Paper
18 December 2019 Small target detection based on infrared patch-tensor model with structured sparse regularization
Author Affiliations +
Proceedings Volume 11338, AOPC 2019: Optical Sensing and Imaging Technology; 1133821 (2019) https://doi.org/10.1117/12.2546185
Event: Applied Optics and Photonics China (AOPC2019), 2019, Beijing, China
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.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xuewei Guan, Zhenming Peng, and Landan Zhang "Small target detection based on infrared patch-tensor model with structured sparse regularization", Proc. SPIE 11338, AOPC 2019: Optical Sensing and Imaging Technology, 1133821 (18 December 2019); https://doi.org/10.1117/12.2546185
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Target detection

Infrared radiation

Infrared detectors

Infrared imaging

3D modeling

Image segmentation

Optimization (mathematics)

Back to Top