Automatically Guided Selection of a Set of Underwater Calibration Images
The 3D reconstruction of underwater scenes from overlapping images requires modeling the sensor. While underwater self-calibration gives good results when coupled with multi-view algorithms, calibration or pre-calibration with a pattern is still necessary when scenes are weakly textured or if there...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-05-01
|
Series: | Journal of Marine Science and Engineering |
Subjects: | |
Online Access: | https://www.mdpi.com/2077-1312/10/6/741 |
_version_ | 1797485767937753088 |
---|---|
author | Laurent Beaudoin Loïca Avanthey Corentin Bunel Charles Villard |
author_facet | Laurent Beaudoin Loïca Avanthey Corentin Bunel Charles Villard |
author_sort | Laurent Beaudoin |
collection | DOAJ |
description | The 3D reconstruction of underwater scenes from overlapping images requires modeling the sensor. While underwater self-calibration gives good results when coupled with multi-view algorithms, calibration or pre-calibration with a pattern is still necessary when scenes are weakly textured or if there are not enough points of view of the same points; however, detecting patterns on underwater images or obtaining a good distribution of these patterns on a dataset is not an easy task. Thus, we propose a methodology to guide the acquisition of a relevant underwater calibration dataset. This process is intended to provide feedback in near real-time to the operator to guide the acquisition and stop it when a sufficient number of relevant calibration images have been reached. To perform this, pattern detection must be optimized both in time and success rate. We propose three variations of optimized detection algorithms, each of which takes into account different hardware capabilities. We present the results obtained on a homemade database composed of 60,000 images taken both in pools and at sea. |
first_indexed | 2024-03-09T23:23:32Z |
format | Article |
id | doaj.art-8b41dc25455245a79ac5f331931ad336 |
institution | Directory Open Access Journal |
issn | 2077-1312 |
language | English |
last_indexed | 2024-03-09T23:23:32Z |
publishDate | 2022-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Journal of Marine Science and Engineering |
spelling | doaj.art-8b41dc25455245a79ac5f331931ad3362023-11-23T17:22:09ZengMDPI AGJournal of Marine Science and Engineering2077-13122022-05-0110674110.3390/jmse10060741Automatically Guided Selection of a Set of Underwater Calibration ImagesLaurent Beaudoin0Loïca Avanthey1Corentin Bunel2Charles Villard3SEAL (Sense, Explore, Analyse and Learn) Research Team, EPITA Computer Engineering School, 94270 Le Kremlin-Bicêtre, FranceSEAL (Sense, Explore, Analyse and Learn) Research Team, EPITA Computer Engineering School, 94270 Le Kremlin-Bicêtre, FranceSEAL (Sense, Explore, Analyse and Learn) Research Team, EPITA Computer Engineering School, 94270 Le Kremlin-Bicêtre, FranceSEAL (Sense, Explore, Analyse and Learn) Research Team, EPITA Computer Engineering School, 94270 Le Kremlin-Bicêtre, FranceThe 3D reconstruction of underwater scenes from overlapping images requires modeling the sensor. While underwater self-calibration gives good results when coupled with multi-view algorithms, calibration or pre-calibration with a pattern is still necessary when scenes are weakly textured or if there are not enough points of view of the same points; however, detecting patterns on underwater images or obtaining a good distribution of these patterns on a dataset is not an easy task. Thus, we propose a methodology to guide the acquisition of a relevant underwater calibration dataset. This process is intended to provide feedback in near real-time to the operator to guide the acquisition and stop it when a sufficient number of relevant calibration images have been reached. To perform this, pattern detection must be optimized both in time and success rate. We propose three variations of optimized detection algorithms, each of which takes into account different hardware capabilities. We present the results obtained on a homemade database composed of 60,000 images taken both in pools and at sea.https://www.mdpi.com/2077-1312/10/6/741underwater blind calibrationpattern detectionrealtime selection |
spellingShingle | Laurent Beaudoin Loïca Avanthey Corentin Bunel Charles Villard Automatically Guided Selection of a Set of Underwater Calibration Images Journal of Marine Science and Engineering underwater blind calibration pattern detection realtime selection |
title | Automatically Guided Selection of a Set of Underwater Calibration Images |
title_full | Automatically Guided Selection of a Set of Underwater Calibration Images |
title_fullStr | Automatically Guided Selection of a Set of Underwater Calibration Images |
title_full_unstemmed | Automatically Guided Selection of a Set of Underwater Calibration Images |
title_short | Automatically Guided Selection of a Set of Underwater Calibration Images |
title_sort | automatically guided selection of a set of underwater calibration images |
topic | underwater blind calibration pattern detection realtime selection |
url | https://www.mdpi.com/2077-1312/10/6/741 |
work_keys_str_mv | AT laurentbeaudoin automaticallyguidedselectionofasetofunderwatercalibrationimages AT loicaavanthey automaticallyguidedselectionofasetofunderwatercalibrationimages AT corentinbunel automaticallyguidedselectionofasetofunderwatercalibrationimages AT charlesvillard automaticallyguidedselectionofasetofunderwatercalibrationimages |