Lightweight CNNs for Embedded SAR Ship Target Detection and Classification
This work addresses bandwidth and latency constraints for satellite-based surveillance, though it is incremental in applying existing CNN methods to a new data type.
The paper tackles the problem of near-real-time maritime vessel monitoring using SAR data by proposing lightweight CNNs for on-board processing of unfocused SAR data, demonstrating feasibility with deployment on an FPGA and achieving target classification between ships and windmills.
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.