Computer Vision Applications in the Navigation of Unmanned Underwater Vehicles

  title={Computer Vision Applications in the Navigation of Unmanned Underwater Vehicles},
  author={Jonathan Horgan and Daniel J. F. Toal},

Figures from this paper

A Robust Technique of Adaptive Retinal Mechanisms Used For Underwater Image Enhancement

This paper presents a fusion technique based on brightness to reconstruct the improved image from fish retina outputs that are both on and off, based on a single image and does not require any prior knowledge of the undersea scene's condition or structure.

An efficient interactive segmentation algorithm using color correction for underwater images

This work proposes an efficient algorithm for extracting the foreground region from the underwater images based on a region of interest using an interactive GrabCut algorithm and inclusion of color correction and contrast enhancement minimizes the number of touch ups required to enhance the segmentation.

Weibull Tone Mapping for Underwater Imagery

  • Chloe A Game
  • Environmental Science
    Color and Imaging Conference
  • 2020
Imagery is a preferred tool for environmental surveys within marine environments, particularly in deeper waters, as it is nondestructive compared to traditional sampling methods. However, underwater

Progressive Underwater Exploration with a Corridor-Based Navigation System

An approach called Corridor SLAM (C-SLAM) was developed, which implements a global exploration strategy that consists of first creating a trunk corridor on the seabed and then branching as far as possible in different directions to increase the explored region.

An Online Platform for Underwater Image Quality Evaluation

This work proposes PUIQE, an online platform for underwater image quality evaluation, which is inspired by other computer vision areas whose progress has been accelerated by evaluation platforms, and supports the comparison of methods through standard datasets and objective evaluation measures.

GPU-Assisted Learning on an Autonomous Marine Robot for Vision-Based Navigation and Image Understanding

A GPU-based integrated robotic platform that enables collision avoidance, navigation, and image understanding on a single underwater vehicle and summary of experimental results for coral detection and collision-free navigation is presented.

A Node-Based Method for SLAM Navigation in Self-Similar Underwater Environments: A Case Study

This work develops a node-based monocular visual methodology for autonomous vehicle navigation which has the goal of exploring unknown regions of the sea bottom with a posterior safe revisiting of them and accentuates characteristics of the seabed like self-similarity and backscattering.



Real-time vision-based tracking of submarine-cables for AUV/ROV

  • S. MatsumotoY. Ito
  • Physics
    'Challenges of Our Changing Global Environment'. Conference Proceedings. OCEANS '95 MTS/IEEE
  • 1995
This paper describes a software that traces submarine cables in image sequences. At first, it creates a set of three kinds of filtered images from the original one. Next, by applying thresholds to

Vision-based linear motion estimation for unmanned underwater vehicles

  • M. Caccia
  • Physics
    2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422)
  • 2003
An optical triangulation-correlation sensor for estimating the linear motion of underwater vehicles at low speed in the proximity of the seabed is described. Experimental results, obtained by

A vision system for an underwater cable tracker

The development of a vision system guiding an autonomous underwater vehicle able to detect and track automatically an underwater power cable laid on the seabed is the main concern and the vision system that is proposed tracks the cable with an average success rate above 90%.

An approach to vision-based station keeping for an unmanned underwater vehicle

An automatic vision-based system for UUV station keeping based on a feature-based motion detection algorithm, which exploits standard correlation and explicit textural analysis to solve the correspondence problem.

Large-area visually augmented navigation for autonomous underwater vehicles

Submitted to the Joint Program in Applied Ocean Science & Engineering in partial fulfillment of the requirements for the degree of Doctor of Philosophy at the Massachusetts Institute of Technology

Visually Navigating the RMS Titanic with SLAM Information Filters

This paper describes a vision-based large-area simultaneous localization and mapping (SLAM) algorithm that respects the constraints of low-overlap imagery typical of underwater vehicles while


Future challenges in underwater vehicle navigation are articulated, including near-bottom navigation, vehicle state estimation, optimal survey, environmental estimation, multiple-vehicle navigation, and mid-water navigation.

3-D motion and depth estimation from sea-floor images for mosaic-based station-keeping and navigation of ROVs/AUVs and high-resolution sea-floor mapping

A vision system has been developed in order to support the autonomous operation or operated-assisted missions of AUV and ROV near the ocean bottom and is described and sample results from various experiments for evaluating performance are provided.

Mosaic-based navigation for autonomous underwater vehicles

It is demonstrated that without resorting to additional sensors, visual information can be used to create environment representations of the sea bottom (mosaics) and support long runs of navigation in a robust manner.

Positioning an underwater vehicle through image mosaicking

It is demonstrated that the use of color and textures as discriminative properties of the image can improve, to a large extent, the accuracy of the constructed mosaic.