Automating Jellyfish Species Recognition through Faster Region-Based Convolution Neural Networks

Gauci, Adam; Deidun, Alan; Abela, John

doi:10.3390/app10228257

Cited by 6 publications

(6 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While the mAP Jellytoring 2.0 ranged from 88% to 90%, Han et al ( 2021 ) showed an mAP of 75%. By contrast, when compared to studies that automatically identified a lower number of species (i.e., 5), Jellytoring 2.0 performance was lower, Gauci et al ( 2020 ) mAP = 96%. However, algorithms trained to identify a lower number of jellyfish species tend to perform better, as shown with the original version of Jellytoring (mAP = 95%).…”

Section: Discussionmentioning

confidence: 85%

“…Identification bias associated with the observer would be reduced, since networks are trained by a multitude of observers and a high volume of images which would level out any potential biases. Recent studies have successfully applied CNNs for the identification of different jellyfish species (Gauci et al, 2020 ; Han et al, 2021 ; Martin‐Abadal et al, 2020 ). The majority focused on the local scale (Gauci et al, 2020 ; Martin‐Abadal et al, 2020 ), while one study used jellyfish images from different geographical areas without a spatially explicit specification (Han et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

“…Recent studies have successfully applied CNNs for the identification of different jellyfish species (Gauci et al, 2020 ; Han et al, 2021 ; Martin‐Abadal et al, 2020 ). The majority focused on the local scale (Gauci et al, 2020 ; Martin‐Abadal et al, 2020 ), while one study used jellyfish images from different geographical areas without a spatially explicit specification (Han et al, 2021 ). Yet, if the objective is to significantly advance and improve the quality and quantity of jellyfish data and spatial and temporal coverage, the first step is to develop a cost‐effective method that allows for efficient data collection at large scales.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The potential of Jellytoring 2.0 smart tool as a global jellyfish monitoring platform

Ruiz‐Frau

Martin‐Abadal

Jennings

et al. 2022

Ecology and Evolution

View full text Add to dashboard Cite

Despite the recent recognition of jellyfish as an important component of marine ecosystems and existing concerns on their potential population increase, they are rarely monitored at the appropriate spatial and temporal scales. Traditional jellyfish monitoring techniques are costly and generally restrict the spatial–temporal resolution limiting the quantity and quality of monitoring data. We introduce Jellytoring 2.0, an automatic recognition tool for jellyfish species based on convolutional neural networks (CNN). We trained Jellytoring 2.0 to identify 15 jellyfish species with a global distribution. Our aim is to offer Jellytoring 2.0 as an open‐access tool to serve as the backbone for a system that promotes the creation of large‐scale and long‐term jellyfish monitoring data. Results reveal that Jellytoring 2.0 performed well in the identification of the 15 species with average precision values ranging between 90% and 99% for most of the species. Four of the species presented slightly lower values (75%–80%). Our system was trained on a relatively small dataset, implying that additional integration of image data will further improve the performance of the CNN. We show how the application of CNNs to image data can deliver a tool that will enable the cost‐effective collection of jellyfish data on larger spatial and temporal scales. For Jellytoring 2.0 to become a truly global automatic identification system, we ask scientists and nonscientists to actively contribute with jellyfish image data to extend the number of species it can identify.

show abstract

Section: Discussionmentioning

confidence: 85%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The potential of Jellytoring 2.0 smart tool as a global jellyfish monitoring platform

Ruiz‐Frau

Martin‐Abadal

Jennings

et al. 2022

Ecology and Evolution

View full text Add to dashboard Cite

show abstract

“…A stock assessment for jellyfish may be achieved similar to how finfish stocks are assessed [96]. New methodologies are being developed for aerial, underwater, and combined estimates of jellyfish biomass and abundances in situ [44,97,98], as well as citizen science approaches [92] and image recognition technology [98,99], that may prove useful for the development of sustainable jellyfish fishery operations.…”

Section: Ecological Interactions and Ecosystem Stabilitymentioning

confidence: 99%

Jellyfishing in Europe: Current Status, Knowledge Gaps, and Future Directions towards a Sustainable Practice

et al. 2021

View full text Add to dashboard Cite

Jellyfish are often described as a nuisance species, but as our understanding shifts to more ecosystem-based conceptions, they are also recognized as both important components of marine ecosystems and a resource for humans. Here, we describe global jellyfish fisheries and review production, fishing methods, and applications based on the existing literature. We then focus on future development of a European jellyfish fishery based on current and recent EU research initiatives. Jellyfish have been a staple food in East Asia for eons and now show a potential for non-food applications as well. The main fishing methods are mostly traditional, with set-nets, driftnets, hand-nets, and scoop-nets utilizing small crafts or beach-seines. All require a lot of manual labor, thus providing vital, albeit seasonal, occupation to weaker populations. Larger commercial vessels such as purse seines and trawlers are newly introduced métiers which may enable a larger catch per unit effort and total catch, but pose questions of selectivity, bycatch, vessel stability, and transshipment. Social concerns arising from the seasonality of jellyfish fisheries must be met in SE Asia, Latin America, and in any location where new fisheries are established. In the EU, we recognize at least 15 species showing potential for commercial harvesting, but as of 2021, a commercial fishery has yet to be developed; as in finfish fisheries, we advise caution and recognition of the role of jellyfish in marine ecosystems in doing so. Sustainable harvesting techniques and practices must be developed and implemented for a viable practice to emerge, and social and ecological needs must also be incorporated into the management plan. Once established, the catch, effort, and stock status must be monitored, regulated, and properly reported to FAO by countries seeking a viable jellyfish fishery. In the near future, novel applications for jellyfish will offer added value and new markets for this traditional resource.

show abstract

“…Along with surface observation, aerial and underwater drones have complementary approaches that can be used together to observe jellyfish in a more comprehensive view [41]. Moreover, automated classification methods recently used to count fish [42] or to distinguish jellyfish species using Convolution Neural Networks [43] may be applied to drone images.…”

Section: Stationmentioning

confidence: 99%

Using Drones to Measure Jellyfish Density in Shallow Estuaries

Hamel

Lhoumeau

Wahlberg

et al. 2021

JMSE

View full text Add to dashboard Cite

Understanding jellyfish ecology and roles in coastal ecosystems is challenging due to their patchy distribution. While standard net sampling or manned aircraft surveys are inefficient, Unmanned Aerial Vehicles (UAVs) or drones represent a promising alternative for data collection. In this technical report, we used pictures taken from a small drone to estimate the density of Aurelia sp. in a shallow fjord with a narrow entrance, where the population dynamic is well-known. We investigated the ability of an image processing software to count small and translucent jellyfish from the drone pictures at three locations with different environmental conditions (sun glare, waves or seagrass). Densities of Aurelia sp. estimated from semiautomated and manual counts from drone images were similar to densities estimated by netting. The semiautomated program was able to highlight the medusae from the background in order to discard false detections of items unlikely to be jellyfish. In spite of this, some objects (e.g., seagrass) were hardly distinguishable from jellyfish and resulted in a small number of false positives. This report presents a preview of the possible applications of drones to observe small and fragile jellyfishes, for which in situ sampling remains delicate. Drones may represent a noninvasive approach to monitoring jellyfish abundance over time, enabling the collection of a large amount of data in a short time. Software development may be useful for automatically measuring jellyfish size and even population biomass.

show abstract

Automating Jellyfish Species Recognition through Faster Region-Based Convolution Neural Networks

Cited by 6 publications

References 27 publications

The potential of Jellytoring 2.0 smart tool as a global jellyfish monitoring platform

The potential of Jellytoring 2.0 smart tool as a global jellyfish monitoring platform

Jellyfishing in Europe: Current Status, Knowledge Gaps, and Future Directions towards a Sustainable Practice

Using Drones to Measure Jellyfish Density in Shallow Estuaries

Contact Info

Product

Resources

About