Machine vision-based motion estimation of flotation froth using mutual information

Abstract

The motion estimation of froths in the flotation of minerals is difficult due to the effects of bubble deformation, bursting and merging making it difficult for the traditional machine vision methods to estimate the froth velocity. In this paper, we propose a new method for the motion estimation of flotation froth using mutual information with a bin size of two (MI2) as the block matching metric. Experimental results show that the proposed motion estimation technique improves the motion estimation accuracy in terms of peak signal-to-noise ratio of the reconstructed frame. The computational cost of the proposed method is almost the same as the standard machine vision methods used for the motion estimation of flotation froth.