Paper ID: 2403.08360

Improved Image-based Pose Regressor Models for Underwater Environments

Luyuan Peng, Hari Vishnu, Mandar Chitre, Yuen Min Too, Bharath Kalyan, Rajat Mishra

We investigate the performance of image-based pose regressor models in underwater environments for relocalization. Leveraging PoseNet and PoseLSTM, we regress a 6-degree-of-freedom pose from single RGB images with high accuracy. Additionally, we explore data augmentation with stereo camera images to improve model accuracy. Experimental results demonstrate that the models achieve high accuracy in both simulated and clear waters, promising effective real-world underwater navigation and inspection applications.

Submitted: Mar 13, 2024