Automatic detection of Western rock lobster using synthetic data. (22nd November 2019)
- Record Type:
- Journal Article
- Title:
- Automatic detection of Western rock lobster using synthetic data. (22nd November 2019)
- Main Title:
- Automatic detection of Western rock lobster using synthetic data
- Authors:
- Mahmood, Ammar
Bennamoun, Mohammed
An, Senjian
Sohel, Ferdous
Boussaid, Farid
Hovey, Renae
Kendrick, Gary - Editors:
- Beyan, Cigdem
- Abstract:
- Abstract: Underwater imaging is being extensively used for monitoring the abundance of lobster species and their biodiversity in their local habitats. However, manual assessment of these images requires a huge amount of human effort. In this article, we propose to automate the process of lobster detection using a deep learning technique. A major obstacle in deploying such an automatic framework for the localization of lobsters in diverse environments is the lack of large annotated training datasets. Generating synthetic datasets to train these object detection models has become a popular approach. However, the current synthetic data generation frameworks rely on automatic segmentation of objects of interest, which becomes difficult when the objects have a complex shape, such as lobster. To overcome this limitation, we propose an approach to synthetically generate parts of the lobster. To handle the variability of real-world images, these parts were inserted into a set of diverse background marine images to generate a large synthetic dataset. A state-of-the-art object detector was trained using this synthetic parts dataset and tested on the challenging task of Western rock lobster detection in West Australian seas. To the best of our knowledge, this is the first automatic lobster detection technique for partially visible and occluded lobsters.
- Is Part Of:
- ICES journal of marine science. Volume 77:Number 4(2020)
- Journal:
- ICES journal of marine science
- Issue:
- Volume 77:Number 4(2020)
- Issue Display:
- Volume 77, Issue 4 (2020)
- Year:
- 2020
- Volume:
- 77
- Issue:
- 4
- Issue Sort Value:
- 2020-0077-0004-0000
- Page Start:
- 1308
- Page End:
- 1317
- Publication Date:
- 2019-11-22
- Subjects:
- deep learning -- lobster detection -- marine science -- synthetic data -- underwater images
Ocean -- Periodicals
Fisheries -- Periodicals
Fishes -- Periodicals
Marine biology -- Bibliography -- Periodicals
551.4605 - Journal URLs:
- http://icesjms.oxfordjournals.org/ ↗
http://www.sciencedirect.com/science/journal/10543139 ↗
http://ukcatalogue.oup.com/ ↗ - DOI:
- 10.1093/icesjms/fsz223 ↗
- Languages:
- English
- ISSNs:
- 1054-3139
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 4361.491000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 15087.xml