4.6 Article

Closing the gap between existing large-area imaging research and marine conservation needs

Related references

Note: Only part of the references are listed.
Article Biodiversity Conservation

A global community-sourced assessment of the state of conservation technology

Talia Speaker et al.

Summary: Conservation technology has the potential to address environmental challenges, but its development and adoption are hindered by constraints such as limited funding, duplication of efforts, and inadequate capacity building. Machine learning and computer vision, eDNA and genomics, and networked sensors are perceived as highly promising technologies. Increasing collaboration, improving tool interoperability, and enhancing data analysis capacity at scale are identified as key opportunities for growth.

CONSERVATION BIOLOGY (2022)

Article Robotics

TagLab: AI-assisted annotation for the fast and accurate semantic segmentation of coral reef orthoimages

Gaia Pavoni et al.

Summary: Semantic segmentation is a widely-used image analysis task, and deep learning-based approaches have the potential to significantly reduce manual annotation time. However, current automated solutions may not meet expert standards. TagLab is introduced as an interactive tool that speeds up semantic segmentation by integrating multiple degrees of automation to empower human capabilities. Through a user study on coral community segmentation, TagLab demonstrated a 90% increase in annotation speed for nonexpert annotators without compromising labeling accuracy, and improved fully automatic predictions by 7% on average and by 14% in challenging cases. Preliminary investigations also suggest further significant reductions in annotation times.

JOURNAL OF FIELD ROBOTICS (2022)

Article Robotics

Automated 2D, 2.5D, and 3D Segmentation of Coral Reef Pointclouds and Orthoprojections

Hugh Runyan et al.

Summary: With advancing technology, coral reef researchers are increasingly favoring image-based surveys over traditional in situ observations by divers. While image-derived data products provide comprehensive digital twins of field sites, the Big Data Problem has emerged as a challenge due to the lack of resources for processing and analyzing imagery at the rate it is collected. The development of unmanned underwater vehicles is expected to further increase the volume of data, posing additional challenges for data handling.

FRONTIERS IN ROBOTICS AND AI (2022)

Article Biochemistry & Molecular Biology

Turning the tide of parachute science

Paris V. Stefanoudis et al.

CURRENT BIOLOGY (2021)

Article Environmental Sciences

Repeatable Semantic Reef-Mapping through Photogrammetry and Label-Augmentation

Matan Yuval et al.

Summary: Automated, high-throughput frameworks are urgently needed for studying natural systems at multiple resolutions. The combination of remote sensing, computer vision, and deep learning has opened up new possibilities in ecological research. Full semantic segmentation of photomosaics is a challenging task, but using label-augmentation can accelerate this process and achieve human-level accuracy in benthic habitat analysis.

REMOTE SENSING (2021)

Article Environmental Sciences

Needs and Gaps in Optical Underwater Technologies and Methods for the Investigation of Marine Animal Forest 3D-Structural Complexity

Paolo Rossi et al.

Summary: Marine animal forests are benthic communities dominated by sessile suspension feeders with the ability to form complex three-dimensional (3D) frameworks, crucial for biodiversity and functioning. However, challenges in data collection and analysis, as well as the need for standardized methods and protocols, hinder the proper investigation and conservation of these ecosystems. Advancements in technology are needed to address issues in data acquisition and processing to accurately map benthic habitats and measure structural complexity.

FRONTIERS IN MARINE SCIENCE (2021)

Article Multidisciplinary Sciences

A Field Primer for Monitoring Benthic Ecosystems using Structure-from-Motion Photogrammetry

Ty N. F. Roach et al.

Summary: Structure-from-motion (SfM) photogrammetry is a technique used to generate 3D reconstructions from a sequence of 2D images, popular for monitoring various systems. This study provides a detailed protocol for collecting SfM imagery in benthic habitats and compares the cost, time efficiency, and output quality of using a DSLR camera versus a less expensive action camera. The DSLR camera produces models with higher resolution but takes longer to produce compared to the action camera.

JOVE-JOURNAL OF VISUALIZED EXPERIMENTS (2021)

Article Environmental Sciences

NeMO-Net - Gamifying 3D Labeling of Multi-Modal Reference Datasets to Support Automated Marine Habitat Mapping

Jarrett van den Bergh et al.

Summary: NASA's NeMO-Net utilizes citizen science and a 3D classification game to create training datasets for a convolutional neural network that generates benthic habitat maps of coral reefs and shallow marine ecosystems. Users are trained through the game to accurately identify benthic categories and semantically segment 3D scenes, improving segmentation accuracy.

FRONTIERS IN MARINE SCIENCE (2021)

Review Ecology

Photogrammetry as a tool to improve ecosystem restoration

Renata Ferrari et al.

Summary: Ecosystem restoration relies on clear and measurable goals with standardized monitoring methods. Photogrammetry, using images to reconstruct landscapes and organisms, has the potential to enhance restoration success rates.

TRENDS IN ECOLOGY & EVOLUTION (2021)

Article Environmental Sciences

Which Method for Which Purpose? A Comparison of Line Intercept Transect and Underwater Photogrammetry Methods for Coral Reef Surveys

Isabel Urbina-Barreto et al.

Summary: The effectiveness of a program designed to assess coral reef ecosystems depends on the choice of ecological monitoring methods and descriptors used. Research comparing traditional Line Intercept Transect (LIT) method with methods derived from underwater photogrammetry found that surface analysis on orthomosaics was the most efficient method, while in situ LIT method was most effective for species-level taxonomic identifications. Factors such as scientific outputs, human expertise, and time requirements also played a role in determining the most suitable monitoring method.

FRONTIERS IN MARINE SCIENCE (2021)

Article Environmental Sciences

Comparing Coral Colony Surveys From In-Water Observations and Structure-From-Motion Imagery Shows Low Methodological Bias

Courtney S. Couch et al.

Summary: A study comparing in-water surveys and SfM imaging methods for assessing coral demography, bleaching, and diversity found that most metrics did not significantly differ between the two methods. While SfM offers a more rigorous approach to reducing observer errors, it also requires more investment and time to handle data effectively.

FRONTIERS IN MARINE SCIENCE (2021)

Article Environmental Sciences

Reefscape Genomics: Leveraging Advances in 3D Imaging to Assess Fine-Scale Patterns of Genomic Variation on Coral Reefs

Pim Bongaerts et al.

Summary: Understanding the ecological and evolutionary processes that govern coral reefs is crucial for their protection, with molecular ecological studies and genomewide sequencing offering important insights. Challenges associated with aquatic environments still exist, but the emerging field of reefscape genomics, leveraging underwater imaging technology, shows promise for spatially explicit genomic studies on coral reefs.

FRONTIERS IN MARINE SCIENCE (2021)

Article Environmental Sciences

A Non-destructive Method to Create a Time Series of Surface Area for Coral Using 3D Photogrammetry

Daniel D. Conley et al.

Summary: This study compared the method of collecting coral surface area data using photogrammetry and wax dipping, finding similar accuracy when measuring objects of known surface area with both methods. The study also proposed two predictive models for estimating surface area from weight measurements.

FRONTIERS IN MARINE SCIENCE (2021)

Article Environmental Sciences

3D Photogrammetry Modeling Highlights Efficient Reserve Effect Apparition After 5 Years and Stillness After 40 for Red Coral (Corallium rubrum) Conservation in French MPAs

Justine Richaume et al.

Summary: Imaging the marine environment is increasingly important for understanding species relationships and natural processes. Photogrammetry has allowed for 3D measuring to study population dynamics of sessile organisms, with a study on red coral showing significant differences between protected and unprotected areas in terms of colony metrics. The study highlights the importance of precautionary measures in maintaining population sustainability and effectiveness, as well as the need for strategies to monitor and understand coral populations' resilience.

FRONTIERS IN MARINE SCIENCE (2021)

Review Biology

Three-dimensional digital mapping of ecosystems: a new era in spatial ecology

Tim D'Urban Jackson et al.

PROCEEDINGS OF THE ROYAL SOCIETY B-BIOLOGICAL SCIENCES (2020)

Editorial Material Ecology

3D Imaging Insights into Forests and Coral Reefs

Kim Calders et al.

TRENDS IN ECOLOGY & EVOLUTION (2020)

Article Multidisciplinary Sciences

Future sea-level rise drives rocky intertidal habitat loss and benthic community change

Nikolas J. Kaplanis et al.

PEERJ (2020)

Editorial Material Geography, Physical

Low-budget topographic surveying comes of age: Structure from motion photogrammetry in geography and the geosciences

Karen Anderson et al.

PROGRESS IN PHYSICAL GEOGRAPHY-EARTH AND ENVIRONMENT (2019)

Article Environmental Sciences

Evaluating the efficacy of small-scale marine protected areas for preserving reef health: A case study applying emerging monitoring technology

Daniel T. Bayley et al.

AQUATIC CONSERVATION-MARINE AND FRESHWATER ECOSYSTEMS (2019)

Article Environmental Sciences

Fluid lensing and machine learning for centimeter-resolution airborne assessment of coral reefs in American Samoa

Ved Chirayath et al.

REMOTE SENSING OF ENVIRONMENT (2019)

Article Ecology

Futurecasting ecological research: the rise of technoecology

Blake M. Allan et al.

ECOSPHERE (2018)

Article Oceanography

Biometric assessment of deep-sea vent megabenthic communities using multi-resolution 3D image reconstructions

Blair Thornton et al.

DEEP-SEA RESEARCH PART I-OCEANOGRAPHIC RESEARCH PAPERS (2016)

Article Multidisciplinary Sciences

GoPros™ as an underwater photogrammetry tool for citizen science

Vincent Raoult et al.

PEERJ (2016)

Article Multidisciplinary Sciences

End to End Digitisation and Analysis of Three-Dimensional Coral Models, from Communities to Corallites

Luis Gutierrez-Heredia et al.

PLOS ONE (2016)

Article Marine & Freshwater Biology

Documenting hurricane impacts on coral reefs using two-dimensional video-mosaic technology

Arthur C. R. Gleason et al.

MARINE ECOLOGY-AN EVOLUTIONARY PERSPECTIVE (2007)

Article Environmental Sciences

Development and application of a video-mosaic survey technology to document the status of coral reef communities

Diego Lirman et al.

ENVIRONMENTAL MONITORING AND ASSESSMENT (2007)