Terrain cover classification based on wavelet feature extraction

The terrain perception technology using passive sensors plays a key role to enhance autonomous mobility for military UGV(unmanned ground vehicle) in off-road environment. In this paper, an effective method is presented to classify terrain cover based on the color and texture features of an image. Coefficients from the discrete wavelet transform are used to extract the color and texture features of the image. Furthermore, spatial coordinates where a terrain class is located in the image are also adopted as additional features. Considering real-time applications, the neural network is applied for the terrain classifier to be trained using real off-road terrain images. By comparing the classification performance according to the applied feature sets and its color space change, the experimental results show that the proposed algorithm has a promising result and potential possibilities for autonomous navigation.