Author Login Editor-in-Chief Peer Review Editor Work Office Work

Computer Engineering ›› 2022, Vol. 48 ›› Issue (4): 276-283. doi: 10.19678/j.issn.1000-3428.0058696

• Development Research and Engineering Application • Previous Articles     Next Articles

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

LI Zhongzhi1, YIN Hang1,2, ZUO Jiankai3, SUN Yifan4   

  1. 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

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. 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
  • 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)。

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

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

CLC Number: