Hidden Markov Models for background clutter

Qian Li; Cui Yang; Jian-Qi Zhang; Dong-Yang Zhang

doi:10.1117/1.OE.52.7.073108

16 July 2013 Hidden Markov Models for background clutter

Qian Li, Cui Yang, Jian-Qi Zhang, Dong-Yang Zhang

Author Affiliations +

Funded by: Fundamental Research Funds for the Central Universities, National Science Foundation of China

Optical Engineering, Vol. 52, Issue 7, 073108 (July 2013). https://doi.org/10.1117/1.OE.52.7.073108

Abstract

The development of a target acquisition performance model for an electro-optical imaging system is seriously affected by the description of the target and background characteristics at present. Based on the Hidden Markov Model (HMM), a different clutter metric is proposed to quantify the influence of background on target detection in this article. It first simulates the process of recording a target in the human brain by optimizing the HMM parameters to represent the target as far as possible. And then the background clutter is defined to be the similarity, estimated by the computed model parameters, between the target and background. Finally, the newly proposed clutter metric is applied to the Search2 database, and the experiment results prove its superiority to other metrics.

Citation Download Citation

Qian Li, Cui Yang, Jian-Qi Zhang, and Dong-Yang Zhang "Hidden Markov Models for background clutter," Optical Engineering 52(7), 073108 (16 July 2013). https://doi.org/10.1117/1.OE.52.7.073108

Published: 16 July 2013

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE