基于UNet++网络与多边输出融合策略的船舶检测模型

doi:10.19678/j.issn.1000-3428.0058696

计算机工程 ›› 2022, Vol. 48 ›› Issue (4): 276-283. doi: 10.19678/j.issn.1000-3428.0058696

基于UNet++网络与多边输出融合策略的船舶检测模型

李忠智¹, 尹航^1,2, 左剑凯³, 孙一凡⁴

1. 沈阳航空航天大学计算机学院, 沈阳 110136;
2. 仲恺农业工程学院信息技术学院, 广东广州 510230;
3. 同济大学计算机科学与技术系, 上海 201804;
4. 沈阳航空航天大学理学院, 沈阳 110136

收稿日期:2020-06-22 修回日期:2020-07-23 发布日期:2020-07-31
作者简介:李忠智(2000—),男,本科生,主研方向为目标检测、深度学习、计算机视觉;尹航(通信作者),副教授、博士;左剑凯,博士研究生;孙一凡,本科生。
基金资助:
国家航空基金（2015ZB54007）；辽宁省教育厅科技基金（L201627，L201704，L201750）。

Ship Detection Model Based on UNet++ Network and Multiple Side-Output Fusion Strategy

LI Zhongzhi¹, YIN Hang^1,2, ZUO Jiankai³, SUN Yifan⁴

1. School of Computer Science, Shenyang Aerospace University, Shenyang 110136, China;
2. School of Information Technology, Zhongkai University of Agriculture and Engineering, Guangzhou, Guangdong 510225, China;
3. Department of Computer Science and Technology, Tongji University, Shanghai 201804, China;
4. School of Science, Shenyang Aerospace University, Shenyang 110136, China

Received:2020-06-22 Revised:2020-07-23 Published:2020-07-31

摘要/Abstract

摘要： 船舶检测与识别技术的发展对海上监视及服务工作起重要作用，目前卫星遥感图像船舶目标检测存在背景复杂、船舶尺度变化大等问题，妨碍了海上威胁事件的预测及海上工作效率的提高。提出一种融合多尺度特征信息的目标检测模型，采用UNet++网络进行目标检测提取卫星图像特征，并将全局信息和细粒度信息相融合生成具有高空间精度的中间特征图。在此基础上，使用MSOF策略融合不同语义层次的特征信息，生成最终的检测特征图，以提高船舶目标检测与识别的精度，并通过将二元交叉熵损失函数与Dice系数损失函数结合使用，降低数据集中样本不均衡对模型准确度的影响。基于空客船舶数据集的实验结果表明，该模型能够对遥感图像中的船舶目标进行精准的检测识别，其Dice系数、IOU系数评估值分别为97.3%、96.8%，优于ResNet-34、UNet++等模型。

关键词: UNet++网络, 多边输出融合策略, 船舶检测, 端到端模型, 深度学习

Abstract: The development of ship detection and recognition technology plays an important role in marine surveillance service.At present, there are some problems in ship target detection in satellite remote sensing images, such as complex background and large changes in ship scale, which hinder the prediction of threat events and the improvement of marine operation efficiency.To address the problems of complex background and large changes in ship scale in satellite remote-sensing image ship target detection, a target detection model integrating multiscale feature information is proposed, and the UNet++ network is used for target detection to extract the satellite image features, what's more, global and fine-grained information are fused to generate an intermediate feature map with high spatial accuracy.On this basis, Multiple Side-Output Fusion (MSOF) strategy is used to fuse the feature information of different semantic levels and generate the final detection feature map to improve the accuracy of ship target detection and recognition.Moreover, the influence of the sample imbalance in the dataset on the accuracy of the model is reduced by combining the binary cross-entropy loss function with the Dice coefficient loss function.The experimental results on the Airbus ship dataset show that the model can accurately detect and recognize ship targets in remote-sensing images, and the evaluation values of the Dice coefficient and Intersection Over Union (IOU) coefficient are 97.3% and 96.8%, respectively, which are better than those of ResNet-34, UNet++, and other models.

Key words: UNet++ network, Multiple Side-Output Fusion (MSOF)strategy, ship detection, end-to-end model, deep learning

中图分类号:

TP391

李忠智, 尹航, 左剑凯, 孙一凡. 基于UNet++网络与多边输出融合策略的船舶检测模型[J]. 计算机工程, 2022, 48(4): 276-283.

LI Zhongzhi, YIN Hang, ZUO Jiankai, SUN Yifan. Ship Detection Model Based on UNet++ Network and Multiple Side-Output Fusion Strategy[J]. Computer Engineering, 2022, 48(4): 276-283.

https://www.ecice06.com/CN/Y2022/V48/I4/276

图/表 10

20230131202547

20230131202551

20230131202554

20230131202557

20230131202601

20230131202604

20230131202607

20230131202610

20230131202613

20230131202616

参考文献

[1] 闫长健, 张艳艳.基于贝叶斯网络的船舶碰撞事故态势分析[J].广州航海学院学报, 2020, 28(4):5-9, 22. YAN C J, ZHANG Y Y.Situation analysis of ship collision accidents based on Bayesian network[J].Journal of Guangzhou Institute of Navigation, 2020, 28(4):5-9, 22.(in Chinese)
[2] QU N, ZUO J, CHEN J, et al.Series arc fault detection of indoor power distribution system based on LVQ-NN and PSO-SVM[J].IEEE Access, 2019, 7:184020-184028.
[3] 林封笑, 陈华杰, 姚勤炜, 等.基于混合结构卷积神经网络的目标快速检测算法[J].计算机工程, 2018, 44(12):222-227. LIN F X, CHEN H J, YAO Q W, et al.A fast target detection algorithm based on hybrid structure convolutional neural network[J].Computer Engineering, 2018, 44(12):222-227.(in Chinese)
[4] 段敬雅, 李彬, 董超, 等.基于YOLOv2的船舶目标检测分类算法[J].计算机工程与设计, 2020, 41(6):1701-1707. DUAN J Y, LI B, DONG C, et al.Ship target detection and classification algorithm based on YOLOv2[J].Computer Engineering and Design, 2020, 41(6):1701-1707.(in Chinese)
[5] QU N, LI Z, ZUO J, et al.Fault detection on insulated overhead conductors based on DWT-LSTM and partial discharge[J].IEEE Access, 2020, 8:87060-87070.
[6] XIE X Y, XU Q Z, HU L.Fast ship detection from optical satellite images based on ship distribution probability analysis[C]//Proceedings of the 4th International Workshop on Earth Observation and Remote Sensing Applications.Washington D.C., USA:IEEE Press, 2016:411-416.
[7] YU J Y, DAN H, WANG L Y, et al.A real-time on-board ship targets detection method for optical remote sensing satellite[C]//Proceedings of the 13th International Conference on Signal Processing.Washington D.C., USA:IEEE Press, 2016:243-250.
[8] YU J Y, DAN H, WANG L Y, et al.On-board ship targets detection method based on multi-scale salience enhancement for remote sensing image[C]//Proceedings of the 13th International Conference on Signal Processing.Washington D.C., USA:IEEE Press, 2016:123-129.
[9] LENG X, JI K, ZHOU S, et al.Ship detection based on complex signal kurtosis in single-channel SAR imagery[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(9):6447-6461.
[10] CHENG D, MENG G, XIANG S, et al.Fusionnet:edge aware deep convolutional networks for semantic segmentation of remote sensing harbor images[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(12):5769-5783.
[11] LIN H, SHI Z, ZOU Z.Fully convolutional network with task partitioning for inshore ship detection in optical remote sensing images[J].IEEE Geoscience and Remote Sensing Letters, 2017, 14(10):1665-1669.
[12] JIAO J, ZHANG Y, SUN H, et al.A densely connected end-to-end neural network for multiscale and multiscene SAR ship detection[J].IEEE Access, 2018, 6:20881-20892.
[13] LI Q, MOU L, LIU Q, et al.HSF-Net:multiscale deep feature embedding for ship detection in optical remote sensing imagery[J].IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(12):7147-7161.
[14] WANG Z C, DU L, MAO J S, et, al.SAR target detection based on SSD with data augmentation and transfer learning[J].IEEE Geoscience and Remote Sensing Letters, 2019, 16(1):150-154.
[15] WANG Z C, DU L, ZHANG P, et, al.Visual attention-based target detection and discrimination for high-resolution SAR images in complex scenes[J].IEEE Transactions on Geoscience and Remote Sensing, 2018, 56(4):1855-1872.
[16] AI J Q, TIAN R T, LUO Q W, et, al.Multi-scale rotation-invariant haar-like feature integrated CNN based ship detection of multiple-target environment in SAR imagery[J].IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(12):10070-10087.
[17] SHI Q Q, LI W, ZHANG F, et al.Deep CNN with multi-scale rotation invariance features for ship classification[J].IEEE Access, 2018, 6:38656-38668.
[18] 王磐, 强彦, 杨晓棠, 等.双注意力3D-UNet肺结节分割网[J].计算机工程, 2021, 47(2):307-313. WANG P, QIANG Y, YANG X T, et al.Dual attention 3D-UNet lung nodule segmentation network[J].Computer Engineering, 2021, 47(2):307-313.(in Chinese)
[19] KLAMBAUER G, UNTERTHINER T, MAYR A, et al.Self-normalizing neural networks[C]//Proceedings of Advances in Neural Information Processing Systems.New York, USA:ACM Press, 2017:971-980.
[20] DEMIR B, BOVOLO F, BRUZZONE L.Updating land-cover maps by classification of image time series:a novel change-detection-driven transfer learning approach[J].IEEE Transactions on Geoscience and Remote Sensing, 2012, 51(1):300-312.
[21] JIN S, YANG L, DANIELSON P, et al.A comprehensive change detection method for updating the national land cover database to circa 2011[J].Remote Sensing of Environment, 2013, 132(11):159-175.
[22] AIRBUS.Airbus ship detection challenge.[EB/OL].[2020-05-10].https://www.kaggle.com/c/airbus-ship-detection.
[23] YANG X, FU K, SUN H, et al.R2CNN++:multi-dimensional attention based rotation invariant detector with robust anchor strategy[EB/OL].[2020-05-10].https://arxiv.org/abs/1811.07126.
[24] FALQUETO L, SÁ A L, PAES R, et al.Oil rig recognition using convolutional neural network on sentinel-1 SAR images[J].IEEE Geoscience and Remote Sensing Letters, 2019, 16(8):1329-1333.
[25] YANG R, HU Z, LIU Y, et al.A novel polarimetric SAR classification method integrating pixel-based and patch-based classification[J].IEEE Geoscience and Remote Sensing Letters, 2019, 17(3):431-435.
[26] HORDIIUK D, OLIINYK I, HNATUSHENKO V, et al.Semantic segmentation for ships detection from satellite imagery[C]//Proceedings of the 39th International Conference on Electronics and Nanotechnology.Washington D.C., USA:IEEE Press, 2019:454-457.
[27] HE K, GKIOXARI G, DOLLÁR P, et al.Mask R-CNN.CoRR[EB/OL].[2020-05-10].https://arxiv.org/abs/1703.06870.
[28] HUANG Z, HUANG L, GONG Y, et al.Mask scoring R-CNN[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2019:6409-6418.

选择文件类型/文献管理软件名称

选择包含的内容

基于UNet++网络与多边输出融合策略的船舶检测模型

Ship Detection Model Based on UNet++ Network and Multiple Side-Output Fusion Strategy

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	魏嵬, 丁香香, 郭梦星, 杨钊, 刘辉. 文本相似度计算方法综述[J]. 计算机工程, 2024, 50(9): 18-32.
[2]	朱凯, 李理, 张彤, 江晟, 别一鸣. 基于Transformer的多阶段运动模糊图像修复网络[J]. 计算机工程, 2024, 50(9): 276-285.
[3]	张天鹏, 韩晶, 吕学强. 基于多任务学习的超分辨率辅助小目标检测[J]. 计算机工程, 2024, 50(9): 304-312.
[4]	高煜宝, 文志诚. 基于注意力机制的双路解码器图像去噪方法[J]. 计算机工程, 2024, 50(9): 324-332.
[5]	张华青, 夏张涛, 陆晓庆, 童基均. 基于字形特征的血管外科命名实体识别[J]. 计算机工程, 2024, 50(8): 13-21.
[6]	张亚洲, 和玉, 戎璐, 王祥凯. 基于上下文知识增强型Transformer网络的抑郁检测[J]. 计算机工程, 2024, 50(8): 75-85.
[7]	高伟, 李帅龙, 茆琳, 王磊, 李颖颖, 韩林. 一种基于TVM的算子生成加速策略[J]. 计算机工程, 2024, 50(8): 353-362.
[8]	王宇, 祁琦, 王纯, 许才. 储能变流器信号高精度故障诊断方法[J]. 计算机工程, 2024, 50(8): 389-396.
[9]	牛瑞婷, 严天峰, 高锐, 王映植. 低信噪比下基于深度学习TCNN-MobileNet的调制识别[J]. 计算机工程, 2024, 50(7): 204-215.
[10]	肖慈, 徐杨, 张永丹, 冯明文, 黄易仟. 结合注意力和低光增强的夜间语义分割[J]. 计算机工程, 2024, 50(7): 271-281.
[11]	张诗婧, 莫绪涛, 赵行, 董杨林. 基于球面折反射成像和YOLOv7的内螺纹缺陷检测[J]. 计算机工程, 2024, 50(7): 282-292.
[12]	徐明亮, 李芳媛, 马浩然, 何飞. 大规模神经记录的峰电位聚类算法(特邀)[J]. 计算机工程, 2024, 50(6): 1-34.
[13]	魏琢艺, 罗迈, 李文兵, 曾远松, 余伟江, 杨跃东. 基于多源域适应的单细胞智能分类[J]. 计算机工程, 2024, 50(6): 48-55.
[14]	李子杰, 周菊香, 韩晓瑜, 甘健侯, 鹿泽光, 王俊. 序列特征与学习过程融合的知识追踪模型[J]. 计算机工程, 2024, 50(6): 77-85.
[15]	李永飞, 李铭洋, 常鑫, 曹可欣. 基于可解释性深度学习的物联网水质监测数据异常检测[J]. 计算机工程, 2024, 50(6): 179-187.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于UNet++网络与多边输出融合策略的船舶检测模型

Ship Detection Model Based on UNet++ Network and Multiple Side-Output Fusion Strategy

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 15

编辑推荐

Metrics

本文评价