Robust visual tracking based on H∞ Particle filter by adaptively integrating multiple cues
This paper proposes a novel tracking algorithm that combines H∞ filter using a linear matrix inequality (LMI) formulation with particle filter. First we use H∞ filter to estimate the global linear motion of the target. The advantage of using H∞ filter is that no statistical assumption on the input is needed, and the filter tends to be more robust when there exists additional uncertainty in the system, in addition the design of H∞ filter is based on LMI formulation. Secondly, the particle filter tracking algorithm is used to compute the local non linear motion. In this stage we merge multiple cues to construct the observation model, and to overcome the problems of complex environments and target’s appearance changes, the weights for each cue is updated on line dynamically thereby the observation model is adapted to the target’s appearance changes. The results of experiments conducted on public sequences which simulate various challenging conditions, show that the tracker achieves a high performance and keeps a good stability deal with dynamic and appearance target’s changes.
Regarding indexing issue:
We have provided the online access of all issues & papers to the all indexing agencies (as given on our journal home web site). It’s depend on indexing agencies when, how and what manner they can index or not. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.