# Efficient SAR Vessel Detection for FPGA-Based On-Satellite Sensing

arXiv: https://arxiv.org/abs/2507.04842 · HTML: https://mlsanity.com/paper/2507.04842/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 99 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 25 of 25)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Trained Quantization Thresholds for Accurate and Efficient Fixed-Point Inference of Deep Neural Networks](https://mlsanity.com/paper/1903.08066/) (2019)
- [Deep Learning Meets SAR](https://mlsanity.com/paper/2006.10027/) (2020)
- [Efficient Multi-Scale Attention Module with Cross-Spatial Learning](https://mlsanity.com/paper/2305.13563/) (2023)
- [BiViT: Extremely Compressed Binary Vision Transformer](https://mlsanity.com/paper/2211.07091/) (2022)
- [xView3-SAR: Detecting Dark Fishing Activity Using Synthetic Aperture Radar Imagery](https://mlsanity.com/paper/2206.00897/) (2022)
- [TerViT: An Efficient Ternary Vision Transformer](https://mlsanity.com/paper/2201.08050/) (2022)
- [Fast model inference and training on-board of Satellites](https://mlsanity.com/paper/2307.08700/) (2023)
- [Layer-specific Optimization for Mixed Data Flow with Mixed Precision in FPGA Design for CNN-based Object Detectors](https://mlsanity.com/paper/2009.01588/) (2020)
- [xT: Nested Tokenization for Larger Context in Large Images](https://mlsanity.com/paper/2403.01915/) (2024)
- [BGF-YOLO: Enhanced YOLOv8 with Multiscale Attentional Feature Fusion for Brain Tumor Detection](https://mlsanity.com/paper/2309.12585/) (2023)
- [A Survey on SAR ship classification using Deep Learning](https://mlsanity.com/paper/2503.11906/) (2025)
- [SATAY: A Streaming Architecture Toolflow for Accelerating YOLO Models on FPGA Devices](https://mlsanity.com/paper/2309.01587/) (2023)
- [DenSe-AdViT: A novel Vision Transformer for Dense SAR Object Detection](https://mlsanity.com/paper/2504.13638/) (2025)

## Abstract (arXiv)

Rapid analysis of satellite imagery within minutes-to-hours of acquisition is increasingly vital for many remote sensing applications, and is an essential component for developing next-generation autonomous and distributed satellite systems. On-satellite machine learning (ML) has the potential for such rapid analysis, by overcoming latency associated with intermittent satellite connectivity to ground stations or relay satellites, but state-of-the-art models are often too large or power-hungry for on-board deployment. Vessel detection using Synthetic Aperture Radar (SAR) is a critical time-sensitive application in maritime security that exemplifies this challenge. SAR vessel detection has previously been demonstrated only by ML models that either are too large for satellite deployment, have not been developed for sufficiently low-power hardware, or have only been tested on small SAR datasets that do not sufficiently represent the difficulty of the real-world task. Here we systematically explore a suite of architectural adaptations to develop a novel YOLOv8 architecture optimized for this task and FPGA-based processing. We deploy our model on a Kria KV260 MPSoC, and show it can analyze a ~700 megapixel SAR image in less than a minute, within common satellite power constraints (<10W). Our model has detection and classification performance only ~2% and 3% lower than values from state-of-the-art GPU-based models on the largest and most diverse open SAR vessel dataset, xView3-SAR, despite being ~50 and ~2500 times more computationally efficient. This work represents a key contribution towards on-satellite ML for time-critical SAR analysis, and more autonomous, scalable satellites.