A BlueROV2-based platform for underwater mapping experiments

TL;DR

This work presents a low-cost, lab-based platform for underwater mapping using a BlueROV2 in a pool equipped with an overhead camera. It combines an extended Kalman filter for pose estimation—fusing overhead-image segmentation, IMU, and pressure data—with YOLOv5-based litter detection and inverse-projection mapping to generate a litter map. Experimental results show centimeter-level pose accuracy in a small tank and around 12 cm XY mapping error in a larger pool, with datasets and code publicly released to enable rapid development and benchmarking. The platform aims to accelerate underwater autonomy research and support field efforts such as SeaClear2.0 by providing an accessible, reproducible testbed for pose estimation, detection, and mapping components.

Abstract

We propose a low-cost laboratory platform for development and validation of underwater mapping techniques, using the BlueROV2 Remotely Operated Vehicle (ROV). Both the ROV and the objects to be mapped are placed in a pool that is imaged via an overhead camera. In our prototype mapping application, the ROV's pose is found using extended Kalman filtering on measurements from the overhead camera, inertial, and pressure sensors; while objects are detected with a deep neural network in the ROV camera stream. Validation experiments are performed for pose estimation, detection, and mapping. The litter detection dataset and code are made publicly available.

Figures (8)

• Figure 1: Capture of working area from the overhead camera
• Figure 2: Functional diagram
• Figure 3: Example of YOLOv5 detections in an camera frame
• Figure 4: Procedure to find an object's world-frame coordinates
• Figure 5: Experimental set-up for pose validation