Detection of vehicles using a cascaded classifier in comparison to a artificial neural network

Abstract

This paper describes the comparison of accuracy and performance of two machine learning approaches for visual object detection and tracking vehicles. The first is a neural network based approach. The classification was carried out with a multilayer feed forward neural network. The second approach is based on boosting It works by sequentially applying a classification algorithm to reweighed versions of the training data, followed by taking a weighted majority vote of the sequence of classifiers thus produced.