Other

·2017

Application Challenges of Underwater Vision

Nuno Gracias , Rafael García , Ricard Campos , Natàlia Hurtós , Ricard Prados , ASM Shihavuddin , Tudor Nicosevici , Armağan Elibol YTU , László Neumann , J. Escartı́n

Abstract

Underwater vehicles, either remotely operated or autonomous, have enabled a growing range of applications over the last two decades. This chapter addresses the creation of 2D mosaics, which is currently the most widely used method for organizing underwater imagery in mapping and inspection applications. Building a 2D mosaic is a task that involves two main steps. From a geometrical point of view, the acquired images should be aligned and warped accordingly into a single common reference frame. Even when navigation data are available, performing a topology estimation step is required to guarantee recovering accurate estimates of the vehicle path, and its value becomes even higher when dealing with large-scale surveys involving hundreds of thousands of images. The image registration problem consists of finding an appropriate planar transformation, which allows aligning in two or more 2D images taken from different viewpoints.

Keywords

Computer vision Computer science Artificial intelligence Underwater Transformation (genetics) Frame (networking) Viewpoints Task (project management) Path (computing) Geography Engineering Telecommunications

Subject Areas

Underwater Vehicles and Communication Systems ·Ocean Engineering ·Physical Sciences
Robotics and Sensor-Based Localization ·Aerospace Engineering ·Physical Sciences
Underwater Acoustics Research ·Oceanography ·Physical Sciences

Citations by Year