Action Recognition in Video Sequences using a Mealy Machine

Authors: L. Rodriguez-Benitez, J. Moreno-Garcia, J.J. Castro-Schez, C. Solana, L. Jimenez

Abstract:

In this paper the use of sequential machines for recognizing actions taken by the objects detected by a general tracking algorithm is proposed. The system may deal with the uncertainty inherent in medium-level vision data. For this purpose, fuzzification of input data is performed. Besides, this transformation allows to manage data independently of the tracking application selected and enables adding characteristics of the analyzed scenario. The representation of actions by means of an automaton and the generation of the input symbols for finite automaton depending on the object and action compared are described. The output of the comparison process between an object and an action is a numerical value that represents the membership of the object to the action. This value is computed depending on how similar the object and the action are. The work concludes with the application of the proposed technique to identify the behavior of vehicles in road traffic scenes.

Keywords: Approximate reasoning, finite state machines, video analysis.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1074569

References:

[1] A. F. Bobick and Y. Ivanov. "Action Recognition Using Probabilistic Parsing", Proc. of CVPR-98, Santa Barbara, California, pp. 196-202. 1998.
[2] S. Hongeng , R. Nevatia and, F. Bremond, Video-based event recognition: activity representation and probabilistic recognition methods, Computer Vision and Image Understanding, v.96 n.2, p.129-162, November 2004
[3] Perera, A. G. Amitha; Hoogs, Anthony; Srinivas, Chukka; Brooksby, Glen; Hu, Wensheng. Evaluation of Algorithms for Tracking Multiple Objects in Video. Applied Imagery and Pattern Recognition Workshop, 2006. AIPR 2006.
[4] Moving Picture Experts Group. The MPEG home page. Available in: http://www.chiariglione.org/mpeg/.
[5] GH. Mealy. A Method to Synthesizing Sequential Circuits. Bell System Technical J, 1045-1079. (1955).
[6] L. Rodriguez-Benitez, J. Moreno-Garcia, J.J. Castro-Schez and, L. Jimenez, Linguistic Motion Description for an Object on MPEG Compressed Domain, In Proceedings of Eleventh International Fuzzy Systems Association World Congress, International Fuzzy Systems Association, 2005.
[7] L. Rodriguez-Benitez, J. Moreno-Garcia, J.J. Castro-Schez, and L. Jimenez, An approximate reasoning technique for segmentation on compressed MPEG video, In Proceedings of VISAPP, 2nd International Conference on Computer Vision Theory and Applications, 2007.
[8] L. Rodriguez-Benitez, J. Moreno-Garcia, J.J. Castro-Schez, and L. Jimenez, Fuzzy logic to track objects from MPEG video sequences, To be published In Proceedings of IPMU, Information processing and management of uncertainty in Knowledge-based systems, 2008. (Available in http://oreto.inf-cr.uclm.es).
[9] V. Van-thinh, Temporal scenario for automatic video interpretation, Doctoral Thesis, 2004.
[10] L.A. Zadeh, Fuzzy Set, Information and Control, 1960.
[11] L.A. Zadeh, The concept of a linguistic variable and its applications to approximate reasoning, Information Science, 1975.