Significance of Bottom-up Attributes in Video Saliency Detection Without Cognitive Bias

Abstract

Saliency in an image or video is the region of interest that stands out relative to its neighbors and consequently attracts more human attention. To determine the salient areas within a scene, visual importance and distinctiveness of the regions must be measured. A key factor in designing saliency detection algorithms for videos is to understand how different visual cues affect the human perceptual and visual system. To this end, we investigated the bottom-up features including color, texture, and motion in video sequences for both one-by-one and combined scenarios to provide a ranking system stating the most dominant circumstances for each feature individually and in combination with other features as well. In this work, we only considered the individual features and various visual saliency attributes investigated under conditions in which we had no cognitive bias. Human cognition refers to a systematic pattern of perceptual and rational judgements and decision-making actions. Since computers do not typically have this ability, we tried to minimize this bias in the design of our experiment. First, we modelled our test data as 2D images and videos in a virtual environment to avoid any cognitive bias. Then, we performed an experiment using human subjects to determine which colors, textures, motion directions, and motion speeds attract human attention more. The proposed ranking system of salient visual attention stimuli was achieved using an eye tracking procedure. This work provides a benchmark to specify the most salient stimulus with comprehensive information.