ReflectiveSigns: Digital Signs That Adapt to Audience Attention

Authors:
Jörg Müller;Juliane Exeler;Markus Buzeck;Antonio Krüger
Affiliations:
University of Münster, Münster, Germany;University of Münster, Münster, Germany;University of Münster, Münster, Germany;University of Münster, Münster, Germany
Venue:
Pervasive '09 Proceedings of the 7th International Conference on Pervasive Computing
Year:
2009

Citing 8
Cited 12

Machine Learning

Machine Learning
UniCast, OutCast & GroupCast: Three Steps Toward Ubiquitous, Peripheral Displays

UbiComp '01 Proceedings of the 3rd international conference on Ubiquitous Computing
Vision for a smart kiosk

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
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
Overcoming Assumptions and Uncovering Practices: When Does the Public Really Look at Public Displays?

Pervasive '08 Proceedings of the 6th International Conference on Pervasive Computing
Auction Mechanisms for Efficient Advertisement Selection on Public Displays

Proceedings of the 2006 conference on ECAI 2006: 17th European Conference on Artificial Intelligence August 29 -- September 1, 2006, Riva del Garda, Italy
Face detection and tracking in video sequences using the modifiedcensus transformation

Image and Vision Computing
Situated public news and reminder displays

AmI'07 Proceedings of the 2007 European conference on Ambient intelligence

MobiDiC: Context Adaptive Digital Signage with Coupons

AmI '09 Proceedings of the European Conference on Ambient Intelligence
TwitterSigns: microblogging on the walls

Proceedings of the international conference on Multimedia
Requirements and design space for interactive public displays

Proceedings of the international conference on Multimedia
Audience behavior around large interactive cylindrical screens

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Context-aware web search in ubiquitous sensor environments

ACM Transactions on Internet Technology (TOIT)
Digifieds: insights into deploying digital public notice areas in the wild

Proceedings of the 10th International Conference on Mobile and Ubiquitous Multimedia
How to evaluate public displays

Proceedings of the 2012 International Symposium on Pervasive Displays
Increasing brand attractiveness and sales through social media comments on public displays --- evidence from a field experiment in the retail industry

Pervasive'12 Proceedings of the 10th international conference on Pervasive Computing
Beyond the channel: A literature review on ambient displays for learning

Computers & Education
Yarely: a software player for open pervasive display networks

Proceedings of the 2nd ACM International Symposium on Pervasive Displays
A Bio-chemical Approach to Awareness in Pervasive Systems

Proceedings of First International Workshop on Sensing and Big Data Mining
Convergence of interactive displays with smart mobile devices for effective advertising: A survey

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents ReflectiveSigns, i.e. digital signage (public electronic displays) that automatically learns the audience preferences for certain content in different contexts and presents content accordingly. Initially, content (videos, images and news) are presented in a random manner. Using cameras installed on the signs, the system observes the audience and detects if someone is watching the content (via face detection). The anonymous view time duration is then stored in a central database, together with date, time and sign location. When scheduling content, the signs calculate the expected view time for each content type depending on sign location and time using a Naive Bayes classifier. Content is then selected randomly, with the probability for each content weighted by the expected view time. The system has been deployed for two months on four digital signs in a university setting using semi-realistic content & content types. We present a first evaluation of this approach that concentrates on major effects and results from interviews with 15 users.