Road Sign Recognition by Single Positioning of Space-Variant Sensor Window

A biologically plausible model of traffic sign detection and recognition invariantly with respect to variable viewing conditions is presented. The model simulates several key mechanisms of biological vision, such as space-variant representation of information (reduction in resolution from the fovea to retinal periphery), orientation selectivity in the cortical neuron responses, and context encoding of information. The model was tested on British traffic signs and demonstrated the ability to recognize these signs from a single position of a space-variant sensor window. After performing colour segmentation and classification and finding the sign centre, 85% of the traffic signs tested were identified under various environmental conditions.