eWaSR -- an embedded-compute-ready maritime obstacle detection network

TL;DR

This paper introduces eWaSR, an efficient maritime obstacle detection network optimized for embedded devices, achieving near state-of-the-art accuracy with significantly improved speed and memory efficiency, enabling practical deployment on autonomous surface vehicles.

Contribution

The paper presents eWaSR, a novel lightweight maritime obstacle detection network that maintains high accuracy while being suitable for embedded hardware, based on transformer-based design improvements.

Findings

eWaSR achieves only 0.52% F1 score drop compared to WaSR.

eWaSR runs 10x faster on GPU than WaSR (115 FPS vs 11 FPS).

eWaSR operates at 5.5 FPS on embedded OAK-D device.

Abstract

Maritime obstacle detection is critical for safe navigation of autonomous surface vehicles (ASVs). While the accuracy of image-based detection methods has advanced substantially, their computational and memory requirements prohibit deployment on embedded devices. In this paper we analyze the currently best-performing maritime obstacle detection network WaSR. Based on the analysis we then propose replacements for the most computationally intensive stages and propose its embedded-compute-ready variant eWaSR. In particular, the new design follows the most recent advancements of transformer-based lightweight networks. eWaSR achieves comparable detection results to state-of-the-art WaSR with only 0.52% F1 score performance drop and outperforms other state-of-the-art embedded-ready architectures by over 9.74% in F1 score. On a standard GPU, eWaSR runs 10x faster than the original WaSR (115 FPS vs 11 FPS). Tests on a real embedded device OAK-D show that, while WaSR cannot run due to memory restrictions, eWaSR runs comfortably at 5.5 FPS. This makes eWaSR the first practical embedded-compute-ready maritime obstacle detection network. The source code and trained eWaSR models are publicly available here: https://github.com/tersekmatija/eWaSR.