The Aqualoc Dataset: Towards Real-Time Underwater Localization from a Visual-Inertial-Pressure Acquisition System
arXiv:1809.07076v12 citations
Originality Synthesis-oriented
AI Analysis
This addresses the need for standardized datasets in underwater robotics for researchers and engineers, but it is incremental as it focuses on data collection rather than novel algorithms.
The paper tackles the problem of benchmarking underwater localization by introducing the Aqualoc dataset, which provides visual-inertial-pressure data and ground-truth trajectories for evaluating odometry and SLAM solutions, and it is publicly available.
This paper presents a new underwater dataset acquired from a visual-inertial-pressure acquisition system and meant to be used to benchmark visual odometry, visual SLAM and multi-sensors SLAM solutions. The dataset is publicly available and contains ground-truth trajectories for evaluation.