A first step towards a n understanding of the semantic content in a video is the reliable detection and recognition of actions performed by objects. This is a dificult problem due t o the enormous vaeability in a n action's appearance when seen from different viewpoints and/or at different times. In this paper we address the recognition of actions by taking a novel approach that models actions as special types of 3d objects. Specifically, we observe that any action can be represented as a generalized cylinder, called the action cylinder. Reliable recognition is achieved by recovering the viewpoint transformation between reference (model) and given action cylinders. A set of 8 corresponding points from time-wise corresponding cross-sections is shown t o be suficient t o align the two cylinders under perspective projection. A surprising conclusion from visualizing actions as objects i s that rigid, articulated, and nonrigid actions can all be modeled an a uniform framework.

An essential component in the ubiquitous computing vision is the ability of detecting with which objects the user is interacting during his or her activities. We explore in this paper a solution to this problem based on wireless motion and orientation sensors (accelerometer and compass) worn by the user and attached to objects. We evaluate the performance in realistic conditions, characterized by limited hardware resources, measurement noise due to motion artifacts and unreliable wireless communication. We describe the complete solution, from the theoretical design, going through simulation and tuning, to the full implementation and testing on wireless sensor nodes. The implementation on sensor nodes is lightweight, with low communication bandwidth and processing needs. Compared to existing work, our approach achieves better performance (higher detection accuracy and faster response times), while being much more computationally efficient. The potential of the concept is further illustrated by means of an interactive multi-user game. We also provide a thorough discussion of the advantages, limitations and trade-offs of the proposed solution.

No abstract

In this paper, we present a method for automatic, online detection of a user's interaction with objects. This represents an essential building block for improving the performance of distributed activity recognition systems. Our method is based on correlating features extracted from motion sensors worn by the user and attached to objects. We present a complete implementation of the idea, using miniaturized wireless sensor nodes equipped with motion sensors. We achieve a recognition accuracy of 97% for a target response time of 2 seconds. The implementation is lightweight, with low communication bandwidth and processing needs. We illustrate the potential of the concept by means of an interactive multi-user game.

No abstract