Research on target detection of Engraulis japonicus purse seine based on improved model of YOLOv5
文献类型： 外文期刊
作者： Zhang, Jiaze 1 ; Wang, Shuxian 1 ; Zhang, Shengmao 1 ; Tang, Fenghua 1 ; Fan, Wei 1 ; Yang, Shenglong 1 ; Sun, Yongwen 4 ; Liu, Yang 3 ; Zhu, Wenbin 5 ; Zhang, Shan 7 ; He, Ruilin 4 ;
作者机构： 1.Minist Agr & Rural Affairs, Key Lab Fisheries Remote Sensing, Beijing, Peoples R China
2.Chinese Acad Fishery Sci, East China Sea Fisheries Res Inst, Shanghai, Peoples R China
3.Shanghai Ocean Univ, Coll Informat, Shanghai, Peoples R China
4.Dalian Ocean Univ, Sch Nav & Naval Architecture, Dalian, Peoples R China
5.Marine Fisheries Res Inst Zhejiang, Key Lab Sustainable Utilizat Technol Res Fishery, Zhoushan, Peoples R China
6.Qingdao Natl Pilot Lab Marine Sci & Technol, Qingdao, Peoples R China
7.Hainan Univ, Sch Tourism, Haikou, Hainan, Peoples R China
关键词： Engraulis japonicus; quota fishing; YOLOv5; attention mechanism; Kalman filter
期刊名称：FRONTIERS IN MARINE SCIENCE （ 影响因子：5.247； 五年影响因子：5.72 ）
ISSN：
年卷期： 2022 年 9 卷
页码：
收录情况： SCI
摘要： The refined monitoring and identification of fishing operations by fishing vessels is of great significance and value to fishing vessels. In order to solve the problem of inaccurate statistics of current Engraulis japonicus fishing quota and classification, this paper proposes an improved identification algorithm based on YOLOv5. This method introduces the SENet attention mechanism into the YOLOv5 backbone network structure, integrates the target information in different periods of fishing operations, reduces the interference of complex backgrounds, improves the precision of model detection, and ensures real-time detection efficiency. The artificially shot Engraulis japonicus videos are used as the dataset of the study, and the video is converted into a picture format to realize pre-labeling and processing. The 5550 images are divided into the training set, validation set, and test set according to 8:1:1. In order to verify the validity of the data, a set of in the control experiment, the YOLOv5 backbone network was replaced by MobileNetV2 and the SENet attention mechanism was introduced, and four models were implemented for comparison. The experimental results show that the research algorithm can obtain a mean average precision (mAP) of 99.3%, a precision of 98.9%, and a recall of 98.7%, which are improved by 1.4%, 1.7% and 2.5% respectively compared with the original model. The experimental results match the expectations. According to the statistics of some categories, the Kalman filter and the Hungarian matching method are used to count the main categories of fishing baskets, and an accuracy of 96.5% can be obtained. The threshold method for fishing nets and processing vessels can obtain 85.8% and 75% accuracy. These results shows that this target detection research can provide new ideas for job identification of Engraulis japonicus and provide auxiliary means for job statistics.
- 相关文献
作者其他论文 更多>>
-
Genome-wide methylation and transcriptome analysis in koi carp (Cyprinus carpio var. koi): Uncovering novel molecular mechanisms in skin color differentiation and pigmentation
作者：Shi, Xiulan;Chen, Xiaoyu;Dong, Zaijie;Zhu, Wenbin;Fu, Jianjun;Wang, Lanmei;Luo, Mingkun;Dong, Zaijie;Guo, Jun;Lin, Kai
关键词：Koi carp; Skin color; DNA methylation; RNA-sequencing
-
Structure dependence of the enhanced sulfur tolerance of core-shell CoMn oxides for benzene oxidation: Discrepant sulfur species and less affected reactant activation
作者：Liu, Yang;Cheng, Lin;Zhang, Di;Zhan, Jingjing;Shan, Jiajia;Zhou, Hao;Yi, Xianliang;Li, Zhonghong;Shen, Xudong
关键词：VOCs; Catalytic oxidation; Manganese oxide; Cobalt decoration; Sulfur resistance
-
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
-
Comparative Analysis of Prediction Models for Trawling Grounds of the Argentine Shortfin Squid Illex argentinus in the Southwest Atlantic High Seas Based on Vessel Position and Fishing Log Data
作者：Xiang, Delong;Sun, Yuyan;Zhu, Hanji;Wang, Jianhua;Huang, Sisi;Zhang, Shengmao;Zhang, Famou;Zhang, Heng;Xiang, Delong;Sun, Yuyan;Huang, Sisi;Zhang, Shengmao;Zhang, Famou;Zhang, Heng;Xiang, Delong;Sun, Yuyan;Huang, Sisi;Zhang, Shengmao;Zhang, Famou;Zhang, Heng;Zhu, Hanji;Wang, Jianhua
关键词：Southwest Atlantic;
Illex argentinus ; AIS; deep learning; fishing ground prediction -
Single atom Z-scheme heterostructure catalysts of photosensitive metal-organic nanorings and graphite-C3N4 for visible light-driven hydrogen production
作者：Hou, Chao-Ping;Liu, Yang;Liu, Jia-Xin;Li, Xin-Ao;Liang, Zi-Zhan;Liu, Jun-Min;Hou, Chao-Ping;Tan, Li-Lin
关键词：Metal-organic nanoring; Z-scheme heterojunction; Single-atom catalyst; Photocatalytic hydrogen evolution
-
Spatial-temporal distribution of phytoplankton HAB species and contamination status of oyster toxins under intensive oyster farming in Jiangmen coasts, the South China Sea
作者：Zou, Jian;Xiao, Yayuan;Su, Jiaqi;Wu, Peng;Wang, Teng;Lin, Lin;Li, Chunhou;Liu, Yu;Liu, Yong;Zou, Jian;Xiao, Yayuan;Wu, Peng;Wang, Teng;Liu, Yong;Liu, Yang;Wang, Teng;Liu, Yu;Liu, Yong
关键词：HAB species of phytoplankton; Alexandrium pacificum; Paralytic shellfish poisoning; Diarrhetic shellfish poisoning; Jiangmen oyster farming area
-
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)
