Computer Vision Models in Intelligent Aquaculture with Emphasis on Fish Detection and Behavior Analysis: A Review

Yang, Ling; Liu, Yeqi; Yu, Huihui; Fang, Xiaomin; Song, Lihua; Li, Bingbing; Chen, Yingyi

doi:10.1007/s11831-020-09486-2

Cited by 111 publications

(54 citation statements)

References 143 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Progress in artificial intelligence for automatic detection of behavioural patterns has emerged as a new tool. Because analysis of animal behaviour is time‐consuming and can be biased by the observer, studies using this technology show progress in this field (Han et al ., 2018; Yang et al ., 2020).…”

Section: Methodological Considerations and Future Directionsmentioning

confidence: 99%

Physiology, endocrinology and chemical communication in aggressive behaviour of fishes

Silva

Canário

Hubbard

et al. 2021

Journal of Fish Biology

View full text Add to dashboard Cite

Fishes show remarkably diverse aggressive behaviour. Aggression is expressed to secure resources; adjusting aggression levels according to context is key to avoid negative consequences for fitness and survival. Nonetheless, despite its importance, the physiological basis of aggression in fishes is still poorly understood. Several reports suggest hormonal modulation of aggression, particularly by androgens, but contradictory studies have been published. Studies exploring the role of chemical communication in aggressive behaviour are also scant, and the pheromones involved remain to be unequivocally characterized. This is surprising as chemical communication is the most ancient form of information exchange and plays a variety of other roles in fishes. Furthermore, the study of chemical communication and aggression is relevant at the evolutionary, ecological and economic levels. A few pioneering studies support the hypothesis that aggressive behaviour, at least in some teleosts, is modulated by "dominance pheromones" that reflect the social status of the sender, but there is little information on the identity of the compounds involved. This review aims to provide a global view of aggressive behaviour in fishes and its underlying physiological mechanisms including the involvement of chemical communication, and discusses the potential use of dominance pheromones to improve fish welfare. Methodological considerations and future research directions are also outlined.

show abstract

Section: Methodological Considerations and Future Directionsmentioning

confidence: 99%

Physiology, endocrinology and chemical communication in aggressive behaviour of fishes

Silva

Canário

Hubbard

et al. 2021

Journal of Fish Biology

View full text Add to dashboard Cite

show abstract

“…The ultimate goal of this approach will be to predict feed intake from environmental changes and various stressors, such as variations in water quality, and adjust feeding accordingly. Conversely, this approach could also have strong potential to spot early problems associated with water quality and disease outbreaks before they become severe (Saberioon et al 2017;Yang et al 2020). To that end, a number of wireless sensors for water quality monitoring already exist on the market and are currently in use on shrimp farms (e.g.…”

Section: Telemetrymentioning

confidence: 99%

Monitoring methods of feeding behaviour to answer key questions in penaeid shrimp feeding

Tailly

Keitel

Owen

et al. 2021

Reviews in Aquaculture

View full text Add to dashboard Cite

The penaeid shrimp farming industry is a fast-growing sector which continues to suffer from significant feeding inefficiencies. Shrimp are slow to feed on pellets, with consumption dependent on a wide range of environmental and physiological parameters. Feed management on farms remains mainly based on feeding trays which can be difficult to observe and often result in overfeeding. While our understanding of shrimp feeding behaviour is beginning to improve under laboratory conditions, much less is known about shrimp behaviour in production ponds. Consequently, there is a growing interest within the industry to improve observations of shrimp feeding behaviour in situ, although this can be difficult due to high water turbidity and the benthic nature of shrimp. This review identifies key questions that remain unanswered in relation to shrimp feeding behaviour under commercial aquaculture conditions, and considers how they could be addressed using state-of-the-art applications based on three technologies commonly used in other areas of aquaculture. The use of passive acoustics, computer vision and telemetry are highlighted, alongside their potential to help farmers achieve better feeding efficiencies and sustainability as well as to help understand shrimp feeding behaviour in relation to various biotic and abiotic parameters.

show abstract

“…Unfortunately, the requirement for manual processing of underwater videos to count target species severely curtails the scalability of camera systems (Sheaves et al 2020). Automated image analysis can overcome this bottleneck, but technical limitations have restricted its use for routine fisheries monitoring to date (Lopez-Marcano et al 2021, Tseng & Kuo 2020, Yang et al 2020).…”

Section: Introductionmentioning

confidence: 99%

“…Baited remote underwater video stations (BRUVS) are the most widely used application of videos for monitoring fish abundances (Whitmarsh et al 2016), and automated analysis therefore needs to be accurate specifically for this method. Along with issues common to all underwater image analysis, such as variable water clarity and complex, dynamic backgrounds (Siddiqui et al 2019, Yang et al 2020), the BRUVS technique raises another challenge by generating potentially large ranges of fish abundances, from none to many individual fish. Automated analysis needs to report accurately across this wide range of abundances, overcoming significant occlusion issues (where an individual fish can obscure parts of another fish) at higher fish densities.…”

Section: Introductionmentioning

confidence: 99%

Improved accuracy for automated counting of a fish in baited underwater videos for stock assessment

Connolly

Fairclough

Jinks

et al. 2021

Preprint

View full text Add to dashboard Cite

The ongoing need to sustainably manage fishery resources necessitates fishery-independent monitoring of the status of fish stocks. Camera systems, particularly baited remote underwater video stations (BRUVS), are a widely-used and repeatable method for monitoring relative abundance, required for building stock assessment models. The potential for BRUVS-based monitoring is restricted, however, by the substantial costs of manual data extraction from videos. Computer vision, in particular deep learning models, are increasingly being used to automatically detect and count fish at low abundances in videos. One of the advantages of BRUVS is that bait attractants help to reliably detect species in relatively short deployments (e.g. 1 hr). The high abundances of fish attracted to BRUVS, however, make computer vision more difficult, because fish often occlude other fish. We build upon existing deep learning methods for identifying and counting a target fisheries species across a wide range of fish abundances. Using BRUVS imagery targeting a recovering fishery species, Australian snapper (Chrysophrys auratus), we tested combinations of three further mathematical steps likely to generate accurate, efficient automation: 1) varying confidence thresholds (CTs), 2) on/off use of sequential non-maximum suppression (Seq-NMS), and 3) statistical correction equations. Output from the deep learning model was accurate at very low abundances of snapper; at higher abundances, however, the model over-predicted counts by as much as 50%. The procedure providing the most accurate counts across all fish abundances, with counts either correct or within 1 to 2 of manual counts (R2 = 93.4%), used Seq-NMS, a 55% confidence threshold, and a cubic polynomial corrective equation. The optimised modelling provides an automated procedure offering an effective and efficient method for accurately identifying and counting snapper in BRUV footage. Further testing is required to ensure that automated counts of snapper remain accurate in the survey region over time, and to determine the applicability to other regions within the distributional range of this species. For monitoring stocks of fishery species more generally, the specific equations will differ but the procedure demonstrated here would help to increase the usefulness of BRUVS, while decreasing costs.

show abstract

Computer Vision Models in Intelligent Aquaculture with Emphasis on Fish Detection and Behavior Analysis: A Review

Cited by 111 publications

References 143 publications

Physiology, endocrinology and chemical communication in aggressive behaviour of fishes

Physiology, endocrinology and chemical communication in aggressive behaviour of fishes

Monitoring methods of feeding behaviour to answer key questions in penaeid shrimp feeding

Improved accuracy for automated counting of a fish in baited underwater videos for stock assessment

Contact Info

Product

Resources

About