Document Type
Thesis
Date of Award
5-31-1991
Degree Name
Master of Science in Electrical Engineering - (M.S.)
Department
Electrical and Computer Engineering
First Advisor
Nirwan Ansari
Second Advisor
Edwin Hou
Third Advisor
A. Banihashemi
Abstract
The development of accurate sensors is of crucial importance in navigation of mobile autonomous robots. The following master's thesis analyzes the use of vanishing points for robot navigation. Parallel lines in the environment of the robot are used to compute vanishing points which serve as a reference for guiding a robot. To accomplish the navigation tasks, three subtasks are to be performed: detection of straight lines, computation of vanishing points, and robot navigation with vanishing points.
An edge detection algorithm is presented that combines Sobel and Laplacian of Gaussian operators. The algorithm preserves the precision of the Laplacian of Gaussian operator while the Sobel operator is mainly used for filtering image noise. A method to determine the Laplacian of Gaussian kernel is described. Recursive subdivision is used to detect raw lines in the edges. Raw lines are approximated by straight lines using a least squares fit.
Several methods for detecting vanishing points are presented. The cross-product method as introduced by Magee and Aggarval is described in detail. The method is modified in order to make the detection of vanishing points appropriate for an indoor environment. The navigation section derives the properties of vanishing points under camera rotation and translation. Using these properties, the location of the vanishing points can serve as a reference for robot navigation. A model of the robot environment is defined, summarizing the minimal number of constraints necessary for the method to work.
Finally, the limitations as well as the advantages of using vanishing points in robot navigation are described.
Recommended Citation
Schuster, Rolf, "Analysis and implementation of a navigation system using vanishing points in a generalized environment" (1991). Theses. 2608.
https://digitalcommons.njit.edu/theses/2608
