基于多尺度卷积的船舶行为识别方法

doi:10.11772/j.issn.1001-9081.2019050896

计算机应用 ›› 2019, Vol. 39 ›› Issue (12): 3691-3696.DOI: 10.11772/j.issn.1001-9081.2019050896

• 应用前沿、交叉与综合 • 上一篇下一篇

基于多尺度卷积的船舶行为识别方法

王立林, 刘俊

通信信息传输与融合技术国防重点学科实验室(杭州电子科技大学), 浙江杭州 310018

收稿日期:2019-05-28 修回日期:2019-07-02 出版日期:2019-12-10 发布日期:2019-07-19
作者简介:王立林(1995-),男,江西吉安人,硕士研究生,主要研究方向:深度学习、行为识别;刘俊(1971-),男,贵州安顺人,教授,博士,主要研究方向:信息融合、模式识别、智能系统。
基金资助:
国家自然科学基金重点项目（61333009）。

Ship behavior recognition method based on multi-scale convolution

WANG Lilin, LIU Jun

Fundamental Science on Communication Information Transmission and Fusion Technology Laboratory(Hangzhou Dianzi University), Hangzhou Zhejiang 310018, China

Received:2019-05-28 Revised:2019-07-02 Online:2019-12-10 Published:2019-07-19
Contact: 刘俊
Supported by:
This work is partially supported by the National Natural Science Foundation of China (Key Program) (61333009).

摘要/Abstract

摘要： 针对复杂海洋环境下人工监管船舶行为效率低的问题，提出了一种基于多尺度卷积神经网络的船舶行为识别方法。首先，从船舶自动识别系统（AIS）中获取海量船舶行驶数据，并提取出具有判别力的船舶行为轨迹；然后，根据轨迹数据的特性，利用多尺度卷积设计并实现了针对船舶轨迹数据的行为识别网络，并且使用特征通道加权以及长短时记忆网络（LSTM）来提高算法的准确率。在船舶行为数据集上的实验结果表明，对于指定长度的船舶轨迹，所提识别网络能够达到92.1%的识别准确率，相较于传统的卷积神经网络提高了5.9个百分点，并且在稳定性以及收敛速度上都有明显提升。该方法能够有效地提高船舶行为的识别精度，为海洋监管部门提供高效的技术支持。

关键词: 深度学习, 行为识别, 多尺度卷积, 长短期记忆网络, 海上交通

Abstract: The ship behavior recognition by human supervision in complex marine environment is inefficient. In order to solve the problem, a new ship behavior recognition method based on multi-scale convolutional neural network was proposed. Firstly, massive ship driving data were obtained from the Automatic Identification System (AIS), and the discriminative ship behavior trajectories were extracted. Secondly, according to the characteristics of the trajectory data, the behavior recognition network for ship trajectory data was designed and implemented by multi-scale convolution, and the feature channel weighting and Long Short-Term Memory network (LSTM) were used to improve the accuracy of algorithm. The experimental results on ship behavior dataset show that, the proposed recognition network can achieve 92.1% recognition accuracy for the ship trajectories with specific length, which is 5.9 percentage points higher than that of the traditional convolutional neural network. In addition, the stability and convergence speed of the proposed network are significantly improved. The proposed method can effectively improve the ship behavior recognition accuracy, and provide efficient technical support for the marine regulatory authority.

Key words: deep learning, behavior recognition, multi-scale convolution, Long Short-Term Memory network (LSTM), maritime traffic

中图分类号:

TP391.4

王立林, 刘俊. 基于多尺度卷积的船舶行为识别方法[J]. 计算机应用, 2019, 39(12): 3691-3696.

WANG Lilin, LIU Jun. Ship behavior recognition method based on multi-scale convolution[J]. Journal of Computer Applications, 2019, 39(12): 3691-3696.

参考文献

[1] RIVEIRO M, PALLOTTA G, VESPE M. Maritime anomaly detection:a review[J]. Wiley Interdisciplinary Reviews:Data Mining and Knowledge Discovery, 2018, 8(5):e1266.
[2] LAXHAMMAR R, FALKMAN G, SVIESTINS E. Anomaly detection in sea traffic-a comparison of the gaussian mixture model and the kernel density estimator[C]//Proceedings of the 12th International Conference on Information Fusion. Piscataway:IEEE, 2009:756-763.
[3] 甄荣,邵哲平,潘家财,等.基于统计学理论的船舶轨迹异常识别[J].集美大学学报(自然科学版),2015,20(3):193-197.(ZHEN R, SHAO Z P, PAN J C, et al. A study on the identification of abnormal ship trajectory based on statistic theories[J]. Journal of Jimei University (Nature Science), 2015, 20(3):193-197.)
[4] 刘磊,初秀民,蒋仲廉,等.基于KNN的船舶轨迹分类算法[J].大连海事大学学报,2018,44(3):15-21.(LIU L, CHU X M, JIANG Z L, et al. Ship trajectory classification algorithm based on KNN[J]. Journal of Dalian Maritime University, 2018, 44(3):15-21.)
[5] KRAUS P, MOHRDIECK C, SCHWENKER F. Ship classification based on trajectory data with machine learning methods[C]//Proceedings of the 19th International Radar Symposium. Piscataway:IEEE, 2018:1-10.
[6] 韩昭蓉,黄廷磊,任文娟,等.基于Bi-LSTM模型的轨迹异常点检测算法[J].雷达学报,2019,8(1):36-43.(HAN Z R, HUANG T L, REN W J, et al. Trajectory outlier detection algorithm based on Bi-LSTM model[J]. Journal of Radars, 2019, 8(1):36-43.)
[7] LJUNGGREN H. Using deep learning for classifying ship trajectories[C]//Proceedings of 21st International Conference on Information Fusion. Piscataway:IEEE, 2018:2158-2164.
[8] JIANG X, de SOUZA E N, LIU X, et al. Partition-wise recurrent neural networks for point-based AIS trajectory classification[C]//Proceedings of 2017 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Amsterdam:Elsevier, 2017:529-534.
[9] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[10] MAO S, TU E, ZHANG G, et al. An Automatic Identification System (AIS) database for maritime trajectory prediction and data mining[M]//CAO J, CAMBRIA E, LENDASSE A, et al. Proceedings of ELM-2016, PALO 9. Cham:Springer, 2018:241-257.
[11] SZEGEDY C, LIU W, JIA Y, et al. Going deeper with convolutions[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2015:1-9.
[12] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2016:770-778.
[13] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE, 2018:7132-7141.
[14] Marinecadastre. Vessel traffic data[EB/OL].[2019-04-28]. https://marinecadastre.gov/ais/.
[15] KARIM F, MAJUMDAR S, DARABI H, et al. LSTM fully convolutional networks for time series classification[J]. IEEE Access, 2018, 6:1662-1669.
[16] KARIM F, MAJUMDAR S, DARABI H, et al. Multivariate LSTM-FCNs for time series classification[J]. Neural Networks, 2019, 116:237-245.
[17] LIU C L, HSAIO W H, TU Y C. Time series classification with multivariate convolutional neural network[J]. IEEE Transactions on Industrial Electronics, 2018, 66(6):4788-4797.
[18] ZHENG Y, LIU Q, CHEN E, et al. Time series classification using multi-channels deep convolutional neural networks[C]//Proceedings of the 2014 International Conference on Web-Age Information Management, LNC 8485. Cham:Springer, 2014:298-310.
[19] CHEN Z, XUE J, WU C, et al. Classification of vessel motion pattern in inland waterways based on automatic identification system[J]. Ocean Engineering, 2018, 161:69-76.
[20] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 25th International Conference on Neural Information Processing Systems. New York:Curran Associates Inc. 2012:1097-1105.

基于多尺度卷积的船舶行为识别方法

Ship behavior recognition method based on multi-scale convolution

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[2]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[3]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[4]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[5]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[6]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[7]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[8]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[9]	党伟超, 李涛, 白尚旺, 高改梅, 刘春霞. 基于自注意力长短期记忆网络的Web软件系统实时剩余寿命预测方法[J]. 计算机应用, 2021, 41(8): 2346-2351.
[10]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[11]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[12]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[13]	张元钧, 张曦煌. 基于图卷积与长短期记忆网络的动态网络表示学习模型[J]. 计算机应用, 2021, 41(7): 1857-1864.
[14]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[15]	李扬志, 袁家政, 刘宏哲. 基于时空注意力图卷积网络模型的人体骨架动作识别算法[J]. 计算机应用, 2021, 41(7): 1915-1921.