[1]王 东,文方青,扶湘典,等. 基于特征共享与多尺度融合的船舶检测方法[J].机械与电子,2026,44(02):1-8.
　WANG Dong,WEN Fangqing,FU Xiangdian,et al. Ship Detection Method Based on Feature Sharing and Multi scale Fusion[J].Machinery & Electronics,2026,44(02):1-8.
点击复制

 基于特征共享与多尺度融合的船舶检测方法()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年02期
页码:
1-8
栏目:
研究与设计
出版日期:
2026-02-26

文章信息/Info

Title:
 Ship Detection Method Based on Feature Sharing and Multi scale Fusion
文章编号:
1001-2257(2026)02-0001-08
作者:
 王 东1; 文方青2; 扶湘典1; 鲁宏伟3
 (1.长江三峡通航管理局, 湖北 宜昌 443002;2.三峡大学计算机与
信息学院, 湖北 宜昌 443002;3.华中科技大学网络空间安全学院, 湖北 武汉 430074)
Author(s):
 WANG Dong1 ; WEN Fangqing2 ; FU Xiangdian1 ; LU Hongwei3
 (1.Three Gorges Navigation Administration of the Yangtze River,Yichang 443002,China;
2.School of Computer and Information Sciences,China Three Gorges University,Yichang 443002,China;
3.School of Cyber Science and Engineering,Huazhong University of Science and Technology,Wuhan 430074,China)
关键词:
 ; 特征共享; 特征融合; 船舶检测; 自适应
Keywords:
feature sharing; feature fusion; ship detection; adaptability
分类号:
TP391
文献标志码:
A
摘要:
 针对现有方法在复杂海上场景下存在的特征提取不足、多尺度目标检测精度下降等问题,提出一种基于特征共享的多尺度船舶检测方法FSMA YOLO。首先,设计一种特征共享检测结构(FSDH),通过权重共享的卷积特征提取器实现不同尺度特征的统一表征,有效减少冗余参数并提升特征一致性;其次,设计多尺度自适应上下文注意模块(MACA),融合通道与空间双维度注意机制,在多尺度卷积下自适应增强关键特征响应,强化模型在复杂背景中的语义辨识能力;最后,引入自适应特征融合模块(ASFF),通过特征尺度归一化与权重自适应融合机制,优化跨层特征整合,增强模型对不同尺寸船舶的检测鲁棒性。实验结果表明,FSMA YOLO 模型在HRSC2016与Levir Ship数据集上检测精度较基准模型显著提升,验证了所提方法的有效性。
Abstract:
 To address the issues of insufficient feature extraction and declining detection accuracy for multi scale targets in complex maritime scenes encountered by existing methods,this paper proposes a multi scale ship detection method named FSMA YOLO based on feature sharing.Firstly,a Feature sharing Detection Head (FSDH) is designed,and a weight shared convolutional feature extractor is employed to achieve unified representation of features across different scales,effectively reducing redundant parameters and enhancing feature consistency.Secondly,a Multi scale Adaptive Context Attention (MACA) module is devised.This module integrates dual dimensional attention mechanisms across channels and space,adaptively enhancing key feature responses under multi scale convolution,thereby strengthening the model’s semantic discrimination capability in complex backgrounds.Finally,an Adaptive Spatial Feature Fusion (ASFF) module is introduced.Through feature scale normalization and an adaptive weight fusion mechanism,it optimizes cross layer feature integration,enhancing the robustness of the model in detecting ships of different sizes.The experimental results show that the FSMA YOLO model achieves a significant improvement in detection accuracy on the HRSC2016 and Levir Ship datasets compared to the baseline model,validating the effectiveness of the proposed approach.

参考文献/References:

 [1] 曹智远,马勇,成雪夫,等.基于PEW YOLOv8的内河船舶目标检测方法[J].交通信息与安全,2025,43(2):36 43.
[2] 董健,赵欣,毋路遥,等.内河船舶检测算法的轻量化改进[J].电子测量技术,2025,48(15):129 140.
[3] 何颖,林智慧.基于深度学习的机器视觉技术在船舶目标检测领域中的应用[J].船舶工程,2025,47(4):194.
[4] 李冬琴,彭琪,吴洋.轻量级注意力机制与跨尺度融合的船舶目标检测[J].电光与控制,2025,32(4):52 57.
[5] YASIR M,WANG J H,XU M M,et al.Ship detection based on deep learning using SAR imagery:a systematic literature review[J].Soft computing,2022,27(1):63 84.
[6] MIN L T,FAN Z M,WANG S Z,et al.Adaptive fusion learningfor compositional zero shot recognition[J].IEEE Transactions on multimedia,2025,27:1193 1204.
[7] CUI Z Y,WANG X Y,LIU N Y,et al.Ship detection in large scale SAR images via spatial shuffle group enhance attention[J].IEEE Transactions on geoscience and remote sensing,2021,59(1):379 391.
[8] HU Q,HU S H,LIU S Q.BANet:a balance attention network for anchor free ship detection in SAR images [J].IEEE Transactions on geoscience and remote sensing,2022,60:1 12.
[9] YANG X,ZHANG X,WANG N N,et al.A robust one stage detector for multiscale ship detection with complex background in massive SAR images[J].IEEE Transactions on geoscience and remote sensing,2022,60:1 12.
[10] YU Y,YANG X,LI J,et al.A cascade rotated anchor aided detector for ship detection in remote sensing images[J].IEEE Transactions on geoscience and remote sensing,2021,60:1 14.
[11] LI D,LIANG Q H,LIU H Q,et al.A novel multidimensional domain deep learning network for SAR ship detection[J].IEEE Transactions on geoscience  and remote sensing,2022,60:1 13.
[12] PAN D C,GAO X,DAI W,et al.SRT Net:scattering region topology network for oriented ship detection in large scale SAR images[J].IEEE Transactions on geoscience and remote sensing,2024,62:1 18.
[13] ZHANG H D,WU Y Q.CSEF Net:cross scale SAR ship detection network based on efficient receptive field and enhanced hierarchical fusion[J].Remote sensing,2024,16(4):622.
[14] REN Z D,TANG Y Q,YANG Y,et aL.SASOD:saliency aware ship object detection in high resolution optical images[J].IEEE Transactions on geoscience and remote sensing,2024,62:1 15.
[15] TANG X,ZHANG J F,XIA Y Z,et al.DBW YOLO:a high precision SAR ship detection method for complex environments[J].IEEE Journal of selected topics in applied earth observations and remote sensing,2024,17:7029 7039.
[16] HAO Y,ZHANG Y.A lightweight convolutional neural network for ship target detection in SAR images[J].IEEE Transactions on aerospace and electronic systems,2024,60(2):1882 1898.
[17] TANG H D,GAO S,LI S,et al.A lightweight SAR image ship detection method based on improved convolution and YOLOv7[J].Remote sensing,2024,16(3):486.
[18] YIN Y F,CHENG X,SHI F,et al.High order spatial interactions enhanced lightweight model for optical remote sensing image based small ship detection [J].IEEE Transactions on geoscience and remote sensing,2024,62:1 16.
[19] CHEN Z H,WU H,WU W,et al.ASFF Det:adaptive space frequency fusion detector for object detection in SAR images[J].IEEE Journal of selected topics in applied earth observations and remote sensing,2025,18:20708 20724.
[20] WEI S J,ZENG X F,QU Q Z,et al.HRSID:a high resolution SAR images dataset for ship detection and instance segmentation[J].IEEE Access,2020,8:120234 120254.
[21] ZOU Z,SHI Z.Random access memories:a new paradigm for target detection in high resolution aerial remotesensing images[J].IEEE Transactions on image processing,2018,27(3):1100 1111.
[22] LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot multibox detector[C]∥European Conference on Computer Vision,2016:21 37.
[23] REN S,HE K,GIRSHICK R,et al.Faster R CNN:towardsreal time object detection with region proposal networks[J].IEEE Transactions on pattern analysis and machine intelligence,2017,39(6):1137 1149.
[24] FENG Y F,HUANG J G,DU S Y,et al.Hyper YOLO:when visual object detection meets hypergraph computation[J].IEEE Transactions on pattern analysis and machine intelligence,2025,47(4):2388 2401.
[25] WANG Z Y,LI C,XU H Y,et al.Mamba YOLO:a simple baseline for object detection with state space model[J].Proceedings of the AAAI conference on artificial intelligence,2025,39(8):8205 8213.

相似文献/References:

[1]雷永涛,周 权,张静静. 基于印制电路连接器变形问题的分析和设计改进[J].机械与电子,2019,(01):7.
　,analysis and design improvement of deformation problem based on printed circuit connector[J].Machinery & Electronics,2019,(02):7.
[2]孟繁萃１,张 达２,张 明１. 自然风力对绝缘子结构的影响[J].机械与电子,2019,(01):3.
　,the influence of natural wind on insulator structure[J].Machinery & Electronics,2019,(02):3.
[3]任智勇１,邓晓政１,马丁峰２. 一种发动机试飞数据快速处理方法[J].机械与电子,2019,(01):11.
　,A Fast Processing Method of Multi-subject Engine Flight Test Data[J].Machinery & Electronics,2019,(02):11.
[4]冷雪锋,吴正明. 基于ＳＴＣ１２Ｃ５Ａ６０Ｓ２的１００Ｗ 小型风力发电系统设计[J].机械与电子,2019,(01):15.
　.The Design of 100W Small Wind Power Generation System Based on STC12C5A60S2[J].Machinery & Electronics,2019,(02):15.
[5]查金水,朱志远,邓友银,等. 某大型相控阵雷达测试系统结构设计[J].机械与电子,2019,(01):19.
　,,et al.Structural Design of a Large Phased Array Radar Test System[J].Machinery & Electronics,2019,(02):19.
[6]万 欢,李伟达,李 娟. 一种面向上肢康复的便携式电刺激器设计[J].机械与电子,2019,(01):33.
　,Design of Portable Electric Stimulator for Upper Limb Rehabilitation[J].Machinery & Electronics,2019,(02):33.
[7]郑锦汤１,李玉忠１,２. 紧凑型纯电动汽车动力系统匹配与性能仿真[J].机械与电子,2019,(01):38.
　,Matching and Performance Simulation of Dynamic Systems of Compact Electric Vehicle[J].Machinery & Electronics,2019,(02):38.
[8]吕明珠１,２,苏晓明 １,等. 改进粒子群算法优化的支持向量机在滚动轴承故障诊断中的应用[J].机械与电子,2019,(01):42.
　,,et al.Application of SVM Optimized by IPSO in Rolling Bearing Fault Diagnosis[J].Machinery & Electronics,2019,(02):42.
[9]韩雪莹１,张佳炜２,刘 梦１,等. 集中控制协调多个并网逆变器的谐波补偿[J].机械与电子,2019,(01):49.
　,,et al.Centralized Control Coordination of Harmonic Compensation for Multiple Grid-connected Inverters[J].Machinery & Electronics,2019,(02):49.
[10]蒋 波１,３,周自强２,等. 基于ＰＬＣ的报废汽车拆解线作业控制系统[J].机械与电子,2019,(01):54.
　,,et al.PLC-based ELV Disassembly Line Operation Control System[J].Machinery & Electronics,2019,(02):54.

备注/Memo

备注/Memo:
 收稿日期:2025-11-06
基金项目:国家自然科学基金资助项目 (62271286)
作者简介:王 东 (1975-),男,湖北宜昌人,高级工程师,研究方向为人工智能、雷达检测;鲁宏伟 (1964-),男,河南许昌人,教授,研究方向为网络安全及网络应用。
更新日期/Last Update: 2026-04-27