J4 ›› 2009, Vol. 36 ›› Issue (6): 1075-1078.

• Original Articles • Previous Articles     Next Articles

Dim infrared targets detection based on background prediction

LI Fan;LIU Shang-qian;HONG Ming;QIN Han-lin   

  1. (School of Technical Physics, Xidian Univ., Xi'an  710071, China)
  • Received:2009-03-10 Online:2009-12-20 Published:2010-01-20
  • Contact: LI Fan E-mail:fionalucifer@gmail.com

Abstract:

In order to solve the difficult problem of dim targets detection in complicated background, a new bilateral filtering method for background prediction is presented. In this method, the true image background is estimated adaptively via bilateral filtering, and the estimated image is subtracted from the source image to suppress background details and enhance target information. To improve the performance of dim targets detection, the gradient statistics is introduced to decrease the compatational amount. Simulations and experiments show that the new algorithm is more efficient in detecting the dim target from complicated background compared with the method based on bilateral filtering.

Key words: image procession, background prediction, dim targets detection, infrared imaging

CLC Number: 

  • TP391