Title :
Considerations of Self-Motion in Motion Saliency
Author :
Hiratani, Akinori ; Nakashima, Ryuichi ; Matsumiya, Kazumichi ; Kuriki, Ichiro ; Shioiri, Satoshi
Author_Institution :
Grad. Sch. of Inf. Sci., Tohoku Univ. Sendai, Sendai, Japan
Abstract :
Despite a number of studies of computational models of visual saliency, it is still difficult to predict where human would attend in a scene. One of the problems is the effect of self-motion on retinal images. Usually saliency is calculated with local motion signals, and high degree of saliency is found in motion components caused by self-motion. Since human observers usually ignore the motion caused by self-motion, the prediction accuracy of attention locations falls off. We developed a framework that reduces the saliency of the motion components caused self-motion, using a physiological model of optic flow processing that extracts object motion among self-motion signals.
Keywords :
feature extraction; image motion analysis; image sequences; attention location; motion saliency; object motion extraction; optic flow processing; physiological model; retinal image; self-motion; visual saliency; Motion pictures; Observers; Optical filters; Predictive models; Videos; Visual systems; Visualization; gaze estimation; global motion; saliency map; self-motion;
Conference_Titel :
Pattern Recognition (ACPR), 2013 2nd IAPR Asian Conference on
Conference_Location :
Naha
DOI :
10.1109/ACPR.2013.183