Saccadic object recognition with an active vision system

Abstract

. An active vision system for saccadic camera gaze shifts and explorative scene analysis as a new integral approach to image understanding is proposed. The model includes several subsystems: preattentive peripheral feature detection, multi resolution foveal image identification based on a hypercolumnar representation and object recognition by means of two memories for foveal identifications and fixation positions. An egocentric interest map and a selective masking mechanism are used to integrate bottom--up and top-- down information flow. 1 System Survey In this paper we propose an animate image understanding system for two--dimensional scene analysis and object recognition by means of camera gaze shifts (fig. 1). The function of the system is designed by a hierarchy of physiological and anatomical motivated structures (i.e. fovea, hypercolumns). The scene is supposed to be a mainly static external memory buffer. An implicit selective attention mechanism modulates perception by con...