Particle filter-based visual tracking with a first order dynamic model and uncertainty adaptation

In many real world applications, tracking must be performed reliably in real-time for sufficiently long periods where target appearance and motion may sensibly change from one frame to the following. In such non ideal conditions this is likely to determine inaccurate estimates of the target location unless dynamic components are incorporated in the model. To deal with these problems effectively, we propose a particle filter-based tracker that exploits a first order dynamic model and continuously performs adaptation of model noise so to balance uncertainty between the static and dynamic components of the state vector. We provide an extensive set of experimental evidences with a comparative performance analysis with tracking methods representative of the principal approaches. Results show that the method proposed is particularly effective for real-time tracking over long video sequences with occlusions and erratic, non-linear target motion.

Research highlights
► We present an Adaptive Particle Filter-based tracker with first order dynamic model.
► Incorporating dynamic in the state model amplifies the uncertainty on target position.
► Adaptation of noise components is key to accurate estimate target position and motion.
► Extensive comparison with other state-of-the-art tracking approaches is provided.