Graph Laplacian regularization based edge-preserving background estimation for single frame small target detection

Kun Bai; Yuehuang Wang; Qiong Song; Mingna Liu; Jiandong Wu

doi:10.1117/12.2193505

13 October 2015 Graph Laplacian regularization based edge-preserving background estimation for single frame small target detection

Kun Bai, Yuehuang Wang, Qiong Song, Mingna Liu, Jiandong Wu

Author Affiliations +

Proceedings Volume 9648, Electro-Optical and Infrared Systems: Technology and Applications XII; and Quantum Information Science and Technology; 96480L (2015) https://doi.org/10.1117/12.2193505
Event: SPIE Security + Defence, 2015, Toulouse, France

Abstract

Small target detection in the clutter infrared image is a tough but significant work. In this paper, we will propose a novel small target detection method. First, Graph Laplacian regularization is utilized to model similarity feature of graph structure in the image. And Graph Laplacian regularization is incorporated in the background estimation model to preserve edges of background in single frame infrared image. At last, the edge-preserving estimated background is eliminated from original image to get foreground image which is used to detect the small target. Experimental results show that our proposed method can achieve edge-preserving estimation of background, suppress clutter efficiently, and get better detection results.

Citation Download Citation

Kun Bai, Yuehuang Wang, Qiong Song, Mingna Liu, and Jiandong Wu "Graph Laplacian regularization based edge-preserving background estimation for single frame small target detection", Proc. SPIE 9648, Electro-Optical and Infrared Systems: Technology and Applications XII; and Quantum Information Science and Technology, 96480L (13 October 2015); https://doi.org/10.1117/12.2193505

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