浏览全部资源
扫码关注微信
Published： 07 February 2020 ，
扫 描 看 全 文
姚红革，王诚，喻钧，白小军，李蔚.2020.复杂卫星图像中的小目标船舶识别.遥感学报，24（2）： 116-125
YAO Hongge,WANG Cheng,YU Jun,BAI Xiaojun,LI Wei. 2020. Recognition of small-target ships in complex satellite images. National Remote Sensing Bulletin. 24(2): 116-125
船舶作为海上的重要目标，实现对船舶自动识别有重要的意义。针对卫星图像中云雾、海岸背景等复杂海情对船舶识别带来的干扰，以及小目标船舶高漏检率问题，本文提出一种多尺度深度学习模型训练策略，在此基础上构建了一种船舶识别的深度学习网络，该网络可分为多尺度训练、特征提取、生成目标建议区域、船舶分类这4个部分。首先，采用多尺度的训练策略，将多尺度的船舶样本送入网络中进行训练，这样在训练样本中加入了大量小目标船舶的样本，使网络充分提取到小目标船舶的特征；其次，通过卷积神经网络对目标船舶进行特征自适应提取；然后，目标区域建议网络可依据卷积神经网络提取到的特征，在图像中找到感兴趣目标区域，即框定船舶的位置；最后，通过多个全连接层的组合，将高维特征映射到一个4元组中，再运用分类函数输出每一类船舶的概率值，概率值最大的则为该船舶的类别。同时为解决云雾遮挡和海岸背景的干扰，采用了一种负样本增强学习的方法，在样本数据集中加入了大量只含有云雾和海岸背景的图片，进行负样本扩充，增强网络模型对云雾及海岸背景的特征学习能力，以此解决复杂海情的影响。实验结果表明，所提方法有效解决了复杂海情条件下的船舶识别难，以及小目标船舶识别难的问题，实现了复杂海情条件下的船舶识别。同时，与现有成熟的深度学习目标识别算法相比，本文算法的精确度和召回率分别提升了6.98%和18.17%，所训练的模型具有良好的泛化能力和鲁棒性。
As an important target at sea
the realization of automatic recognition of ships is of great siguificance. The diversity of ship classes and complexity of marine environment exert higher requirements for fine-grained recognition of ships in satellite remote sensing images. Many domestic and foreign experts and scholars have carried out extensive research on ship recognition in remote sensing images. However
no universal method can recognize all kinds of ships. Most of the existing methods have strong specificity; poor portability
that is
these methods can only recognize certain classes of ship targets; and complex processing methods. This work proposes a multiscale deep learning model
which avoids complex modeling methods
such as template matching and background modeling. The network can adaptively determine the network parameters and realize the fine-grained recognition of ships by training large number of samples.
First
this work uses negative sample enhancement learning to train the model
and fog and coastal backgrounds are sent as negative samples to the network for training to solve the influence of complex sea conditions
such as cloud–fog occlusion
and coastal background. At the same time
a multiscale sample training method is used in this paper in view of the problem that the size of some targets in the image is small and affects recognition accuracy. The images are compressed into multiple scales and sent to the network for training so that the network can fully learn the features of various ship sizes
thereby solving the difficulty of small target recognition. Second
the pre-trained ZF model is used for feature extraction
and the feature maps are sent to the region proposal network to generate proposal areas. Finally
the generated candidate areas are sent to the fully connected layer for ship fine-grained recognition.
Experimental results show that the precision and recall of our method increased by 6.98% and 18.17% respectively
and the accuracy of ship recognition can reach 92.27% compared with Faster R-CNN. The method can guarantee real-time requirement based on high recognition accuracy and recognize ships under various conditions.
The trained model can realize the fine-grained recognition of ships. The model not only solves the problems of cloud–fog occlusion to ships
but also the difficulty of small target recognition. The accuracy and real-time performance of the model meet the actual requirements and has strong robustness. However
the experimental results also show that the method used still has shortcomings. First
the constructed network structure has high complexity and excessive network overhead
which increase the processing time of ship target recognition; Secondly
the accuracy of the trained ship recognition model can still be improved. These two points are also the key tasks for the follow-up work.
遥感船舶识别复杂海情多尺度细粒度深度学习
remote sensingship recognitioncomplex sea conditionsmulti-scalefine-graineddeep learning
Bentes C, Velotto D and Tings B. 2018. Ship classification in terraSAR-X images with convolutional neural networks. IEEE Journal of Oceanic Engineering, 43(1): 258-266 [DOI: 10.1109/JOE.2017.2767106http://dx.doi.org/10.1109/JOE.2017.2767106]
Bousetouane F and Morris B. 2015. Off-the-shelf CNN features for fine-grained classification of vessels in a maritime environment//Proceedings of the 11th International Symposium on Visual Computing. Las Vegas, NV, USA: Springer: 379-388 [DOI: 10.1007/978-3-319-27863-6_35http://dx.doi.org/10.1007/978-3-319-27863-6_35]
DataFountain[EB/OL].2017. http://www.datafountain.cn/#/competitions/275/introhttp://www.datafountain.cn/#/competitions/275/intro. [2018-06-11]
Girshick R. 2015. Fast R-CNN//Proceedings of 2015 IEEE International Conference on Computer Vision. Santiago, Chile: IEEE: 1440-1448 [DOI: 10.1109/ICCV.2015.169http://dx.doi.org/10.1109/ICCV.2015.169]
Girshick R, Donahue J, Darrell T and Malik J. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE: 580-587 [DOI: 10.1109/CVPR.2014.81http://dx.doi.org/10.1109/CVPR.2014.81]
He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE: 770-778 [DOI: 10.1109/CVPR.2016.90http://dx.doi.org/10.1109/CVPR.2016.90]
Hinton G E and Salakhutdinov R R. 2006. Reducing the dimensio-nality of data with neural networks. Science, 313(5786): 504-507 [DOI: 10.1126/science.1127647http://dx.doi.org/10.1126/science.1127647]
Krizhevsky A, Sutskever I and Hinton G E. 2012. ImageNet classification with deep convolutional neural networks//Proceedings of the 25th International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada: Curran Associates Inc.: 1097-1105
LeCun Y, Bengio Y and Hinton G. 2015. Deep learning. Nature, 521(7553): 436-444 [DOI: 10.1038/nature14539http://dx.doi.org/10.1038/nature14539]
Liao M, Zhan Z Q, Wo W, Pang C and Liu Y. 2019. Study on rainfall-run off simulation and prediction in lake basin based on dynamic data-driven deep recurrent network. Journal of Remote Sensing, 23(05): 911-923
廖明， 詹总谦， 呙维， 庞超， 刘异. 2019. 动态数据驱动模式下的湖泊流域降雨径流模拟. 遥感学报， 23(05): 911-923 [DOI： 10.11834/jrs.20198027http://dx.doi.org/10.11834/jrs.20198027]
Lin Y O, Lei H, Li X Y and Wu J. 2017. Deep learning in NLP: methods and applications. Journal of University of Electronic Science and Technology of China, 46(6): 913-919
林奕欧, 雷航, 李晓瑜, 吴佳. 2017. 自然语言处理中的深度学习: 方法及应用. 电子科技大学学报, 46(6): 913-919 [DOI: 10.3969/j.issn.1001-0548.2017.06.021http://dx.doi.org/10.3969/j.issn.1001-0548.2017.06.021]
Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C Y and Berg A C. 2016. SSD: single shot multibox detector//Proceedings of 14th European Conference on Computer Vision. Msterdam, The Netherlands: Springer: 21-37 [DOI: 10.1007/978-3-319-46448-0_2http://dx.doi.org/10.1007/978-3-319-46448-0_2]
Liu Y, Hu D and Fan J L. 2018. A survey of crime scene investigation image retrieval. Acta Electronica Sinica, 46(3): 761-768
刘颖, 胡丹, 范九伦. 2018. 现勘图像检索综述. 电子学报, 46(3): 761-768 [DOI: 10.3969/j.issn.0372-2112.2018.03.035http://dx.doi.org/10.3969/j.issn.0372-2112.2018.03.035]
Rafique M A, Pedrycz W and Jeon M. 2018. Vehicle license plate detection using region-based convolutional neural networks. Soft Computing, 22(19): 6429-6440 [DOI: 10.1007/s00500-017-2696-2http://dx.doi.org/10.1007/s00500-017-2696-2]
Redmon J, Divvala S, Girshick R and Farhadi A. 2016. You only look once: unified, real-time object detection//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE: 779-788 [DOI: 10.1109/CVPR.2016.91http://dx.doi.org/10.1109/CVPR.2016.91]
Ren S Q, He K M, Girshick R and Sun J. 2017. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6): 1137-1149 [DOI: 10.1109/TPAMI.2016.2577031http://dx.doi.org/10.1109/TPAMI.2016.2577031]
Szegedy C, Liu W, Jia Y Q, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V and Rabinovich A. 2015. Going deeper with convolutions//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA: IEEE: 1-9 [DOI: 10.1109/CVPR.2015.7298594http://dx.doi.org/10.1109/CVPR.2015.7298594]
Tang Z T, Shao K, Zhao D B and Zhu Y H. 2017. Recent progress of deep reinforcement learning: from AlphaGo to AlphaGo Zero. Control Theory and Applications, 34(12): 1529-1546
唐振韬, 邵坤, 赵冬斌, 朱圆恒. 2017. 深度强化学习进展: 从AlphaGo到AlphaGo Zero. 控制理论与应用, 34(12): 1529-1546 [DOI: 10.7641/CTA.2017.70808http://dx.doi.org/10.7641/CTA.2017.70808]
Tian J X, Liu G C, Gu S S, Ju Z J, Liu J G and Gu D D. 2018. Deep learning in medical image analysis and its challenges. Acta Automatica Sinica, 44(3): 401-424
田娟秀, 刘国才, 谷珊珊, 鞠忠建, 刘劲光, 顾冬冬. 2018. 医学图像分析深度学习方法研究与挑战. 自动化学报, 44(3): 401-424 [DOI: 10.16383/j.aas.2018.c170153http://dx.doi.org/10.16383/j.aas.2018.c170153]
Vedaldi A and Lenc K. 2015. MatConvNet: convolutional neural networks for MATLAB//Proceedings of the 23rd ACM international conference on Multimedia. Brisbane, Australia: ACM: 689-692 [DOI: 10.1145/2733373.2807412http://dx.doi.org/10.1145/2733373.2807412]
Wang P Y, Li F, Zhou S R and Liao Z F. 2017. A ship detection and tracking algorithm under complex wharf environment. Computer Engineering and Science, 39(5): 992-998
王培玉, 李峰, 周书仁, 廖卓凡. 2017. 复杂码头环境下的船舶检测与跟踪算法. 计算机工程与科学, 39(5): 992-998 [DOI: 10.3969/j.issn.1007-130X.2017.05.026http://dx.doi.org/10.3969/j.issn.1007-130X.2017.05.026]
Wei N. 2016. The application of template matching and BP neural network in ship identification. Ship Science and Technology, 38(20): 133-135
魏娜. 2016. 模板匹配和BP神经网络在船舶识别中的应用. 舰船科学技术, 38(20): 133-135 [DOI: 10.3404/j.issn.1672-7649.2016.10A.045http://dx.doi.org/10.3404/j.issn.1672-7649.2016.10A.045]
Xiao Z L. 2017. Research on ship identification and control terminal system based on active RFID Technology. Ship Science and Technology, 39(8A): 142-144
肖志良. 2017. 基于有源RFID技术的船舶识别与控制终端系统研究. 舰船科学技术, 39(8A): 142-144 [DOI: 10.3404/j.issn.1672-7619.2017.6A005]
Yang M, Ruan Y D, Chen L K, Zhang P and Chen Q M. 2017. New video recognition algorithms for inland river ships based on faster R-CNN. Journal of Beijing University of Posts and Telecommunications, 40(S1): 130-134
杨名, 阮雅端, 陈林凯, 张鹏, 陈启美. 2017. 甚高速区域卷积神经网络的船舶视频检测方法. 北京邮电大学学报, 40(S1): 130-134 [DOI: 10.13190/j.jbupt.2017.s.029http://dx.doi.org/10.13190/j.jbupt.2017.s.029]
Zhang M M, Choi J, Daniilidis K, Wolf M T and Kanan C. 2015. VAIS: a dataset for recognizing maritime imagery in the visible and infrared spectrums//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston, MA, USA: IEEE: 10-16 [DOI: 10.1109/CVPRW.2015.7301291http://dx.doi.org/10.1109/CVPRW.2015.7301291]
Zhou Y and Zhang J P. 2017. Multi-scale deep learning for product image search. Journal of Computer Research and Development, 54(8): 1824-1832
周晔, 张军平. 2017. 基于多尺度深度学习的商品图像检索. 计算机研究与发展, 54(8): 1824-1832 [DOI: 10.7544/issn1000-1239.2017.20170197http://dx.doi.org/10.7544/issn1000-1239.2017.20170197]
相关文章
相关作者
相关机构
京公网安备11010802024621