Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
Authors:
- 13 December 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 44-51
Abstract
In this paper we present results related to achieving finegrained activity recognition for context-aware computing applications. We examine the advantages and challenges of reasoning with globally unique object instances detected by an RFID glove. We present a sequence of increasingly powerful probabilistic graphical models for activity recognition. We show the advantages of adding additional complexity and conclude with a model that can reason tractably about aggregated object instances and gracefully generalizes from object instances to their classes by using abstraction smoothing. We apply these models to data collected from a morning household routine.Keywords
This publication has 13 references indexed in Scilit:
- Implementation and Evaluation of a Low-Power Sound-Based User Activity Recognition System2004
- A Model for Human Interruptability: Experimental Evaluation and Automatic Estimation from Wearable Sensors2004
- Inferring Activities from Interactions with ObjectsIEEE Pervasive Computing, 2004
- The Use of Computer Vision in an Intelligent Environment to Support Aging-in-Place, Safety, and Independence in the HomeIEEE Transactions on Information Technology in Biomedicine, 2004
- Sensing and modeling human networks using the sociometer2004
- SoundButton: design of a low power wearable audio classification system2004
- RFID: A Key to Automating EverythingScientific American, 2004
- A Closed-Form Solution for Mapping General Distributions to Minimal PH DistributionsLecture Notes in Computer Science, 2003
- Relational Markov models and their application to adaptive web navigation2002
- A tutorial on hidden Markov models and selected applications in speech recognitionProceedings of the IEEE, 1989