Toward Scalable Activity Recognition for Sensor Networks
Sensor networks hold the promise of truly intelligent buildings: buildings that adapt to the behavior of their occupants to improve productivity, efficiency, safety, and security. To be practical, such a network must be economical to manufacture, install and maintain. Similarly, the methodology must be efficient and must scale well to very large spaces. Finally, be be widely acceptable, it must be inherently privacy-sensitive. We propose to address these requirements by employing networks of passive infrared (PIR) motion detectors. PIR sensors are inexpensive, reliable, and require very little bandwidth. They also protect privacy since they are neither capable of directly identifying individuals nor of capturing identifiable imagery or audio. However, with an appropriate analysis methodology, we show that they are capable of providing useful contextual information. The methodology we propose supports scalability by adopting a hierarchical framework that splits computation into localized, distributed tasks. To support our methodology we provide theoretical justification for the method that grounds it in the action recognition literature. We also present quantitative results on a dataset that we have recorded from a 400 square meter wing of our laboratory. Specifically, we report quantitative results that show better than 90% recognition performance for low-level activities such as walking, loitering, and turning. We also present experimental results for mid-level activities such as visiting and meeting.
KeywordsSensor Network Sensor Node Activity Recognition Building Occupant Unconstrained Motion
Unable to display preview. Download preview PDF.
- 2.Horling, B., Vincent, R., Mailler, R., Shen, J., Becker, R., Rawlins, K., Lesser, V.: Distributed Sensor Network for Real Time Tracking. In: Proceedings of the 5th International Conference on Autonomous Agents, pp. 417–424 (2001), http://mas.cs.umass.edu/paper/199
- 3.Ye, W., Heidemann, J., Estrin, D.: An energy-efficient mac protocol for wireless sensor networks. In: Proceedings 21st International Annual Joint Conference of the IEEE Computer and Communications Societies, New York, USA (2002)Google Scholar
- 4.Wilson, D.H., Atkeson, C.: Simultaneous tracking & activity recognition (star) using many anonymous, binary sensors. In: The Third International Conference on Pervasive Computing, pp. 62–79 (2005)Google Scholar
- 6.Johnson, N., Hogg, D.: Learning the distribution of object trajectories for event recognition. Image and Vision Computing 14(8)Google Scholar
- 7.Minnen, D., Essa, I., Starner, T.: Expectation grammars: Leveraging high-level expectations for activity recognition. In: Workshop on Event Mining, Event Detection, and Recognition in Video, held in Conjunction with Computer Vision and Pattern Recognition, vol. 2, p. 626. IEEE, Los Alamitos (2003)Google Scholar
- 8.Cutler, R., Davis, L.: Real-time periodic motion detection, analysis and applications. In: Conference on Computer and Pattern Recognition, Fort Collins, USA, pp. 326–331. IEEE, Los Alamitos (1999)Google Scholar
- 10.Wilson, A., Bobick, A.: Realtime online adaptive gesture recognition. In: Proceedings of the International Conference on Pattern Recognition, Barcelona, Spain, pp. 111–116 (2000)Google Scholar
- 11.Ivanov, Y., Blumberg, B., Pentland, A.: Em for perceptual coding and reinforcement learning tasks. In: 8th International Symposium on Intelligent Robotic Systems, Reading, UK, pp. 93–100 (2000)Google Scholar
- 13.Wren, C.R., Rao, S.G.: Self-configuring, lightweight sensor networks for ubiquitous computing. In: The Fifth International Conference on Ubiquitous Computing: Adjunct Proceedings, 2003, pp. 205–206 (2003); also MERL Technical Report TR2003-24Google Scholar
- 15.Langley, P., Iba, W., Thompson, K.: An analysis of bayesian classifiers. In: Proceedings of the Tenth National Conference on Artificial Intelligence, AAAI Press, San Jose (1992)Google Scholar
- 16.John, G., Langley, P.: Estimating continuous distributions in bayesian classifiers. In: Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence, San Mateo, CA (1995)Google Scholar
- 17.Domingos, P., Pazzani, M.: Beyond independence: Conditions for the optimality of a simple bayesian classifier. In: Saitta, L. (ed.) Proceedings of the Thirteenth International Conference on Machine Learning, Morgan Kaufmann, San Francisco (1996)Google Scholar