Share Email Print

Proceedings Paper

Multi-frame adaptive object recognition
Author(s): Abhijit Mahalanobis
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Many traditional methods produce classification results by processing one image frame at a time. For instance, conventional correlation filters are designed to yield well defined correlation peaks when a pattern or object of interest is present in the input image. However, the decision process is memory-less, and does not take advantage of the history of results on previous frames in a sequence. Recently, Kerekes and Kumar introduced a new Bayesian approach for multi-frame correlation that first produces an estimate of the object's location based on previous results, and then builds up the hypothesis using both the current data as well as the historical estimate. A motion model is used as part of this estimation process to predict the probability of the object at a particular location. Since the movement and behavior of objects can change with time, it may be disadvantageous to use a fixed motion model. In this paper, we show that it is possible to let the motion model vary over time, and adaptively update it based on data. Preliminary analysis shows that the adaptive multi-frame approach has the potential for yielding significant performance improvements over the conventional approach based on individual frames.

Paper Details

Date Published: 2 May 2008
PDF: 11 pages
Proc. SPIE 6967, Automatic Target Recognition XVIII, 69670O (2 May 2008); doi: 10.1117/12.781478
Show Author Affiliations
Abhijit Mahalanobis, Lockheed Martin Missiles and Fire Control (United States)

Published in SPIE Proceedings Vol. 6967:
Automatic Target Recognition XVIII
Firooz A. Sadjadi; Abhijit Mahalanobis, Editor(s)

© SPIE. Terms of Use
Back to Top