Optimizing ship detection efficiency in SAR images

TL;DR

This paper develops and evaluates efficiency optimization methods for ship detection in satellite SAR images, significantly reducing detection time and cost with minimal performance loss, crucial for timely illegal fishing intervention.

Contribution

It introduces two novel efficiency optimization techniques that can be integrated with existing CNN-based ship detection models to improve speed and reduce computational costs.

Findings

Detection time reduced by up to 75%

Average precision maintained above 92%

Efficiency optimizations are adaptable to different models

Abstract

The detection and prevention of illegal fishing is critical to maintaining a healthy and functional ecosystem. Recent research on ship detection in satellite imagery has focused exclusively on performance improvements, disregarding detection efficiency. However, the speed and compute cost of vessel detection are essential for a timely intervention to prevent illegal fishing. Therefore, we investigated optimization methods that lower detection time and cost with minimal performance loss. We trained an object detection model based on a convolutional neural network (CNN) using a dataset of satellite images. Then, we designed two efficiency optimizations that can be applied to the base CNN or any other base model. The optimizations consist of a fast, cheap classification model and a statistical algorithm. The integration of the optimizations with the object detection model leads to a trade-off between speed and performance. We studied the trade-off using metrics that give different weight to execution time and performance. We show that by using a classification model the average precision of the detection model can be approximated to 99.5% in 44% of the time or to 92.7% in 25% of the time.