Lightweight CNNs for Embedded SAR Ship Target Detection and Classification

TL;DR

This paper introduces lightweight neural networks tailored for real-time onboard processing of SAR data to detect and classify maritime vessels, aiming to reduce data transmission and latency in satellite surveillance.

Contribution

It proposes and evaluates neural network models suitable for deployment on satellites' limited hardware, enabling onboard ship detection and classification from SAR data.

Findings

Feasibility of real-time onboard SAR data processing using lightweight neural networks.

Successful deployment of a model on FPGA hardware.

Effective binary classification between ships and windmills.

Abstract

Synthetic Aperture Radar (SAR) data enables large-scale surveillance of maritime vessels. However, near-real-time monitoring is currently constrained by the need to downlink all raw data, perform image focusing, and subsequently analyze it on the ground. On-board processing to generate higher-level products could reduce the data volume that needs to be downlinked, alleviating bandwidth constraints and minimizing latency. However, traditional image focusing and processing algorithms face challenges due to the satellite's limited memory, processing power, and computational resources. This work proposes and evaluates neural networks designed for real-time inference on unfocused SAR data acquired in Stripmap and Interferometric Wide (IW) modes captured with Sentinel-1. Our results demonstrate the feasibility of using one of our models for on-board processing and deployment on an FPGA. Additionally, by investigating a binary classification task between ships and windmills, we demonstrate that target classification is possible.