Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Survey

Reviews in Aquaculture, Год журнала: 2025, Номер 17(1)

Опубликована: Янв. 1, 2025

ABSTRACT Digital aquaculture leverages advanced technologies and data‐driven methods, providing substantial benefits over traditional practices. This article presents a comprehensive review of three interconnected digital tasks, namely, fish tracking, counting, behaviour analysis, using novel unified approach. Unlike previous reviews which focused on single modalities or individual we analyse vision‐based (i.e., image‐ video‐based), acoustic‐based, biosensor‐based methods across all tasks. We examine their advantages, limitations, applications, highlighting recent advancements identifying critical cross‐cutting research gaps. The also includes emerging ideas such as applying multitask learning large language models to address various aspects monitoring, an approach not previously explored in literature. identify the major obstacles hindering progress this field, including scarcity datasets lack evaluation standards. To overcome current explore potential multimodal data fusion deep improve accuracy, robustness, efficiency integrated monitoring systems. In addition, provide summary existing available for analysis. holistic perspective offers roadmap future research, emphasizing need standards facilitate meaningful comparisons between promote practical implementations real‐world settings.

Язык: Английский

---

Recent advances in acoustic technology for aquaculture: A review

Reviews in Aquaculture, Год журнала: 2023, Номер 16(1), С. 357 - 381

Опубликована: Июнь 21, 2023

Abstract Acoustic technology has great application prospects in aquaculture. In particular, two indispensable, critical technologies for the future aquaculture industry are multi‐sensor acquisition that can achieve multi‐scale information fusion, collection and establishment of a global acoustic fish database highly developed deep learning intelligent algorithms establish correlation mechanism between behaviour characteristics. offers remarkable advantages large turbid water bodies studying spatial temporal distribution patterns aquatic organism populations, developing on‐demand feeding systems estimating biomass. This article reviews development its over last 30 years. It further analyses, detail, disadvantages evaluating biomass morphological physical indicators, welfare improvement. Challenges acquiring dynamic target data accurately, building establishing connections characteristics also discussed. brief, this aims to help researchers practitioners better understand current state‐of‐the‐art technologies, which provide strong support smart applications.

Язык: Английский

---

Global inventory of species categorized by known underwater sonifery

Scientific Data, Год журнала: 2023, Номер 10(1)

Опубликована: Дек. 18, 2023

A working group from the Global Library of Underwater Biological Sounds effort collaborated with World Register Marine Species (WoRMS) to create an inventory species confirmed or expected produce sound underwater. We used several existing inventories and additional literature searches compile a dataset categorizing scientific knowledge sonifery for 33,462 subspecies across marine mammals, other tetrapods, fishes, invertebrates. found 729 documented as producing active and/or passive sounds under natural conditions, another 21,911 deemed likely based on evaluated taxonomic relationships. The is available both figshare WoRMS where it can be regularly updated new information becomes available. data also integrated databases (e.g., SeaLifeBase, Biodiversity Information Facility) advance future research distribution, evolution, ecology, management, conservation underwater soniferous worldwide.

Язык: Английский

---

FishSounds Version 1.0: A website for the compilation of fish sound production information and recordings

Ecological Informatics, Год журнала: 2022, Номер 74, С. 101953 - 101953

Опубликована: Дек. 13, 2022

Язык: Английский

---

Applications of machine learning to identify and characterize the sounds produced by fish

ICES Journal of Marine Science, Год журнала: 2023, Номер 80(7), С. 1854 - 1867

Опубликована: Авг. 11, 2023

Abstract Aquatic ecosystems are constantly changing due to anthropic stressors, which can lead biodiversity loss. Ocean sound is considered an essential ocean variable, with the potential improve our understanding of its impact on marine life. Fish produce a variety sounds and their choruses often dominate underwater soundscapes. These have been used assess communication, behaviour, spawning location, biodiversity. Artificial intelligence provide robust solution detect classify fish sounds. However, main challenge in applying artificial recognize lack validated data for individual species. This review provides overview recent publications use machine learning, including deep detection, classification, identification. Key challenges limitations discussed, some points guide future studies also provided.

Язык: Английский

---

Identification of fish sounds in the wild using a set of portable audio‐video arrays

Methods in Ecology and Evolution, Год журнала: 2023, Номер 14(8), С. 2165 - 2186

Опубликована: Апрель 17, 2023

Abstract Associating fish sounds to specific species and behaviours is important for making passive acoustics a viable tool monitoring fish. While recording in tanks can sometimes be performed, many do not produce captivity. Consequently, there need identify situ characterise these under wide variety of habitats. We designed three portable audio‐video platforms capable identifying species‐specific the wild: large array, mini array mobile array. The arrays are static autonomous than deployed on seafloor record audio video one two weeks. They use multichannel acoustic recorders low‐cost cameras mounted PVC frames. also uses recorder, but remotely operated vehicle with built‐in video, which allows remote control real‐time positioning response observed presence. For all arrays, were localised dimensions matched positions data. at four locations off British Columbia, Canada. provided best localisation accuracy and, its larger footprint, was well suited habitats flat seafloor. had lower easier deploy, rough/uneven seafloors. Using we identified, first time, from quillback rockfish Sebastes maliger , copper caurinus lingcod Ophiodon elongatus . In addition measuring temporal spectral characteristics each species, estimated mean source levels (115.4 113.5 dB re 1 μ Pa, respectively) maximum detection ranges sites (between 10.5 33 m). All proposed designs successfully identified wild adapted various budget, logistical habitat constraints. include here building instructions processing scripts help users replicate this methodology, more around world make way monitor

Язык: Английский

---

The potential of acoustic monitoring of aquatic insects for freshwater assessment

Philosophical Transactions of the Royal Society B Biological Sciences, Год журнала: 2024, Номер 379(1904)

Опубликована: Май 5, 2024

Aquatic insects are a major indicator used to assess ecological condition in freshwater environments. However, current methods collect and identify aquatic require advanced taxonomic expertise rely on invasive techniques that lack spatio-temporal replication. Passive acoustic monitoring (PAM) is emerging as non-invasive complementary sampling method allowing broad coverage. The application of PAM ecosystems has already proved useful, revealing unexpected diversity produced by fishes, amphibians, submerged plants, insects. the identity species producing sounds remains largely unknown. Among them, appear be contributor soundscapes. Here, we estimate potential number soniferous worldwide using data from Global Biodiversity Information Facility. We found four insect orders produce totalling over 7000 species. This probably underestimated owing poor knowledge bioacoustics. then value sound evaluate find they might useful despite having similar responses pristine degraded environments some cases. Both expert automated identifications will necessary build international reference libraries conduct bioassessment freshwaters. article part theme issue ‘Towards toolkit for global biodiversity monitoring’.

Язык: Английский

---

Automatic detection of unidentified fish sounds: a comparison of traditional machine learning with deep learning

Frontiers in Remote Sensing, Год журнала: 2024, Номер 5

Опубликована: Авг. 22, 2024

Many species of fishes around the world are soniferous. The types sounds produce vary among and regions but consist typically low-frequency ( < 1.5 kHz) pulses grunts. These can potentially be used to monitor non-intrusively could complement traditional monitoring techniques. However, significant time required for human analysts manually label fish in acoustic recordings does not yet allow passive acoustics as a viable tool fishes. In this paper, we compare two different approaches automatically detect sounds. One is more machine learning technique based on detection transients spectrogram classification using Random Forest (RF). other deep approach overlapping segments (0.2 s) ResNet18 Convolutional Neural Network (CNN). Both algorithms were trained 21,950 annotated non-fish collected from 2014 2019 at five locations Strait Georgia, British Columbia, Canada. performance detectors was tested part data Georgia that withheld training phase, Barkley Sound, Port Miami, Florida, United States. CNN performed up 1.9 times better than RF id="m2">F1 score: 0.82 vs. 0.43). some cases, able find faint analyst well environments one it (Miami id="m3">F1 0.88). Noise analysis 20–1,000 Hz frequency band shows still reliable noise levels greater 130 dB re 1 id="m4">μ Pa Miami becomes less Sound past 100 id="m5">μ due mooring noise. proposed efficiently (unidentified) variety also facilitate development species-specific detectors. We provide software FishSound Finder, an easy-to-use open-source implementation detector with detailed documentation.

Язык: Английский

---

Biodiversity assessment using passive acoustic recordings from off-reef location—Unsupervised learning to classify fish vocalization

The Journal of the Acoustical Society of America, Год журнала: 2023, Номер 153(3), С. 1534 - 1553

Опубликована: Март 1, 2023

We present the quantitative characterization of Grande Island's off-reef acoustic environment within Zuari estuary during pre-monsoon period. Passive recordings reveal prominent fish choruses. Detailed characteristics call employing oscillograms and individual parameters segmented data include vocal groups such as Sciaenidae, Terapon theraps, planktivorous well invertebrate sounds, e.g., snapping shrimp. calculated biodiversity (i) Acoustic Evenness Index (AEI), (ii) Complexity (ACI), mean sound pressure level (SPLrms) for three frequency bands full band (50–22 050 Hz), low-frequency (100–2000 high-frequency shrimp (2000–20 000 Hz). Here, ACI AEI metrics characterize location's soundscape effectively indicating increased species both bands. Whereas variations SPLrms are Moreover, we employ unsupervised classification through a hybrid technique comprising principal component analysis (PCA) K-means clustering features four types. Employed PCA dimensionality reduction related successfully provides 96.20%, 76.81%, 100.00%, 86.36% dominant chorus. Overall, performance (89.84%) is helpful in real-time monitoring stocks ecosystem.

Язык: Английский

---

SoundScape learning: An automatic method for separating fish chorus in marine soundscapes

The Journal of the Acoustical Society of America, Год журнала: 2023, Номер 153(3), С. 1710 - 1722

Опубликована: Март 1, 2023

Marine soundscapes provide the opportunity to non-invasively learn about, monitor, and conserve ecosystems. Some fishes produce sound in chorus, often association with mating, there is much about fish choruses species producing them. Manually analyzing years of acoustic data increasingly unfeasible, especially challenging as multiple can co-occur time frequency overlap vessel noise other transient sounds. This study proposes an unsupervised automated method, called SoundScape Learning (SSL), separate chorus from soundscape using integrated technique that makes use randomized robust principal component analysis (RRPCA), clustering, a neural network. SSL was applied 14 recording locations off southern central California able detect single interest 5.3 yrs acoustically diverse soundscapes. Through application SSL, found be nocturnal, increased intensity at sunset sunrise, seasonally present late Spring Fall. Further will improve understanding behavior, essential habitat, distribution, potential human climate change impacts, thus allow for protection vulnerable species.

Язык: Английский

---