DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model

Detecting small targets in complex infrared backgrounds is challenging due to edge aliasing and noise interference. Tensor decomposition methods show potential but have limitations in these conditions. This paper proposes a dynamic motion saliency infrared tensor model that integrates temporal infor...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoling Ge, Weixian Qian, Zipeng Fu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10762872/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164952411668480
author Xiaoling Ge
Weixian Qian
Zipeng Fu
author_facet Xiaoling Ge
Weixian Qian
Zipeng Fu
author_sort Xiaoling Ge
collection DOAJ
description Detecting small targets in complex infrared backgrounds is challenging due to edge aliasing and noise interference. Tensor decomposition methods show potential but have limitations in these conditions. This paper proposes a dynamic motion saliency infrared tensor model that integrates temporal information to address these challenges. The method formulates target detection as a low-rank sparse tensor decomposition problem in the spatiotemporal domain. First, we construct the infrared sequence into a holistic spatiotemporal tensor model (STTM) to utilize both spatial and temporal information. Then, based on the sparse-enhanced Tucker decomposition framework, we design a multi-scale energy movement saliency map (MESM) from target motion characteristics. This map serves as a sparse prior, incorporated into the STTM, providing strong decomposition guidance even when the target contrast is weak or overlapped with strong edges. Additionally, we propose a reweighted scheme integrating motion saliency based on the minimum temporal projection of the target component after each iteration, suppressing background clutter and enhancing target separation. Next, for more precise background estimation, we use an accurate low-rank approximation and extend the overlapping group sparse total variation (OGSTV) regularization from 2D to 3D. Compared to traditional variational methods, 3D-OGSTV better distinguishes edges from flat regions, improving background suppression and detection accuracy. Finally, an alternating direction method of multipliers (ADMM) is used for efficient optimization. Experimental results show our approach outperforms state-of-the-art methods, offering better robustness and accuracy in complex scenes.
format Article
id doaj-art-d8f669b5130549cc9ae96bc59e910d93
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-d8f669b5130549cc9ae96bc59e910d932025-08-20T02:21:51ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01181472149910.1109/JSTARS.2024.350440210762872DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor ModelXiaoling Ge0https://orcid.org/0009-0008-7485-8639Weixian Qian1https://orcid.org/0009-0000-5061-712XZipeng Fu2School of Electronic and Optical Engineering and the Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Electronic and Optical Engineering and the Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, ChinaSchool of Electronic and Optical Engineering and the Jiangsu Key Laboratory of Spectral Imaging and Intelligent Sense, Nanjing University of Science and Technology, Nanjing, ChinaDetecting small targets in complex infrared backgrounds is challenging due to edge aliasing and noise interference. Tensor decomposition methods show potential but have limitations in these conditions. This paper proposes a dynamic motion saliency infrared tensor model that integrates temporal information to address these challenges. The method formulates target detection as a low-rank sparse tensor decomposition problem in the spatiotemporal domain. First, we construct the infrared sequence into a holistic spatiotemporal tensor model (STTM) to utilize both spatial and temporal information. Then, based on the sparse-enhanced Tucker decomposition framework, we design a multi-scale energy movement saliency map (MESM) from target motion characteristics. This map serves as a sparse prior, incorporated into the STTM, providing strong decomposition guidance even when the target contrast is weak or overlapped with strong edges. Additionally, we propose a reweighted scheme integrating motion saliency based on the minimum temporal projection of the target component after each iteration, suppressing background clutter and enhancing target separation. Next, for more precise background estimation, we use an accurate low-rank approximation and extend the overlapping group sparse total variation (OGSTV) regularization from 2D to 3D. Compared to traditional variational methods, 3D-OGSTV better distinguishes edges from flat regions, improving background suppression and detection accuracy. Finally, an alternating direction method of multipliers (ADMM) is used for efficient optimization. Experimental results show our approach outperforms state-of-the-art methods, offering better robustness and accuracy in complex scenes.https://ieeexplore.ieee.org/document/10762872/Infrared (IR) small target detectionmultiscale energy movementoverlapping group sparse total variation (OGSTV)
spellingShingle Xiaoling Ge
Weixian Qian
Zipeng Fu
DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Infrared (IR) small target detection
multiscale energy movement
overlapping group sparse total variation (OGSTV)
title DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model
title_full DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model
title_fullStr DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model
title_full_unstemmed DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model
title_short DMS-OGSTV: A Novel Infrared Small Target Detection Based on Spatial-Temporal Tensor Model
title_sort dms ogstv a novel infrared small target detection based on spatial temporal tensor model
topic Infrared (IR) small target detection
multiscale energy movement
overlapping group sparse total variation (OGSTV)
url https://ieeexplore.ieee.org/document/10762872/
work_keys_str_mv AT xiaolingge dmsogstvanovelinfraredsmalltargetdetectionbasedonspatialtemporaltensormodel
AT weixianqian dmsogstvanovelinfraredsmalltargetdetectionbasedonspatialtemporaltensormodel
AT zipengfu dmsogstvanovelinfraredsmalltargetdetectionbasedonspatialtemporaltensormodel