Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles
Abstract In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Typically, these observations are collected via divers, tags, and remotely-operated or human-piloted vehicles. Recently, howev...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Springer US
2023
|
| Online Access: | https://hdl.handle.net/1721.1/148296 |
| _version_ | 1826213907423821824 |
|---|---|
| author | Cai, Levi McGuire, Nathan E. Hanlon, Roger Mooney, T. A. Girdhar, Yogesh |
| author2 | Woods Hole Oceanographic Institution |
| author_facet | Woods Hole Oceanographic Institution Cai, Levi McGuire, Nathan E. Hanlon, Roger Mooney, T. A. Girdhar, Yogesh |
| author_sort | Cai, Levi |
| collection | MIT |
| description | Abstract
In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Typically, these observations are collected via divers, tags, and remotely-operated or human-piloted vehicles. Recently, however, autonomous underwater vehicles equipped with cameras and embedded computers with GPU capabilities are being developed for a variety of applications, and in particular, can be used to supplement these existing data collection mechanisms where human operation or tags are more difficult. Existing approaches have focused on using fully-supervised tracking methods, but labelled data for many underwater species are severely lacking. Semi-supervised trackers may offer alternative tracking solutions because they require less data than fully-supervised counterparts. However, because there are not existing realistic underwater tracking datasets, the performance of semi-supervised tracking algorithms in the marine domain is not well understood. To better evaluate their performance and utility, in this paper we provide (1) a novel dataset specific to marine animals located at
http://warp.whoi.edu/vmat/
, (2) an evaluation of state-of-the-art semi-supervised algorithms in the context of underwater animal tracking, and (3) an evaluation of real-world performance through demonstrations using a semi-supervised algorithm on-board an autonomous underwater vehicle to track marine animals in the wild. |
| first_indexed | 2024-09-23T15:56:44Z |
| format | Article |
| id | mit-1721.1/148296 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T15:56:44Z |
| publishDate | 2023 |
| publisher | Springer US |
| record_format | dspace |
| spelling | mit-1721.1/1482962024-01-22T18:45:16Z Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles Cai, Levi McGuire, Nathan E. Hanlon, Roger Mooney, T. A. Girdhar, Yogesh Woods Hole Oceanographic Institution Abstract In-situ visual observations of marine organisms is crucial to developing behavioural understandings and their relations to their surrounding ecosystem. Typically, these observations are collected via divers, tags, and remotely-operated or human-piloted vehicles. Recently, however, autonomous underwater vehicles equipped with cameras and embedded computers with GPU capabilities are being developed for a variety of applications, and in particular, can be used to supplement these existing data collection mechanisms where human operation or tags are more difficult. Existing approaches have focused on using fully-supervised tracking methods, but labelled data for many underwater species are severely lacking. Semi-supervised trackers may offer alternative tracking solutions because they require less data than fully-supervised counterparts. However, because there are not existing realistic underwater tracking datasets, the performance of semi-supervised tracking algorithms in the marine domain is not well understood. To better evaluate their performance and utility, in this paper we provide (1) a novel dataset specific to marine animals located at http://warp.whoi.edu/vmat/ , (2) an evaluation of state-of-the-art semi-supervised algorithms in the context of underwater animal tracking, and (3) an evaluation of real-world performance through demonstrations using a semi-supervised algorithm on-board an autonomous underwater vehicle to track marine animals in the wild. 2023-03-06T15:42:14Z 2023-03-06T15:42:14Z 2023-03-01 2023-03-05T04:08:24Z Article http://purl.org/eprint/type/JournalArticle https://hdl.handle.net/1721.1/148296 Cai, Levi, McGuire, Nathan E., Hanlon, Roger, Mooney, T. A. and Girdhar, Yogesh. 2023. "Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles." PUBLISHER_CC en https://doi.org/10.1007/s11263-023-01762-5 Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf Springer US Springer US |
| spellingShingle | Cai, Levi McGuire, Nathan E. Hanlon, Roger Mooney, T. A. Girdhar, Yogesh Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles |
| title | Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles |
| title_full | Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles |
| title_fullStr | Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles |
| title_full_unstemmed | Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles |
| title_short | Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles |
| title_sort | semi supervised visual tracking of marine animals using autonomous underwater vehicles |
| url | https://hdl.handle.net/1721.1/148296 |
| work_keys_str_mv | AT cailevi semisupervisedvisualtrackingofmarineanimalsusingautonomousunderwatervehicles AT mcguirenathane semisupervisedvisualtrackingofmarineanimalsusingautonomousunderwatervehicles AT hanlonroger semisupervisedvisualtrackingofmarineanimalsusingautonomousunderwatervehicles AT mooneyta semisupervisedvisualtrackingofmarineanimalsusingautonomousunderwatervehicles AT girdharyogesh semisupervisedvisualtrackingofmarineanimalsusingautonomousunderwatervehicles |