Visual Temporal Fusion Based Free Space Segmentation for Autonomous Surface Vessels

TL;DR

This paper presents a novel visual temporal fusion model for free space segmentation in autonomous surface vessels, addressing water surface challenges with a new evaluation method and loss function, resulting in high accuracy and robustness.

Contribution

The paper introduces a visual temporal fusion approach, a new evaluation procedure, and a contour-based loss function tailored for surface free space segmentation in ASVs.

Findings

Achieved high-accuracy free space segmentation results.

Demonstrated robustness against water surface reflections and vibrations.

Provided a new dataset for surface free space segmentation tasks.

Abstract

The use of Autonomous Surface Vessels (ASVs) is growing rapidly. For safe and efficient surface auto-driving, a reliable perception system is crucial. Such systems allow the vessels to sense their surroundings and make decisions based on the information gathered. During the perception process, free space segmentation is essential to distinguish the safe mission zone and segment the operational waterways. However, ASVs face particular challenges in free space segmentation due to nearshore reflection interference, complex water textures, and random motion vibrations caused by the water surface conditions. To deal with these challenges, we propose a visual temporal fusion based free space segmentation model to utilize the previous vision information. In addition, we also introduce a new evaluation procedure and a contour position based loss calculation function, which are more suitable for surface free space segmentation tasks. The proposed model and process are tested on a continuous video segmentation dataset and achieve both high-accuracy and robust results. The dataset is also made available along with this paper.