Efficient tracking approach of multiple interacting objects using data association
Ayoub Al-Hamadi, Ulrike Homberg, Robert Niese, Bernd Michaelis · 2007
Robust tracking of multiple interacting objects in image sequences is a challenging problem due to the disturbances that occur often in the real environment. In this context, a system of independent particle filters and an adaptive motion model is used which allow the separated handling of moving objects in conflict situations. For solving the problems of the fluctuation detection and dealings with object interactions, a data association step is suggested with data exclusion, data allocation and data administration. Furthermore, this enables us to recognize conflict image situations and to adjust and adapt the particle filters to these situations. The fitness of the approach will be shown for various real image sequences.