Infrared small target detection based on local contrast vector and signed normalization

Chaoqun Xia; Xiaorun Li; Shuhan Chen; Liaoying Zhao

doi:10.1117/12.2518194

7 May 2019 Infrared small target detection based on local contrast vector and signed normalization

Chaoqun Xia, Xiaorun Li, Shuhan Chen, Liaoying Zhao

Proceedings Volume 11002, Infrared Technology and Applications XLV; 1100227 (2019) https://doi.org/10.1117/12.2518194
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

Infrared small target detection under intricate background and heavy noise is one of the crucial tasks in the field of infrared search and tracking (IRST) system. The images with small targets are usually of quite low signal-to-noise ratios, which makes the targets very difficult to be detected. To solve this problem, an effective infrared small target detection algorithm is presented in this paper. Firstly, a nested structure of the original pixel-wise image is constructed and the local structural discontinuity of each pixel is measured by a vector so-called local contrast vector (LCV). Each element of LCV describes the minimal difference between the central region and its neighboring regions, and the scale variety of regions results in the variety of elements. Then, a multi-dimensional image is generated with respect to LCV. After that, a confidence map for small target detection is reconstructed by signed normalization, that is, each pixel in the confidence map is generated by signed inner product of LCV. Finally, we segment the targets from the confidence map by utilizing an adaptive threshold. Extensive experimental evaluation results on a real test dataset demonstrate that our algorithm is superior to the state-of-the-art algorithms in detection performance.

Conference Presentation

Citation Download Citation

Chaoqun Xia, Xiaorun Li, Shuhan Chen, and Liaoying Zhao "Infrared small target detection based on local contrast vector and signed normalization", Proc. SPIE 11002, Infrared Technology and Applications XLV, 1100227 (7 May 2019); https://doi.org/10.1117/12.2518194

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