Abstract
In this paper we present the development of an interactive, content-aware and cost-effective digital signage system. Using a monocular camera installed within the frame of a digital signage display, we employ real-time computer vision algorithms to extract temporal, spatial and demographic features of the observers, which are further used for observer-specific broadcasting of digital signage content. The number of observers is obtained by the Viola and Jones face detection algorithm, whilst facial images are registered using multi-view Active Appearance Models. The distance of the observers from the system is estimated from the interpupillary distance of registered faces. Demographic features, including gender and age group, are determined using SVM classifiers to achieve individual observer-specific selection and adaption of the digital signage broadcasting content. The developed system was evaluated at the laboratory study level and in a field study performed for audience measurement research. Comparison of our monocular localization module with the Kinect stereo-system reveals a comparable level of accuracy. The facial characterization module is evaluated on the FERET database with 95% accuracy for gender classification and 92% for age group. Finally, the field study demonstrates the applicability of the developed system in real-life environments.
Highlights
Digital signage flat‐panel displays are emerging as a new, efficient method for providing targeted information [1,2]
The outline of the paper is as follows: Section 2 presents the architecture of our interactive and audience adaptive digital signage system, Section 3 evaluates the performance of the system in a laboratory setting, Section 4 describes the use of the system in a real‐world audience measurement study and Section 5 gives a discussion and conclusions
Module 3 performance: Content‐aware broadcasting was tested in a laboratory field study with a limited group of selected observers, which offered a more controlled environment, i.e. observers, locations and demographics were controlled in the testing of the developed modules, which are the main focus of this paper
Summary
Digital signage flat‐panel displays are emerging as a new, efficient method for providing targeted information [1,2] They are found in airports, hotels, universities, retail stores and various outdoor public spaces (Figure 1), all providing optimized information‐and‐appearance attractive multimedia content. To make digital signage a more effective information interface, the displayed content should be informative, dynamic and attractive [11] Such interactive audience adaptive digital signage systems have the potential to be applied to a large number of displays. The hardware cost of a single display is important as well as the cost of software solutions, especially the use of algorithms without copyright limitations These considerations were our main motivation for using a monocular camera in our system for the interaction of the system with the observers, as it is very frequently already built into the frame of flat digital displays. The outline of the paper is as follows: Section 2 presents the architecture of our interactive and audience adaptive digital signage system, Section 3 evaluates the performance of the system in a laboratory setting, Section 4 describes the use of the system in a real‐world audience measurement study and Section 5 gives a discussion and conclusions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have