Studying vision-based multiple-user interaction with in-home large displays

ABSTRACT

Large displays at home such as TVs are becoming larger in size and more interactive in functionality. When multiple co-located users share the screen space of a large display, when, where and how to display their media contents becomes an issue. This paper compares the use of automatic versus manual methods for managing personal screen real-estate on large in-home displays. We assume horizontally laid out "personal interaction spaces" as the user interface for multiple users to manage their screen real-estate. In this case, users need to sign in and out as well as have their personal spaces placed on the display. We constructed a computer-vision based system that tracks the identities and positions of multiple people in front of the display to support the user studies that compare the use of tracker-based mechanisms versus manual ones for managing the display. Our results suggest that the tracking system shows promise for a) simplifying the user registration process in conjunction with a manual sign-in/out process and b) effective tracker-based user-centric placement of people's interaction space. Proper integration of manual methods could improve the sense of control and ownership for users.

REFERENCES

• 1: Arksey, N. 2007. Exploring the Design Space for Concurrent Use of Personal and Large Displays for In-home Collaboration. Master Thesis. The University of British Columbia, Canada.
• 2: Keni Bernardin , Rainer Stiefelhagen, Audio-visual multi-person tracking and identification for smart environments, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291388]
• 3: Burton, M., Jenkins, R., Hancock, P., and White. D. 2005. Robust representations for face recognition: The power of averages. Cognitive Psychology, Volume 51, Issue 3, November 2005, Pages 256--284.
• 4: Shahram Izadi , Harry Brignull , Tom Rodden , Yvonne Rogers , Mia Underwood, Dynamo: a public interactive surface supporting the cooperative sharing and exchange of media, Proceedings of the 16th annual ACM symposium on User interface software and technology, p.159-168, November 02-05, 2003, Vancouver, Canada [doi>10.1145/964696.964714]
• 5: Jiang, H., Fels, S., and Little, J. 2007. A Linear Programming Approach for Multiple Object Tracking. IEEE Conference on Computer Vision and Pattern Recognition 2007 (CVPR'07).
• 6: Edward Tse , Jonathan Histon , Stacey D. Scott , Saul Greenberg, Avoiding interference: how people use spatial separation and partitioning in SDG workspaces, Proceedings of the 2004 ACM conference on Computer supported cooperative work, November 06-10, 2004, Chicago, Illinois, USA [doi>10.1145/1031607.1031647]
• 7: Viola, P., and Jones, M. Rapid Object Detection using a Boosted Cascade of Simple Features. 2001. IEEE Conference on Computer Vision and Pattern Recognition 2001. (CVPR'01).
• 8: Daniel Vogel , Ravin Balakrishnan, Interactive public ambient displays: transitioning from implicit to explicit, public to personal, interaction with multiple users, Proceedings of the 17th annual ACM symposium on User interface software and technology, October 24-27, 2004, Santa Fe, NM, USA [doi>10.1145/1029632.1029656]
• 9: Adam Williams , Deepak Ganesan , Allen Hanson, Aging in place: fall detection and localization in a distributed smart camera network, Proceedings of the 15th international conference on Multimedia, September 25-29, 2007, Augsburg, Germany [doi>10.1145/1291233.1291435]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.9 Applications

General Terms:
Algorithms, Design, Human Factors

Keywords:
interactive large display, multi-user, screen real-estate management, tracking