Paul Viola, Stephen Lisberger, Terrence J. Sejnowski
This paper briefly describes an artificial neural network for preattentive visual processing. The network is capable of determiuing image motioll in a type of stimulus which defeats most popular methods of motion detect.ion - a subset of second-order visual motion stimuli known as drift-balanced stimuli(DBS). The processing st.ages of the network described in this paper are integratable into a model capable of simultaneous motion extractioll. edge detection, and the determination of occlusion.