Online underwater optical mapping for trajectories with gaps

Armagan Elibol, Hyunjung Shim, Seonghun Hong, Jinwhan Kim, Nuno Gracias, Rafael Garcia

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

This paper proposes a vision-only online mosaicing method for underwater surveys. Our method tackles a common problem in low-cost imaging platforms, where complementary navigation sensors produce imprecise or even missing measurements. Under these circumstances, the success of the optical mapping depends on the continuity of the acquired video stream. However, this continuity cannot be always guaranteed due to the motion blurs or lack of texture, common in underwater scenarios. Such temporal gaps hinder the extraction of reliable motion estimates from visual odometry, and compromise the ability to infer the presence of loops for producing an adequate optical map. Unlike traditional underwater mosaicing methods, our proposal can handle camera trajectories with gaps between time-consecutive images. This is achieved by constructing minimum spanning tree which verifies whether the current topology is connected or not. To do so, we embed a trajectory estimate correction step based on graph theory algorithms. The proposed method was tested with several different underwater image sequences and results were presented to illustrate the performance.

Original languageEnglish
Pages (from-to)217-229
Number of pages13
JournalIntelligent Service Robotics
Volume9
Issue number3
DOIs
Publication statusPublished - 2016 Jul 1

Fingerprint

Trajectories
Graph theory
Navigation
Textures
Cameras
Topology
Imaging techniques
Sensors
Costs

All Science Journal Classification (ASJC) codes

  • Computational Mechanics
  • Engineering (miscellaneous)
  • Mechanical Engineering
  • Artificial Intelligence

Cite this

Elibol, Armagan ; Shim, Hyunjung ; Hong, Seonghun ; Kim, Jinwhan ; Gracias, Nuno ; Garcia, Rafael. / Online underwater optical mapping for trajectories with gaps. In: Intelligent Service Robotics. 2016 ; Vol. 9, No. 3. pp. 217-229.
@article{0066e553116f44deac90bdf3f4b6f24e,
title = "Online underwater optical mapping for trajectories with gaps",
abstract = "This paper proposes a vision-only online mosaicing method for underwater surveys. Our method tackles a common problem in low-cost imaging platforms, where complementary navigation sensors produce imprecise or even missing measurements. Under these circumstances, the success of the optical mapping depends on the continuity of the acquired video stream. However, this continuity cannot be always guaranteed due to the motion blurs or lack of texture, common in underwater scenarios. Such temporal gaps hinder the extraction of reliable motion estimates from visual odometry, and compromise the ability to infer the presence of loops for producing an adequate optical map. Unlike traditional underwater mosaicing methods, our proposal can handle camera trajectories with gaps between time-consecutive images. This is achieved by constructing minimum spanning tree which verifies whether the current topology is connected or not. To do so, we embed a trajectory estimate correction step based on graph theory algorithms. The proposed method was tested with several different underwater image sequences and results were presented to illustrate the performance.",
author = "Armagan Elibol and Hyunjung Shim and Seonghun Hong and Jinwhan Kim and Nuno Gracias and Rafael Garcia",
year = "2016",
month = "7",
day = "1",
doi = "10.1007/s11370-016-0195-4",
language = "English",
volume = "9",
pages = "217--229",
journal = "Intelligent Service Robotics",
issn = "1861-2776",
publisher = "Springer Verlag",
number = "3",

}

Online underwater optical mapping for trajectories with gaps. / Elibol, Armagan; Shim, Hyunjung; Hong, Seonghun; Kim, Jinwhan; Gracias, Nuno; Garcia, Rafael.

In: Intelligent Service Robotics, Vol. 9, No. 3, 01.07.2016, p. 217-229.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Online underwater optical mapping for trajectories with gaps

AU - Elibol, Armagan

AU - Shim, Hyunjung

AU - Hong, Seonghun

AU - Kim, Jinwhan

AU - Gracias, Nuno

AU - Garcia, Rafael

PY - 2016/7/1

Y1 - 2016/7/1

N2 - This paper proposes a vision-only online mosaicing method for underwater surveys. Our method tackles a common problem in low-cost imaging platforms, where complementary navigation sensors produce imprecise or even missing measurements. Under these circumstances, the success of the optical mapping depends on the continuity of the acquired video stream. However, this continuity cannot be always guaranteed due to the motion blurs or lack of texture, common in underwater scenarios. Such temporal gaps hinder the extraction of reliable motion estimates from visual odometry, and compromise the ability to infer the presence of loops for producing an adequate optical map. Unlike traditional underwater mosaicing methods, our proposal can handle camera trajectories with gaps between time-consecutive images. This is achieved by constructing minimum spanning tree which verifies whether the current topology is connected or not. To do so, we embed a trajectory estimate correction step based on graph theory algorithms. The proposed method was tested with several different underwater image sequences and results were presented to illustrate the performance.

AB - This paper proposes a vision-only online mosaicing method for underwater surveys. Our method tackles a common problem in low-cost imaging platforms, where complementary navigation sensors produce imprecise or even missing measurements. Under these circumstances, the success of the optical mapping depends on the continuity of the acquired video stream. However, this continuity cannot be always guaranteed due to the motion blurs or lack of texture, common in underwater scenarios. Such temporal gaps hinder the extraction of reliable motion estimates from visual odometry, and compromise the ability to infer the presence of loops for producing an adequate optical map. Unlike traditional underwater mosaicing methods, our proposal can handle camera trajectories with gaps between time-consecutive images. This is achieved by constructing minimum spanning tree which verifies whether the current topology is connected or not. To do so, we embed a trajectory estimate correction step based on graph theory algorithms. The proposed method was tested with several different underwater image sequences and results were presented to illustrate the performance.

UR - http://www.scopus.com/inward/record.url?scp=84961644886&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961644886&partnerID=8YFLogxK

U2 - 10.1007/s11370-016-0195-4

DO - 10.1007/s11370-016-0195-4

M3 - Article

AN - SCOPUS:84961644886

VL - 9

SP - 217

EP - 229

JO - Intelligent Service Robotics

JF - Intelligent Service Robotics

SN - 1861-2776

IS - 3

ER -