Share Email Print
cover

Proceedings Paper • new

Small target detection based on infrared patch-tensor model with structured sparse regularization
Author(s): Xuewei Guan; Zhenming Peng; Landan Zhang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Infrared (IR) small target detection in complex background is one of the key techniques in many defense systems. In this paper, a novel method based on infrared patch-tensor model with structured sparse regularization (IPTSS) is proposed for small IR target detection. To overcome the structured edge interferences , the IPTSS model adds an edge structured sparse item utilizing the ℓ1,1,2 norm minimization constraint to the IPT model based on partial sum of tensor nuclear norm (PSTNN). An efficient optimization algorithm based on alternating direction method of multipliers (ADMM) is designed to solve the proposed IPTSS model. After the target-background-edge components are separated, the target image can be reconstructed. Finally, small targets can be extracted easily via adaptive threshold segmentation in the reconstructed target image. Extensive experimental results demonstrate that the proposed method can effectively enhance small IR targets while suppressing the complex background in various scenes.

Paper Details

Date Published: 18 December 2019
PDF: 6 pages
Proc. SPIE 11338, AOPC 2019: Optical Sensing and Imaging Technology, 1133821 (18 December 2019); doi: 10.1117/12.2546185
Show Author Affiliations
Xuewei Guan, Univ. of Electronic Science and Technology of China (China)
Zhenming Peng, Univ. of Electronic Science and Technology of China (China)
Landan Zhang, Univ. of Electronic Science and Technology of China (China)


Published in SPIE Proceedings Vol. 11338:
AOPC 2019: Optical Sensing and Imaging Technology
John E. Greivenkamp; Jun Tanida; Yadong Jiang; HaiMei Gong; Jin Lu; Dong Liu, Editor(s)

© SPIE. Terms of Use
Back to Top