Visual selective attention modeling is an advanced topic in cognitive information perception. According to human visual perception theory, which is based on the introduction of the representative visual attention model (Itti model), in its initial stages of feature extraction, in order to form a new guidance note of the saliency map, new low-level visual features are introduced, which achieves a more accurate target detection. The results prove that this method can avoid the leakage detection to some extent, which makes attention regional more close to the actuality of biological visual system.