaching and commanding procedures 7.5 Task planning and exception handling 7.6 Intuitive interaction and cooperation 7.7 Telepresence and telerobotics 7.8 Exercises / Case studies 8 Assisted human action (Kraiss) 8.1 Introduction 8.2 Assisted manual control 8.3 Assisted dialog operation 8.4 Case studies APPENDICES A Public domain software environments A.1 LTI-Lib (Computer vision and classification) A.2 VISTA (Virtual and augmented reality) B Test data bases B.1 Head, faces, eye, lip templates B.2 Hand gestures, ambidextrous sign language sequences B.3 Speech templates B.4 Static and dynamic signature templates References CD: Software (Impressario) packages examples