基于改进YOLOv8的渔港船舶进出港目标检测与统计方法
Detection and statistics method of ship entry and exit in a fishing port based on improved YOLOv8
惠卓凡 1李鹏龙 2沈烈 1沈辉 3隋江华 1张胜茂4
作者信息
- 1. 大连海洋大学航海与船舶工程学院,辽宁大连 116023
- 2. 大连海洋大学航海与船舶工程学院,辽宁大连 116023;中国水产科学研究院东海水产研究所农业农村部渔业遥感重点试验室,上海 200090
- 3. 辽宁省海洋与渔业行政执法总队,辽宁大连 116023
- 4. 中国水产科学研究院东海水产研究所农业农村部渔业遥感重点试验室,上海 200090
- 折叠
摘要
为减轻渔港执法人员在渔船进出港统计工作中的压力,提出了一种基于改进YOLOv8模型的渔港船舶进出港目标检测与统计模型YOLOv8n-Bi-FPN-EMA,该模型采用加权双向特征金字塔网络结构(Bi-FPN),引入高效多尺度注意模块(EMA)以提高模型的目标检测准确性和稳定性,并结合BoT-SORT跟踪算法实现对不同类型船舶进出渔港的分类统计.结果表明:与YOLOv8n模型相比,YOLOv8n-Bi-FPN-EMA模型的准确率提高了 5.0％,mAP@0.5提高了 0.2％,对执法船、拖船和渔船的识别准确率分别提高了9.9％、4.9％、0.3％.其中,对渔船的识别准确率为99.1％,召回率为84.4％,mAP@0.5为97.8％.研究表明,YOLOv8n-Bi-FPN-EMA模型在渔船识别上有较好的表现,可用于渔船识别与进出港统计的辅助工作.
Abstract
In order to alleviate the working pressure of law enforcement officers in fishing ports in the statistics of fishing vessels entering and leaving the port,a target detection and statistical model YOLOv8n-Bi-FPN-EMA for ships entering and leaving in a fishing port was proposed based on the improved YOLOv8n model.In the model YOLOv8n-Bi-FPN-EMA,the weighted bidirectional feature pyramid network structure(Bi-FPN)and the efficient multi-scale attention module(EMA)were adopted to improve the accuracy and stability of target detection,and the statistics of the entry and exit of various types of ships in the fishing port were realized through BoT-SORT.Com-pared with the YOLOv8n model,the accuracy of the YOLOv8n-Bi-FPN-EMA model was increased by 5.0％,mAP@0.5 improved by 0.2％,the recognition accuracy for law enforcement vessels,tugboats,and fishing vessels in-creased by 9.9％,4.9％,and 0.3％,respectively.With the identification accuracy for fishing vessels of 99.1％,a recall rate of 84.4％and an mAP@0.5 of 97.8％.Research indicates that the YOLOv8n-Bi-FPN-EMA model has good performance in fishing vessel identification,and can be used for auxiliary work of fishing vessel identification and port entry and exit statistics.
关键词
深度学习/目标检测/YOLOv8/渔船识别/进出港统计/伏渔季管理Key words
deep learning/object detection/YOLOv8/identification of fishing vessel/port entry and exit statis-tics./management of the fishing season引用本文复制引用
出版年
2024
NETL
NSTL
万方数据