One fish, two fish, three fish, more: novel resighting method produces precise and cost‐effective estimates of abundance DOI Creative Commons
Joshua D. Dennis, Lauren Meyer, Christine L. Dudgeon

et al.

Journal of Fish Biology, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 10, 2024

Estimates of abundance are essential to manage and conserve marine species. Numerous methods available determine population size, but the suitability for schooling fishes associated precision can vary depending on species system. Here, we developed compared three mark-recapture/resight assess most robust method estimate silver trevally (Pseudocaranx georgianus). While recapture rate was similar across methods, swim pass (resighting) recorded largest number individuals (mean ± standard error 211 14.9) had lowest coefficient variation (CV; 4.5%-12%) 360-video (resighting, 45 2.1 surveyed, 14.8%-22.2% CV) large-scale capture (recapture, 30 3.8 17.3%-26.5% CV). The inclusion individual identification into estimator models did not change estimates showed resolution between (CV 18.2%-26.7%). We that is logistically easy implement generates precise abundance. This new provides a low-cost, time-efficient resighting be adapted suit aggregating pelagic interacting with wildlife tourism operations, enabling researchers rapidly have been previously difficult count.

Language: Английский

Fish Tracking, Counting, and Behaviour Analysis in Digital Aquaculture: A Comprehensive Survey DOI Open Access
Ming-Shu Cui, Xubo Liu, Haohe Liu

et al.

Reviews in Aquaculture, Journal Year: 2025, Volume and Issue: 17(1)

Published: Jan. 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.

Language: Английский

Citations

5

Measuring the Impact of Conservation: The Growing Importance of Monitoring Fauna, Flora and Funga DOI Creative Commons
P. J. Stephenson, María Cecilia Londoño, Paulo A. V. Borges

et al.

Diversity, Journal Year: 2022, Volume and Issue: 14(10), P. 824 - 824

Published: Sept. 30, 2022

Many stakeholders, from governments to civil society businesses, lack the data they need make informed decisions on biodiversity, jeopardising efforts conserve, restore and sustainably manage nature. Here we review importance of enhancing biodiversity monitoring, assess challenges involved identify potential solutions. Capacity for monitoring needs be enhanced urgently, especially in poorer, high-biodiversity countries where gaps are disproportionately high. Modern tools technologies, including remote sensing, bioacoustics environmental DNA, should used at larger scales fill taxonomic geographic gaps, tropics, marine freshwater biomes, plants, fungi invertebrates. Stakeholders follow best practices, adopting appropriate indicators using counterfactual approaches measure attribute outcomes impacts. Data made openly freely available. Companies invest collecting required enhance sustainability their operations supply chains. With soon commit post-2020 global framework, time is right a concerted push monitoring. However, action scale needed now if results-based management adequately conserve ecosystem services all depend on.

Language: Английский

Citations

30

Artificial intelligence for life sciences: A comprehensive guide and future trends DOI

Ming Luo,

Wenyu Yang, Long Bai

et al.

The Innovation Life, Journal Year: 2024, Volume and Issue: unknown, P. 100105 - 100105

Published: Jan. 1, 2024

<p>Artificial intelligence has had a profound impact on life sciences. This review discusses the application, challenges, and future development directions of artificial in various branches sciences, including zoology, plant science, microbiology, biochemistry, molecular biology, cell developmental genetics, neuroscience, psychology, pharmacology, clinical medicine, biomaterials, ecology, environmental science. It elaborates important roles aspects such as behavior monitoring, population dynamic prediction, microorganism identification, disease detection. At same time, it points out challenges faced by application data quality, black-box problems, ethical concerns. The are prospected from technological innovation interdisciplinary cooperation. integration Bio-Technologies (BT) Information-Technologies (IT) will transform biomedical research into AI for Science paradigm.</p>

Language: Английский

Citations

9

Charting the aquaculture internet of things impact: Key applications, challenges, and future trend DOI Creative Commons
Ahmad Fikri Abdullah, Hasfalina Che Man, Mohammed Abdulsalam

et al.

Aquaculture Reports, Journal Year: 2024, Volume and Issue: 39, P. 102358 - 102358

Published: Sept. 20, 2024

Language: Английский

Citations

4

Identification and counting of fish targets using adaptive resolution imaging sonar DOI
Shen Wei, Zhanfei Peng, Jin Zhang

et al.

Journal of Fish Biology, Journal Year: 2023, Volume and Issue: 104(2), P. 422 - 432

Published: Feb. 17, 2023

Abstract Fish are a critical component of marine biology; therefore, the accurate identification and counting fish essential for objective monitoring assessment biological resources. High‐frequency adaptive resolution imaging sonar (ARIS) is widely used underwater object detection imaging, it quickly obtains close‐up video free‐swimming in high‐turbidity water environments. Nonetheless, processing massive data output using sonars remains major challenge. Here, authors developed an automatic image‐processing programme that fuses K‐nearest neighbour background subtraction with DeepSort target tracking to automatically track count fish. The was evaluated four test sets different sizes observation ranges differently deployed sonars. According results, approach successfully counted targets accuracy index 73% completeness 70%. Under appropriate conditions, this could replace time‐consuming semi‐automatic approaches improve efficiency processing, while providing technical support future real‐time processing.

Language: Английский

Citations

9

Deep Learning Algorithms for Sonar Imagery Analysis and Its Application in Aquaculture: A Review DOI
Yingqian Chai, Huihui Yu, Ling Xu

et al.

IEEE Sensors Journal, Journal Year: 2023, Volume and Issue: 23(23), P. 28549 - 28563

Published: Oct. 27, 2023

With the rapid development of underwater sensor techniques, using acoustic techniques to obtain and analyze images is an effective approach due superior nature sonar, especially in turbidity dim environment. In recent years, sonar image processing based on deep learning (DL) being developed applied automatic target recognization tasks. This article outlines research DL-based algorithms for imagery, including denoising, feature extraction, classification, detection, segmentation. review shows that classification most studied transfer has put into spotlight. Besides, datasets applications are listed can be used aquaculture. Currently known include behavior analysis, biomass estimation, species identification, habitat survey. Furthermore, smart aquaculture, as one important application fields technique, challenges future directions aquaculture discussed. The purpose this work aims help researchers find DL processing, potential

Language: Английский

Citations

9

Evaluating the Effectiveness of an Acoustic Camera for Monitoring Three Large Jellyfish Species in the Coastal Waters of Liaodong Bay, China DOI Creative Commons
Bin Wang,

Xiuze Liu,

Jing Dong

et al.

Fishes, Journal Year: 2025, Volume and Issue: 10(3), P. 105 - 105

Published: Feb. 28, 2025

A survey was conducted to evaluate the effectiveness of adaptive resolution imaging sonar (ARIS), also known as an acoustic camera, for monitoring large jellyfish in Liaodong Bay area, China. The abundance and vertical distribution species, such Nemopilema nomurai, Aurelia coerulea, Cyanea nozakii, were obtained from camera observation images, method determined. provided visual information on number their positions water column demonstrated that they more frequently located mid-upper surveyed area. results show it is possible identify three different types using based size, shape, outline, movement trajectory. enables effective distribution, demonstrating its suitability shallow waters. observations through can be used study horizontal spatial characteristics observe behavior.

Language: Английский

Citations

0

The capacity of imaging sonar for quantifying the abundance, species richness, and size of reef fish assemblages DOI Creative Commons

ECP Sibley,

Alethea S. Madgett,

TS Elsdon

et al.

Marine Ecology Progress Series, Journal Year: 2023, Volume and Issue: 717, P. 157 - 179

Published: July 19, 2023

Reef fish assemblages across tropical and temperate latitudes are increasingly threatened by human impacts climate change. Accurate efficient survey methods essential for quantifying these communities to inform management strategies. Imaging sonars (ISs) high-frequency acoustic devices that produce camera-like images of objects. Unlike optical instruments, IS functions effectively in turbid dark water has proven valuable detecting fishes poor visibility at night. Abundance, species richness, size desirable metrics most reef surveys. This review investigates previous attempts quantify using different habitats. These often quantified comparison with alternative (e.g. cameras, extractive techniques). examines the causes agreement or incongruence between estimates from alternatives. Any instrument employed should be able operate structurally complex habitats, thus ability function circumstances is also reviewed. Finally, 5 notable limitations described solutions discussed. Overall, this underlines net value surveying but advises complement abundance, size.

Language: Английский

Citations

8

Applications and analytical approaches using imaging sonar for quantifying behavioural interactions among aquatic organisms and their environment DOI Creative Commons
Ryan T. Munnelly, José Carlos Castillo, Nils Olav Handegard

et al.

ICES Journal of Marine Science, Journal Year: 2023, Volume and Issue: 81(2), P. 207 - 251

Published: Nov. 30, 2023

Abstract For many aquatic animals, distributional patterns, trophodynamic relationships, and reproductive activity are driven by complex biotic abiotic ecosystem interactions that influence behaviour. Linking behavioural information to environmental stimuli stressors can, therefore, help anticipate population responses changing conditions inform management. However, is challenging obtain because sampling gears do not provide adequate spatial or temporal resolution, potentially alter behaviours. Traditionally, most studies have been laboratory experiments, while behaviour in situ has often inferred indirectly. Advancements imaging sonar technology enable the study of behaviours with potential address understudied relationships. In this review we discuss applications among a meta-analysis 155 organisms their environments. We evaluate performance for studying inter- intra-specific interactions, associations sensitive habitats low-visibility environments, traditional fisheries gears. examine data processing analytical methods used refine taxonomic manage time use autocorrelation through sub-sampling, extract metrics applied ecological processes, automating abundance estimates image classification goal providing resource researchers.

Language: Английский

Citations

6

Fish as a Deformable Solid: An Innovative Method to Characterize Fish Swimming Behavior on Acoustic Videos DOI Creative Commons
Azénor Le Quinio, François Martignac, Alexandre Girard

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 134486 - 134497

Published: Jan. 1, 2024

Acoustic cameras are increasingly used for continuous, non-intrusive recording and counting of fish passage in natural environments artificial structures such as fishways. However, analysing the large number videos recorded is time consuming. Although automatic reading processes have been developed, poor quality acoustic images, including discontinuity signal a single object, challenging. We developed an innovative method videos. Unlike previous methods, it focuses on swimming locomotion instead morphological properties fish. Each image pre-processed to remove discontinuities restore entire body cluster pixels. The set pixels then tracked retrieve movement, independent displacement fish, using mesh solid deformable model. deformation which subjected between each pair frames (i.e., body) summarised map passage. Testing dataset four species strongly suggested that maps species-dependent. These results must be extended other confirm effectiveness identification characterisation their behaviour camera records.

Language: Английский

Citations

2