Tree Detection using Color, and Texture Cues for Autonomous Navigation in Forest Environment

This master thesis presents a novel classification based tree detection method for autonomous navigation in forest environment. The fusion of color, and texture cues has been used to segment the image into tree trunk and background objects. The segmentation of forest images into tree trunk and background objects is a challenging task due to high variations of illumination, effect of different color shades, non-homogenous bark texture, shadows and foreshortening. To accomplish this, the attempt have been made in researching the best methodology among different combinations of color, and texture descriptors, and two classification techniques to detect nearby trees and estimate the distance between forest vehicle and the base of segmented trees using monocular vision. A simple heuristic distance measurement method is proposed that is based on pixel height and a reference length. The performance of various color and texture operators, and accuracy of classifiers has been evaluated using cross validation techniques.