Visual guidance of an unmanned vehicle

• Main Author: Ong, Pei Jo.
• Other Authors: Xie Ming
• Format: Final Year Project
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Mechanical engineering
• Online Access: http://hdl.handle.net/10356/40271
• Institution: Nanyang Technological University

In autonomous mobile vehicle navigation, object avoidance is one of the fundamental complications that arise and with the recent advances in technology, the availability of low cost camera systems have lead to the possibilities of utilising vision-based algorithms to assist the robot in avoiding the obstacles. The research focuses on the various methods that were investigated to develop an effective and robust real time avoidance system and a homography-based approach was presented to extract the ground plane from consecutive sequences of images captured on a vehicle platform. It focused on the generation of 2D maps obtained from stereo vision. In addition, numerous optimization techniques are also discussed and performed to enhance the images to suit the specific application. With the guidance from the vision-based algorithms, the unmanned vehicle will be able to interpret and determine the positions of the obstacles and to manoeuvre smoothly in an outdoor environment.