Aerial-target detection using the recursive temporal profile and spatiotemporal gradient pattern in infrared image sequences

Yun Sik Jung; Taek Lyul Song

doi:10.1117/1.OE.51.6.066401

5 June 2012 Aerial-target detection using the recursive temporal profile and spatiotemporal gradient pattern in infrared image sequences

Yun Sik Jung, Taek Lyul Song

Author Affiliations +

Optical Engineering, Vol. 51, Issue 6, 066401 (June 2012). https://doi.org/10.1117/1.OE.51.6.066401

Abstract

A new spatiotemporal target detection method that utilizes the recursive temporal profile (RTP) and the spatiotemporal gradient pattern (STGP) is proposed for infrared (IR) image sequence. In the IR search and tracking system, long-distance aerial targets compared with short-distance aerial targets appear to be composed of several pixels with no special shapes and their movements are slow. Considering the characteristics of aerial targets, an algorithm based on the STGP and fuzzy-set theory is proposed to detect long-distance aerial targets while the recursive temporal profile algorithm based on the temporal profile and mean estimation is proposed to detect short-distance aerial targets. In addition, the RTP and the STGP are combined to detect the aerial targets that exist at diverse distances in the IR image sequence. The performance of the proposed method is examined by using the receiver operating characteristic curve. The experiment results show that the proposed method performs better than the existing methods in terms of target detection and clutter removal.

Citation Download Citation

Yun Sik Jung and Taek Lyul Song "Aerial-target detection using the recursive temporal profile and spatiotemporal gradient pattern in infrared image sequences," Optical Engineering 51(6), 066401 (5 June 2012). https://doi.org/10.1117/1.OE.51.6.066401

Published: 5 June 2012

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

Includes PDF, HTML & Video, when available