Salient Motion Features for Visual Attention Models

The human vision system (HVS) pays more attention to the moving objects than the static areas. Due to this fact, motion becomes one of the important features of the visual attention model. In this paper, we have integrated motion features with the visual computational model to detect salient moving objects. To implement this objective, several sub-features such as colour, colour change between different frames, optical flow estimation and background subtraction are explored and integrated using arithmetic operation. Here, pyramidal and non-pyramidal approaches are used to analyse these features. Our study concludes that multiplication is a better operation for feature integration. The experiments revealed that the individual colour feature gives low precision-recall scores. However, integrating this colour feature with other features has positive impact on the performance of detecting moving salient objects.