Automated sea floor extraction from underwater video

Lauren Kelly; Mark Rahmes; James Stiver; Mike McCluskey

doi:10.1117/12.2223774

17 May 2016 Automated sea floor extraction from underwater video

Lauren Kelly, Mark Rahmes, James Stiver, Mike McCluskey

Proceedings Volume 9827, Ocean Sensing and Monitoring VIII; 98270C (2016) https://doi.org/10.1117/12.2223774
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

Ocean floor mapping using video is a method to simply and cost-effectively record large areas of the seafloor. Obtaining visual and elevation models has noteworthy applications in search and recovery missions. Hazards to navigation are abundant and pose a significant threat to the safety, effectiveness, and speed of naval operations and commercial vessels. This project’s objective was to develop a workflow to automatically extract metadata from marine video and create image optical and elevation surface mosaics. Three developments made this possible. First, optical character recognition (OCR) by means of two-dimensional correlation, using a known character set, allowed for the capture of metadata from image files. Second, exploiting the image metadata (i.e., latitude, longitude, heading, camera angle, and depth readings) allowed for the determination of location and orientation of the image frame in mosaic. Image registration improved the accuracy of mosaicking. Finally, overlapping data allowed us to determine height information. A disparity map was created using the parallax from overlapping viewpoints of a given area and the relative height data was utilized to create a three-dimensional, textured elevation map.

Citation Download Citation

Lauren Kelly, Mark Rahmes, James Stiver, and Mike McCluskey "Automated sea floor extraction from underwater video", Proc. SPIE 9827, Ocean Sensing and Monitoring VIII, 98270C (17 May 2016); https://doi.org/10.1117/12.2223774

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available