In this paper,a novel and robust method which exploits the spatio-temporal context for orderless and blurred visual tracking is presented.This lets the tracker adapt to both rigid and deformable objects on-line even if the image is blurred.We observe that a RGB vectorof animage which is resizedinto a small fixed size can keep enough useful information.Based on this observation and computational reasons,we propose to resize the windows ofboth template and candidate target images into 2 × 2 and use Euclidean Distance to compute the similarity between these two RGB imagevectors for the preliminary screening.We then apply spatio-temporal context based on Bayesian framework to further compute a confidence map for obtaining the best target location.Experimental results on challenging video sequences in MATLAB without code optimization show the proposed tracking method outperforms eightstate-of-the-art methods.