Stable Yaw Estimation of Boats from the Viewpoint of UAVs and USVs

TL;DR

This paper introduces an extended HyperPosePDF method for robust boat yaw estimation from UAV and USV viewpoints, utilizing video data and probability aggregation to improve accuracy in marine robotics applications.

Contribution

We extend HyperPosePDF for video-based scenarios and propose a probability aggregation technique to enhance yaw estimation accuracy in marine robotics.

Findings

Significant improvement in yaw prediction accuracy with probability aggregation.

Robust orientation predictions across video sequences.

Effective application on datasets like SeaDronesSee-3D and BOArienT.

Abstract

Yaw estimation of boats from the viewpoint of unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) or boats is a crucial task in various applications such as 3D scene rendering, trajectory prediction, and navigation. However, the lack of literature on yaw estimation of objects from the viewpoint of UAVs has motivated us to address this domain. In this paper, we propose a method based on HyperPosePDF for predicting the orientation of boats in the 6D space. For that, we use existing datasets, such as PASCAL3D+ and our own datasets, SeaDronesSee-3D and BOArienT, which we annotated manually. We extend HyperPosePDF to work in video-based scenarios, such that it yields robust orientation predictions across time. Naively applying HyperPosePDF on video data yields single-point predictions, resulting in far-off predictions and often incorrect symmetric orientations due to unseen or visually different data. To alleviate this issue, we propose aggregating the probability distributions of pose predictions, resulting in significantly improved performance, as shown in our experimental evaluation. Our proposed method could significantly benefit downstream tasks in marine robotics.