RSNC-YOLO: A Deep-Learning-Based Method for Automatic Fine-Grained Tuna Recognition in Complex Environments
文献类型： 外文期刊
作者： Xu, Wenjie 1 ; Fang, Hui 1 ; Yu, Shengchi 1 ; Yang, Shenglong 1 ; Yang, Haodong 1 ; Xie, Yujia 1 ; Dai, Yang 1 ;
作者机构： 1.Chinese Acad Fishery Sci, Minist Agr & Rural Affairs, East China Sea Fisheries Res Inst, Key Lab Fisheries Remote Sensing, Shanghai 200090, Peoples R China
2.Laoshan Lab, Qingdao 266237, Peoples R China
3.Shanghai Ocean Univ, Coll Informat, Shanghai 201306, Peoples R China
关键词： tuna; fine-grained recognition; fishing vessel; complex scenarios; improved YOLOv8; segmentation
期刊名称：APPLIED SCIENCES-BASEL （ 影响因子：2.5； 五年影响因子：2.7 ）
ISSN：
年卷期： 2024 年 14 卷 22 期
页码：
收录情况： SCI
摘要： Tuna accounts for 20% of the output value of global marine capture fisheries, and it plays a crucial role in maintaining ecosystem stability, ensuring global food security, and supporting economic stability. However, improper management has led to significant overfishing, resulting in a sharp decline in tuna populations. For sustainable tuna fishing, it is essential to accurately identify the species of tuna caught and to count their numbers, as these data are the foundation for setting scientific catch quotas. The traditional manual identification method suffers from several limitations and is prone to errors during prolonged operations, especially due to factors like fatigue, high-intensity workloads, or adverse weather conditions, which ultimately compromise its accuracy. Furthermore, the lack of transparency in the manual process may lead to intentional underreporting, which undermines the integrity of fisheries' data. In contrast, an intelligent, real-time identification system can reduce the need for human labor, assist in more accurate identification, and enhance transparency in fisheries' management. This system not only provides reliable data for refined management but also enables fisheries' authorities to dynamically adjust fishing strategies in real time, issue timely warnings when catch limits are approached or exceeded, and prevent overfishing, thus ultimately contributing to sustainable tuna management. In light of this need, this article proposes the RSNC-YOLO algorithm, an intelligent model designed for recognizing tuna in complex scenarios on fishing vessels. Based on YOLOv8s-seg, RSNC-YOLO integrates Reparameterized C3 (RepC3), Selective Channel Down-sampling (SCDown), a Normalization-based Attention Module (NAM), and C2f-DCNv3-DLKA modules. By utilizing a subset of images selected from the Fishnet Open Image Database, the model achieves a 2.7% improvement in mAP@0.5 and a 0.7% improvement in mAP@0.5:0.95. Additionally, the number of parameters is reduced by approximately 30%, and the model's weight size is reduced by 9.6 MB, while maintaining an inference speed comparable to that of YOLOv8s-seg.
- 相关文献
作者其他论文 更多>>
-
Effects of western boundary currents and sea surface temperature anomalies on interannual variability of chub mackerel abundance in the Northwest Pacific
作者：Li, Jiasheng;Zhou, Weifeng;Dai, Yang;Tang, Fenghua;Wu, Yumei;Zhang, Heng;Fan, Xiumei;Cui, Xuesen;Li, Jiasheng
关键词：Chub mackerel; Abundance; Kuroshio; Oyashio; Sea surface temperature anomaly; Northwest Pacific
-
Computation and analysis of phenotypic parameters of Scylla paramamosain based on YOLOv11-DYPF keypoint detection
作者：Wu, Chong;Zhang, Shengmao;Wang, Wei;Wu, Zuli;Yang, Shenglong;Chen, Wei;Wu, Chong;Zhang, Shengmao;Zhang, Shengmao
关键词：Scylla paramamosain; Mud crab; Keypoint detection; YOLOv11; Multi-scale fusion; Dynamic upsampling; Support vector regression (SVR)
-
Enhancing Landmark Point Detection in Eriocheir Sinensis Carapace with Differentiable End-to-End Networks
作者：Wu, Chong;Wang, Shuxian;Zhang, Shengmao;Zheng, Hanfeng;Wang, Wei;Yang, Shenglong;Wu, Chong;Zhang, Shengmao;Zheng, Hanfeng
关键词：Eriocheir sinensis; Chinese mitten crab; landmark detection; Gaussian heatmaps; deep convolutional neural network; DSNT module; generalization ability; power consumption
-
Prediction of potential fishing grounds for chub mackerel in the Northwest Pacific utilizing a combination of multivariable Gaussian mixture model and Bayesian approach
作者：Tang, Fenghua;Ba, Yaoji;Zhang, Shengmao;Yang, Shenglong;Zhao, Guoqing;Wu, Zuli;Li, Jiasheng;Cui, Xuesen;Tang, Fenghua;Ba, Yaoji;Zhang, Shengmao;Yang, Shenglong;Zhao, Guoqing;Wu, Zuli
关键词：Chub mackerel; Northwest Pacific; Gaussian mixture model; Bayesian approach
-
Seedling Selection of the Large Yellow Croaker (Larimichthys crocea) for Sustainable Aquaculture: A Review
作者：Han, Xinran;Zhang, Shengmao;Wang, Yabing;Fang, Hui;Peng, Shiming;Yang, Shenglong;Wu, Zuli;Han, Xinran
关键词：
Larimichthys crocea ; seedling selection; genomics; artificial intelligence; marker-assisted selection; sustainable aquaculture -
Revealing the effects of environmental and spatio-temporal variables on changes in Japanese sardine (Sardinops melanostictus) high abundance fishing grounds based on interpretable machine learning approach
作者：Shi, Yongchuang;Zhang, Shengmao;Tang, Fenghua;Yang, Shenglong;Fan, Wei;Han, Haibin;Dai, Yang;Yan, Lei
关键词：
Sardinops melanostictus ; model prediction performance; SHAP visualization; fishery management; Northwest Pacific Ocean -
Clean fishing: Construction of prediction model for high-catch Antarctic krill (Euphausia superba) fishing grounds based on deep learning and dynamic sliding window methods
作者：Han, Haibin;Jiang, Bohui;Huang, Hongliang;Li, Yang;Zhao, Guoqing;Zhang, Heng;Yang, Shenglong;Shi, Yongchuang;Han, Haibin;Jiang, Bohui;Li, Yang;Sui, Jianghua;Wang, Yuhan;Zhao, Guoqing
关键词：Euphausia superba; Deep learning; Dynamic sliding window; Fishing grounds prediction; Polar fishery
