Share Email Print

Proceedings Paper

Infrared small target detection based on local contrast vector and signed normalization
Author(s): Chaoqun Xia; Xiaorun Li; Shuhan Chen; Liaoying Zhao
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 7 May 2019
PDF: 6 pages
Proc. SPIE 11002, Infrared Technology and Applications XLV, 1100227 (7 May 2019); doi: 10.1117/12.2518194
Show Author Affiliations
Chaoqun Xia, Zhejiang Univ. (China)
Xiaorun Li, Zhejiang Univ. (China)
Shuhan Chen, Zhejiang Univ. (China)
Liaoying Zhao, Hangzhou Dianzi Univ. (China)

Published in SPIE Proceedings Vol. 11002:
Infrared Technology and Applications XLV
Bjørn F. Andresen; Gabor F. Fulop; Charles M. Hanson, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?