Fishes

Research

21 pages, 5041 KiB

Open AccessArticle

DDEYOLOv9: Network for Detecting and Counting Abnormal Fish Behaviors in Complex Water Environments

by Yinjia Li, Zeyuan Hu, Yixi Zhang, Jihang Liu, Wan Tu and Hong Yu

Fishes 2024, 9(6), 242; https://doi.org/10.3390/fishes9060242 - 20 Jun 2024

Cited by 1 | Viewed by 1894

Accurately detecting and counting abnormal fish behaviors in aquaculture is essential. Timely detection allows farmers to take swift action to protect fish health and prevent economic losses. This paper proposes an enhanced high-precision detection algorithm based on YOLOv9, named DDEYOLOv9, to facilitate the [...] Read more.

Accurately detecting and counting abnormal fish behaviors in aquaculture is essential. Timely detection allows farmers to take swift action to protect fish health and prevent economic losses. This paper proposes an enhanced high-precision detection algorithm based on YOLOv9, named DDEYOLOv9, to facilitate the detection and counting of abnormal fish behavior in industrial aquaculture environments. To address the lack of publicly available datasets on abnormal behavior in fish, we created the “Abnormal Behavior Dataset of Takifugu rubripes”, which includes five categories of fish behaviors. The detection algorithm was further enhanced in several key aspects. Firstly, the DRNELAN4 feature extraction module was introduced to replace the original RepNCSPELAN4 module. This change improves the model’s detection accuracy for high-density and occluded fish in complex water environments while reducing the computational cost. Secondly, the proposed DCNv4-Dyhead detection head enhances the model’s multi-scale feature learning capability, effectively recognizes various abnormal fish behaviors, and improves the computational speed. Lastly, to address the issue of sample imbalance in the abnormal fish behavior dataset, we propose EMA-SlideLoss, which enhances the model’s focus on hard samples, thereby improving the model’s robustness. The experimental results demonstrate that the DDEYOLOv9 model achieves high

P r e c i s i o n

,

R e c a l l

, and

m e a n A v e r a g e P r e c i s i o n

(

m A P

) on the “Abnormal Behavior Dataset of Takifugu rubripes”, with values of 91.7%, 90.4%, and 94.1%, respectively. Compared to the YOLOv9 model, these metrics are improved by 5.4%, 5.5%, and 5.4%, respectively. The model also achieves a running speed of 119 frames per second (

F P S

), which is 45

F P S

faster than YOLOv9. Experimental results show that the DDEYOLOv9 algorithm can accurately and efficiently identify and quantify abnormal fish behaviors in specific complex environments. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Figure 1

19 pages, 4100 KiB

Open AccessArticle

Research on Measuring the Bodies of Underwater Fish with Inclined Positions Using the YOLOv8 Model and a Line-Laser System

by Jiakang Li, Shengmao Zhang, Penglong Li, Yang Dai and Zuli Wu

Fishes 2024, 9(6), 206; https://doi.org/10.3390/fishes9060206 - 1 Jun 2024

Viewed by 1042

Abstract

Fish body measurement is essential for monitoring fish farming and evaluating growth. Non-destructive underwater measurements play a significant role in aquaculture management. This study involved annotating images of fish in aquaculture settings and utilized a line laser for underwater distance calibration and fish [...] Read more.

Fish body measurement is essential for monitoring fish farming and evaluating growth. Non-destructive underwater measurements play a significant role in aquaculture management. This study involved annotating images of fish in aquaculture settings and utilized a line laser for underwater distance calibration and fish body inclined-angle calculation. The YOLOv8 model was employed for fish identification and key-point detection, enabling the determination of actual body dimensions through a mathematical model. The results show a root-mean-square error of 6.8 pixels for underwater distance calibration using the line laser. The pre-training YOLOv8-n, with its lower parameter counts and higher MAP values, proved more effective for fish identification and key-point detection, considering speed and accuracy. Average body length measurements within 1.5 m of the camera showed a minor deviation of 2.46% compared to manual measurements. The average relative errors for body length and width were 2.46% and 5.11%, respectively, with corresponding average absolute errors. This study introduces innovative techniques for fish body measurement in aquaculture, promoting the digitization and informatization of aquaculture processes. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Graphical abstract

21 pages, 4385 KiB

Open AccessArticle

Feature Selection for Explaining Yellowfin Tuna Catch per Unit Effort Using Least Absolute Shrinkage and Selection Operator Regression

by Ling Yang and Weifeng Zhou

Fishes 2024, 9(6), 204; https://doi.org/10.3390/fishes9060204 - 30 May 2024

Cited by 2 | Viewed by 983

Abstract

To accurately identify the key features influencing the fisheries distribution of Pacific yellowfin tuna, this study analyzed data from 43 longline fishing vessels operated from 2008 to 2019. These vessels operated in the Pacific Ocean region (0° to 30° S; 110° E to [...] Read more.

To accurately identify the key features influencing the fisheries distribution of Pacific yellowfin tuna, this study analyzed data from 43 longline fishing vessels operated from 2008 to 2019. These vessels operated in the Pacific Ocean region (0° to 30° S; 110° E to 170° W), with a specific focus on 25 features of yellowfin tuna derived from marine environment data. For this purpose, this study opted for the Lasso regression analysis method to select features to predict Pacific yellowfin tuna fishing grounds, exploring the relationship between the catch per unit effort (CPUE) of yellowfin tuna and multiple features. This study reveals that latitude and water temperature at various depths, particularly the sea surface temperature of the preceding and subsequent months and the temperature at depths between 300 and 450 m, are the most significant features influencing CPUE. Additionally, chlorophyll concentration and large-scale climate indices (ONI and NPGIO) also have a notable impact on the distribution of CPUE for yellowfin tuna. Lasso regression effectively identifies features that are significantly correlated with the CPUE of yellowfin tuna, thereby demonstrating superior fit and predictive accuracy in comparison with other models. It provides a suitable methodological approach for selecting fishing ground features of yellowfin tuna in the Pacific Ocean. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Figure 1

35 pages, 8118 KiB

Open AccessArticle

Quantifying Variability in Zebrafish Larvae Locomotor Behavior across Experimental Conditions: A Learning-Based Tracker

by Zhuo Zhang, Xinyu Chai, Guoning Si and Xuping Zhang

Fishes 2024, 9(6), 193; https://doi.org/10.3390/fishes9060193 - 23 May 2024

Cited by 1 | Viewed by 1126

Abstract

This study investigated the effects of environmental changes on zebrafish larval behavior, using single-factor and orthogonal experiments to assess locomotion during temperature and pH changes. In single-factor experiments, zebrafish larvae were exposed to variations in temperature (22 to 30 °C) and pH levels [...] Read more.

This study investigated the effects of environmental changes on zebrafish larval behavior, using single-factor and orthogonal experiments to assess locomotion during temperature and pH changes. In single-factor experiments, zebrafish larvae were exposed to variations in temperature (22 to 30 °C) and pH levels (6.0, 7.0, 9.0). The simultaneous temperature and pH changes were investigated by orthogonal tests. In both experiments, each zebrafish larva was recorded in three 5 min videos at different stages (before exposure, during short-term exposure (10 min), and after long-term exposure (60 min)). You Look Only Once (YOLOv5) and Deep Simple Online Real Time Tracking (DeepSORT) models were adopted to develop a zebrafish larva tracking system, and YOLOv5 was improved in two aspects of anchor clustering and network structure. The tracking accuracy of the tracking system for small targets effectively improved, reaching more than 98% MOTA (Multiple Object Tracking Accuracy). Principal Component Analysis (PCA) was employed to extract three behavioral features from 13 motion parameters, namely motion activity, edge behavior, and motion direction preference. Our findings reveal that lower temperatures and acidic conditions both led to a decrease in motion behavioral activity, and the former also increased edge behavior. Conversely, elevated temperatures and alkaline conditions had a muted impact on these behaviors. Interestingly, concurrent changes in temperature and pH significantly altered directional preference. Additionally, we observed that lower temperatures elicited distinct temporal behavioral patterns at a constant pH level. In summary, we recommend the precise control and explicit reporting of ambient temperature and pH in both breeding devices and experimental wells to minimize the environmental impact on zebrafish behavior and enhance experiment repeatability and reliability. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Figure 1

14 pages, 1941 KiB

Open AccessArticle

Predicting the Fishery Ground of Jumbo Flying Squid (Dosidicus gigas) off Peru by Extracting Features of the Ocean Environment

by Tianjiao Zhang, Jia Xin, Wei Yu, Hongchun Yuan, Liming Song and Zhuo Yang

Fishes 2024, 9(3), 81; https://doi.org/10.3390/fishes9030081 - 21 Feb 2024

Viewed by 1749

Abstract

We introduce a novel method that combines satellite data, advanced clustering techniques, machine learning feature extraction, and statistical models to enhance fishery forecasting accuracy. Focusing on jumbo flying squid in the southeast Pacific Ocean near Peru, we utilize MODIS-Aqua and MODIS-Terra satellite data [...] Read more.

We introduce a novel method that combines satellite data, advanced clustering techniques, machine learning feature extraction, and statistical models to enhance fishery forecasting accuracy. Focusing on jumbo flying squid in the southeast Pacific Ocean near Peru, we utilize MODIS-Aqua and MODIS-Terra satellite data on sea surface temperature (SST) to construct a deep convolutional embedded clustering (DCEC) model and extract the monthly SST features (

F_{M})

based on an optimized number of clusters determined by the Davies–Bouldi index (DBI). We use the extracted

F_{M}

to construct a series of Generalized Additive Models (GAM) to forecast the catch per unit effort (CPUE) of jumbo flying squid within a spatial resolution of 0.5° × 0.5°. Our results demonstrate the following findings: (1) The SST feature clusters obtained through the DCEC model could capture the SST monthly variations; (2) The GAM models with

F_{M}

outperform the models with the traditional monthly average SST in terms of predictive accuracy; (3) Using both

F_{M}

and average SST together can further improve model performance. This study demonstrates the effectiveness of the DCEC combined with DBI in extracting marine environmental features and highlights the ocean environment feature extraction method to enhance the precision and reliability of fishery forecasting models. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Figure 1

17 pages, 4699 KiB

Open AccessArticle

Deep Learning-Based Fishing Ground Prediction Using Asymmetric Spatiotemporal Scales: A Case Study of Ommastrephes bartramii

by Mingyang Xie, Bin Liu, Xinjun Chen, Wei Yu and Jintao Wang

Fishes 2024, 9(2), 64; https://doi.org/10.3390/fishes9020064 - 4 Feb 2024

Cited by 3 | Viewed by 2184

Abstract

Selecting the optimal spatiotemporal scale in fishing ground prediction models can maximize prediction accuracy. Current research on spatiotemporal scales shows that they are symmetrically distributed, which may not capture specific oceanographic features conducive to fishing ground formation. Recent studies have shown that deep [...] Read more.

Selecting the optimal spatiotemporal scale in fishing ground prediction models can maximize prediction accuracy. Current research on spatiotemporal scales shows that they are symmetrically distributed, which may not capture specific oceanographic features conducive to fishing ground formation. Recent studies have shown that deep learning is a promising research direction for addressing spatiotemporal scale issues. In the era of big data, deep learning outperforms traditional methods by more accurately and efficiently mining high-value, nonlinear information. In this study, taking Ommastrephes bartramii in the Northwest Pacific as an example, we used the U-Net model with sea surface temperature (SST) as the input factor and center fishing ground as the output factor. We constructed 80 different combinations of temporal scales and asymmetric spatial scales using data in 1998–2020. By comparing the results, we found that the optimal temporal scale for the deep learning fishing ground prediction model is 15 days, and the spatial scale is 0.25° × 0.25°. Larger time scales lead to higher model accuracy, and latitude has a greater impact on the model than longitude. It further enriches and refines the criteria for selecting spatiotemporal scales. This result deepens our understanding of the oceanographic characteristics of the Northwest Pacific environmental field and lays the foundation for future artificial intelligence-based fishery research. This study provides a scientific basis for the sustainable development of efficient fishery production. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Graphical abstract

14 pages, 9118 KiB

Open AccessArticle

Advanced Robotic System with Keypoint Extraction and YOLOv5 Object Detection Algorithm for Precise Livestock Monitoring

by Balaji Natesan, Chuan-Ming Liu, Van-Dai Ta and Raymond Liao

Fishes 2023, 8(10), 524; https://doi.org/10.3390/fishes8100524 - 21 Oct 2023

Cited by 2 | Viewed by 1858

Abstract

Molting is an essential operation in the life of every lobster, and observing this process will help us to assist lobsters in their recovery. However, traditional observation consumes a significant amount of time and labor. This study aims to develop an autonomous AI-based [...] Read more.

Molting is an essential operation in the life of every lobster, and observing this process will help us to assist lobsters in their recovery. However, traditional observation consumes a significant amount of time and labor. This study aims to develop an autonomous AI-based robot monitoring system to detect molt. In this study, we used an optimized Yolov5s algorithm and DeepLabCut tool to analyze and detect all six molting phases such as S1 (normal), S2 (stress), S3–S5 (molt), and S6 (exoskeleton). We constructed the proposed optimized Yolov5s algorithm to analyze the frequency of posture change between S1 (normal) and S2 (stress). During this stage, if the lobster stays stressed for 80% of the past 6 h, the system will assign the keypoint from the DeepLabCut tool to the lobster hip. The process primarily concentrates on the S3–S5 stage to identify the variation in the hatching spot. At the end of this process, the system will re-import the optimized Yolov5s to detect the presence of an independent shell, S6, inside the tank. The optimized Yolov5s embedded a Convolutional Block Attention Module into the backbone network to improve the feature extraction capability of the model, which has been evaluated by evaluation metrics, comparison studies, and IoU comparisons between Yolo’s to understand the network’s performance. Additionally, we conducted experiments to measure the accuracy of the DeepLabCut Tool’s detections. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Figure 1

17 pages, 38616 KiB

Open AccessEditor’s ChoiceArticle

An Improved Deep Learning Model for Underwater Species Recognition in Aquaculture

by Mahdi Hamzaoui, Mohamed Ould-Elhassen Aoueileyine, Lamia Romdhani and Ridha Bouallegue

Fishes 2023, 8(10), 514; https://doi.org/10.3390/fishes8100514 - 16 Oct 2023

Cited by 7 | Viewed by 5017

Abstract

The ability to differentiate between various fish species plays an essential role in aquaculture. It helps to protect their populations and monitor their health situations and their nutrient systems. However, old machine learning methods are unable to detect objects in images with complex [...] Read more.

The ability to differentiate between various fish species plays an essential role in aquaculture. It helps to protect their populations and monitor their health situations and their nutrient systems. However, old machine learning methods are unable to detect objects in images with complex backgrounds and especially in low-light conditions. This paper aims to improve the performance of a YOLO v5 model for fish recognition and classification. In the context of transfer learning, our improved model FishDETECT uses the pre-trained FishMask model. Then it is tested in various complex scenes. The experimental results show that FishDETECT is more effective than a simple YOLO v5 model. Using the evaluation metrics Precision, Recall, and mAP50, our new model achieved accuracy rates of 0.962, 0.978, and 0.995, respectively. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Figure 1

20 pages, 16539 KiB

Open AccessArticle

Behavior Recognition of Squid Jigger Based on Deep Learning

by Yifan Song, Shengmao Zhang, Fenghua Tang, Yongchuang Shi, Yumei Wu, Jianwen He, Yunyun Chen and Lin Li

Fishes 2023, 8(10), 502; https://doi.org/10.3390/fishes8100502 - 8 Oct 2023

Cited by 1 | Viewed by 1679

Abstract

In recent years, with the development of pelagic fishing, the working environment and monitoring of crew (squid jigger) members have become increasingly important. However, traditional methods of pelagic human observers suffer from high costs, low coverage, poor timeliness, and susceptibility to subjective factors. [...] Read more.

In recent years, with the development of pelagic fishing, the working environment and monitoring of crew (squid jigger) members have become increasingly important. However, traditional methods of pelagic human observers suffer from high costs, low coverage, poor timeliness, and susceptibility to subjective factors. In contrast, the Electronic Monitoring System (EMS) has advantages such as continuous operation under various weather conditions; more objective, transparent, and efficient data; and less interference with fishing operations. This paper shows how the 3DCNN model, LSTM+ResNet model, and TimeSformer model are applied to video-classification tasks, and for the first time, they are applied to an EMS. In addition, this paper tests and compares the application effects of the three models on video classification, and discusses the advantages and challenges of using them for video recognition. Through experiments, we obtained the accuracy and relevant indicators of video recognition using different models. The research results show that when NUM_FRAMES is set to 8, the LSTM+ResNet-50 model has the best performance, with an accuracy of 88.47%, an

F 1

score of 0.8881, and an

m_{a p}

score of 0.8133. Analyzing the EMS for pelagic fishing can improve China’s performance level and management efficiency in pelagic fishing, and promote the development of the fishery knowledge service system and smart fishery engineering. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Graphical abstract

16 pages, 40655 KiB

Open AccessArticle

A Real-Time Lightweight Detection Algorithm for Deck Crew and the Use of Fishing Nets Based on Improved YOLOv5s Network

by Jiaming Wang, Xiangbo Yin and Guodong Li

Fishes 2023, 8(7), 376; https://doi.org/10.3390/fishes8070376 - 20 Jul 2023

Viewed by 1298

Abstract

A real-time monitoring system for the operational status of fishing vessels is an essential element for the modernization of the fishing industry. The operational status of fishing vessels can be identified by using onboard cameras to detect the deck crew and the use [...] Read more.

A real-time monitoring system for the operational status of fishing vessels is an essential element for the modernization of the fishing industry. The operational status of fishing vessels can be identified by using onboard cameras to detect the deck crew and the use of fishing nets. Due to the typically limited processing capacity of shipboard equipment and the significant memory consumption of detection models, general target detection models are unable to perform real-time image detection to identify the operational status of fishing vessels. In this paper, we propose a lightweight real-time deck crew and the use of a fishing net detection method, YOLOv5s-SGC. It is based on the YOLOv5s model, which uses surveillance cameras to obtain video of fishing vessels operating at sea and enhances the dataset. YOLOv5s-SGC replaces the backbone of YOLOv5s with ShuffleNetV2, replaces the feature fusion network with a modified Generalized-FPN, and adds the CBAM attention module in front of the detection head. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Graphical abstract

19 pages, 9426 KiB

Open AccessArticle

Automated Identification of Morphological Characteristics of Three Thunnus Species Based on Different Machine Learning Algorithms

by Liguo Ou, Bilin Liu, Xinjun Chen, Qi He, Weiguo Qian and Leilei Zou

Fishes 2023, 8(4), 182; https://doi.org/10.3390/fishes8040182 - 29 Mar 2023

Cited by 4 | Viewed by 2687

Abstract

Tuna are economically important fish species. The automated identification of tuna species is of importance in fishery production and resource assessment in that it would facilitate the informed monitoring of tuna fishing vessels and the establishment of electronic observer systems. As morphological characteristics [...] Read more.

Tuna are economically important fish species. The automated identification of tuna species is of importance in fishery production and resource assessment in that it would facilitate the informed monitoring of tuna fishing vessels and the establishment of electronic observer systems. As morphological characteristics are important for tuna identification, this study aims to verify the performance of the automated identification of three Thunnus species through morphological characteristics based on different machine learning algorithms. Firstly, morphological outlines were visually analyzed using EFT (elliptic Fourier transform) and CNN (convolutional neural network). Then, the EFT feature data and deep feature data of the tuna outline images were extracted, and principal component analysis of the two different morphological characteristics was performed. Finally, different machine learning algorithms were used to analyze the identification performance of tuna of the same genus and different species. The experimental results showed that EFT features had the highest identification accuracy in KNN (K-nearest neighbor), with 90% for T. obesus, 90% for T. albacores, and 85% for T. alalunga. Deep features had the best identification performance in SVM (support vector machine), with 80% for T. obesus, 90% for T. albacores, and 100% for T. alalunga. Deep features were better than EFT features in identification performance. The biodiversity and intergeneric differences among tuna species can be well analyzed using these two different morphological characteristics. Machine learning algorithms open up the way for rapid near-real-time electronic observer systems in these important international fisheries. Full article

(This article belongs to the Special Issue AI and Fisheries)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

AI and Fisheries

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (11 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI