Object Tracking using Image Registration and Kalman Filter

Naidu, VPS and Raol, JR Object Tracking using Image Registration and Kalman Filter. In: International Conference on Avionics Systems, 22-23 Feb. 2008,, RCI, Hyderabad.

[img] PDF
S8-8.pdf

Download (448kB)

Abstract

Image registration and Kalman filter based object tracking algorithm is presented. Image registration algorithms viz., sum absolute difference (SAD) and normalized cross correlation (NCC) algorithms are used to find the centroid of the object of interest and Kalman filter is used to track the centroid of the target. Paraboloid interpolation has been used to compute the centroid in sub pixel accuracy. It was observed that in presence of salt and pepper noise, the SAD algorithm performed better and in presence of Gaussian noise, the NCC performed better.

Item Type: Conference or Workshop Item (Paper)
Subjects: AERONAUTICS > Aircraft Communication & Navigation
AERONAUTICS > Avionics & Aircraft Instrumentation
ENGINEERING > Communications and Radar
Depositing User: Dr VPS Naidu
Date Deposited: 06 Jul 2010 04:53
Last Modified: 06 Jul 2010 04:53
URI: http://nal-ir.nal.res.in/id/eprint/8530

Actions (login required)

View Item View Item