Attenuation-Aware Weighted Optical Flow with Medium Transmission Map for Learning-based Visual Odometry in Underwater terrain

TL;DR

This paper introduces wflow-TartanVO, a novel underwater optical flow method that improves visual odometry accuracy by weighting flow estimates based on medium transmission, without needing fine-tuning of existing models.

Contribution

It presents a medium transmission map-based weighting scheme for optical flow in underwater VO, enhancing robustness and accuracy without retraining pre-existing models.

Findings

Outperforms baseline VO methods on real underwater datasets.

Significantly reduces Absolute Trajectory Error (ATE).

Does not require fine-tuning of pre-trained models.

Abstract

This paper addresses the challenge of improving learning-based monocular visual odometry (VO) in underwater environments by integrating principles of underwater optical imaging to manipulate optical flow estimation. Leveraging the inherent properties of underwater imaging, the novel wflow-TartanVO is introduced, enhancing the accuracy of VO systems for autonomous underwater vehicles (AUVs). The proposed method utilizes a normalized medium transmission map as a weight map to adjust the estimated optical flow for emphasizing regions with lower degradation and suppressing uncertain regions affected by underwater light scattering and absorption. wflow-TartanVO does not require fine-tuning of pre-trained VO models, thus promoting its adaptability to different environments and camera models. Evaluation of different real-world underwater datasets demonstrates the outperformance of wflow-TartanVO over baseline VO methods, as evidenced by the considerably reduced Absolute Trajectory Error (ATE). The implementation code is available at: https://github.com/bachzz/wflow-TartanVO