Impact of Surface Reflections in Maritime Obstacle Detection

TL;DR

This paper investigates how water surface reflections impact maritime obstacle detection performance, demonstrating their adverse effects and proposing a novel filtering method to reduce false positives caused by reflections.

Contribution

The study quantifies the effect of surface reflections on detector accuracy and introduces the Heatmap Based Sliding Filter to effectively reduce false positives from reflections.

Findings

Reflections decrease mAP by 1.2 to 9.6 points across detectors.

The proposed filter reduces false positives by 34.64%.

Datasets with and without reflections are publicly available.

Abstract

Maritime obstacle detection aims to detect possible obstacles for autonomous driving of unmanned surface vehicles. In the context of maritime obstacle detection, the water surface can act like a mirror on certain circumstances, causing reflections on imagery. Previous works have indicated surface reflections as a source of false positives for object detectors in maritime obstacle detection tasks. In this work, we show that surface reflections indeed adversely affect detector performance. We measure the effect of reflections by testing on two custom datasets, which we make publicly available. The first one contains imagery with reflections, while in the second reflections are inpainted. We show that the reflections reduce mAP by 1.2 to 9.6 points across various detectors. To remove false positives on reflections, we propose a novel filtering approach named Heatmap Based Sliding Filter. We show that the proposed method reduces the total number of false positives by 34.64% while minimally affecting true positives. We also conduct qualitative analysis and show that the proposed method indeed removes false positives on the reflections. The datasets can be found on https://github.com/SamedYalcin/MRAD.