"

Cookies ussage consent

I agree.

Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.

A novel LBP based algorithm for small target detection in infrared image

TONG GUOa1, XIECHANG SUN2,* , MENG LI2, WEIDONG XIAO1

Affiliation

  1. Science and Technology on Information System Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
  2. Space Star Technology Co., Ltd., China Academy of Space Technology (CAST), Beijing 100086, China

Abstract

Small target detection is a crucial problem in Infrared Search and Track (IRST) systems. Conventional algorithms encounter a high false alarm ratio under situations with cluttered background. Here a novel algorithm based on modified local binary pattern (LBP) model is proposed to deal with this problem. The modified LBP process will generate a specific uniform pattern at the position where potential small targets exist, while background and other image components will generate different patterns because of their different intensity distribution from target. After potential small target is determined a post process using fusion image of two LBP images is incorporated to preserve target information. The algorithm is real-time. Comparative experimental results demonstrate its efficiency and robustness..

Keywords

Small target detection, Local binary patterns, Fusion image, Target preservation.

Citation

TONG GUOa, XIECHANG SUN, MENG LI, WEIDONG XIAO, A novel LBP based algorithm for small target detection in infrared image, Optoelectronics and Advanced Materials - Rapid Communications, 7, 9-10, September-October 2013, pp.672-675 (2013).

Submitted at: Dec. 22, 2012

Accepted at: Sept. 18, 2013