Vehicle tracking from an aerial platform poses a number of unique challenges including the small number of pixels representing a vehicle, large camera motion, and parallax error. For these reasons, it is accepted to be a more challenging task than traditional object tracking and it is generally tackled through a number of different sensor modalities. Recently, the Wide Area Motion Imagery sensor platform has received reasonable attention as it can provide higher resolution single band imagery in addition to its large area coverage. However, still, richer sensory information is required to persistently track vehicles or more research on the application of WAMI for tracking is required. With the advancements in sensor technology, hyperspectral data acquisition at video frame rates become possible as it can be cruical in identifying objects even in low resolution scenes. For this reason, in this thesis, a multi-modal optical sensor concept is considered to improve tracking in adverse scenes.
The Rochester Institute of Technology Multi-object Spectrometer is capable of collecting limited hyperspectral data at desired locations in addition to full-frame single band imagery. By acquiring hyperspectral data quickly, tracking can be achieved at reasonableframe rates which turns out to be crucial in tracking. On the other hand, the relatively high cost of hyperspectral data acquisition and transmission need to be taken into account to design a realistic tracking. By inserting extended data of the pixels of interest we can address or avoid the unique challenges posed by aerial tracking. In this direction, we integrate limited hyperspectral data to improve measurement-to-track association. Also, a hyperspectral data based target detection method is presented to avoid the parallax effect and reduce the clutter density. Finally, the proposed system is evaluated on realistic, synthetic scenarios generated by the Digital Image and Remote Sensing software.
Library of Congress Subject Headings
Vehicles--Remote sensing; Multispectral imaging; Automatic tracking
Imaging Science (Ph.D.)
Department, Program, or Center
Chester F. Carlson Center for Imaging Science (COS)
Matthew J. Homan
Shanchieh Jay Yang
Uzkent, Burak, "Real-time Aerial Vehicle Detection and Tracking using a Multi-modal Optical Sensor" (2016). Thesis. Rochester Institute of Technology. Accessed from
RIT – Main Campus