A Pedestrian Tracking Using the Association of Cellular Automata and a Neural Network

⎯ This paper describes a pedestrian tracking system that uses a new movement prediction technique based on an association of Cellular Automata (CA) and a Neural Network (NN). The proposed prediction technique aims to learn the behaviour of pedestrian movement directly from images. A CA is applied to capture the pedestrian movement. The derived CA patterns are then used to train the NN. The trained NN is employed to simulate pedestrian movement, and then to estimate the pedestrian future position. The results indicate that the effectiveness of the technique depends on the following factors: the speed of pedestrians and the movement patterns. Other applications of the technique are also mentioned.