Much 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.
Visual Target Tracking in the Presence of Unknown Observer Motion
SPIE Defense, Security and Sensing Conference ; 2009 ; Orlando, FL, United States
2009-04-13
Conference paper
No indication
English
Motion priors for multiple target visual tracking
British Library Online Contents | 2015
|Visual tracking in the presence of motion blur
IEEE | 2005
|Lunar Observer Efficacy for NRHO Target Tracking
TIBKAT | 2023
|Eye tracking of observer-generated target movements.
NTRS | 1968
|Camera motion and visual information fusion for 3D target tracking
Tema Archive | 2004
|