Header logo is

Simultaneous Underwater Visibility Assessment, Enhancement and Improved Stereo

2014

Conference Paper

avg

ps


Vision-based underwater navigation and obstacle avoidance demands robust computer vision algorithms, particularly for operation in turbid water with reduced visibility. This paper describes a novel method for the simultaneous underwater image quality assessment, visibility enhancement and disparity computation to increase stereo range resolution under dynamic, natural lighting and turbid conditions. The technique estimates the visibility properties from a sparse 3D map of the original degraded image using a physical underwater light attenuation model. Firstly, an iterated distance-adaptive image contrast enhancement enables a dense disparity computation and visibility estimation. Secondly, using a light attenuation model for ocean water, a color corrected stereo underwater image is obtained along with a visibility distance estimate. Experimental results in shallow, naturally lit, high-turbidity coastal environments show the proposed technique improves range estimation over the original images as well as image quality and color for habitat classification. Furthermore, the recursiveness and robustness of the technique allows real-time implementation onboard an Autonomous Underwater Vehicles for improved navigation and obstacle avoidance performance.

Author(s): M. Roser and M. Dunbabin and A. Geiger
Book Title: IEEE International Conference on Robotics and Automation
Pages: 3840 - 3847
Year: 2014
Month: June

Department(s): Autonomous Vision, Perceiving Systems
Bibtex Type: Conference Paper (conference)
Paper Type: Conference

DOI: 10.1109/ICRA.2014.6907416
Event Name: IEEE International Conference on Robotics and Automation
Event Place: Hong Kong, China

Address: Hong Kong, China
Attachments: pdf

BibTex

@conference{Roser2014ICRA,
  title = {Simultaneous Underwater Visibility Assessment, Enhancement and Improved Stereo},
  author = {Roser, M. and Dunbabin, M. and Geiger, A.},
  booktitle = {IEEE International Conference on Robotics and Automation},
  pages = {3840 - 3847 },
  address = {Hong Kong, China},
  month = jun,
  year = {2014},
  doi = {10.1109/ICRA.2014.6907416},
  month_numeric = {6}
}