Abstract
Non-invasive methods of fish counting are crucial for the effective management of aquaculture and aquatic resources. However, accurate and reliable estimation of fish populations in real-time is a significant challenge due to severe occlusion, body deformation, and rapid movement of fish. Recent advancements in computer vision and deep learning algorithms offer substantial potential to revolutionize fish counting methodologies, thereby enhancing conservation efforts and promoting the sustainable management of aquatic resources. This paper presents a comprehensive dataset of 256,580 fish instances annotated with mask information at the pixel level. To address the challenges associated with geometric variations in fish size, pose, perspective, and body shape, we propose a lightweight instance segmentation model based on YOLOv8, which integrates the CSP bottleneck with dual convolutions and the deformable convolutional networks (DConv). In addition, an efficient feature fusion network incorporating multi-scale information was introduced to improve segmentation accuracy by enhancing the representation of feature information, and a decoupled head with attention mechanisms was designed to detect and segment fish bodies in real time. Our proposed approach achieved an outstanding mAP50 of 98.1 % at 60.6 FPS, with model parameters and floating point operations per second (FLOPS) amounting to 25.4 M and 96.9 G, respectively. The instance segmentation-based counting system exhibited impressive performance metrics, with Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-Square (R2) values of 1.19, 1.65, and 0.992, respectively. The proposed method demonstrates strong potential for practical application as an intelligent solution for biomass estimation in recirculating aquaculture systems.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call