DOVE: Drawing over Video to Support Remote Collaboration
Speaker
Susan Fussell and Jie Yang
Senior System Scientists, Human-Computer Interaction Institute, Carnegie Mellon University
When
-
Where
Newell-Simon Hall 1305 (Michael Mauldin Auditorium)
Description
Collaboration on physical tasks in the 3D world is an essential component of work in a variety of domains, including medicine, education, and industry. Surgical teams, for example, work together on a patient using a variety of medical implements and machinery. In such work, a shared view of the physical environment of the activity is essential for task coordination and performance. In this talk, we describe our work on technologies aimed to support remote collaboration on physical tasks. Our goal is to enable remote collaborators to share views of the task environment and to communicate about task objects and locations as easily as they can do so when co-located.
In the first section of this talk, we review earlier research on the use of task-oriented video conferencing systems to support remote collaboration on physical tasks. In task-oriented video systems, the camera(s) are pointed towards the work environment, rather than towards partners’ faces. We highlight one finding of this earlier work—the asynchrony of partners’ ability to point to objects in a shared visual space. With video systems alone, remote partners find it difficult to point at objects and locations in the work space. We then consider ways in which pointing and other gestures can be incorporated into video systems for remote collaboration. We show the limitations of a simple cursor-based pointing system and describe the DOVE (Drawing Over Video Environment) tool. DOVE allows remote collaborators to point and make other gestures and sketches overlaid on a live video feed from the work environment. As we will show, DOVE improves task performance significantly over a video-only system. DOVE also contains a gesture recognition component that can be used for remote camera manipulation. Taken together, the studies highlight the importance of supporting gesture in systems for remote collaboration on physical tasks and demonstrate the feasibility of inexpensive systems such as DOVE for providing gesture support.
Speaker's Bio
Susan R. Fussell is a Senior System Scientist in the Human-Computer Interaction Institute at Carnegie Mellon University. She received her Ph.D. in social psychology from Columbia University in 1990. Dr. Fussell’s primary interests are in the areas of computer-supported cooperative work and computer-mediated communication. Her current projects include developing video systems to support remote collaboration, understanding and supporting large scale collaboration across multiple teams and projects, devising metrics to evaluate the health benefits of online support chatrooms, and studies of shared mental models in work groups. She is the editor of two books, The Verbal Communication of Emotions: Interdisciplinary Perspectives (Erlbaum, 2002), and, with Roger Kreuz, Social and Cognitive Approaches to Interpersonal Communication (Erlbaum, 1998).
Jie Yang is a Senior System Scientist in the Human-Computer Interaction Institute at Carnegie Mellon University. He joined Interactive Systems Lab in 1994, where he has been leading research efforts to develop visual tracking and recognition technologies for improving human-computer interaction and enhancing human-human communication. He has involved developments of many multimodal systems in both intelligent working spaces and mobile platforms, such as gaze-based interface, lipreading system, image-based multimodal translation agent, multimodal people ID, and automatic sign translation systems. His current projects include developing technologies to robustly track people in a dynamic environment, to understand human activities in a nurse, to support remote collaboration, understanding and supporting large scale collaboration across multiple teams and projects, and to automatic extract text from nature scenes.