Hide/Show Apps

Particle filter based Conjoint Individual-Group Tracker (CIGT)

YİĞİT, Ahmet
Temizel, Alptekin
In this paper, we present a method for joint tracking of individuals and groups in surveillance scenarios. Groups are dynamic entities and they may grow or shrink with merge-split events. This dynamic nature makes it difficult to track groups using conventional trackers. In this paper, we propose a new tracking method named Conjoint Individual and Group Tracker (CIGT) based on particle filter with multi-observation model and particle advection. The proposed multi-observation model uses in-group and out-group observations inspired from sociological domain and jointly models individuals and groups. Particle advection is a method used to extract flows and analyze flow stability. In this work, particle advection is integrated into the motion model of CIGT to facilitate tracking of dense groups. Experimental results show that the performance of the proposed method compares favorably with those in the literature.