From On-Going to Complete Activity Recognition Exploiting Related Activities
Activity recognition can be seen as a local task aimed at identifying an on-going activity performed at a certain time, or a global one identifying time segments in which a certain activity is being performed. We combine these tasks by a hierarchical approach which locally predicts on-going activities by a Support Vector Machine and globally refines them by a Conditional Random Field focused on time segments involving related activities. By varying temporal scales in order to account for widely different activity durations, we achieve substantial improvements in on-going activity recognition on a realistic dataset from the PlaceLab sensing environment. When focusing on periods within which related activities are known to be performed, the refinement stage manages to exploit these relationships in order to correct inaccurate local predictions.
KeywordsSupport Vector Machine Activity Recognition Conditional Random Field Local Prediction Inductive Logic Programming
Unable to display preview. Download preview PDF.
- 2.Lepri, B., Mana, N., Cappelletti, A., Pianesi, F., Zancanaro, M.: What is happening now? detection of activities of daily living from simple visual features. Personal and Ubiquitous Computing (2010)Google Scholar
- 4.Pentney, W., Philipose, M., Bilmes, J.A., Kautz, H.A.: Learning large scale common sense models of everyday life. In: AAAI, pp. 465–470 (2007)Google Scholar
- 6.Stikic, M., Huynh, T., Van Laerhoven, K., Schiele, B.: Adl recognition based on the combination of rfid and accelerometer sensing. In: 2nd International Conference on Pervasive Computing Technologies for Healthcare 2008 (2008)Google Scholar
- 10.Wyatt, D., Philipose, M., Choudhury, T.: Unsupervised activity recognition using automatically mined common sense. In: AAAI, pp. 21–27 (2005)Google Scholar
- 11.Oliver, N., Horvitz, E., Garg, A.: Layered representations for human activity recognition. In: Fourth IEEE Int. Conf. on Multimodal Interfaces, pp. 3–8 (2002)Google Scholar
- 12.Ogawa, M., Ochiai, S., Shoji, K., Nishihara, M., Togawa, T.: An attempt of monitoring daily activities at home. In: 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 1, pp. 786–788 (2000)Google Scholar
- 14.van Kasteren, T., Noulas, A., Englebienne, G., Kröse, B.: Accurate activity recognition in a home setting. In: UbiComp 2008, pp. 1–9. ACM, New York (2008)Google Scholar
- 15.Liao, L., Fox, D., Kautz, H.: Location-based activity recognition using relational markov networks. In: IJCAI 2005 (2005)Google Scholar
- 16.Landwher, N., Gutmann, B., Thon, I., Philipose, M., De Raedt, L.: Relational transformation-based tagging for human activity recognition. In: Proceedings of the 6th Workshop on Multi-Relational Data Mining (MRDM), Warsaw, Poland (September 2007)Google Scholar
- 18.Sutton, C., Mccallum, A.: Introduction to conditional random fields for relational learning. In: Getoor, L., Taskar, B. (eds.) Introduction to Statistical Relational Learning. MIT Press, Cambridge (2006)Google Scholar
- 19.yu Wu, T., chun Lian, C., jen Hsu, J.Y.: Joint recognition of multiple concurrent activities using factorial conditional random fields. In: 2007 AAAI Workshop on Plan, Activity, and Intent Recognition (2007)Google Scholar