Long-term, automated fish detection provides invaluable data for deep-sea aquaculture, which is crucial for safe and efficient seawater aquafarming. In this paper, we used an infrared camera installed on a deep-sea truss-structure net cage to collect fish images, which were subsequently labeled to establish a fish dataset. Comparison experiments with our dataset based on Faster R-CNN as the basic objection detection framework were conducted to explore how different backbone networks and network improvement modules influenced fish detection performances. Furthermore, we also experimented with the effects of different learning rates, feature extraction layers, and data augmentation strategies. Our results showed that Faster R-CNN with the EfficientNetB0 backbone and FPN module was the most competitive fish detection network for our dataset, since it took a significantly shorter detection time while maintaining a high AP50 value of 0.85, compared to the best AP50 value of 0.86 being achieved by the combination of VGG16 with all improvement modules plus data augmentation. Overall, this work has verified the effectiveness of deep learning-based object detection methods and provided insights into subsequent network improvements.

To address the highly demanding assessment of the quantity of fish in cages, a method for estimating the fish quantity in cages based on image sonar is proposed. In this method, forward-looking image sonar is employed for continuous detection in cages, and the YOLO target detection model with attention mechanism as well as a BP neural network are combined to achieve a real-time automatic estimation of fish quantity in cages. A quantitative experiment was conducted in the South China Sea to render a database for training the YOLO model and neural network. The experimental results show that the average detection accuracy mAP50 of the improved YOLOv8 is 3.81% higher than that of the original algorithm. The accuracy of the neural network in fitting the fish quantity reaches 84.63%, which is 0.72% better than cubic polynomial fitting. In conclusion, the accurate assessment of the fish quantity in cages contributes to the scientific and intelligent management of aquaculture and the rational formulation of feeding and fishing plans.

In order to accurately estimate the distribution of Trachinotus ovatus in marine cages, a novel method was developed using omnidirectional scanning sonar and deep-learning techniques. This method involved differentiating water layers and clustering data layer by layer to achieve precise location estimation. The approach comprised two main components: fish identification and fish clustering. Firstly, omnidirectional scanning sonar was employed to perform spiral detection within marine cages, capturing fish image data. These images were then labeled to construct a training dataset for an enhanced CS-YOLOv8s model. After training, the CS-YOLOv8s model was used to identify and locate fish within the images. Secondly, the cages were divided into water layers with depth intervals of 40 cm. The identification coordinate data for each water layer were clustered using the DBSCAN method to generate location coordinates for the fish in each layer. Finally, the coordinate data from all water layers were consolidated to determine the overall distribution of fish within the cage. This method was shown, through multiple experimental results, to effectively estimate the distribution of Trachinotus ovatus in marine cages, closely matching the distributions detected manually.

Obtaining clear underwater images is crucial for smart aquaculture, so it is necessary to repair degraded underwater images. Although underwater image restoration techniques have achieved remarkable results in recent years, the scarcity of labeled data poses a significant challenge to continued advancement. It is well known that semi-supervised learning can make use of unlabeled data. In this study, we proposed a semi-supervised underwater image enhancement method, MCR-UIE, which utilized multimodal contrastive learning and a dynamic quality reliability repository to leverage the unlabeled data during training. This approach used multimodal feature contrast regularization to prevent the overfitting of incorrect labels, and secondly, introduced a dynamic quality reliability repository to update the output as pseudo ground truth. The robustness and generalization of the model in pseudo-label generation and unlabeled data learning were improved. Extensive experiments conducted on the UIEB and LSUI datasets demonstrated that the proposed method consistently outperformed existing traditional and deep learning-based approaches in both quantitative and qualitative evaluations. Furthermore, its successful application to images captured from deep-sea cage aquaculture environments validated its practical value. These results indicated that MCR-UIE held strong potential for real-world deployment in intelligent monitoring and visual perception tasks in complex underwater scenarios.

Introduction: Fish keypoint detection is a prerequisite for accurate fish behavior analysis and biomass weight estimation, and is therefore crucial for efficient and intelligent offshore aquaculture. Traditional keypoint detection networks typically employ coordinate regression methods, which do not impose any constraints on the output of the regression head or the training process of the neural network. As a result, output keypoints of such networks do not always conform to the shape of a fish and the training process can be affected by incorrect labels, leading to errors in subsequent tasks.Methods: To address these issues, this paper proposes a robust deep learning approach characterized by three improvements. 1) A shape model of fish that includes the average shape of fish, principal components of fish keypoints, and corresponding eigenvalues is constructed using principal component analysis (PCA) and unscented transform. 2) A customized version of anchor boxes is introduced and referred to as “anchor fish”, which along with the shape model, can be used to encode and decode fish keypoints. 3) Shape variation loss, calculated based on the eigenvalues in the shape model, is added as part of the loss function to constrain the output of the regression head. Moreover, we built a fish keypoint dataset using infrared cameras mounted on a truss-structure net cage.Results and discussion: Comparative experiments on our dataset using the keypoint evaluation method from COCO are conducted. The results show that our method achieves an AP50 value of 0.656, significantly outperforming the well-designed YOLO5Face, which produces an AP50 value of 0.503. Furthermore, we have comprehensively explored the impact of key hyperparameters on detection performance and robustness to labeling outliers in the training set. The code is available at https://github.com/LMX-BY/fish_landmark_detection_using_PCA_based_fish_shape_model.

This study investigated the structural response characteristics of a novel single-point mooring gravity-type deep-water (SPM-GDW) net cage under irregular waves and currents. A hydrodynamic numerical model of the cage was created and validated through model experiments. Based on the validated cage model, the structural response characteristics such as cage motion response, mooring line forces, and floating collar stress were studied, considering the actual operating conditions in the target sea area. The response time history curves, wave height time history, and spectral density statistics were studied and compared. The results showed that the heave motion of the cage was consistent with wave elevation in the vertical direction and mainly influenced by wave conditions. The surge motion of the cage was closely related to the current, with a significant lag effect compared to wave elevation motion. Low-frequency loads under the combined action of waves and currents had a significant impact on the surge motion of the cage. In addition, the mooring line tension and pontoon stress were closely related to the wave elevation, with peak values of tension and stress occurring almost simultaneously with the peak wave elevation. However, the pontoon stress exhibited high-frequency response characteristics while satisfying the wave frequency response trend. It was found that the flow velocity had a significant impact on the spectral density of mooring line tension and pontoon stress in the low-frequency range, with an increase in spectral density values as the flow velocity increased. The structural response characteristics identified in this study provide a computational basis for the optimized design and analysis of single-point mooring gravity-type deep-water cages.