This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition
Oct. 2013 (vol. 35 no. 10)
pp. 2468-2483
Yongmian Zhang, IT Res. Div., Konica Minolta Lab. U.S.A. Inc., San Mateo, CA, USA
Yifan Zhang, Dept. of Electr., Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
E. Swears, Dept. of Electr., Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
N. Larios, Dept. of Electr., Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Ziheng Wang, Dept. of Electr., Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Qiang Ji, Dept. of Electr., Comput. & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY, USA
Complex activities typically consist of multiple primitive events happening in parallel or sequentially over a period of time. Understanding such activities requires recognizing not only each individual event but, more importantly, capturing their spatiotemporal dependencies over different time intervals. Most of the current graphical model-based approaches have several limitations. First, time--sliced graphical models such as hidden Markov models (HMMs) and dynamic Bayesian networks are typically based on points of time and they hence can only capture three temporal relations: precedes, follows, and equals. Second, HMMs are probabilistic finite-state machines that grow exponentially as the number of parallel events increases. Third, other approaches such as syntactic and description-based methods, while rich in modeling temporal relationships, do not have the expressive power to capture uncertainties. To address these issues, we introduce the interval temporal Bayesian network (ITBN), a novel graphical model that combines the Bayesian Network with the interval algebra to explicitly model the temporal dependencies over time intervals. Advanced machine learning methods are introduced to learn the ITBN model structure and parameters. Experimental results show that by reasoning with spatiotemporal dependencies, the proposed model leads to a significantly improved performance when modeling and recognizing complex activities involving both parallel and sequential events.
Index Terms:
Hidden Markov models,Bayesian methods,Computational modeling,Probabilistic logic,Uncertainty,Graphical models,interval temporal Bayesian networks,Activity recognition,temporal reasoning,Bayesian networks
Citation:
Yongmian Zhang, Yifan Zhang, E. Swears, N. Larios, Ziheng Wang, Qiang Ji, "Modeling Temporal Interactions with Interval Temporal Bayesian Networks for Complex Activity Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 10, pp. 2468-2483, Oct. 2013, doi:10.1109/TPAMI.2013.33
Usage of this product signifies your acceptance of the Terms of Use.