Automated classification of fauna in seabed photographs: The impact of training and validation dataset size, with considerations for the class imbalance
Published 2021 View Full Article
- Home
- Publications
- Publication Search
- Publication Details
Title
Automated classification of fauna in seabed photographs: The impact of training and validation dataset size, with considerations for the class imbalance
Authors
Keywords
Computer vision, Deep learning, Benthic ecology, Image annotation, Marine photography, Artificial intelligence, Convolutional neural networks, Sample size
Journal
PROGRESS IN OCEANOGRAPHY
Volume 196, Issue -, Pages 102612
Publisher
Elsevier BV
Online
2021-05-21
DOI
10.1016/j.pocean.2021.102612
References
Ask authors/readers for more resources
Related references
Note: Only part of the references are listed.- Three critical factors affecting automated image species recognition performance for camera traps
- (2020) Stefan Schneider et al. Ecology and Evolution
- Ecological variables for developing a global deep-ocean monitoring and conservation strategy
- (2020) Roberto Danovaro et al. Nature Ecology & Evolution
- Assessing the Repeatability of Automated Seafloor Classification Algorithms, with Application in Marine Protected Area Monitoring
- (2020) America Zelada Leon et al. Remote Sensing
- Subtle variation in abyssal terrain induces significant change in benthic megafaunal abundance, diversity, and community structure
- (2020) Jennifer M. Durden et al. PROGRESS IN OCEANOGRAPHY
- First network analysis of interspecific associations of abyssal benthic megafauna reveals potential vulnerability of abyssal hill community
- (2020) Emily G. Mitchell et al. PROGRESS IN OCEANOGRAPHY
- Gear-Induced Concept Drift in Marine Images and Its Effect on Deep Learning Classification
- (2020) Daniel Langenkämper et al. Frontiers in Marine Science
- Enduring science: Three decades of observing the Northeast Atlantic from the Porcupine Abyssal Plain Sustained Observatory (PAP-SO)
- (2020) Susan E. Hartman et al. PROGRESS IN OCEANOGRAPHY
- Monitoring mosaic biotopes in a marine conservation zone by autonomous underwater vehicle
- (2019) Noëlie M.A. Benoist et al. CONSERVATION BIOLOGY
- New high-tech flexible networks for the monitoring of deep-sea ecosystems
- (2019) Jacopo Aguzzi et al. ENVIRONMENTAL SCIENCE & TECHNOLOGY
- Automated identification of benthic epifauna with computer vision
- (2019) N Piechaud et al. MARINE ECOLOGY PROGRESS SERIES
- Biological effects 26 years after simulated deep-sea mining
- (2019) Erik Simon-Lledó et al. Scientific Reports
- Climate-Driven Shifts in Marine Species Ranges: Scaling from Organisms to Communities
- (2019) Malin L. Pinsky et al. Annual Review of Marine Science
- Response of deep-sea deposit-feeders to detrital inputs: A comparison of two abyssal time-series sites
- (2019) Jennifer M. Durden et al. DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY
- Mask R-CNN
- (2018) Kaiming He et al. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
- Tracking Fish Abundance by Underwater Image Recognition
- (2018) Simone Marini et al. Scientific Reports
- Megafaunal variation in the abyssal landscape of the Clarion Clipperton Zone
- (2018) Erik Simon-Lledó et al. PROGRESS IN OCEANOGRAPHY
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- (2017) Shaoqing Ren et al. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
- Differences in the carbon flows in the benthic food webs of abyssal hill and plain habitats
- (2017) Jennifer M. Durden et al. LIMNOLOGY AND OCEANOGRAPHY
- Effectiveness of a deep-sea cold-water coral Marine Protected Area, following eight years of fisheries closure
- (2016) V.A.I. Huvenne et al. BIOLOGICAL CONSERVATION
- Fish identification from videos captured in uncontrolled underwater environments
- (2016) Faisal Shafait et al. ICES JOURNAL OF MARINE SCIENCE
- Fish species classification in unconstrained underwater environments based on deep learning
- (2016) Ahmad Salman et al. LIMNOLOGY AND OCEANOGRAPHY-METHODS
- Comparison of image annotation data generated by multiple investigators for benthic ecology
- (2016) JM Durden et al. MARINE ECOLOGY PROGRESS SERIES
- DeepFish: Accurate underwater live fish recognition with a deep architecture
- (2016) Hongwei Qin et al. NEUROCOMPUTING
- Comparison of image annotation data generated by multiple investigators for benthic ecology
- (2016) JM Durden et al. MARINE ECOLOGY PROGRESS SERIES
- A new method for ecological surveying of the abyss using autonomous underwater vehicle photography
- (2016) Kirsty J. Morris et al. LIMNOLOGY AND OCEANOGRAPHY-METHODS
- Landscape-scale spatial heterogeneity in phytodetrital cover and megafauna biomass in the abyss links to modest topographic variation
- (2016) Kirsty J. Morris et al. Scientific Reports
- Abyssal hills – hidden source of increased habitat heterogeneity, benthic megafaunal biomass and diversity in the deep sea
- (2015) Jennifer M. Durden et al. PROGRESS IN OCEANOGRAPHY
- Towards Automated Annotation of Benthic Survey Images: Variability of Human Experts and Operational Modes of Automation
- (2015) Oscar Beijbom et al. PLoS One
- Marine Litter Distribution and Density in European Seas, from the Shelves to Deep Basins
- (2014) Christopher K. Pham et al. PLoS One
- Rarefaction and extrapolation with Hill numbers: a framework for sampling and estimation in species diversity studies
- (2013) Anne Chao et al. ECOLOGICAL MONOGRAPHS
- Semi-Automated Image Analysis for the Assessment of Megafaunal Densities at the Arctic Deep-Sea Observatory HAUSGARTEN
- (2012) Timm Schoening et al. PLoS One
- Time to automate identification
- (2010) Norman MacLeod et al. NATURE
- Long-term change in the abyssal NE Atlantic: The ‘Amperima Event’ revisited
- (2009) D.S.M. Billett et al. DEEP-SEA RESEARCH PART II-TOPICAL STUDIES IN OCEANOGRAPHY
- Use of machine-learning algorithms for the automated detection of cold-water coral habitats: a pilot study
- (2009) A Purser et al. MARINE ECOLOGY PROGRESS SERIES
Find Funding. Review Successful Grants.
Explore over 25,000 new funding opportunities and over 6,000,000 successful grants.
ExploreBecome a Peeref-certified reviewer
The Peeref Institute provides free reviewer training that teaches the core competencies of the academic peer review process.
Get Started