Unlocking the potential of deep learning for marine ecology: overview, applications, and outlook

ICES Journal of Marine Science, Journal Year: 2021, Volume and Issue: 79(2), P. 319 - 336

Published: Dec. 9, 2021

Abstract The deep learning (DL) revolution is touching all scientific disciplines and corners of our lives as a means harnessing the power big data. Marine ecology no exception. New methods provide analysis data from sensors, cameras, acoustic recorders, even in real time, ways that are reproducible rapid. Off-the-shelf algorithms find, count, classify species digital images or video detect cryptic patterns noisy These endeavours require collaboration across ecological science disciplines, which can be challenging to initiate. To promote use DL towards ecosystem-based management sea, this paper aims bridge gap between marine ecologists computer scientists. We insight into popular approaches for analysis, focusing on supervised techniques with neural networks, illustrate challenges opportunities through established emerging applications ecology. present case studies plankton, fish, mammals, pollution, nutrient cycling involve object detection, classification, tracking, segmentation visualized conclude broad outlook field’s challenges, including potential technological advances issues managing complex sets.

Language: Английский

---

Computer vision and deep learning for fish classification in underwater habitats: A survey

Fish and Fisheries, Journal Year: 2022, Volume and Issue: 23(4), P. 977 - 999

Published: April 15, 2022

Abstract Marine scientists use remote underwater image and video recording to survey fish species in their natural habitats. This helps them get a step closer towards understanding predicting how respond climate change, habitat degradation fishing pressure. information is essential for developing sustainable fisheries human consumption, preserving the environment. However, enormous volume of collected videos makes extracting useful daunting time‐consuming task being. A promising method address this problem cutting‐edge deep learning (DL) technology. DL can help marine parse large volumes promptly efficiently, unlocking niche that cannot be obtained using conventional manual monitoring methods. In paper, we first provide computer visions (CVs) studies conducted between 2003 2021 on classification We then give an overview key concepts DL, while analysing synthesizing studies. also discuss main challenges faced when processing propose approaches them. Finally, insights into research domain shed light what future may hold. paper aims inform who would like gain high‐level state‐of‐the‐art DL‐based habitat.

Language: Английский

---

Underwater object detection: architectures and algorithms – a comprehensive review

Multimedia Tools and Applications, Journal Year: 2022, Volume and Issue: 81(15), P. 20871 - 20916

Published: March 12, 2022

Language: Английский

---

A Review on the Use of Computer Vision and Artificial Intelligence for Fish Recognition, Monitoring, and Management

Fishes, Journal Year: 2022, Volume and Issue: 7(6), P. 335 - 335

Published: Nov. 17, 2022

Computer vision has been applied to fish recognition for at least three decades. With the inception of deep learning techniques in early 2010s, use digital images grew strongly, and this trend is likely continue. As number articles published grows, it becomes harder keep track current state art determine best course action new studies. In context, article characterizes by identifying main studies on subject briefly describing their approach. contrast with most previous reviews related technology recognition, monitoring, management, rather than providing a detailed overview being proposed, work focuses heavily challenges research gaps that still remain. Emphasis given prevalent weaknesses prevent more widespread type practical operations under real-world conditions. Some possible solutions potential directions future are suggested, as an effort bring developed academy closer meeting requirements found practice.

Language: Английский

---

Digital twin-based intelligent fish farming with Artificial Intelligence Internet of Things (AIoT)

Smart Agricultural Technology, Journal Year: 2023, Volume and Issue: 5, P. 100285 - 100285

Published: July 9, 2023

This paper focuses on designing a Digital Twin infrastructure that supports an agile-based Artificial Intelligence Internet of Things (AIoT) system for intelligent fish farming in aquaculture. Our includes the Things, cloud technology, and (AI) as its building blocks. physical entity is equipped with smart devices such sensors actuators embedded machines (fish feeding sorting machines) collect transmits big data to using wireless communication networks real-time remote monitoring. We have four major digital twin services: automate process, metric estimation count, size, weight), environmental monitoring (water condition, net hole, green algae), health (vitality, mortality, diseases). Each service multiple AI services (or objects) capable performing complex other functions optimizations, predictions, analyses decision-making optimize farm profits production. integrated prototype represents virtual accessible web mobile where users can perform various their related services.

Language: Английский

---

Applications of deep learning in fish habitat monitoring: A tutorial and survey

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 238, P. 121841 - 121841

Published: Oct. 1, 2023

Marine ecosystems and their fish habitats are becoming increasingly important due to integral role in providing a valuable food source conservation outcomes. Due remote difficult access nature, marine environments often monitored using underwater cameras record videos images for understanding life ecology, as well preserve the environment. There currently many permanent camera systems deployed at different places around globe. In addition, there exists numerous studies that use temporary survey habitats. These generate massive volume of digital data, which cannot be efficiently analysed by current manual processing methods, involve human observer. Deep Learning (DL) is cutting-edge Artificial Intelligence (AI) technology has demonstrated unprecedented performance analysing visual data. Despite its application myriad domains, habitat monitoring remains under explored. this paper, we provide tutorial covers key concepts DL, help reader grasp high-level how DL works. The also explains step-by-step procedure on algorithms should developed challenging applications such monitoring. comprehensive deep learning techniques including classification, counting, localisation, segmentation. Furthermore, publicly available datasets, compare various domains. We discuss some challenges opportunities emerging field processing. This paper written serve scientists who would like develop it following our tutorial, see evolving facilitate research efforts. At same time, suitable computer state-of-the-art DL-based methodologies

Language: Английский

---

Deep learning-based visual detection of marine organisms: A survey

Neurocomputing, Journal Year: 2023, Volume and Issue: 532, P. 1 - 32

Published: Feb. 17, 2023

Language: Английский

---

Detection of fish freshness using artificial intelligence methods

European Food Research and Technology, Journal Year: 2023, Volume and Issue: 249(8), P. 1979 - 1990

Published: April 27, 2023

Language: Английский

---

Artificial intelligence for fish behavior recognition may unlock fishing gear selectivity

Frontiers in Marine Science, Journal Year: 2023, Volume and Issue: 10

Published: Feb. 23, 2023

Through the advancement of observation systems, our vision has far extended its reach into world fishes, and how they interact with fishing gears—breaking through physical boundaries visually adapting to challenging conditions in marine environments. As sciences step era artificial intelligence (AI), deep learning models now provide tools for researchers process a large amount imagery data (i.e., image sequence, video) on fish behavior more time-efficient cost-effective manner. The latest AI detect categorize species are reaching human-like accuracy. Nevertheless, robust track movements situ under development primarily focused tropical species. Data accurately interpret interactions gears is still lacking, especially temperate fishes. At same time, this an essential selectivity studies advance integrate methods assessing effectiveness modified gears. We here conduct bibliometric analysis review recent advances applications automated tracking, classification, recognition, highlighting may ultimately help improve gear selectivity. further show transforming external stimuli that influence behavior, such as sensory cues background, interpretable features learn distinguish remains challenging. By presenting applied improvements (e.g., Long Short-Term Memory (LSTM), Generative Adversarial Network (GAN), coupled networks), we discuss advances, potential limits meet demands policies sustainable goals, scientists developers continue collaborate building database needed train models.

Language: Английский

---

ConvFishNet: An efficient backbone for fish classification from composited underwater images

Information Sciences, Journal Year: 2024, Volume and Issue: 679, P. 121078 - 121078

Published: June 19, 2024

Language: Английский

---