基于多任务学习的船舶行为识别与轨迹预测

doi:10.3969/j.issn.1674-0696.2022.04.01

重庆交通大学学报（自然科学版） ›› 2022, Vol. 41 ›› Issue (04): 1-7.DOI: 10.3969/j.issn.1674-0696.2022.04.01

• 交通+大数据人工智能 • 下一篇

基于多任务学习的船舶行为识别与轨迹预测

杨红，韩鹏，刘畅，宫珊珊

(大连海事大学信息科学技术学院，辽宁大连 116026)

收稿日期:2020-09-03 修回日期:2020-10-16 发布日期:2022-04-13
作者简介:杨红（1977—），女，辽宁大连人，副教授，博士，主要从事大数据挖掘与分析方面的研究。E-mail：yanghong@dlmu.edu.cn 通信作者：刘畅（1976—），女，辽宁大连人，副教授，博士，主要从事海上移动通信网方面的研究。E-mail：liuchang@dlmu.edu.cn

Vessel Behavior Recognition and Trajectory Prediction Based on Multi-task Learning Model

YANG Hong, HAN Peng, LIU Chang, GONG Shanshan

(School of Information Science & Technology, Dalian Maritime University, Dalian 116026, Liaoning, China)

Received:2020-09-03 Revised:2020-10-16 Published:2022-04-13

摘要/Abstract

摘要： 针对复杂海洋环境下，船舶行为识别与轨迹预测困难的问题，提出一种基于多任务学习模型。将卷积神经网络(convolutional neural network, CNN)与通过注意力机制优化过的双向长短时记忆网络(bidirectional long short-term memory, BiLSTM)并联作为训练网络，对船舶的行为识别与轨迹预测两个任务进行联合训练；选取船舶自动识别系统(Automatic Identification System, AIS)提供数据基础。研究结果表明：所提出的模型具有更高的预测和识别精度，能有效地辅助海事部门监管工作，同时多任务学习模型也为海上智能交通研究提供新思路。

关键词: 交通工程；智能交通；行为识别与轨迹预测；多任务学习；船舶；船舶自动识别系统

Abstract: To solve the difficulty of vessel behavior recognition and trajectory prediction in complex marine environment, a model based on multi-task learning was proposed. The convolutional neural network (CNN) was connected in parallel with the bidirectional long short-term memory (BiLSTM) optimized by the attention mechanism as a training network, to complete the missions of vessel behavior identification and trajectory prediction at the same time. Vessel automatic identification system (AIS) was selected to provide data base. The research results show that the proposed method has higher prediction accuracy and identification accuracy. It can effectively assist the supervision work of maritime supervision. Meanwhile, the idea of multi-task learning provides a new idea for the study of maritime intelligent transportation.

Key words: traffic engineering; intelligent traffic; behavior recognition and trajectory prediction; multi-task learning; vessel; vessel automatic identification system (AIS)

中图分类号:

U675.79

杨红，韩鹏，刘畅，宫珊珊. 基于多任务学习的船舶行为识别与轨迹预测[J]. 重庆交通大学学报（自然科学版）, 2022, 41(04): 1-7.

YANG Hong, HAN Peng, LIU Chang, GONG Shanshan. Vessel Behavior Recognition and Trajectory Prediction Based on Multi-task Learning Model[J]. Journal of Chongqing Jiaotong University(Natural Science), 2022, 41(04): 1-7.

参考文献

［1］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 Lei, CHU Xiumin, JIANG Zhonglian, et al. Ship trajectory classification algorithm based on KNN［J］. Journal of Dalian Maritime University, 2018, 44(3): 15-21.
［2］ LJUNGGREN H. Using deep learning for classifying ship trajectories［C］∥ 2018 International Conference on Information Fusion (FUSION). IEEE, 2018, 2158-2164.
［3］ JIANG Xiang, LIU Xuan, SOUZA E N D, et al. Improving point-based AIS trajectory classification with partition-wise gated recurrent units［C］∥2017 International
Joint Conference on Neural Networks(IJCNN). IEEE, 2017, 4044-4051.
［4］ LIU Chao, GUO Shuai, FENG Yuan, et al. L-VTP: Long-term vessel trajectory prediction based on multi-source data analysis［J］.Sensors-Basel, 2019, 19(20): 1-18.
［5］乔少杰，金琨，韩楠，等.一种基于高斯混合模型的轨迹预测算法［J］.软件学报，2015，26(5)：1048-1063.
QIAO Shaojie, JIN Kun, HAN Nan, et al. Trajectory prediction algorithm based on gaussian mixture model［J］. Journal of Software, 2015, 26(5): 1048-1063.
［6］ LIU Jiao, SHI Guoyou, ZHU Kaige. Vessel trajectory prediction model based on AIS sensor data and adaptive chaos differential evolution support vector regression
(ACDE-SVR)［J］. Applied Sciences, 2019, 9(15): 2983-3005.
［7］ TANG Huang, YIN Yong, SHEN Helong. A model for vessel trajectory prediction based on long short-term memory neural network［J］. Journal of Marine
Engineering & Technology, 2019: 1-10.
［8］ LIU Xiaodong, HE Pengcheng, CHEN Weizhu, et al. Multi-Task deep neural networks for natural language understanding［C］∥ Proceedings of the 57th Annual
Meeting of the Association for Computational Linguistics. ［S.l.］:［s.n.］, 2019: 4487-4496.
［9］ ZHENG Xiaolong, QIN A K, GONG Maoguo, et al. Self-regulated evolutionary multitask optimization［J］. IEEE Transactions on Evolutionary Computation, 2019, 24
(1): 16-28.
［10］ LIANG Ming, YANG Bin, CHEN Yun, et al. Multi-task multi-sensor fusion for 3d object detection［C］∥ Proceedings of the IEEE Conference on Computer Vision
and Pattern Recognition. ［S.l.］:［s.n.］, 2019: 7345-7353.
［11］尹忠勋，刘强，李东林.基于马尔科夫链的恶劣天气船舶行为预测［J］.广州航海学院学报，2020，28(1)：20-24.
YIN Zhongxun, LIU Qiang, LI Donglin. Prediction of ship behaviors in heavy weather based on Markov chain［J］. Journal of Guangzhou Maritime Institute, 2020, 28(1):
20-24.
［12］徐婷婷，柳晓鸣，杨鑫.基于BP神经网络的船舶航迹实时预测［J］.大连海事大学学报，2012，38(1)：9-11.
XU Tingting, LIU Xiaoming, YANG Xin. BP neural network-based ship track real-time prediction［J］. Journal of Dalian Maritime University, 2012, 38(1): 9-11.
［13］王贵槐，钟诚，初秀民，等.基于BLSTM-RNN的船舶轨迹修复方法［J］.重庆交通大学学报(自然科学版)，2019，38(10)：7-12.
WANG Guihuai, ZHONG Cheng, CHU Xiumin, et al. Ship trajectory restoration method based on BLSTM-RNN［J］. Journal of Chongqing Jiaotong University (Natural
Science), 2019, 38(10): 7-12.

[1]	李永攀1,2，刘正江1，郑中义1. 基于时空密度的船载AIS数据聚类分析方法研究[J]. 重庆交通大学学报（自然科学版）, 2018, 37(10): 117-122.
[2]	田延飞1,2，黄立文1,2，陈姚节1,2，谭天力1,2. 内河船舶航行环境视景三维仿真[J]. 重庆交通大学学报（自然科学版）, 2018, 37(03): 115-120.

基于多任务学习的船舶行为识别与轨迹预测

Vessel Behavior Recognition and Trajectory Prediction Based on Multi-task Learning Model

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics