Attentional scene segmentation: Integrating depth and motion

We present an approach to attention in active computer vision. The notion o f attention plays an important role in biological vision. In recent years, and especially with the emerging interest in active vision, computer vision researchers have been increasingly concerned with attentional mechanisms a s well. The basic principles behind these efforts are greatly influenced by psychophysical research. That is the case also in the work presented here, which adapts to the model of Treisman (1985, Comput. Vision Graphics Image Process. Image Understanding 31., 156-177), with an early parallel stage w ith preattentive cues followed by a later serial stage where the cues are i ntegrated. The contributions in our approach are (i) the incorporation of d epth information from stereopsis, (ii) the simple implementation of low lev el modules such as disparity and flow by local phase, and (iii) the cue int egration along pursuit and saccade mode that allows us a proper target sele ction based on nearness and motion. We demonstrate the technique by experim ents in which a moving observer selectively masks out different moving obje cts in real scenes. (C) 2000 Academic Press.