Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

NASTaR: NovaSAR Automated Ship Target Recognition Dataset

Benyamin Hosseiny, Kamirul Kamirul, Odysseas Pappas, Alin Achim

TL;DR

The paper tackles the challenge of fine-grained ship-type classification in SAR imagery, emphasizing the scarcity of large, annotated S-band datasets. It introduces NASTaR, a NovaSAR S-band benchmark built from AIS-aligned ship patches, with inshore/offshore tags and a wake subset, and benchmarks multiple deep learning architectures to establish baselines. Key contributions include a 1891 Ship patches and 500 wake patches dataset across 23 ship classes, plus a semi-automated extraction workflow and extensive statistics on ship morphology and movement. The work enables cross-band generalization studies and wake-informed maritime surveillance research, providing a valuable resource for future architecture design and analysis of wake effects on SAR signatures.

Abstract

Synthetic Aperture Radar (SAR) offers a unique capability for all-weather, space-based maritime activity monitoring by capturing and imaging strong reflections from ships at sea. A well-defined challenge in this domain is ship type classification. Due to the high diversity and complexity of ship types, accurate recognition is difficult and typically requires specialized deep learning models. These models, however, depend on large, high-quality ground-truth datasets to achieve robust performance and generalization. Furthermore, the growing variety of SAR satellites operating at different frequencies and spatial resolutions has amplified the need for more annotated datasets to enhance model accuracy. To address this, we present the NovaSAR Automated Ship Target Recognition (NASTaR) dataset. This dataset comprises of 3415 ship patches extracted from NovaSAR S-band imagery, with labels matched to AIS data. It includes distinctive features such as 23 unique classes, inshore/offshore separation, and an auxiliary wake dataset for patches where ship wakes are visible. We validated the dataset applicability across prominent ship-type classification scenarios using benchmark deep learning models. Results demonstrate over 60% accuracy for classifying four major ship types, over 70% for a three-class scenario, more than 75% for distinguishing cargo from tanker ships, and over 87% for identifying fishing vessels. The NASTaR dataset is available at https://10.5523/bris, while relevant codes for benchmarking and analysis are available at https://github.com/benyaminhosseiny/nastar.

NASTaR: NovaSAR Automated Ship Target Recognition Dataset

TL;DR

The paper tackles the challenge of fine-grained ship-type classification in SAR imagery, emphasizing the scarcity of large, annotated S-band datasets. It introduces NASTaR, a NovaSAR S-band benchmark built from AIS-aligned ship patches, with inshore/offshore tags and a wake subset, and benchmarks multiple deep learning architectures to establish baselines. Key contributions include a 1891 Ship patches and 500 wake patches dataset across 23 ship classes, plus a semi-automated extraction workflow and extensive statistics on ship morphology and movement. The work enables cross-band generalization studies and wake-informed maritime surveillance research, providing a valuable resource for future architecture design and analysis of wake effects on SAR signatures.

Abstract

Synthetic Aperture Radar (SAR) offers a unique capability for all-weather, space-based maritime activity monitoring by capturing and imaging strong reflections from ships at sea. A well-defined challenge in this domain is ship type classification. Due to the high diversity and complexity of ship types, accurate recognition is difficult and typically requires specialized deep learning models. These models, however, depend on large, high-quality ground-truth datasets to achieve robust performance and generalization. Furthermore, the growing variety of SAR satellites operating at different frequencies and spatial resolutions has amplified the need for more annotated datasets to enhance model accuracy. To address this, we present the NovaSAR Automated Ship Target Recognition (NASTaR) dataset. This dataset comprises of 3415 ship patches extracted from NovaSAR S-band imagery, with labels matched to AIS data. It includes distinctive features such as 23 unique classes, inshore/offshore separation, and an auxiliary wake dataset for patches where ship wakes are visible. We validated the dataset applicability across prominent ship-type classification scenarios using benchmark deep learning models. Results demonstrate over 60% accuracy for classifying four major ship types, over 70% for a three-class scenario, more than 75% for distinguishing cargo from tanker ships, and over 87% for identifying fishing vessels. The NASTaR dataset is available at https://10.5523/bris, while relevant codes for benchmarking and analysis are available at https://github.com/benyaminhosseiny/nastar.

Paper Structure

This paper contains 7 sections, 6 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Existing SAR Ship Recognition Datasets
  4. Deep learning Techniques in Ship Target Recognition
  5. The NASTaR Dataset
  6. Benchmark Experiments
  7. Conclusion

Figures (6)

  • Figure 1: Geographic and temporal distribution of the constructed dataset
  • Figure 2: Block diagram of the semi-automated patch extraction pipeline.
  • Figure 3: Class distribution of the extracted ship images.
  • Figure 4: Corresponding class distribution of extracted ship wakes.
  • Figure 5: Statistical distribution of ship characteristics: a) Length, b) Width, c) SOG, d) Heading angle
  • ...and 1 more figures