Title :
Camera motion influence on dynamic saliency central bias
Author :
Baudrier, E. ; Rosselli, V. ; Larabi, M.C.
Author_Institution :
LSIIT, Univ. of Strasbourg, Strasbourg
Abstract :
Saliency models have been extensively studied for static images and the focus is now on moving images. There is a central bias in both cases that is emphasized in the dynamic case. One aspect in this latter is the camera motion that influences the scene interpretation. The movie director exploits this motion to make the observer focus on the targeted object which is often in the center of the scene. This aspect is not taken into account in current saliency dynamic models. In this paper, we study the camera motion influence on the gaze distribution in order to include it in a new saliency model. Observers´ gazes are recorded with an eye tracker, camera motions (e.g. tracking, zoom ...) are calculated thanks to a polynomial projection of the motion field and the motion influence is statistically tested on the recorded gazes.
Keywords :
cameras; image motion analysis; object detection; statistical testing; visual perception; camera motion influence; current saliency dynamic models; dynamic saliency central bias; eye tracker; gaze distribution; moving images; polynomial projection; recorded gazes; saliency models; scene interpretation; static images; statistical testing; Application software; Cameras; Focusing; Image motion analysis; Image sequences; Layout; Motion pictures; Testing; Tracking; Visual system; Image analysis; Image motion analysis; Visual system;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
978-1-4244-2353-8
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2009.4959709