Accurate detection of ship violations in bridge area waters is very important for the pre-control of ship-bridge collisions. To ensure the safety of ship navigation, this paper presents a detection model of ship violation facing bridge area waters. AIS data of continuous bridge area in the Wuhan section of the Yangtze River is real-time collected and preprocessed, and the Convolutional Neural Network (CNN) with powerful feature learning ability is used to extract ship behavior information.And combined with the Long Short Term Memory (LSTM),a deep CNN-LSTM is established to learn the spatiotemporal behavior characteristics of ships, and the experimental analysis is carried out based on three kinds of illegal behaviors on ship overspeed, turning around, and overtaking. The results show that the DCNN-LSTM model proposed has a strong advantage over the CNN, LSTM, and Support Vector Machine (SVM) models, and its accuracy rate, precision rate, and F1 are 88.96%, 96.49%, and 92.87%, respectively, realizing the accurate identification of ship violation. The validity and superiority of DCNN-LSTM are further demonstrated by analyzing the violation of ships in typical waters. The research results provide a reliable theoretical basis for ship safety supervision in bridge waters and promote the development of ship intelligence.
LIM X, SHUY Q, ZHENGY Z,et al .Identification of unsafe behavior of ship overtaking and deviation in bridge area[J].Journal of Wuhan University of Technology (Transportation Science & Engineering),2023,47(3):561-567.(in Chinese)
YANGH, HANP, LIUC,et al .Vessel behavior recognition and trajectory prediction based on multi-task learning model[J].Journal of Chongqing Jiaotong University (Natural Science),2022,41(4):1-7.(in Chinese)
HANDAYANID O D, SEDIONOW, SHAHA .Anomaly detection in vessel tracking using support vector machines (SVMs)[C]//2013 International Conference on Advanced Computer Science Applications and Technologies.December 23-24,2013,Kuching,Malaysia:IEEE,2013:213-217.
ZHANGD Y, WUQ, ZHONGC, et al. Research on behavior feature extraction method of inland river ships [C]// Academic Committee of the 12th China Intelligent Transportation Annual Conference. Proceedings of the 12th China Intelligent Transportation Annual Conference. Changshu: Publishing House of Electronics Industry, 2017:586-594. (in Chinese)
MAJ, LIW K, ZHANGC W,et al .Ship encounter situation recognition by processing AIS data from traffic intersection waters[J].Navigation of China,2021,44(1):68-74.(in Chinese)
HEF, HEZ W, YANGF,et al .Research on recognition method of abnormal behavior of ships based on electronic chart[J].Journal of Wuhan University of Technology (Transportation Science & Engineering),2019,43(4):631-636.(in Chinese)
WANGL L, LIUJ .Ship behavior recognition method based on multi-scale convolution[J].Journal of Computer Applications,2019,39(12):3691-3696.(in Chinese)
[15]
李爽 .基于AIS的渔船可疑行为检测[D].大连:大连海洋大学,2022.
[16]
LIS .Behavior detection of fishing vessels based on AIS [D].Dalian:Dalian Ocean University,2022.(in Chinese)
[17]
D’AFFLISIOE, BRACAP, WILLETTP .Malicious AIS spoofing and abnormal stealth deviations:a comprehensive statistical framework for maritime anomaly detection[J]. IEEE Transactions on Aerospace and Electronic Systems, 2021, 57(4): 2093-2108.
MAW Y, WUZ L, LIW F. Conformal detection algorithm of anomalous behaviors of vessel[J]. Journal of Traffic and Transportation Engineering,2017, 17(5): 149-158.(in Chinese)
[20]
QIANL, ZHENGY Z, LIL,et al .A new method of inland water ship trajectory prediction based on long short-term memory network optimized by genetic algorithm[J]. Applied Sciences,2022, 12(8): 4073.
[21]
KIRANYAZS, AVCIO, ABDELJABERO, et al. 1D convolutional neural networks and applications: a survey[J]. Mechanical Systems and Signal Processing, 2019, 19(5): 50-54.
[22]
DEIHIMIA, ORANGO, SHOWKATIH .Short-term electric load and temperature forecasting using wavelet echo state networks with neural reconstruction[J].Energy,2013,57:382-401.
QIANL, WANGW B, CHENG C,et al .A fetal electrocardiogram signal extraction method based on long short term memory network optimized by genetic algorithm[J].Journal of Biomedical Engineering,2021,38(2):257-267.(in Chinese)
[25]
KRIZHEVSKYA, SUTSKEVERI, HINTONG E .ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[26]
GERSF A, SCHMIDHUBERJ, CUMMINSF .Learning to forget:continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
FANGQ G. The application of rot indicator for ship’s manoeuvring[J]. Journal of Shanghai Ship and Shipping Research Institute, 1994, 17(1): 73-78.(in Chinese)