A visual nervous network for moving object recognition

In this paper, we propose a visual nervous network for moving object recognition. This network is based on a visual nervous network which has a hierarchical parallel-structure. The network consists of three modules: the movement detection module, the moving object estimation module and the moving object recognition module. The movement detection module detects moving points and their direction. The moving object estimation module estimates the moving object on motion features. The moving object recognition module recognizes the moving object on its form feature. The network is able to recognize the moving object by uniting motion recognition and pattern recognition. We carried out computer simulations using real moving images to confirm the effectiveness of the proposed network.