Detection and Avoidance of Simulated Potholes in Autonomous Vehicles in an Unstructured Environment

by Karuppuswamy, Jaiganesh

Abstract (Summary)
This research discusses a solution to detection and avoidance of simulated potholes in the path of an autonomous vehicle operating in an unstructured environment. Pothole avoidance may be considered similar to other obstacle avoidance except that the potholes are depressions rather than extrusions from a surface. Simulated potholes were used in this research. A vision approach was used since the simulated potholes were significantly different visually from the background surface. Large potholes more than 2 feet in diameter were detected. Furthermore, only white potholes will be detected on a background of grass, asphalt, sand or green painted bridges. The solution to the problem was developed in a systematic manner. Various approaches to solving the problem were considered. After a specific camera and frame grabber were chosen, the physical and mechanical issues of camera mounting were solved. Then a software solution was designed using an object-oriented approach after modeling the solution in UML (Unified Modeling Language). The signals from the environment were captured by the vehicle's vision systems and pre-processed. A histogram was used to determine a brightness threshold to determine if a pothole is within the field of view. Then, a binary image is formed. Regions are then detected in the binary image. Regions that have a diameter close to 2 feet and a ratio of circumference to diameter close to 2 feet are considered potholes. The logic controller where navigational strategies are evaluated uses these signals to decide a final course of navigation. The primary significance of the solution is that it is interfaced seamlessly into the existing central logic controller. The solution can also be easily extended to detect and avoid any two dimensional shape. The solution was tested with different scenarios of pothole orientation. The results indicated the presence/absence of a pothole satisfactorily and a few snapshots of the experimental results are illustrated in Chapter 6.
Bibliographical Information:


School:University of Cincinnati

School Location:USA - Ohio

Source Type:Master's Thesis

Keywords:pothole detection object oriented software design image processing and analysis autonomous vehicle navigation


Date of Publication:01/01/2001

© 2009 All Rights Reserved.