There are a large number of different approaches to vehicle tracking currently available. In this report we look at different problems faced when tracking vehicles, such as background subtraction and vehicle recognition, and look at possible solutions to these. We present a layered approach to vehicle tracking, which includes the use of background subtraction based on a statistical colour model, shape approximation using contour creation algorithms, and two dimensional object recognition using colour histograms and geometric moments. We improve on the standard statistical RGB background removal model by adding a second pass HSV shadow removal filter and demonstrate that this provides cleaner background segmentation that other approaches including optical flow. We improve on prior research into simple vehicle tracking solutions by combining object recognition based on both colour histograms and geometric moments, and demonstrate the robust nature of our solution through a number of example scenarios.