Search citation statements
Paper Sections
Citation Types
Year Published
Publication Types
Relationship
Authors
Journals
The interplay between environmental, biological, and physical factors often leads to the deterioration of dead fish in marine cages prior to their removal. Depending on the weight of the dead fish and the frequency of their removal, deterioration can progress to a stage where visual identification by divers becomes challenging, thereby disrupting accurate counting of dead fish. This study presents a practical precision tool for monitoring the number of dead fish during the pregrowth and growth phases of caged European sea bass (Dicentrarchus labrax). To improve the assessment of collected mortality, experiments were conducted in farming cages with various fish weights. Identifiable fish rates (I, %) were calculated every 24 hr and classified into four weight classes: WC1 (4–15 g), WC2 (15–30 g), WC3 (30–80 g), and WC4 (>80 g). The corrected number of dead fish (M) was calculated by dividing the collected number (C) by a correction factor (McR), which was determined based on the adopted removal frequency. The possible mortality removal frequencies per week (Fn) included operations such as F7 (daily), F3 (3 times), F2 (2 times), and F1 (once). The smallest correction denominator was 22% for WC1 at a frequency of once per week, whereas the maximum was 100% for WC3 and WC4 daily. The results revealed a high negative significant correlation between Fn and uncollected degraded fish rate (UR) (r = –0.841, p < 0.05). Applying corrections to mortality collected in three finished batches (B2, B3, and B7) led to an increase in the mortality rate by 3.9% ± 1.5%, 5.5% ± 0.7%, and 5.0% ± 0.5%, respectively. This explained 16.8% ± 4.7%, 65.5% ± 26.7%, and 30.3% ± 3.7% of fish disappearances in B2, B3, and B7, respectively. The significance of this study lies in its practical applicability to fish farms as a precise tool for monitoring fish raised in marine cages.
The interplay between environmental, biological, and physical factors often leads to the deterioration of dead fish in marine cages prior to their removal. Depending on the weight of the dead fish and the frequency of their removal, deterioration can progress to a stage where visual identification by divers becomes challenging, thereby disrupting accurate counting of dead fish. This study presents a practical precision tool for monitoring the number of dead fish during the pregrowth and growth phases of caged European sea bass (Dicentrarchus labrax). To improve the assessment of collected mortality, experiments were conducted in farming cages with various fish weights. Identifiable fish rates (I, %) were calculated every 24 hr and classified into four weight classes: WC1 (4–15 g), WC2 (15–30 g), WC3 (30–80 g), and WC4 (>80 g). The corrected number of dead fish (M) was calculated by dividing the collected number (C) by a correction factor (McR), which was determined based on the adopted removal frequency. The possible mortality removal frequencies per week (Fn) included operations such as F7 (daily), F3 (3 times), F2 (2 times), and F1 (once). The smallest correction denominator was 22% for WC1 at a frequency of once per week, whereas the maximum was 100% for WC3 and WC4 daily. The results revealed a high negative significant correlation between Fn and uncollected degraded fish rate (UR) (r = –0.841, p < 0.05). Applying corrections to mortality collected in three finished batches (B2, B3, and B7) led to an increase in the mortality rate by 3.9% ± 1.5%, 5.5% ± 0.7%, and 5.0% ± 0.5%, respectively. This explained 16.8% ± 4.7%, 65.5% ± 26.7%, and 30.3% ± 3.7% of fish disappearances in B2, B3, and B7, respectively. The significance of this study lies in its practical applicability to fish farms as a precise tool for monitoring fish raised in marine cages.
In aquaculture, the presence of dead fish on the water surface can serve as a bioindicator of health issues or environmental stressors. To enhance the precision of detecting dead fish floating on the water’s surface, this paper proposes a detection approach that integrates data-driven insights with advanced modeling techniques. Firstly, to reduce the influence of aquatic disturbances and branches during the identification process, prior information, such as branches and ripples, is annotated in the dataset to guide the model to better learn the scale and shape characteristics of dead fish, reduce the interference of branch ripples on detection, and thus improve the accuracy of target identification. Secondly, leveraging the foundational YOLOv8 architecture, a DD-IYOLOv8 (Data-Driven Improved YOLOv8) dead fish detection model is designed. Considering the significant changes in the scale of dead fish at different distances, DySnakeConv (Dynamic Snake Convolution) is introduced into the neck network detection head to adaptively adjust the receptive field, thereby improving the network’s capability to capture features. Additionally, a layer for detecting minor objects has been added, and the detection head of YOLOv8 has been modified to 4, allowing the network to better focus on small targets and occluded dead fish, which improves detection performance. Furthermore, the model incorporates a HAM (Hybrid Attention Mechanism) in the later stages of the backbone network to refine global feature extraction, sharpening the model’s focus on dead fish targets and further enhancing detection accuracy. The experimental results showed that the accuracy of DD-IYOLOv8 in detecting dead fish reached 92.8%, the recall rate reached 89.4%, the AP reached 91.7%, and the F1 value reached 91.0%. This study can achieve precise identification of dead fish, which will help promote the research of automatic pond patrol machine ships.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.