Egocentric Spatial Representation in Early Vision

Recent physiological experiments have shown that the responses of many neurons in V1 and V3a are modulated by the direction of gaze. We have developed a neural network model of the hierarchy of maps in visual cortex to explore the hypothesis that visual features are encoded in egocentric (spatiotopic) coordinates at early stages of visual processing. Most psychophysical studies that have attempted to examine this question have concluded that features are represented in retiThe three most common types of coordinates used for representing visual objects in biological and computer vision systems are eye-centered (retinal), object-centered, and viewer-centered (egocentric). Eye-centered representations are consistent with many physiological and psychophysical studies of early vision. Neurons in primary visual cortex and most extrastriate areas are organized into retinotopic maps (Felleman & Van Essen, 1991). Most psychophysical experiments designed to determine the nature of spatial representation at early visual stages have reached the same conclusion, as we review in the discussion. Other types of representation are believed to be used at the highest stages of visual processing. Mishkin, Ungerleider, and Macko (1983) proposed a functional distinction between two main streams of processing, the "what" and "where" pathways leading, respectively, in the temporal and parietal cortex. Object-centered reference frames have been suggested for the representation of objects in the inferior temporal cortex and egocentric reference frames have been proposed for the representation of spatial location in the parietal cortex (Andersen, 1989). Goodale and Milner (1990) recently proposed that the dorsal pathway to parietal cortex could also be involved *Present address: Department of Psychology, Yale University. O 1993 Mmachuset& Institute of Technology nal coordinates, but the interpretation of these experiments does not preclude the type of retinospatiotopic representation that is embodied in our model. The model also explains why electrical stimulation experiments in visual cortex cannot distinguish between retinal and retinospatiotopic coordinates in the early stages of visual processing. Psychophysical predictions are made for testing the existence of retinospatiotopic repre-