Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak
The disposal of unexploded ordnance (UXOs) at sea is a global problem. The mapping and remediation of historic UXOs can be assisted by autonomous underwater vehicles (AUVs) carrying sensor payloads such as synthetic aperture sonar (SAS) and optical cameras. AUVs can image large areas of the seafloor...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/11/2619 |
| _version_ | 1827664106844323840 |
|---|---|
| author | Oscar Bryan Roy Edgar Hansen Tom S. F. Haines Narada Warakagoda Alan Hunter |
| author_facet | Oscar Bryan Roy Edgar Hansen Tom S. F. Haines Narada Warakagoda Alan Hunter |
| author_sort | Oscar Bryan |
| collection | DOAJ |
| description | The disposal of unexploded ordnance (UXOs) at sea is a global problem. The mapping and remediation of historic UXOs can be assisted by autonomous underwater vehicles (AUVs) carrying sensor payloads such as synthetic aperture sonar (SAS) and optical cameras. AUVs can image large areas of the seafloor in high resolution, motivating an automated approach to UXO detection. Modern methods commonly use supervised machine learning which requires labelled examples from which to learn. This work investigates the often-overlooked labelling process and resulting dataset using an example historic UXO dumpsite at Skagerrak. A counterintuitive finding of this work is that optical images cannot be relied on for ground truth as a significant number of UXOs visible in SAS images are not in optical images, presumed buried. Given the lack of ground truth, we use an ordinal labelling scheme to incorporate a measure of labeller uncertainty. We validate this labelling regime by quantifying label accuracy compared to optical labels with high confidence. Using this approach, we explore different taxonomies and conclude that grouping objects into shells, bombs, debris, and natural gave the best trade-off between accuracy and discrimination. |
| first_indexed | 2024-03-10T00:54:34Z |
| format | Article |
| id | doaj.art-2d42ad5327fa44818283b6426ae2c400 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T00:54:34Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-2d42ad5327fa44818283b6426ae2c4002023-11-23T14:44:36ZengMDPI AGRemote Sensing2072-42922022-05-011411261910.3390/rs14112619Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at SkagerrakOscar Bryan0Roy Edgar Hansen1Tom S. F. Haines2Narada Warakagoda3Alan Hunter4Faculty of Engineering and Design, University of Bath, Bath BA2 7AY, UKNorwegian Defence Research Establishment (FFI), 2007 Kjeller, NorwayFaculty of Engineering and Design, University of Bath, Bath BA2 7AY, UKNorwegian Defence Research Establishment (FFI), 2007 Kjeller, NorwayFaculty of Engineering and Design, University of Bath, Bath BA2 7AY, UKThe disposal of unexploded ordnance (UXOs) at sea is a global problem. The mapping and remediation of historic UXOs can be assisted by autonomous underwater vehicles (AUVs) carrying sensor payloads such as synthetic aperture sonar (SAS) and optical cameras. AUVs can image large areas of the seafloor in high resolution, motivating an automated approach to UXO detection. Modern methods commonly use supervised machine learning which requires labelled examples from which to learn. This work investigates the often-overlooked labelling process and resulting dataset using an example historic UXO dumpsite at Skagerrak. A counterintuitive finding of this work is that optical images cannot be relied on for ground truth as a significant number of UXOs visible in SAS images are not in optical images, presumed buried. Given the lack of ground truth, we use an ordinal labelling scheme to incorporate a measure of labeller uncertainty. We validate this labelling regime by quantifying label accuracy compared to optical labels with high confidence. Using this approach, we explore different taxonomies and conclude that grouping objects into shells, bombs, debris, and natural gave the best trade-off between accuracy and discrimination.https://www.mdpi.com/2072-4292/14/11/2619synthetic aperture sonar (SAS)unexplored ordnance (UXO)machine learning |
| spellingShingle | Oscar Bryan Roy Edgar Hansen Tom S. F. Haines Narada Warakagoda Alan Hunter Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak Remote Sensing synthetic aperture sonar (SAS) unexplored ordnance (UXO) machine learning |
| title | Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak |
| title_full | Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak |
| title_fullStr | Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak |
| title_full_unstemmed | Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak |
| title_short | Challenges of Labelling Unknown Seabed Munition Dumpsites from Acoustic and Optical Surveys: A Case Study at Skagerrak |
| title_sort | challenges of labelling unknown seabed munition dumpsites from acoustic and optical surveys a case study at skagerrak |
| topic | synthetic aperture sonar (SAS) unexplored ordnance (UXO) machine learning |
| url | https://www.mdpi.com/2072-4292/14/11/2619 |
| work_keys_str_mv | AT oscarbryan challengesoflabellingunknownseabedmunitiondumpsitesfromacousticandopticalsurveysacasestudyatskagerrak AT royedgarhansen challengesoflabellingunknownseabedmunitiondumpsitesfromacousticandopticalsurveysacasestudyatskagerrak AT tomsfhaines challengesoflabellingunknownseabedmunitiondumpsitesfromacousticandopticalsurveysacasestudyatskagerrak AT naradawarakagoda challengesoflabellingunknownseabedmunitiondumpsitesfromacousticandopticalsurveysacasestudyatskagerrak AT alanhunter challengesoflabellingunknownseabedmunitiondumpsitesfromacousticandopticalsurveysacasestudyatskagerrak |