Home // COGNITIVE 2014, The Sixth International Conference on Advanced Cognitive Technologies and Applications // View article

Robust Detection and Tracking of Regions of Interest for Autonomous Underwater Robotic Exploration

Authors:
Ángel Alejandro Maldonado Ramírez
Luz Abril Torres Méndez
Edgar Alonso Martínez García

Keywords: visual attention models; regions of interest; superpixel segmentation; feature tracking; underwater vision

Abstract:
Autonomous robotic exploration of unstructured and highly dynamic environments is a complex task, particularly, in underwater environments. An underwater robot needs to quickly detect a region of interest and then track it for a certain period of time in order to plan for the next trajectory; all of these while keeping its motion control stable. In this paper, we present a novel approach that robustly detects and tracks regions of interest in underwater video streams at frame rate. First, to detect relevant regions in an image, our approach combines two existing visual attention schemes with some improvements to adjust it to underwater scenes. Second, a scaled version of the resulting image is segmented by using a superpixel segmentation algorithm, and each relevant point is associated to a superpixel descriptor. The descriptor helps to track the same region as long as it results interesting for the visual attention algorithm. The experimental results demonstrate that our approach is robust when tested on different videos of underwater explorations.

Pages: 165 to 171

Copyright: Copyright (c) IARIA, 2014

Publication date: May 25, 2014

Published in: conference

ISSN: 2308-4197

ISBN: 978-1-61208-340-7

Location: Venice, Italy

Dates: from May 25, 2014 to May 29, 2014