Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Dehazing-aided Multi-Rate Multi-Modal Pose Estimation Framework for Mitigating Visual Disturbances in Extreme Underwater Domain

Vidya Sudevan, Fakhreddine Zayer, Taimur Hassan, Sajid Javed, Hamad Karki, Giulia De Masi, Jorge Dias

TL;DR

DU-VIO offers a robust solution to the persistent challenge of underwater visibility, significantly improving the accuracy of pose estimation, and contributes valuable insights and tools for advancing underwater technology.

Abstract

This paper delves into the potential of DU-VIO, a dehazing-aided hybrid multi-rate multi-modal Visual-Inertial Odometry (VIO) estimation framework, designed to thrive in the challenging realm of extreme underwater environments. The cutting-edge DU-VIO framework is incorporating a GAN-based pre-processing module and a hybrid CNN-LSTM module for precise pose estimation, using visibility-enhanced underwater images and raw IMU data. Accurate pose estimation is paramount for various underwater robotics and exploration applications. However, underwater visibility is often compromised by suspended particles and attenuation effects, rendering visual-inertial pose estimation a formidable challenge. DU-VIO aims to overcome these limitations by effectively removing visual disturbances from raw image data, enhancing the quality of image features used for pose estimation. We demonstrate the effectiveness of DU-VIO by calculating RMSE scores for translation and rotation vectors in comparison to their reference values. These scores are then compared to those of a base model using a modified AQUALOC Dataset. This study's significance lies in its potential to revolutionize underwater robotics and exploration. DU-VIO offers a robust solution to the persistent challenge of underwater visibility, significantly improving the accuracy of pose estimation. This research contributes valuable insights and tools for advancing underwater technology, with far-reaching implications for scientific research, environmental monitoring, and industrial applications.

Dehazing-aided Multi-Rate Multi-Modal Pose Estimation Framework for Mitigating Visual Disturbances in Extreme Underwater Domain

TL;DR

DU-VIO offers a robust solution to the persistent challenge of underwater visibility, significantly improving the accuracy of pose estimation, and contributes valuable insights and tools for advancing underwater technology.

Abstract

This paper delves into the potential of DU-VIO, a dehazing-aided hybrid multi-rate multi-modal Visual-Inertial Odometry (VIO) estimation framework, designed to thrive in the challenging realm of extreme underwater environments. The cutting-edge DU-VIO framework is incorporating a GAN-based pre-processing module and a hybrid CNN-LSTM module for precise pose estimation, using visibility-enhanced underwater images and raw IMU data. Accurate pose estimation is paramount for various underwater robotics and exploration applications. However, underwater visibility is often compromised by suspended particles and attenuation effects, rendering visual-inertial pose estimation a formidable challenge. DU-VIO aims to overcome these limitations by effectively removing visual disturbances from raw image data, enhancing the quality of image features used for pose estimation. We demonstrate the effectiveness of DU-VIO by calculating RMSE scores for translation and rotation vectors in comparison to their reference values. These scores are then compared to those of a base model using a modified AQUALOC Dataset. This study's significance lies in its potential to revolutionize underwater robotics and exploration. DU-VIO offers a robust solution to the persistent challenge of underwater visibility, significantly improving the accuracy of pose estimation. This research contributes valuable insights and tools for advancing underwater technology, with far-reaching implications for scientific research, environmental monitoring, and industrial applications.

Paper Structure

This paper contains 16 sections, 5 equations, 8 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. State-of-the-Art Approaches
  3. Visibility Enhancement in Harsh Environments
  4. Data-Driven Visual-Inertial Odometry Approaches
  5. DEHAZING AIDED UNDERWATER VISUAL-INERTIAL ODOMETRY (DU-VIO) FRAMEWORK
  6. Dehazing Module
  7. Visual Feature Encoder
  8. Inertial Feature Encoder
  9. Multi-Modal Fusion Module
  10. Temporal Modelling and Pose Regression Module
  11. TRAINING OF POSE ESTIMATION FRAMEWORKS
  12. Underwater Multi-Modal Dataset
  13. Parameters of DU-VIO Framework
  14. Details of Computing Resources
  15. EXPERIMENTAL RESULTS AND DISCUSSIONS
  16. ...and 1 more sections

Figures (8)

  • Figure 2: High-level representation of DU-VIO Framework – Dehazing module reduces visual disturbances in raw camera images before feeding them, along with multi-rate IMU data, to the pose estimation module for translation and orientation estimation.
  • Figure 3: DU-VIO Framework Overview: Raw camera images are dehazed to improve visibility. Visual features are extracted with a visual feature encoder, while inertial features are extracted from unprocessed IMU data. The two sets of features are fused using a multimodal fusion module, and the 6D pose is estimated with a temporal modeling and pose regression module.
  • Figure 4: Detailed Illustration of the Dehazing-aided Underwater Visual-Inertial Odometry (DU-VIO) Framework
  • Figure 5: Scenarios: (a) Original (b) Distortion, and (c) Turbid
  • Figure 6: Translation RMSE ($\boldsymbol{v _{rmse}}$) scores for sequence: h01 (a) Without dehazing module, and (b) With dehazing module
  • ...and 3 more figures