Credal human activity recognition based-HMM by combining hierarchical and temporal reasoning

Human activities recognition in videos sequences is a very current research topic being investigated in computer vision. This paper offers an approach for video analysis by exploiting hidden Markov models. We propose an extension of the standard model by integrating three abstraction layers through the management of hierarchical structure and the temporal evolution of events. In addition, data imperfections are also managed through a more generic framework than the probabilistic that is the Transferable Belief Model. The proposed approach has been assessed with the "baggage abandoned" scenario of PETS'06 dataset of computer vision community. Lastly, the proposed scenario recognition system performance is analysed and compared to the result of classic HMM models.

[1]  Svetha Venkatesh,et al.  Policy Recognition in the Abstract Hidden Markov Model , 2002, J. Artif. Intell. Res..

[2]  Alessandro Saffiotti,et al.  The Transferable Belief Model , 1991, ECSQARU.

[3]  Noureddine Zerhouni,et al.  Time-Sliced Temporal Evidential Networks: The case of Evidential HMM with application to dynamical system analysis , 2011, 2011 IEEE Conference on Prognostics and Health Management.

[4]  L. Baum,et al.  An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process , 1972 .

[5]  Emmanuel Ramasso,et al.  Contribution of belief functions to hidden markov models with an application to fault diagnosis , 2009, 2009 IEEE International Workshop on Machine Learning for Signal Processing.

[6]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[7]  Yoram Singer,et al.  The Hierarchical Hidden Markov Model: Analysis and Applications , 1998, Machine Learning.

[8]  Kevin P. Murphy.  Hidden semi-Markov models ( HSMMs ) , 2002 .

[9]  Svetha Venkatesh,et al.  Explicit State Duration HMM for Abnormality Detection in Sequences of Human Activity , 2004, PRICAI.

[10]  Denis Pellerin,et al.  Forward-Backward-Viterbi Procedures in the Transferable Belief Model for State Sequence Analysis Using Belief Functions , 2007, ECSQARU.

[11]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for automatic speech recognition , 1986 .

[12]  François Brémond,et al.  Scene Understanding: perception, multi-sensor fusion, spatio-temporal reasoning and activity recognition. (Interprétation de Scènes : perception, fusion multi-capteurs, raisonnement spatio-temporel et reconnaissance d'activités) , 2007 .

[13]  Arnaud Ahouandjinou,et al.  Reconnaissance de scénario par les Modèles de Markov Cachés Crédibilistes : Application à l'interprétation automatique de séquences vidéos médicales. (Scenario recognition by evidentials hidden Markov models : Application for the automatic interpretation of medical video sequences) , 2014 .

[14]  David Mercier.  Fusion d'informations pour la reconnaissance automatique d'adresses postales dans le cadre de la théorie des fonctions de croyance , 2006 .

[15]  Svetha Venkatesh,et al.  Activity recognition and abnormality detection with the switching hidden semi-Markov model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[16]  David He,et al.  A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology , 2007 .

[17]  Philippe Smets,et al.  Decision making in the TBM: the necessity of the pignistic transformation , 2005, Int. J. Approx. Reason..

[18]  Eric Horvitz,et al.  Layered representations for human activity recognition , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.

[19]  Shunzheng Yu,et al.  Hidden semi-Markov models , 2010, Artif. Intell..

[20]  Anita Sant'Anna,et al.  A Symbolic Approach to Human Motion Analysis Using Inertial Sensors : Framework and Gait Analysis Study , 2012 .

[21]  Svetha Venkatesh,et al.  Efficient duration and hierarchical modeling for human activity recognition , 2009, Artif. Intell..