☆ 4.7 Article

A Biologist's Guide to the Galaxy: Leveraging Artificial Intelligence and Very High-Resolution Satellite Imagery to Monitor Marine Mammals from Space

JOURNAL OF MARINE SCIENCE AND ENGINEERING (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Multidisciplinary Sciences

Annotating very high-resolution satellite imagery: A whale case study

Hannah Charlotte Cubaynes et al.

Summary: The use of very high-resolution (VHR) optical satellites is becoming popular in wildlife monitoring, especially for less studied regions such as whales. However, automated systems are needed to detect targets in large areas surveyed using VHR optical satellite imagery. Machine learning requires annotated training datasets, and our proposed workflow provides a step-by-step protocol for annotating VHR optical satellite imagery using ESRI ArcMap 10.8 and ESRI ArcGIS Pro 2.5, with cetaceans as the case study, to develop AI-ready annotations.

METHODSX (2023)

添加到收藏夹

Article Marine & Freshwater Biology

Individual North Atlantic right whales identified from space

Matus Hodul et al.

Summary: This study demonstrates that satellite imagery can be used to detect and confirm the presence of the critically endangered North Atlantic right whale. It provides another tool for conservation efforts, especially in areas where visual and acoustic methods are not applicable.

MARINE MAMMAL SCIENCE (2023)

添加到收藏夹

Review Ecology

Review on methods used for wildlife species and individual identification

Tinao Petso et al.

Summary: This work provides a literature review on animal species and individual identification tools, as well as animal monitoring capabilities. The study explores various technologies for animal identification, from traditional methods to the latest advancements. Machine learning and deep learning techniques have shown potential for high-accuracy identification of both species and individual animals, reducing the need for manual processing.

EUROPEAN JOURNAL OF WILDLIFE RESEARCH (2022)

添加到收藏夹

Article Zoology

Advanced image recognition: a fully automated, high-accuracy photo-identification matching system for humpback whales

Ted Cheeseman et al.

Summary: This new convolutional neural network-based photo-identification algorithm is able to extract features and automatically recognize individuals in large humpback whale photo datasets, significantly reducing time and error rates compared to manual matching.

MAMMALIAN BIOLOGY (2022)

添加到收藏夹

Article Marine & Freshwater Biology

Use of satellite imagery to identify southern right whales (Eubalaena australis) on a Southwest Atlantic Ocean breeding ground

Audrey A. Correa et al.

Summary: This study used satellite images to identify southern right whales, finding that VHR satellite images performed best in detecting whales and were able to correlate with aerial survey data. This technique may be an important tool for monitoring right whales, especially in countries with limited research funding.

MARINE MAMMAL SCIENCE (2022)

添加到收藏夹

Article Marine & Freshwater Biology

Lords of the Rings: Mud ring feeding by bottlenose dolphins in a Caribbean estuary revealed from sea, air, and space

Eric A. Ramos et al.

MARINE MAMMAL SCIENCE (2022)

添加到收藏夹

Article Zoology

Flukebook: an open-source AI platform for cetacean photo identification

Drew Blount et al.

Summary: Determining the risk and vulnerability of species, as well as understanding the trajectories of their populations and communities, is crucial for conservation and management. Flukebook.org is an open-source web platform that addresses the challenges of collecting data on globally distributed whales and dolphins. With advanced photo-identification algorithms and collaboration between researchers and engineers, Flukebook enables comprehensive understanding of cetacean populations while respecting data privacy and ownership.

MAMMALIAN BIOLOGY (2022)

添加到收藏夹

Article Zoology

Artificial intelligence for right whale photo identification: from data science competition to worldwide collaboration

Christin Khan et al.

Summary: Photo identification is crucial for the conservation management of endangered species. Recent advancements in artificial intelligence have revolutionized the identification process. The winning algorithms from a data science competition were able to identify individual North Atlantic right whales with an accuracy of 87% using convolutional neural networks. A web-based platform has been developed to allow biologists without machine learning expertise to utilize semi-automated photo identification. The system has expanded to incorporate photo identification catalogs from various countries and is fully operational for both North Atlantic and southern right whales.

MAMMALIAN BIOLOGY (2022)

添加到收藏夹

Article Multidisciplinary Sciences

Whales from space dataset, an annotated satellite image dataset of whales for training machine learning models

Hannah C. Cubaynes et al.

Summary: Monitoring whales in remote areas is crucial for conservation, but using traditional survey platforms is difficult. Very high-resolution satellite imagery shows promise, but accurate automated whale detection systems are lacking. This study presents a dataset of 633 annotated whale objects detected in satellite images, creating a valuable resource for training and testing automatic detection systems. The dataset covers four species across various regions and was captured by different high-resolution satellites.

SCIENTIFIC DATA (2022)

添加到收藏夹

Article Chemistry, Analytical

The Potential of Satellite Imagery for Surveying Whales

Caroline Hoeschle et al.

Summary: The emergence of very high-resolution (VHR) satellite imagery has opened up new opportunities in the fields of ecology and conservation biology by providing higher confidence in ground feature detection and identification, as well as broadening the range of research questions possible. While VHR imagery studies have mainly focused on terrestrial environments, there has been incremental progress in using this technology for cetacean detection in the last two decades. Collaborative efforts between biology, computation science, and engineering are necessary to overcome the current challenges and achieve basin-scale marine surveys with VHR satellite imagery.

SENSORS (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Counting using deep learning regression gives value to ecological surveys

Jeroen P. A. Hoekendijk et al.

Summary: This study demonstrates the use of machine learning to automate counting tasks without the need to label individual objects of interest. By leveraging image-level annotations, historical data collected over longer time series can also be utilized, showing potential for applications in ecological research.

SCIENTIFIC REPORTS (2021)

添加到收藏夹

Article Environmental Sciences

Evaluation of Satellite Imagery for Monitoring Pacific Walruses at a Large Coastal Haulout

Anthony S. Fischbach et al.

Summary: Climate warming has caused Pacific walruses in the Chukchi Sea to rest more often on coastal haulouts. Satellite imagery, especially SAR, is effective for monitoring walrus aggregations, with radar imagery being more suitable than optical imagery.

REMOTE SENSING (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Insights from the first global population estimate of Weddell seals in Antarctica

Michelle LaRue et al.

Summary: Weddell seals are one of the most well-studied marine mammals in the world, but little is known about their larger scale distribution, population size, and structure. A recent study estimated the global population of around 202,000 sub-adult and adult female seals, with factors such as ocean depth and fast ice influencing their spatial prevalence. The distance to penguin colonies and the population size of emperor penguins were also found to have an impact on the presence of Weddell seals.

SCIENCE ADVANCES (2021)

添加到收藏夹

Review Environmental Sciences

Cetacean Strandings From Space: Challenges and Opportunities of Very High Resolution Satellites for the Remote Monitoring of Cetacean Mass Strandings

Penny J. Clarke et al.

Summary: The study of cetacean strandings is recognized as a priority topic globally, and utilizing Very High Resolution satellite imagery to monitor strandings offers the potential to understand threats to cetacean communities and ecosystems. Addressing technical, practical, and environmental challenges, as well as ensuring inclusivity in knowledge sharing and access to imagery, are essential for monitoring mass strandings over global scales.

FRONTIERS IN MARINE SCIENCE (2021)

添加到收藏夹

Article Multidisciplinary Sciences

Mapping Arctic cetaceans from space: A case study for beluga and narwhal

Bertrand Charry et al.

Summary: This study successfully detected and classified Arctic narwhals and beluga whales using very high-resolution satellite imagery, contributing to our understanding of Arctic cetacean distribution.

PLOS ONE (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Robust Re-identification of Manta Rays from Natural Markings by Learning Pose Invariant Embeddings

Olga Moskvyak et al.

Summary: This paper presents a novel application of a deep convolutional neural network for visual re-identification of individual manta rays based on natural markings. The experimental results demonstrate the superiority of CNNs in learning embeddings for patterns under challenging conditions, achieving a top-10 accuracy of 98% with only 2 matching examples in the database.

2021 INTERNATIONAL CONFERENCE ON DIGITAL IMAGE COMPUTING: TECHNIQUES AND APPLICATIONS (DICTA 2021) (2021)

添加到收藏夹

Article Environmental Sciences

SealNet: A fully-automated pack-ice seal detection pipeline for sub-meter satellite imagery

B. C. Goncalves et al.

REMOTE SENSING OF ENVIRONMENT (2020)

添加到收藏夹

Article Biodiversity Conservation

Citizen science and habitat modelling facilitates conservation planning for crabeater seals in the Weddell Sea

Mia Wege et al.

DIVERSITY AND DISTRIBUTIONS (2020)

添加到收藏夹

Article Multidisciplinary Sciences

A comparison of baleen whale density estimates derived from overlapping satellite imagery and a shipborne survey

C. C. G. Bamford et al.

SCIENTIFIC REPORTS (2020)

添加到收藏夹

Article Ecology

Engaging 'the crowd' in remote sensing to learn about habitat affinity of the Weddell seal in Antarctica

Michelle A. LaRue et al.

REMOTE SENSING IN ECOLOGY AND CONSERVATION (2020)

添加到收藏夹

Article Biodiversity Conservation

Applying deep learning to right whale photo identification

Robert Bogucki et al.

CONSERVATION BIOLOGY (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Aerial-trained deep learning networks for surveying cetaceans from satellite imagery

Alex Borowicz et al.

PLOS ONE (2019)

添加到收藏夹

Correction Multidisciplinary Sciences

Using remote sensing to detect whale strandings in remote areas: The case of sei whales mass mortality in Chilean Patagonia (vol 14, e0222498, 2019)

Peter T. Fretwell et al.

PLOS ONE (2019)

添加到收藏夹

Article Multidisciplinary Sciences

Whale counting in satellite and aerial images with deep learning

Emilio Guirado et al.

SCIENTIFIC REPORTS (2019)

添加到收藏夹

Article Marine & Freshwater Biology

Whales from space: Four mysticete species described using new VHR satellite imagery

Hannah C. Cubaynes et al.

MARINE MAMMAL SCIENCE (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep Learning in Microscopy Image Analysis: A Survey

Fuyong Xing et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

添加到收藏夹

Editorial Material Multidisciplinary Sciences

3 Combating deforestation: From satellite to intervention

Matt Finer et al.

SCIENCE (2018)

添加到收藏夹

Article Biodiversity Conservation

Estimating the abundance of polar bears on Wrangel Island during late summer using high-resolution satellite imagery: a pilot study

Michelle A. LaRue et al.

POLAR BIOLOGY (2018)

添加到收藏夹

Article Biology

Google Haul Out: Earth Observation Imagery and Digital Aerial Surveys in Coastal Wildlife Management and Abundance Estimation

Jerry H. Moxley et al.

BIOSCIENCE (2017)

添加到收藏夹

Article Biodiversity Conservation

Free and open-access satellite data are key to biodiversity conservation

W. Turner et al.

BIOLOGICAL CONSERVATION (2015)

添加到收藏夹

Article Biodiversity Conservation

Testing Methods for Using High-Resolution Satellite Imagery to Monitor Polar Bear Abundance and Distribution

Michelle A. LaRue et al.

WILDLIFE SOCIETY BULLETIN (2015)

添加到收藏夹

Article Multidisciplinary Sciences

Satellites, the All-Seeing Eyes in the Sky: Counting Elephant Seals from Space

Clive R. McMahon et al.

PLOS ONE (2014)

添加到收藏夹

Article Multidisciplinary Sciences

Whales from Space: Counting Southern Right Whales by Satellite

Peter T. Fretwell et al.

PLOS ONE (2014)

添加到收藏夹

Article Multidisciplinary Sciences

Polar Bears from Space: Assessing Satellite Imagery as a Tool to Track Arctic Wildlife

Seth Stapleton et al.

PLOS ONE (2014)

添加到收藏夹

Review Remote Sensing

Recent advances in pansharpening and key problems in applications

Qizhi Xu et al.

INTERNATIONAL JOURNAL OF IMAGE AND DATA FUSION (2014)

添加到收藏夹

Article Biology

The possibility of using high resolution satellite images for detection of marine mammals

N. G. Platonov et al.

BIOLOGY BULLETIN (2013)

添加到收藏夹

Article Multidisciplinary Sciences

Current and Future Patterns of Global Marine Mammal Biodiversity

Kristin Kaschner et al.

PLOS ONE (2011)

添加到收藏夹

Article Biodiversity Conservation

Satellite imagery can be used to detect variation in abundance of Weddell seals (Leptonychotes weddellii) in Erebus Bay, Antarctica

Michelle A. LaRue et al.

POLAR BIOLOGY (2011)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep, Big, Simple Neural Nets for Handwritten Digit Recognition

Dan Claudiu Ciresan et al.

NEURAL COMPUTATION (2010)

添加到收藏夹

Article Oceanography

OBIS-SEAMAP The World Data Center for Marine Mammal, Sea Bird, and Sea Turtle Distributions

Patrick N. Halpin et al.

OCEANOGRAPHY (2009)

添加到收藏夹

Article Computer Science, Artificial Intelligence

GPU implementation of neural networks

KS Oh et al.

PATTERN RECOGNITION (2004)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.