Robust visual tracking based on Informative random fern
Hao Dong, Rui Wang · Advances in computer science research · 2016
In this paper, a novel visual tracking algorithm named as Informative random fern -Tracking Learning Detection (IRF-TLD) has been proposed.Instead of a binary comparison in the standard random fern of TLD, we use the real value feature and Gaussian random projection to acquire the advantages of high accuracy and low memory requirement.Experimental results on challenging sequences have demonstrated the superior performance of our IRF-TLD when compared with several state-of-the-art tracking algorithms.