We describe an experimental wearable augmented reality system that enables users to experience hypermedia presentations that are integrated with the actual outdoor locations to which they are are relevant. Our mobile prototype uses a tracked see-through head-worn display to overlay 3D graphics, imagery, and sound on top of the real world, and presents additional, coordinated material on a hand-held pen computer. We have used these facilities to create several situated documentaries that tell the stories of events that took place on our campus. We describe the software and hardware that underly our prototype system and explain the user interface that we have developed for it.

This paper describes what we see as fundamental difficulties in both the pure ubiquitous computing and pure wearable computing paradigms when applied to context-aware applications. In particular, ubiquitous computing and smart room systems tend to have difficulties with privacy and personalization, while wearable systems have trouble with localized information, localized resource control, and resource management between multiple people. These difficulties are discussed, and a peer-to-peer network of wearable and ubiquitous computing components is proposed as a solution. This solution is demonstrated through several implemented applications.

Abstract not found

Small, body-mounted video cameras enable a different style of wearable computing interface. As processing power increases, a wearable computer can spend more time observing its user to provide serendipitous information, manage interruptions and tasks, and predict future needs without being directly commanded by the user. This paper introduces an assistant for playing the real-space game Patrol. This assistant tracks the wearer’s location and current task through computer vision techniques and without off-body infrastructure. In addition, this paper continues augmented reality research, started in 1995, for binding virtual data to physical locations. 1.

I propose a common framework that combines three different paradigms in machine learning: generative, discriminative and imitative learning. A generative probabilistic distribution is a principled way to model many machine learning and machine perception problems. Therein, one provides domain specific knowledge in terms of structure and parameter priors over the joint space of variables. Bayesian networks and Bayesian statistics provide a rich and flexible language for specifying this knowledge and subsequently refining it with data and observations. The final result is a distribution that is a good generator of novel exemplars.

In this paper we present a framework for a navigation system in an indoor environment using only omnidirectional video. Within a Bayesian framework we seek the appropriate place and image from the training data to describe what we currently see and infer a location. The posterior distribution over the state space conditioned on image similarity is typically not Gaussian. The distribution is represented using sampling and the location is predicted and verified over time using the Condensation algorithm. The system does not require complicated feature detection, but uses a simple metric between two images. Even with low resolution input, the system may achieve accurate results with respect to the training data when given favorable initial conditions. 1. Introduction and Previous Work Recognizing location is a difficult but often essential part of identifying a wearable computer user's context. Location sensing may be used to provide mobility aids for the blind [13], spatially-based not...

Abstract not found

Nomadic Radio provides an audio-only wearable interface to unify remote information services such as email, voice mail, hourly news broadcasts, and personal calendar events. These messages are automatically downloaded to a wearable device throughout the day and users can browse them using speech recognition and tactile input. To provide an unobtrusive interface for nomadic users, the audio/text information is presented using a combination of ambient and auditory cues, synthetic speech and spatialized audio. A notification model developed in Nomadic Radio dynamically selects the relevant presentation level for incoming messages based on message priority, user activity and the level of conversation in the environment. Temporal actions of the user such as activating or ignoring messages while listening, reinforce or decay the presentation level over time and change the underlying notification model. Scaleable notification allows incoming messages to be dynamically presented as subtle ambient sounds, distinct VoiceCues, spoken summaries or spatialized audio streams foregrounded for the listener. This thesis addresses techniques for peripheral awareness, spatial listening and contextual notification to manage the user's focus of attention on a wearable audio computing platform.

This technical report provides a brief overview of how human hand gestures can be used in wearable Human Computer Interfaces (HCI).

This paper describes an algorithm to detect and track a hand in each image taken by a wearable camera. We primarily use color information, however, instead of prede ned skin-color models, we dynamically construct hand- and background-color models by using a Gaussian mixture model to approximate the color histogram. Not only to obtain the estimated mean of hand color necessary for the restricted EM algorithm that estimates the GMM but to classify hand pixels based on the Bayes decision theory, we use a spatial probability distribution of hand pixels. Because the static distribution is inadequate for the hand-tracking stage, we translate the distribution with the hand motion based onthe mean shift algorithm. Using the proposed method, we implemented the Hand Mouse, that uses the wearer's hand as a pointing device, on our Wearable Vision System.