A Selective Attention Based Method for Target Detection

This paper describes a new selective attention based method which can be used effectively in wide range of target detection tasks without using any a-priori knowledge about the target. In our proposed system, several basic features are extracted directly from original input visual stimuli, and these features are integrated based on their local competitive relations and statistical information. Through integration process, unnecessary features for detecting the target are spontaneously decreased, while useful features are enhanced. The performance of our system was evaluated over some simple synthetic images which were generated by computer, and complex real images of natural environment taken from different domains which also include severe amounts of noise. Key-Words: Selective Attention, Target Detection, Feature Extraction, Feature Integration, local competition