Open Access. Powered by Scholars. Published by Universities.®

Engineering Commons

Open Access. Powered by Scholars. Published by Universities.®

Other Computer Engineering

Air Force Institute of Technology

Theses/Dissertations

#antcenter

Publication Year

Articles 1 - 2 of 2

Full-Text Articles in Engineering

Small Fixed-Wing Aerial Positioning Using Inter-Vehicle Ranging Combined With Visual Odometry, Benjamin M. Fain Mar 2017

Small Fixed-Wing Aerial Positioning Using Inter-Vehicle Ranging Combined With Visual Odometry, Benjamin M. Fain

Theses and Dissertations

There has been increasing interest in developing the ability for small unmanned aerial systems (SUAS) to be able to operate in environments where GPS is not available. This research considers the case of a larger aircraft loitering above a smaller GPS-denied SUAS. This larger aircraft is assumed to have greater resources which can overcome the GPS jamming and provide range information to the SUAS flying a mission below. This research demonstrates that using a ranging update combined with an aircraft motion model and visual odometry can greatly improve the accuracy of a SUASs estimated position in a GPS-denied environment.


Overcoming Pose Limitations Of A Skin-Cued Histograms Of Oriented Gradients Dismount Detector Through Contextual Use Of Skin Islands And Multiple Support Vector Machines, Jonathon R. Climer Mar 2011

Overcoming Pose Limitations Of A Skin-Cued Histograms Of Oriented Gradients Dismount Detector Through Contextual Use Of Skin Islands And Multiple Support Vector Machines, Jonathon R. Climer

Theses and Dissertations

This thesis provides a novel visualization method to analyze the impact that articulations in dismount pose and camera aspect angle have on histograms of oriented gradients (HOG) features and eventual detections. Insights from these relationships are used to identify limitations in a state of the art skin cued HOG dismount detector's ability to detect poses not in a standard upright stances. Improvements to detector performance are made by further leveraging available skin information, reducing false detections by an additional order of magnitude. In addition, a method is outlined for training supplemental support vector machines (SVMs) from computer generated data, for …