Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques
With advances in both classical and modern methods,synthetic aperture radar (SAR) automatic target recognition (ATR) has made enormous progress. This article reviews a wide range of SAR ATR techniques, from model- and template-based approaches to statistical techniques, such as constant false alarm...
Saved in:
| Main Authors: | , |
|---|---|
| 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/11082447/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849243600971366400 |
|---|---|
| author | Jakub Slesinski Damian Wierzbicki |
| author_facet | Jakub Slesinski Damian Wierzbicki |
| author_sort | Jakub Slesinski |
| collection | DOAJ |
| description | With advances in both classical and modern methods,synthetic aperture radar (SAR) automatic target recognition (ATR) has made enormous progress. This article reviews a wide range of SAR ATR techniques, from model- and template-based approaches to statistical techniques, such as constant false alarm rate, as well as the increasing impact of machine learning and deep learning. What makes SAR imagery particularly unique are problems, such as speckle noise, target variability, and clutter, for which there are specialized solutions described in this article. Feature-based approaches in traditional SAR ATR followed from conventional feature-driven strategies, while modern data-driven end-to-end recognition methods, consisting primarily of convolutional neural network based and hybrid networks, have been applied. The performance has further been enhanced with techniques, such as transfer learning, unsupervised learning, and adversarial learning, to overcome data scarcity and variability. Alongside these techniques, this review also looks at application-specific methods suited to operational needs, such as real-time detection, robust classification, an identification of small objects, and new data handling techniques, such as data augmentation and multimodal fusion. Based on architectures, learning paradigms, and operational contexts, a detailed taxonomy bridges classical and contemporary SAR ATR methods. This article consolidates advancements and outlines challenges to present a unified framework for researchers and practitioners to understand future directions of SAR ATR development in military and civilian applications. |
| format | Article |
| id | doaj-art-6bb7d794f5694b95b0e53d8036f1d69f |
| institution | Kabale University |
| 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-6bb7d794f5694b95b0e53d8036f1d69f2025-08-20T03:59:25ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118189781902410.1109/JSTARS.2025.358980411082447Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning TechniquesJakub Slesinski0Damian Wierzbicki1https://orcid.org/0000-0001-6192-3894Department of Imagery Intelligence, Faculty of Civil Engineering and Geodesy, Military University of Technology, Warsaw, PolandDepartment of Imagery Intelligence, Faculty of Civil Engineering and Geodesy, Military University of Technology, Warsaw, PolandWith advances in both classical and modern methods,synthetic aperture radar (SAR) automatic target recognition (ATR) has made enormous progress. This article reviews a wide range of SAR ATR techniques, from model- and template-based approaches to statistical techniques, such as constant false alarm rate, as well as the increasing impact of machine learning and deep learning. What makes SAR imagery particularly unique are problems, such as speckle noise, target variability, and clutter, for which there are specialized solutions described in this article. Feature-based approaches in traditional SAR ATR followed from conventional feature-driven strategies, while modern data-driven end-to-end recognition methods, consisting primarily of convolutional neural network based and hybrid networks, have been applied. The performance has further been enhanced with techniques, such as transfer learning, unsupervised learning, and adversarial learning, to overcome data scarcity and variability. Alongside these techniques, this review also looks at application-specific methods suited to operational needs, such as real-time detection, robust classification, an identification of small objects, and new data handling techniques, such as data augmentation and multimodal fusion. Based on architectures, learning paradigms, and operational contexts, a detailed taxonomy bridges classical and contemporary SAR ATR methods. This article consolidates advancements and outlines challenges to present a unified framework for researchers and practitioners to understand future directions of SAR ATR development in military and civilian applications.https://ieeexplore.ieee.org/document/11082447/Automatic target recognition (ATR)convolutional neural networks (CNNs)data enhancementdeep learning (DL)feature extractionmachine learning (ML) |
| spellingShingle | Jakub Slesinski Damian Wierzbicki Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Automatic target recognition (ATR) convolutional neural networks (CNNs) data enhancement deep learning (DL) feature extraction machine learning (ML) |
| title | Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques |
| title_full | Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques |
| title_fullStr | Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques |
| title_full_unstemmed | Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques |
| title_short | Review of Synthetic Aperture Radar Automatic Target Recognition: A Dual Perspective on Classical and Deep Learning Techniques |
| title_sort | review of synthetic aperture radar automatic target recognition a dual perspective on classical and deep learning techniques |
| topic | Automatic target recognition (ATR) convolutional neural networks (CNNs) data enhancement deep learning (DL) feature extraction machine learning (ML) |
| url | https://ieeexplore.ieee.org/document/11082447/ |
| work_keys_str_mv | AT jakubslesinski reviewofsyntheticapertureradarautomatictargetrecognitionadualperspectiveonclassicalanddeeplearningtechniques AT damianwierzbicki reviewofsyntheticapertureradarautomatictargetrecognitionadualperspectiveonclassicalanddeeplearningtechniques |