Low-power Ship Detection in Satellite Images Using Neuromorphic Hardware

TL;DR

This paper presents a low-power, two-stage satellite ship detection system combining a lightweight classifier on neuromorphic hardware with a YOLOv5 detector, significantly reducing energy use while maintaining high accuracy.

Contribution

It introduces a novel two-stage approach utilizing neuromorphic hardware for efficient on-board ship detection in satellite images, reducing power consumption compared to traditional methods.

Findings

Achieves 76.9% mAP on the dataset.

Reduces energy consumption from 111.4 kJ to 27.3 kJ.

Operates efficiently on neuromorphic hardware.

Abstract

Transmitting Earth observation image data from satellites to ground stations incurs significant costs in terms of power and bandwidth. For maritime ship detection, on-board data processing can identify ships and reduce the amount of data sent to the ground. However, most images captured on board contain only bodies of water or land, with the Airbus Ship Detection dataset showing only 22.1\% of images containing ships. We designed a low-power, two-stage system to optimize performance instead of relying on a single complex model. The first stage is a lightweight binary classifier that acts as a gating mechanism to detect the presence of ships. This stage runs on Brainchip's Akida 1.0, which leverages activation sparsity to minimize dynamic power consumption. The second stage employs a YOLOv5 object detection model to identify the location and size of ships. This approach achieves a mean Average Precision (mAP) of 76.9\%, which increases to 79.3\% when evaluated solely on images containing ships, by reducing false positives. Additionally, we calculated that evaluating the full validation set on a NVIDIA Jetson Nano device requires 111.4 kJ of energy. Our two-stage system reduces this energy consumption to 27.3 kJ, which is less than a fourth, demonstrating the efficiency of a heterogeneous computing system.