Performance evaluation of the parallel object tracking algorithm employing the particle filter

An algorithm based on particle filters is employed to track moving objects in video streams from fixed and non-fixed cameras. Particle weighting is based on color histograms computed in the iHLS color space. Particle computations are parallelized with CUDA framework. The algorithm was tested on various GPU devices: a desktop GPU card, a mobile chipset and two embedded GPU platforms. The processing speed depending on the number of particles and the size of a tracked object was measured. The aim of experiments was to assess the performance of the parallel algorithm and to test whether the currently available GPU devices are capable of real-time tracking of large moving objects in video streams from surveillance cameras.