Optical Flow-Based Odometry for Underground Tunnel Exploration

摘要

As military operations in degraded or GPS-denied environments continue to increase in frequency and importance, there is an increased necessity to be able to determine precision location within these environments. Furthermore, authorities are finding a record number of tunnels along the U.S.- Mexico border; therefore, underground tunnel characterization is becoming a high priority for U.S. Homeland Security as well. This thesis investigates the performance of a new image registration technique based on a two camera optical- flow configuration using phase correlation techniques. These techniques differ from other image based navigation methods but present a viable alternative increasing autonomy and answering the tunnel based navigation problem. This research presents an optical flow based image registration technique and validates its use with experimental results on a mobile vehicle. Results reveal that further extension to pose estimation yields accuracy within 1.3 cm.