On-Road Automotive Vehicle Detection using Gaussian Mixture Model and NNs

This work presents an approach in study for the vehicle traffic control through the use of computer vision techniques. The videos captured are processed frame-to-frame, where the movement of objects is segmented using the Gaussian Mixture Model. Later, characteristics are extracted and applied to a Neural Network so that segmented objects are classified as vehicles and non-vehicles and, in the case of vehicles, they will be classified according to the size of the vehicle as follows: small size, intermediate size and large size