Applicability of deep-learning technology for relative object-based navigation
Lai, Wee Leong
Yakimenko, Oleg A.
Papoulias, Fotis A.
MetadataShow full item record
In a GPS-denied environment, one of the possible selections for navigating an unmanned ground vehicle (UGV) is through real-time visual odometry. To navigate in such an environment, the UGV needs to be able to detect, identify, and relate the static and dynamic objects such as trucks, motorbikes, and pedestrians in the on-board camera field of view. Therefore, object recognition becomes crucial in navigating UGVs. However, object recognition is known to be one of the challenges in the field of computer vision. Current analytic video software inadequately utilizes heuristics like size, shape, and direction to determine whether a detected object is a human, a vehicle, or an animal. This thesis explores another approach, the deep-learning technique, which makes use of neural networks based on vast collections of training data images. This thesis follows a systems engineering approach in analyzing the need and suggesting a solution. It shows how to create and train the aforementioned networks using just three objects: a chair, a table, and a car. A Pioneer UGV equipped with the corresponding sensors is then used to test the developed algorithms. The preliminary analysis conducted in this thesis shows good potential for using the deep-learning technique on future UGVs.
RightsCopyright is reserved by the copyright owner.
Showing items related by title, author, creator and subject.
Knopf, Jeffery W. (British International Studies Association, 2003);A programme of research on learning in international relations began developing in the 1980s. However, learning research has not reached its potential. This article seeks to stimulate new work on learning by analysing ...
Impact of Homeland Security Communities of learning : developing a strategy for training and collaboration Braziel, Rick (Monterey, California. Naval Postgraduate School, 2006-09);As the threat of domestic terrorism increases and the demands on Emergency Responders and the public intensify, a more distributed, efficient, and flexible training and collaboration model is needed to guide future efforts. ...
Fansler, Aaron A.D. (Naval Postgraduate School, Monterey, California, 2018);Mr. Fansler presentation will discuss the use of machine learning in cyber security. Some significant steps have been made in the I.T. world but not in the O.T. world. The only advances come from the attacker’s side where ...