ORCID Profile
0000-0001-6612-2738
Current Organisations
University of Sydney
,
Norwegian University of Science and Technology
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Artificial Intelligence and Image Processing | Adaptive Agents and Intelligent Robotics | Computer Vision | Control Systems, Robotics and Automation | Ocean Engineering | Pattern Recognition and Data Mining | Image Processing | Field robotics | Machine learning | Ecological Applications | Knowledge Representation And Machine Learning | Special Vehicles | Intelligent robotics | Computer vision | Biological Oceanography | Computer Vision | Ecological Impacts of Climate Change | Special Vehicles | Autonomous Vehicles | Environmental Impact Assessment | Mechanical Engineering | Maritime Engineering | Landscape Ecology | Environmental Monitoring | Ocean Engineering | Semi- and unsupervised learning | Artificial intelligence | Data Communications | Intelligent Robotics |
Ecosystem Assessment and Management of Marine Environments | Marine protected areas | Integrated (ecosystem) assessment and management | Command, Control and Communications | Navy | Integrated (ecosystem) assessment and management | Marine Flora, Fauna and Biodiversity | Effects of Climate Change and Variability on Australia (excl. Social Impacts) | Navy | Oil and Gas Exploration | Physical and Chemical Conditions of Water in Coastal and Estuarine Environments | Expanding Knowledge in the Environmental Sciences | Expanding Knowledge in History and Archaeology
Publisher: Public Library of Science (PLoS)
Date: 10-11-2014
Publisher: Public Library of Science (PLoS)
Date: 12-12-2012
Publisher: Inter-Research Science Center
Date: 03-05-2011
DOI: 10.3354/MEPS09046
Publisher: IEEE
Date: 05-2016
Publisher: IEEE
Date: 05-2011
Publisher: IEEE
Date: 12-2010
Publisher: Wiley
Date: 14-12-2020
DOI: 10.1111/GCB.14911
Abstract: Rapid intensification of environmental disturbances has sparked widespread decline and compositional shifts in foundation species in ecosystems worldwide. Now, an emergent challenge is to understand the consequences of shifts and losses in such habitat‐forming species for associated communities and ecosystem processes. Recently, consecutive coral bleaching events shifted the morphological makeup of habitat‐forming coral assemblages on the Great Barrier Reef (GBR). Considering the disparity of coral morphological growth forms in shelter provision for reef fishes, we investigated how shifts in the morphological structure of coral assemblages affect the abundance of juvenile and adult reef fishes. We used a temporal dataset from shallow reefs in the northern GBR to estimate coral convexity (a fine‐scale quantitative morphological trait) and two widely used coral habitat descriptors (coral cover and reef rugosity) for disentangling the effects of coral morphology on reef fish assemblages. Changes in coral convexity, rather than live coral cover or reef rugosity, disproportionately affected juvenile reef fishes when compared to adults, and explained more than 20% of juvenile decline. The magnitude of this effect varied by fish body size with juveniles of small‐bodied species showing higher vulnerability to changes in coral morphology. Our findings suggest that continued large‐scale shifts in the relative abundance of morphological groups within coral assemblages are likely to affect population replenishment and dynamics of future reef fish communities. The different responses of juvenile and adult fishes according to habitat descriptors indicate that focusing on coarse‐scale metrics alone may mask fine‐scale ecological responses that are key to understand ecosystem functioning and resilience. Nonetheless, quantifying coral morphological traits may contribute to forecasting the structure of reef fish communities on novel reef ecosystems shaped by climate change.
Publisher: American Chemical Society (ACS)
Date: 06-10-2016
Abstract: Benthic accumulations of filamentous, mat-forming bacteria occur throughout the oceans where bisulfide mingles with oxygen or nitrate, providing key but poorly quantified linkages between elemental cycles of carbon, nitrogen and sulfur. Here we used the autonomous underwater vehicle Sentry to conduct a contiguous, 12.5 km photoimaging survey of sea-floor colonies of filamentous bacteria between 80 and 579 m water depth, spanning the continental shelf to the deep suboxic waters of the Santa Barbara Basin (SBB). The survey provided >31 000 images and revealed contiguous, white-colored bacterial colonization coating > ∼80% of the ocean floor and spanning over 1.6 km, between 487 and 523 m water depth. Based on their localization within the stratified waters of the SBB we hypothesize a dynamic and annular biogeochemical zonation by which the bacteria capitalize on periodic flushing events to accumulate and utilize nitrate. Oceanographic time series data bracket the imaging survey and indicate rapid and contemporaneous nitrate loss, while autonomous capture of microbial communities from the benthic boundary layer concurrent with imaging provides possible identities for the responsible bacteria. Based on these observations we explore the ecological context of such mats and their possible importance in the nitrogen cycle of the SBB.
Publisher: SPIE
Date: 14-02-2013
DOI: 10.1117/12.2002239
Publisher: IEEE
Date: 30-05-2021
Publisher: IEEE
Date: 05-2010
Publisher: IEEE
Date: 05-2018
Publisher: Public Library of Science (PLoS)
Date: 18-02-2015
Publisher: Cold Spring Harbor Laboratory
Date: 21-10-2021
DOI: 10.1101/2021.10.19.464984
Abstract: The process of coral recruitment is crucial to the functioning of coral reef ecosystems, as well as recovery of coral assemblages following disturbances. Fishes can be key mediators of this process by removing benthic competitors like algae, but their foraging impacts are capable of being facilitative or harmful to coral recruits depending on species traits. Reef fish assemblages are highly erse in foraging strategies and the relationship between this ersity with coral settlement and recruitment success remains poorly understood. Here, we investigate how foraging trait ersity of reef fish assemblages covaries with coral settlement and recruitment success across multiple sites at Lizard Island, Great Barrier Reef. Using a multi-model inference approach incorporating six metrics of fish assemblage foraging ersity (foraging rates, trait richness, trait evenness, trait ergence, herbivore abundance, and sessile invertivore abundance), we found that herbivore abundance was positively related to both coral settlement and recruitment success. However, the correlation with herbivore abundance was not as strong in comparison with foraging trait ersity metrics. Coral settlement and recruitment exhibited a negative relationship with foraging trait ersity, especially with trait ergence and richness in settlement. Our findings provide further evidence that fish play a role in making benthic habitats more conducive for coral settlement and recruitment. Because of their ability to shape the reef benthos, the variation of fish bio ersity is likely to contribute to spatially uneven patterns of coral recruitment and reef recovery.
Publisher: IEEE
Date: 09-2006
Publisher: Elsevier BV
Date: 02-2015
Publisher: SAGE Publications
Date: 03-2014
DOI: 10.4276/030802214X13941036266621
Abstract: Work engagement, characterized by vigour, dedication, and absorption, is often perceived as the opposite of burnout. Occupational therapists with burnout feel exhausted and disengaged from their work. This study aims to investigate demographic and work-related psychosocial factors associated with burnout and work engagement. A cross-sectional postal survey of 951 occupational therapists was conducted. Two models representing factors associated with burnout (F(15,871) = 28.01, p .001) and work engagement (F(10,852) = 16.15, p .001) accounted for 32.54% and 15.93% of the variance respectively. Burnout and work engagement were inversely associated (χ 2 (n = 941) = 55.16, p .001). Factors associated with burnout and work engagement were identified. The variables associated with burnout included: low psychological detachment from work during out-of-work hours, low income satisfaction, perceived work overload, difficulty saying ‘no’, 10 years' experience, low frequency of having a ‘belly laugh’, and not having children. High levels of work engagement were reported by therapists with the following: low psychological detachment from work, high income satisfaction, postgraduate qualifications, 40 hours work/week, high frequency of having a ‘belly laugh’, and having children. Understanding the factors associated with burnout and work engagement provides prerequisite information to inform strategies aimed at building healthy workforces.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2009
Publisher: IEEE
Date: 23-05-2022
Publisher: IEEE
Date: 09-2010
Publisher: IEEE
Date: 11-2013
Publisher: Wiley
Date: 07-2018
DOI: 10.1111/GEB.12729
Publisher: Springer Science and Business Media LLC
Date: 27-07-2013
Publisher: IEEE
Date: 05-2014
Publisher: Elsevier BV
Date: 07-2000
Publisher: IEEE
Date: 10-2012
Publisher: Wiley
Date: 25-03-2023
DOI: 10.1111/ELE.14208
Abstract: In their recent synopsis, Loke and Chisholm ( Ecology Letters, 25, 2269–2288, 2022 ) present an overview of habitat complexity metrics for ecologists. They provide a review and some sound advice. However, we found several of their analyses and opinions misleading. This technical note provides a different perspective on the complexity metrics assessed.
Publisher: Elsevier
Date: 2012
Publisher: IEEE
Date: 10-2010
Publisher: Wiley
Date: 15-02-2017
DOI: 10.1002/ECE3.2701
Publisher: IEEE
Date: 05-2010
Publisher: IEEE
Date: 09-2007
Publisher: Oxford University Press (OUP)
Date: 18-05-2012
Abstract: Smale, D. A., Kendrick, G. A., Harvey, E. S., Langlois, T. J., Hovey, R. K., Van Niel, K. P., Waddington, K. I., Bellchambers, L. M., Pember, M. B., Babcock, R. C., Vanderklift, M. A., Thomson, D. P., Jakuba, M. V., Pizarro, O., and Williams, S. B. 2012. Regional-scale benthic monitoring for ecosystem-based fisheries management (EBFM) using an autonomous underwater vehicle (AUV). – ICES Journal of Marine Science, 69: 1108–1118. Monitoring marine habitats and bio ersity is critical for understanding ecological processes, conserving natural resources, and achieving ecosystem-based fisheries management (EBFM). Here, we describe the application of autonomous underwater vehicle (AUV) technology to conduct ongoing monitoring of benthic habitats at two key locations in Western Australia. Benthic assemblages on rocky reefs were s led with an AUV, which captured 000 geo-referenced images. Surveys were designed to obtain 100% coverage of 25 × 25 m patches of benthic habitat. In 2010, multiple patches were surveyed at 15–40-m depths at three reference sites at the Houtman Abrolhos Islands and at six reference sites at Rottnest Island. The following year, repeat surveys of the same geo-referenced patches were conducted. Benthic assemblages at the Houtman Abrolhos Islands were varied in that one reference site was dominated by hard corals, whereas the other two were macroalgae dominated. Conversely, assemblages at Rottnest Island were dominated by the kelp Ecklonia radiata. The AUV resurveyed each patch with high precision and demonstrated adequate power to detect change. Repeated observations at the reference sites will track natural variability in benthic habitat structure, which in turn will facilitate the detection of ecological change and ultimately feed back into EBFM processes.
Publisher: SAGE Publications
Date: 2007
Abstract: Large area mapping at high resolution underwater continues to be constrained by sensor-level environmental constraints and the mismatch between available navigation and sensor accuracy. In this paper, advances are presented that exploit aspects of the sensing modality, and consistency and redundancy within local sensor measurements to build high-resolution optical and acoustic maps that are a consistent representation of the environment. This work is presented in the context of real-world data acquired using autonomous underwater vehicles (AUVs) and remotely operated vehicles (ROVs) working in erse applications including shallow water coral reef surveys with the Seabed AUV, a forensic survey of the RMS Titanic in the North Atlantic at a depth of 4100 m using the Hercules ROV, and a survey of the TAG hydrothermal vent area in the mid-Atlantic at a depth of 3600 m using the Jason II ROV. Specifically, the focus is on the related problems of structure from motion from underwater optical imagery assuming pose instrumented calibrated cameras. General wide baseline solutions are presented for these problems based on the extension of techniques from the simultaneous localization and mapping (SLAM), photogrammetric and the computer vision communities. It is also examined how such techniques can be extended for the very different sensing modality and scale associated with multi-beam bathymetric mapping. For both the optical and acoustic mapping cases it is also shown how the consistency in mapping can be used not only for better global mapping, but also to refine navigation estimates.
Publisher: IEEE
Date: 20-09-2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Publisher: Springer International Publishing
Date: 2016
Publisher: IEEE
Date: 09-2007
Publisher: IEEE
Date: 09-2006
Publisher: American Chemical Society (ACS)
Date: 04-03-2019
Abstract: Industrial-scale dumping of organic waste to the deep ocean was once common practice, leaving a legacy of chemical pollution for which a paucity of information exists. Using a nested approach with autonomous and remotely operated underwater vehicles, a dumpsite offshore California was surveyed and s led. Discarded waste containers littered the site and structured the suboxic benthic environment. Dichlorodiphenyltrichloroethane (DDT) was reportedly dumped in the area, and sediment analysis revealed substantial variability in concentrations of p, p-DDT and its analogs, with a peak concentration of 257 μg g
Publisher: Marine Technology Society
Date: 05-2021
DOI: 10.4031/MTSJ.55.3.51
Abstract: Abstract Up to 90% of global coral reefs are predicted to be severely degraded by 2050 under “business-as-usual” scenarios. To meet the scale and scope of this challenge, we propose designing and demonstrating a multi-modal system that can incorporate data from remote sensing (satellites, aircraft, and aerial drones), acoustics, genetics, sensor arrays, and low-cost imaging systems. The latter will be collected by low-cost smart sensing and autonomous underwater vehicles (AUVs) guided by adaptive s ling modeling software and rapidly analyzed using automated machine learning systems. Development and deployment will be linked to extensive and ersity-enhancing training programs. The Coral Sentinel System will be globally deployed to enable rapid-response adaptive management and to build public engagement in conservation interventions to save coral reefs.Phase 1 (Year 1) will involve testing assumptions, coalition building, fundraising, and initial system development. Phase 2 (Years 2‐4) will focus on engineering and development with a pilot deployment in the Caribbean. Phase 3 (Years 5‐6) will involve system expansion and iteration along the Tropical Eastern Pacific corridor. Phase 4 (Years 7‐10) will involve global deployment to over 50 reef sites. This will lead during the following decade (Phase 5) to provisioning of low-cost Sentinel systems to coastal communities globally.
Publisher: PeerJ
Date: 06-02-2018
DOI: 10.7717/PEERJ.4280
Abstract: Coral reefs are a valuable and vulnerable marine ecosystem. The structure of coral reefs influences their health and ability to fulfill ecosystem functions and services. However, monitoring reef corals largely relies on 1D or 2D estimates of coral cover and abundance that overlook change in ecologically significant aspects of the reefs because they do not incorporate vertical or volumetric information. This study explores the relationship between 2D and 3D metrics of coral size. We show that surface area and volume scale consistently with planar area, albeit with morphotype specific conversion parameters. We use a photogrammetric approach using open-source software to estimate the ability of photogrammetry to provide measurement estimates of corals in 3D. Technological developments have made photogrammetry a valid and practical technique for studying coral reefs. We anticipate that these techniques for moving coral research from 2D into 3D will facilitate answering ecological questions by incorporating the 3rd dimension into monitoring.
Publisher: IEEE
Date: 06-03-2023
Publisher: Wiley
Date: 03-12-2010
DOI: 10.1002/ROB.20324
Publisher: American Geophysical Union (AGU)
Date: 10-06-2008
DOI: 10.1029/2008EO240002
Publisher: IEEE
Date: 10-2018
Publisher: Frontiers Media SA
Date: 24-05-2021
Publisher: Elsevier BV
Date: 2016
Publisher: Wiley
Date: 15-06-2017
DOI: 10.1002/ECE3.3127
Publisher: Elsevier BV
Date: 10-2016
Publisher: IEEE
Date: 05-2012
Publisher: IEEE
Date: 05-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2021
Publisher: SAGE Publications
Date: 14-12-2017
Abstract: Autonomous vehicles are often tasked to explore unseen environments, aiming to acquire and understand large amounts of visual image data and other sensory information. In such scenarios, remote sensing data may be available a priori, and can help to build a semantic model of the environment and plan future autonomous missions. In this paper, we introduce two multimodal learning algorithms to model the relationship between visual images taken by an autonomous underwater vehicle during a survey and remotely sensed acoustic bathymetry (ocean depth) data that is available prior to the survey. We present a multi-layer architecture to capture the joint distribution between the bathymetry and visual modalities. We then propose an extension based on gated feature learning models, which allows the model to cluster the input data in an unsupervised fashion and predict visual image features using just the ocean depth information. Our experiments demonstrate that multimodal learning improves semantic classification accuracy regardless of which modalities are available at classification time, allows for unsupervised clustering of either or both modalities, and can facilitate mission planning by enabling class-based or image-based queries.
Publisher: IEEE
Date: 10-2009
Publisher: Field Robotics Publication Society
Date: 10-03-2022
DOI: 10.55417/FR.2022037
Abstract: This paper describes georeference contrastive learning of visual representation (GeoCLR) for efficient training of deep-learning convolutional neural networks (CNNs). The method leverages georeference information by generating a similar image pair using images taken of nearby locations, and contrasting these with an image pair that is far apart. The underlying assumption is that images gathered within a close distance are more likely to have similar visual appearance, where this can be reasonably satisfied in seafloor robotic imaging applications where image footprints are limited to edge lengths of a few meters and are taken so that they overlap along a vehicle’s trajectory, whereas seafloor substrates and habitats have patch sizes that are far larger. A key advantage of this method is that it is self-supervised and does not require any human input for CNN training. The method is computationally efficient, where results can be generated between es during multi-day autonomous underwater vehicle (AUV) missions using computational resources that would be accessible during most oceanic field trials. We apply GeoCLR to habitat classification on a dataset that consists of ~86,000 images gathered using an AUV. We demonstrate how the latent representations generated by GeoCLR can be used to efficiently guide human annotation efforts, where the semi-supervised framework improves classification accuracy by an average of 10.2% compared to the state-of-the-art SimCLR using the same CNN and equivalent number of human annotations for training.
Publisher: SAGE Publications
Date: 11-09-2012
Abstract: We present an efficient and featureless approach to bathymetric simultaneous localization and mapping (SLAM) that utilizes a Rao–Blackwellized particle filter (RBPF) and Gaussian process (GP) regression to provide loop closures in areas with little to no overlap with previously explored terrain. To significantly reduce the memory requirements (thereby allowing for the processing of large datasets) a novel map representation is also introduced that, instead of directly storing estimates of seabed depth, records the trajectory of each particle and synchronizes them to a common log of bathymetric observations. Upon detecting a loop closure each particle is weighted by matching new observations to the current predictions generated from a local reconstruction of their map using GP regression. Here the spatial correlation in the environment is fully exploited, allowing predictions of seabed depth in areas that may not have been directly observed previously. The results demonstrate how observations of seafloor structure with partial overlap can be used by bathymetric SLAM to improve map self consistency when compared with dead reckoning fused with long-baseline (LBL) observations. In addition we show how mapping corrections can still be achieved even when no map overlap is present.
Publisher: Springer Science and Business Media LLC
Date: 19-09-2011
Publisher: Wiley
Date: 08-10-2010
DOI: 10.1002/ROB.20372
Publisher: Springer Science and Business Media LLC
Date: 19-03-2018
Publisher: IEEE
Date: 09-2010
Publisher: Field Robotics Publication Society
Date: 10-03-2022
DOI: 10.55417/FR.2022045
Abstract: In this report, we present the system design, operational strategy, and results of coordinated multivehicle field demonstrations of autonomous marine robotic technologies in searchfor- life missions within the Pacific shelf margin of Costa Rica and the Santorini-Kolumbo caldera complex, which serve as analogs to environments that may exist in oceans beyond Earth. This report focuses on the automation of remotely operated vehicle (ROV) manipulator operations for targeted biological s le-collection-and-return from the seafloor. In the context of future extraterrestrial exploration missions to ocean worlds, an ROV is an analog to a planetary lander, which must be capable of high-level autonomy. Our field trials involve two underwater vehicles, the SuBastian ROV and the Nereid Under Ice (NUI) hybrid ROV for mixed initiative (i.e., teleoperated or autonomous) missions, both equipped seven-degrees-of-freedom hydraulic manipulators.We describe an adaptable, hardware-independent computer vision architecture that enables high-level automated manipulation. The vision system provides a three-dimensional understanding of the workspace to inform manipulator motion planning in complex unstructured environments. We demonstrate the effectiveness of the vision system and control framework through field trials in increasingly challenging environments, including the automated collection and return of biological s les from within the active undersea volcano Kolumbo. Based on our experiences in the field, we discuss the performance of our system and identify promising directions for future research.
Publisher: IEEE
Date: 2008
Publisher: Cold Spring Harbor Laboratory
Date: 04-02-2020
DOI: 10.1101/2020.02.03.929521
Abstract: Structurally complex habitats tend to contain more species and higher total abundances than simple habitats. This ecological paradigm is grounded in first principles: species richness scales with area, and surface area and niche density increase with three-dimensional complexity. Here we present a geometric basis for surface habitats that unifies ecosystems and spatial scales. The theory is framed by fundamental geometric constraints among three structure descriptors—surface height, rugosity and fractal dimension—and explains 98% of surface variation in a structurally complex test system: coral reefs. We then show how coral bio ersity metrics (species richness, total abundance and probability of interspecific encounter) vary over the theoretical structure descriptor plane, demonstrating the value of the theory for predicting the consequences of natural and human modifications of surface structure.
Publisher: IEEE
Date: 03-2013
Publisher: Association for Computing Machinery (ACM)
Date: 02-03-2015
DOI: 10.1145/2665074
Abstract: We demonstrate that the redundant information in light field imagery allows volumetric focus, an improvement of signal quality that maintains focus over a controllable range of depths. To do this, we derive the frequency-domain region of support of the light field, finding it to be the 4D hyperfan at the intersection of a dual fan and a hypercone, and design a filter with correspondingly shaped passband. Drawing ex les from the Stanford Light Field Archive and images captured using a commercially available lenslet-based plenoptic camera, we demonstrate that the hyperfan outperforms competing methods including planar focus, fan-shaped antialiasing, and nonlinear image and video denoising techniques. We show the hyperfan preserves depth of field, making it a single-step all-in-focus denoising filter suitable for general-purpose light field rendering. We include results for different noise types and levels, through murky water and particulate matter, in real-world scenarios, and evaluated using a variety of metrics. We show that the hyperfan's performance scales with aperture count, and demonstrate the inclusion of aliased components for high-quality rendering.
Publisher: IEEE
Date: 05-2020
Publisher: Wiley
Date: 07-10-2016
DOI: 10.1002/ROB.21638
Publisher: Springer International Publishing
Date: 2015
Publisher: Public Library of Science (PLoS)
Date: 26-11-2014
Publisher: Marine Technology Society
Date: 03-2010
DOI: 10.4031/MTSJ.44.2.3
Abstract: Abstract Underwater gliders use a buoyancy engine and symmetric wings to produce lift. During operation, gliders follow a saw-tooth trajectory, making them useful vehicles for profiling ocean chemistry. By operating at low speeds with low hotel loads, gliders achieve a high endurance. Man-portable, propeller-driven autonomous underwater vehicles (AUVs) are capable of level flight and can also follow terrain to yield high-quality benthic imagery. These platforms typically operate at high speeds with high hotel loads resulting in relatively low endurance. Although both vehicles are used to collect oceanographic data, constraints on how these vehicles are used differentiate the nature of data they collect. This article examines whether one method of propulsion can provide an intrinsic advantage in terms of horizontal range at low speed, regardless of s ling design. We employ first-principle analysis that concludes that either class of vehicle can be designed to achieve the same horizontal transit performance regardless of speed. This result implies that the choice of propulsion method should be driven exclusively by the application and operational requirements.
Publisher: IEEE
Date: 06-2013
Publisher: Springer Science and Business Media LLC
Date: 06-03-2023
Publisher: Informa UK Limited
Date: 15-05-2013
Publisher: IEEE
Date: 05-2010
Publisher: No publisher found
Date: 2014
Publisher: IEEE
Date: 2008
Publisher: Elsevier BV
Date: 02-2015
Publisher: Springer Science and Business Media LLC
Date: 11-02-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2003
Publisher: Wiley
Date: 15-12-2011
DOI: 10.1002/ROB.20382
Publisher: Elsevier BV
Date: 03-2023
Publisher: IEEE
Date: 30-09-2020
Publisher: Springer Science and Business Media LLC
Date: 27-10-2015
Abstract: This Australian benthic data set (BENTHOZ-2015) consists of an expert-annotated set of georeferenced benthic images and associated sensor data, captured by an autonomous underwater vehicle (AUV) around Australia. This type of data is of interest to marine scientists studying benthic habitats and organisms. AUVs collect georeferenced images over an area with consistent illumination and altitude, and make it possible to generate broad scale, photo-realistic 3D maps. Marine scientists then typically spend several minutes on each of thousands of images, labeling substratum type and biota at a subset of points. Labels from four Australian research groups were combined using the CATAMI classification scheme, a hierarchical classification scheme based on taxonomy and morphology for scoring marine imagery. This data set consists of 407,968 expert labeled points from around the Australian coast, with associated images, geolocation and other sensor data. The robotic surveys that collected this data form part of Australia's Integrated Marine Observing System (IMOS) ongoing benthic monitoring program. There is reuse potential in marine science, robotics, and computer vision research.
Publisher: IEEE
Date: 05-2013
Publisher: Field Robotics Publication Society
Date: 10-01-2023
DOI: 10.55417/FR.2023021
Abstract: Special-purpose Autonomous Underwater Vehicles (AUVs) are utilized for benthic (seafloor) surveys, where the vehicle collects optical imagery of the seafloor. Due to the small-sensor footprint of the cameras and the vast areas to be surveyed, these AUVs can not feasibly collect full coverage imagery of areas larger than a few tens of thousands of square meters. Therefore it is necessary for AUV paths to s le the surveys areas sparsely, yet effectively. Broad-scale acoustic bathymetric data are readily available over large areas and are often a useful prior of seafloor cover. As such, prior bathymetry can be used to guide AUV data collection. This research proposes methods for planning initial AUV surveys that efficiently explore a feature space representation of the bathymetry, in order to s le from a erse set of bathymetric terrain. This will enable the AUV to visit areas that likely contain unique habitats and are representative of the entire survey site. We propose several information gathering planners that utilize a feature space exploration reward, to plan freeform paths or to optimize the placement of a survey template. The suitability of these methods to plan AUV surveys is evaluated based on the coverage of the feature space and also the ability to visit all classes of benthic habitat on the initial e. Informative planners based on Rapidly expanding Random Trees (RRT) and Monte Carlo Tree Search (MCTS) were found to be the most effective. This is a valuable tool for AUV surveys as it increases the utility of initial es. It also delivers a comprehensive training set to learn the relationship between acoustic bathymetry and visually derived seafloor classifications.
Publisher: Springer Science and Business Media LLC
Date: 20-12-2016
Abstract: Scientific Data 2:150057 doi:10.1038/sdata.2015.57 (2015) Published 27 Oct 2015 Updated 20 Dec 2016 The authors regret that Ezequiel Marzinelli was omitted in error from the author list of the original version of this Data Descriptor. This omission has now been corrected in the HTML and PDF versions of this Data Descriptor.
Publisher: IEEE
Date: 05-2010
Publisher: Wiley
Date: 03-08-2010
DOI: 10.1002/ROB.20356
Publisher: IEEE
Date: 1998
Publisher: IEEE
Date: 07-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2008
Publisher: IEEE
Date: 05-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2023
Publisher: IEEE
Date: 05-2009
Publisher: IEEE
Date: 05-2011
Publisher: IEEE
Date: 12-2013
Publisher: Springer Berlin Heidelberg
Date: 2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2004
Publisher: Public Library of Science (PLoS)
Date: 15-01-2010
Publisher: Springer Science and Business Media LLC
Date: 25-04-2010
DOI: 10.1038/NGEO848
Publisher: Wiley
Date: 13-02-2016
DOI: 10.1002/LOM3.10089
Publisher: Wiley
Date: 08-2014
DOI: 10.1002/AQC.2505
Publisher: IEEE
Date: 29-05-2023
Publisher: Optica Publishing Group
Date: 24-10-2023
DOI: 10.1364/AO.499334
Publisher: IEEE
Date: 05-2010
Publisher: IEEE
Date: 05-2014
Publisher: Springer Science and Business Media LLC
Date: 24-08-2020
Publisher: IEEE
Date: 05-06-2023
Start Date: 07-2023
End Date: 06-2026
Amount: $419,886.00
Funder: Australian Research Council
View Funded ActivityStart Date: 10-2010
End Date: 10-2013
Amount: $320,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2023
End Date: 06-2026
Amount: $478,994.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2013
End Date: 12-2014
Amount: $385,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 05-2014
End Date: 05-2019
Amount: $290,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 06-2016
End Date: 08-2019
Amount: $315,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2005
End Date: 11-2008
Amount: $228,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 01-2010
End Date: 05-2015
Amount: $798,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2015
End Date: 02-2019
Amount: $323,500.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2011
End Date: 12-2016
Amount: $245,538.00
Funder: Australian Research Council
View Funded ActivityStart Date: 03-2019
End Date: 12-2022
Amount: $420,000.00
Funder: Australian Research Council
View Funded Activity