An intelligent and cost-effective remote underwater video device for fish size monitoring

Coro, Gianpaolo; Walsh, Matthew Bjerregaard

doi:10.1016/j.ecoinf.2021.101311

Cited by 23 publications

(9 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning, a form of machine learning, has been used to automate the analysis of imagery from a wide range of environments, including aquatic ecosystems (Dawkins et al, 2017;Jalal et al, 2020;Salman et al, 2020). Deep learning techniques such as convolutional neural networks (CNNs) have proven successful for fish recognition and tracking from stationary cameras such as baited/unbaited remote underwater video systems (BRUVs/RUVs) (Mandal et al, 2018;Villon et al, 2018;Ditria et al, 2020a;Coro and Walsh, 2021;Ditria et al, 2021;Lopez-Marcano et al, 2021). Object recognition can be conventionally achieved by object-and background-centric methods (Heo et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Fish surveys on the move: Adapting automated fish detection and classification frameworks for videos on a remotely operated vehicle in shallow marine waters

et al. 2022

View full text Add to dashboard Cite

Mobile underwater cameras, diver-operated or on underwater vehicles, have become popular for monitoring fisheries. Replacing divers with cameras has clear advantages, such as creating permanent records and accessing waters unavailable to divers. The use of cameras, however, typically produces large quantities of video that are time-consuming to process manually. Automated analysis of underwater videos from stationary cameras using deep learning techniques has advanced considerably in recent years, but the use of mobile cameras potentially raises new challenges for existing methods. We tested how well three automation procedures for stationary underwater cameras, taking an object-centric rather than background-centric approach, performed on surveys of fish using a mobile camera. We analyzed underwear drone videos from reef and seagrass habitat to detect and count two marine fisheries species, luderick (Girella tricuspidata) and yellowfin bream (Acanthopagrus australis). Three convolutional neural network (CNN) frameworks were compared: Detectron Faster R-CNN, Detectron2 Faster R-CNN (using a Regional Proposal Network, RPN), and YOLOv5 (a single-stage detector, SSD). Models performed well overall. Per frame, overall F1 scores ranged 81.4 - 87.3%, precision 88.2 – 96.0%, and recall 73.2 - 88.2%. For quantifying MaxN per video, overall F1 ranged 85.9 – 91.4%, precision 81.9 – 95.3%, and recall 87.1 – 91.1%. For luderick, F1 was > 80% for all frameworks per frame and 89% or higher for MaxN. For yellowfin bream, F1 scores were lower (35.0 - 73.8% for frames, 43.4 - 73.0% for MaxN). Detectron2 performed poorly, and YOLOv5 and Detectron performed similarly with advantages depending on metrics and species. For these two frameworks, performance was as good as in videos from stationary cameras. Our findings show that object detection technology is very useful for extracting fish data from mobile underwater cameras for the system tested here. There is a need now to test performance over a wider range of environments to produce generalizable models. The key steps required area to test and enhance performance: 1. for suites of species in the same habitats with different water clarity, 2. in other coastal environments, 3. trialing cameras moving at different speeds, and 4. using different frame-rates.

show abstract

Section: Introductionmentioning

confidence: 99%

Fish surveys on the move: Adapting automated fish detection and classification frameworks for videos on a remotely operated vehicle in shallow marine waters

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Beyond the capabilities developed and demonstrated specifically for kelp farms in this paper, such technologies could have numerous other applications. While automated aquaculture monitoring has been proposed in [25,26], these are designed as fixed camera systems and lack the mobility that would be needed to collect information on a seaweed farm spread over a large area. Other types of aquaculture support activities could be performed for other seaweeds, bivalves, fin-fish [14], or other marine species aquaculture, however, the usefulness could be extended to other sectors by developing capabilities such as infrastructure inspection (e.g., underwater power or fiber optic cables), especially at depths where diving is impractical.…”

Section: Discussionmentioning

confidence: 99%

A System for Autonomous Seaweed Farm Inspection with an Underwater Robot

Stenius

Folkesson

Bhat

et al. 2022

Sensors

View full text Add to dashboard Cite

This paper outlines challenges and opportunities in operating underwater robots (so-called AUVs) on a seaweed farm. The need is driven by an emerging aquaculture industry on the Swedish west coast where large-scale seaweed farms are being developed. In this paper, the operational challenges are described and key technologies in using autonomous systems as a core part of the operation are developed and demonstrated. The paper presents a system and methods for operating an AUV in the seaweed farm, including initial localization of the farm based on a prior estimate and dead-reckoning navigation, and the subsequent scanning of the entire farm. Critical data from sidescan sonars for algorithm development are collected from real environments at a test site in the ocean, and the results are demonstrated in a simulated seaweed farm setup.

show abstract

“…For example, emerging sediment structures can be monitored to depict key functions and then relate to species’ traits producing them. New monitoring and sampling techniques associated with continuous recoding can place this in the temporal context (e.g., Coro & Bjerregaard Walsh, 2021 ; Hopkins et al, 2021 ).…”

Section: Bta In Marine Systems: Advantages and Current Shortcomingsmentioning

confidence: 99%

“…Some of these technologies are still expensive, but low‐cost technologies are emerging and gaining traction. For example, cost‐effective video recording techniques offer a wide range of opportunities as well as continuous activity monitoring via accelerometer technology (Coro & Bjerregaard Walsh, 2021 ; Hopkins et al, 2021 ). On the other hand, the marine ecology community could be encouraged to record data on traits during routine studies, field courses, student teaching, etc.…”

Section: New Paths: On Solutions To Advance the Bta Approachmentioning

confidence: 99%

Biological traits approaches in benthic marine ecology: Dead ends and new paths

Juan

Bremner

Hewitt

et al. 2022

Ecology and Evolution

View full text Add to dashboard Cite

Biological traits analysis (BTA) links community structure to both ecological functions and response to environmental drivers through species’ attributes. In consequence, it has become a popular approach in marine benthic studies. However, BTA will reach a dead end if the scientific community does not acknowledge its current shortcomings and limitations: (a) uncertainties related to data origins and a lack of standardized reporting of trait information; (b) knowledge gaps on the role of multiple interacting traits on driving the organisms’ responses to environmental variability; (c) knowledge gaps regarding the mechanistic links between traits and functions; (d) a weak focus on the spatial and temporal variability that is inherent to the trait expression of species; and, last but not least, (e) the large reliance on expert knowledge due to an enormous knowledge gap on the basic ecology of many benthic species. BTA will only reach its full potential if the scientific community is able to standardize and unify the reporting and storage of traits data and reconsider the importance of baseline observational and experimental studies to fill knowledge gaps on the mechanistic links between biological traits, functions, and environmental variability. This challenge could be assisted by embracing new technological advances in marine monitoring, such as underwater camera technology and artificial intelligence, and making use of advanced statistical approaches that consider the interactive nature and spatio‐temporal variability of biological systems. The scientific community has to abandon some dead ends and explore new paths that will improve our understanding of individual species, traits, and the functioning of benthic ecosystems.

show abstract

An intelligent and cost-effective remote underwater video device for fish size monitoring

Cited by 23 publications

References 43 publications

Fish surveys on the move: Adapting automated fish detection and classification frameworks for videos on a remotely operated vehicle in shallow marine waters

Fish surveys on the move: Adapting automated fish detection and classification frameworks for videos on a remotely operated vehicle in shallow marine waters

A System for Autonomous Seaweed Farm Inspection with an Underwater Robot

Biological traits approaches in benthic marine ecology: Dead ends and new paths

Contact Info

Product

Resources

About