Activity Recognition Using A Mixture of Vector Fields
Figueiredo, M. A. T.
; Marques, J. S.
IEEE Transactions on Image Processing Vol. 22, Nº 5, pp. 1712 - 1725, May, 2013.
ISSN (print): 1057-7149
Journal Impact Factor: 3,315 (in 2008)
Digital Object Identifier: 10.1109/TIP.2012.2226899
The analysis of moving objects in image sequences (video) has been one of the major themes in computer vision. In this paper, we focus on video-surveillance tasks; more speciﬁcally, we consider pedestrian trajectories and propose modeling them through a small set of motion/vector ﬁelds together with a space-varying switching mechanism. Despite the diversity of motion patterns that can occur in a given scene, we show that it is often possible to ﬁnd a relatively small number of typical behaviors, and model each of these behaviors by a “simple” motion ﬁeld. We increase the expressiveness of the formulation by allowing the trajectories to switch from one motion ﬁeld to another, in a space-dependent manner. We present an expectation-maximization algorithm to learn all the parameters of the model, and apply it to trajectory classiﬁcation tasks. Experiments with both synthetic and real data support the claims about the performance of the proposed approach.