The active badge location system
ACM Transactions on Information Systems (TOIS)
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Bayesian Networks and Decision Graphs
Bayesian Networks and Decision Graphs
A Dynamic Bayesian Network Approach to Tracking Using Learned Switching Dynamic Models
HSCC '00 Proceedings of the Third International Workshop on Hybrid Systems: Computation and Control
Person recognition by pressure sensors
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IV
Pheromone Approach to the Adaptive Discovery of Sensor-Network Topology
WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Person recognition by pressure sensors
KES'05 Proceedings of the 9th international conference on Knowledge-Based Intelligent Information and Engineering Systems - Volume Part IV
Hi-index | 0.00 |
We consider a person tracking system that is robust to environmental changes and users are unaware of. Once a user is identified at an entrance door in a room with his/her biometrics, we can keep tracking the user continuously. The pyroelectric infrared sensors in the ceiling are used for this goal. These sensors are resistant to environmental changes, but give only a weak piece of evidence. We applied a Bayesian network to infer the position of the user, and investigated how the Bayesian network works. We gained 64.0% in average for a single-person tracking.