• Document: The Smart Floor: A Mechanism for Natural User Identification and Tracking
  • Size: 94.14 KB
  • Uploaded: 2019-03-24 08:41:21
  • Status: Successfully converted

Some snippets from your converted document:

The Smart Floor: A Mechanism for Natural User Identification and Tracking Robert J. Orr and Gregory D. Abowd Graphics, Visualization, and Usability (GVU) Center Georgia Institute of Technology Atlanta, GA 30332-0280 USA +1 404 894 5103 {rjo, abowd}@cc.gatech.edu ABSTRACT the identity and location of Mary is an important piece of We have created a system for identifying people based on information. Furthermore, if the system cannot their footstep force profiles and have tested its accuracy transparently track and identify users, they will be much against a large pool of footstep data. This floor system less likely to use the system, and the services the system may be used to transparently identify users in their offers will be much less likely to be successful. On the everyday living and working environments. We have other hand, if the system is transparent enough, the ability created user footstep models based on footstep profile to track frequently lost objects may be a compelling features and have been able to achieve a recognition rate of enough service that users are willing to be tracked and 93% using this feature-based approach. We have also identified, and willing to have that information made shown that the effect of footwear is negligible on available to a small group of people within the house. recognition accuracy. However, most identification methods to date have not Keywords been especially transparent. The Active Badge system [16] Interaction technology, ubiquitous computing, tactile I/O, is one of the most widely used systems and illustrates some user identification, biometrics, indoor positioning, of the problems with many identification schemes. (Radio intelligent home environments, intelligent systems. frequency identification systems, or RFID, have many of the same features and problems.) First and foremost, the INTRODUCTION user must carry a badge or tag in order to be identified. Transparent user identification has in recent years become While this can be a feature at times--if the user desires a goal of computer science researchers. With the advent of privacy, all she does is remove the badge--it can be an ubiquitous computing [17] and smart environments, impediment to use and also narrowly defines the transparent user identification has become an even more environments in which the system can be used. For pressing goal than before the rise of these paradigms. If a example, the Active Badge system is not particularly computer or environment could transparently identify the amenable to use in a smart house: users will not wear the user, it could customize its interface and behavior to match badge while sleeping (in order, for example, that the house the preferences, history, and context of that particular user. can identify them when they arise to use the facilities in Computers could become easier to use, and could the middle of the night), or while doing work in the yard. themselves become more transparent overall. But the They must remember to put it on when they arise or come system must provide a service or services of enough value back into the house. In addition, adding new users, such that the user will tolerate the additional technology, no as frequent visitors, requires another physical badge or tag. matter how transparent it may be. Finally, badge systems only provide gross positioning. For example, many users may appreciate a system that The best badge-based indoor positioning system to date tracks certain objects around their living spaces for them. [18] only has a resolution of 6 feet. In many cases, we will Frequently lost objects, such as keys, wallets, and glasses, want to know the position of a user to a finer resolution. could be tagged with small radio frequency ID tags, and There has also been much work recently that has focused their location could be correlated with the location of on more passive forms of user recognition, such as face people in the house [8]. As an example, if Mary were to recognition using video and voice recognition using audio. walk out of the house with a set of keys and Joe needed to These types of recognition do not require that the user locate the keys some time later, the system could inform carry any

Recently converted files (publicly available):