NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Visual Target Tracking in the Presence of Unknown Observer MotionMuch attention has been given to the visual tracking problem due to its obvious uses in military surveillance. However, visual tracking is complicated by the presence of motion of the observer in addition to the target motion, especially when the image changes caused by the observer motion are large compared to those caused by the target motion. Techniques for estimating the motion of the observer based on image registration techniques and Kalman filtering are presented and simulated. With the effects of the observer motion removed, an additional phase is implemented to track individual targets. This tracking method is demonstrated on an image stream from a buoy-mounted or periscope-mounted camera, where large inter-frame displacements are present due to the wave action on the camera. This system has been shown to be effective at tracking and predicting the global position of a planar vehicle (boat) being observed from a single, out-of-plane camera. Finally, the tracking system has been extended to a multi-target scenario.
Document ID
20150008335
Acquisition Source
Jet Propulsion Laboratory
Document Type
Conference Paper
External Source(s)
Authors
Williams, Stephen
(Georgia Inst. of Tech. Atlanta, GA, United States)
Lu, Thomas
(Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)
Date Acquired
May 18, 2015
Publication Date
April 13, 2009
Subject Category
Instrumentation And Photography
Optics
Meeting Information
Meeting: SPIE Defense, Security and Sensing Conference
Location: Orlando, FL
Country: United States
Start Date: April 13, 2009
End Date: April 17, 2009
Sponsors: Jet Propulsion Lab., California Inst. of Tech.
Distribution Limits
Public
Copyright
Other
Keywords
image mosaic
kalman filter

Available Downloads

There are no available downloads for this record.
No Preview Available