Liang Maohan

Liang Maohan

Research Fellow

Publications

You can also find my articles on my Google Scholar profile.

Deep-TCP: Multi-source data fusion for deep learning-powered tropical cyclone intensity prediction to enhance urban sustainability

Published in Information Fusion, 2025

Tropical cyclones (TC) exert a profound impact on cities, causing extensive damage and losses. Thus, TC Intensity Prediction is crucial for creating sustainable cities as it enables proactive measures to be taken, including evacuation planning, infrastructure reinforcement, and emergency response coordination. In this study, we propose a Deep learning-powered TC Intensity Prediction (Deep-TCP) framework. In particular, Deep-TCP contains a data constraint module for fusing data features from multiple sources and establishing a unified global representation. To capture the spatiotemporal attributes, a Spatial-Temporal Attention (ST-Attention) module is built to distill insights from environmental variables. To improve the robustness and stability of the predictions, an encoder-decoder module that utilizes the ConvGPU unit is introduced to enhance feature maps. Then, a novel feature enhancement module is built to?

Recommended citation: Jiang, S., Liang, M., Wang, C., Fan, H., & Ma, Y. (2025). Deep-TCP: Multi-source data fusion for deep learning-powered tropical cyclone intensity prediction to enhance urban sustainability.?nformation Fusion,?14, 102670. https://doi.org/10.1016/j.inffus.2024.102670

Wave energy forecasting: A state-of-the-art survey and a comprehensive evaluation

Published in Applied Soft Computing, 2025

Wave energy, a promising renewable energy source, has the potential to diversify the global energy mix significantly. Accurate forecasting of significant wave height (SWH) is crucial for enhancing the efficiency and reliability of wave energy conversion systems. As interest in this field grows, research into SWH forecasting has expanded dramatically. This comprehensive survey evaluates sixteen SWH forecasting methods, including Persistence, decision trees, deep neural networks, random neural networks, and random forests. The paper begins by establishing a detailed taxonomy that categorizes SWH forecasting algorithms, providing a framework to interpret the complexities of different methodological approaches. We then explore the interconnections between ensemble learning and decomposition-based frameworks and the integration of individual forecasting techniques within ensemble and hybrid models. In?

Recommended citation: Gao, R., Zhang, X., Liang, M., Suganthan, P. N., & Dong, H. (2025). Wave energy forecasting: A state-of-the-art survey and a comprehensive evaluation.?pplied Soft Computing, 112652. https://doi.org/10.1016/j.asoc.2024.112652

Integrating GPU-Accelerated for Fast Large-Scale Vessel Trajectories Visualization in Maritime IoT Systems

Published in IEEE Transactions on Intelligent Transportation Systems, 2025

With the advancement of satellite communication technology, the maritime Internet of Things (IoT) has made significant progress. As a result, vast amounts of Automatic Identification System (AIS) data from global vessels are transmitted to various maritime stakeholders through Maritime IoT systems. AIS data contains a large amount of dynamic and static information that requires effective and intuitive visualization for comprehensive analysis. However, two major deficiencies challenge current visualization models: a lack of consideration for interactions between distant pixels and low efficiency. To address these issues, we developed a large-scale vessel trajectories visualization algorithm, called the Non-local Kernel Density Estimation (NLKDE) algorithm, which incorporates a non-local convolution process. It accurately calculates the density distribution of vessel trajectories by considering correlations between?

Recommended citation: Liang, M., Liu, K., Gao, R., & Li, Y. (2025). Integrating GPU-Accelerated for Fast Large-Scale Vessel Trajectories Visualization in Maritime IoT Systems.?EEE Transactions on Intelligent Transportation Systems. 10.1109/TITS.2024.3521050

From ports to routes: Extracting multi-scale shipping networks using massive AIS data

Published in Ocean Engineering, 2024

Maritime transportation is a critical component of global trade and commerce. To ensure maritime safety, fixed shipping routing has been established in many complex waters. However, there is currently a lack of comprehensive digital shipping networks in wide-range maritime areas. To better understand the navigational patterns, this paper proposes a data-driven extraction framework for multi-scale shipping networks, including port-, node-, and route-level shipping networks. It is essentially a hierarchical approach, which progresses from port to route. In particular, for the extraction of port-level shipping networks, the clustering in quest (CLIQUE) and alpha-shapes algorithms are employed to accurately extract the boundaries and spatial extents of individual ports. For the node-level shipping network extraction, an adaptive Douglas-Peucker algorithm is developed to identify crucial feature points, and CLIQUE?

Recommended citation: Liu, R. W., Zhou, S., Liang, M., Gao, R., & Wang, H. (2024). From ports to routes: Extracting multi-scale shipping networks using massive AIS data.?cean Engineering,?11, 118969. https://doi.org/10.1016/j.oceaneng.2024.118969

AISClean: AIS data-driven vessel trajectory reconstruction under uncertain conditions

Published in Ocean Engineering, 2024

In maritime transportation, intelligent vessel surveillance has become increasingly prevalent and widespread by collecting and analyzing high massive spatial data from automatic identification system (AIS). The state-of-the-art AIS devices contain various functionalities, such as position transmission, tracking navigation, etc. Widely equipped shipboard AIS devices provide a large amount of real-time and historical vessel trajectory data for maritime management. However, the original AIS data often suffers from unwanted noise (i.e., poorly tracked timestamped points for vessel trajectories) and missing (i.e., no data is received or transmitted for a long term) data during signal acquisition, transmission, and analog-to-digital conversion. This degradation in data quality poses significant risks, including potential miscalculations in vessel collision avoidance systems, inaccuracies in emission calculations, and challenges in

Recommended citation: Liang, M., Su, J., Liu, R. W., & Lam, J. S. L. (2024). AISClean: AIS data-driven vessel trajectory reconstruction under uncertain conditions.?cean Engineering,?06, 117987. https://doi.org/10.1016/j.oceaneng.2024.117987

AIS-based vessel trajectory compression: a systematic review and software development

Published in IEEE Open Journal of Vehicular Technology, 2024

?"With the advancement of satellite and 5G communication technologies, vehicles can transmit and exchange data from anywhere in the world. It has resulted in the generation of massive spatial trajectories, particularly from the Automatic Identification System (AIS) for surface vehicles. The massive AIS data lead to high storage requirements and computing costs, as well as low data transmission efficiency. These challenges highlight the critical importance of vessel trajectory compression for surface vehicles. However, the complexity and diversity of vessel trajectories and behaviors make trajectory compression imperative and challenging in maritime applications. Therefore, trajectory compression has been one of the hot spots in research on trajectory data mining. The major purpose of this work is to provide a comprehensive reference source for beginners involved in vessel trajectory compression.?

Recommended citation: Liu, R. W., Zhou, S., Yin, S., Shu, Y., & Liang, M. (2024). AIS-based vessel trajectory compression: a systematic review and software development.?EEE Open Journal of Vehicular Technology.""" 10.1109/OJVT.2024.3443675

A survey of distance-based vessel trajectory clustering: Data pre-processing, methodologies, applications, and experimental evaluation

Published in arXiv, 2024

Vessel trajectory clustering, a crucial component of the maritime intelligent transportation systems, provides valuable insights for applications such as anomaly detection and trajectory prediction. This paper presents a comprehensive survey of the most prevalent distance-based vessel trajectory clustering methods, which encompass two main steps: trajectory similarity measurement and clustering. Initially, we conducted a thorough literature review using relevant keywords to gather and summarize pertinent research papers and datasets. Then, this paper discussed the principal methods of data pre-processing that prepare data for further analysis. The survey progresses to detail the leading algorithms for measuring vessel trajectory similarity and the main clustering techniques used in the field today. Furthermore, the various applications of trajectory clustering within the maritime context are explored. Finally, the paper evaluates the effectiveness of different algorithm combinations and pre-processing methods through experimental analysis, focusing on their impact on the performance of distance-based trajectory clustering algorithms. The experimental results demonstrate the effectiveness of various trajectory clustering algorithms and notably highlight the significant improvements that trajectory compression techniques contribute to the efficiency and accuracy of trajectory clustering. This comprehensive approach ensures a deep understanding of current capabilities and future directions in vessel trajectory clustering.

Recommended citation: Liang, M., Liu, R. W., Gao, R., Xiao, Z., Zhang, X., & Wang, H. (2024). A survey of distance-based vessel trajectory clustering: Data pre-processing, methodologies, applications, and experimental evaluation.?rXiv preprint arXiv:2407.11084. arXiv preprint arXiv:2407.11084

Multi-ship encounter situation graph structure learning for ship collision avoidance based on AIS big data with spatio-temporal edge and node attention graph convolutional networks

Published in Ocean Engineering, 2024

With the increasing number of ships on the sea, the frequency multi-ship encounters situation was becoming more common than two-ship encounter. The complexity and risk of the navigation will exponentially increase with the more ships involved. Relying solely on the International Regulations for Preventing Collisions at Sea (COLREGS) (objective knowledge) was insufficient to handle the multi-ship intelligent collision avoidance problem, also needed the ship officer's good seamanship (subjective knowledge). In this study, we propose a methodology that combines subjective insights from AIS big data with objective analysis through multi-ship encounters recognition with graph convolutional networks (GCN). (1) The ship encounter 8-azimuths map was utilized to identify the two-ship encounter situation (25 types) from the AIS data. (2) Identify the multi-ship encounters trajectory data by cross-matching the two

Recommended citation: Gao, M., Liang, M., Zhang, A., Hu, Y., & Zhu, J. (2024). Multi-ship encounter situation graph structure learning for ship collision avoidance based on AIS big data with spatio-temporal edge and node attention graph convolutional networks.?cean Engineering,?01, 117605. https://doi.org/10.1016/j.oceaneng.2024.117605

Spatio-Temporal Multi-Graph Transformer Network for Joint Prediction of Multiple Vessel Trajectories

Published in Engineering Applications of Artificial Intelligence, 2024

The vessel trajectory prediction plays a vital role in guaranteeing traffic safety for unmanned surface vehicles and autonomous surface vessels. By leveraging advanced satellite communication technology, AIS provides massive vessel trajectories, significantly enhancing maritime safety and decision-making. This research proposes a spatio-temporal multi-graph transformer network (ST-MGT), aiming to predict multiple vessel trajectories simultaneously. This innovative model amalgamates the capabilities of graph convolutional networks (GCNs) and transformer models to proficiently address the spatial and temporal interactions amongst vessels. The ST-MGT is comprised of three crucial layers. The temporal transformer layer employs sophisticated temporal transformer and memory mechanisms to discern the intricate temporal correlations between vessel movements. The spatial multi-graph transformer layer constructs a comprehensive multi-graph representation to illuminate spatial correlations between vessels. It incorporates a spatial graph convolutional network and transformer to meticulously understand and interpret the diverse and complex spatial interactions amongst varying vessels. Lastly, the Regularized LSTM (RegLSTM) layer is implemented for predicting vessel trajectories accurately, based on the unraveled spatio-temporal patterns. Extensive and meticulous experiments reveal that our proposed ST-MGT method transcends other state-of-the-art prediction models in robustness and accuracy. The model? capability to facilitate multi-vessel and multi-step prediction showcases its immense potential and adaptability in intricate and multifaceted navigation environments, underscoring its practical applicability and significance in enhancing maritime navigational safety.

Recommended citation: Liu, R. W., Zheng, W., & Liang, M. (2024). Spatio-temporal multi-graph transformer network for joint prediction of multiple vessel trajectories. Engineering Applications of Artificial Intelligence, 129, 107625. http://doi.org/10.1016/j.engappai.2023.107625

PiracyAnalyzer: Spatial Temporal Patterns Analysis of Global Piracy Incidents

Published in Reliability Engineering & System Safety, 2024

Maritime piracy incidents present significant threats to maritime security, resulting in material damages and jeopardizing the safety of crews. Despite the scope of the issue, existing research has not adequately explored the diverse risks and theoretical implications involved. To fill that gap, this paper aims to develop a comprehensive framework for analyzing global piracy incidents. The framework assesses risk levels and identifies patterns from spatial, temporal, and spatio-temporal dimensions, which facilitates the development of informed anti-piracy policy decisions. Firstly, the paper introduces a novel risk assessment mechanism for piracy incidents and constructs a dataset encompassing 3,716 recorded incidents from 2010 to 2021. Secondly, this study has developed a visualization and analysis framework capable of examining piracy incidents through the identification of clusters, outliers, and hot spots. Thirdly, a number of experiments are conducted on the constructed dataset to scrutinize current spatial-temporal patterns of piracy accidents. In experiments, we analyze the current trends in piracy incidents on temporal, spatial, and spatio-temporal dimensions to provide a detailed examination of piracy incidents. The paper contributes new understandings of piracy distribution and patterns, thereby enhancing the effectiveness of anti-piracy measures.

Recommended citation: Liang, M., Li, H., Liu, R. W., Lam, J. S. L., & Yang, Z. (2024). PiracyAnalyzer: Spatial temporal patterns analysis of global piracy incidents. Reliability Engineering & System Safety, 243, 109877. https://doi.org/10.1016/j.ress.2023.109877

Unsupervised Maritime Anomaly Detection for Intelligent Situational Awareness Using AIS Data

Published in Knowledge-Based Systems, 2024

With the mandatory implementation of the automatic identification system and the rapid advancement of relevant satellite communication technologies, a vast amount of vessel trajectory data has been amassed. It has catalyzed advancements in the field of maritime anomaly detection, significantly contributing to the enhancement of intelligent maritime situational awareness. However, detecting abnormal vessel trajectories from massive data is a highly challenging task that requires extensive manual effort. To address the challenge, this paper develops an unsupervised deep learning method for detecting abnormal vessel trajectories. Specifically, we first generate the informative trajectory images by remapping the raw vessel trajectories into two-dimensional matrices while maintaining the spatio-temporal properties. Then, a Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is trained on normal vessel trajectories. Next, an encoder is trained to map these trajectory images to a latent space. Finally, the trained encoder and WGAN-GP are used to design an anomaly score for detecting abnormal vessel trajectories and anomalies in vessel trajectories. Experimental evaluations using multiple evaluation metrics on diverse simulated and real-world maritime environments validate the efficacy of the proposed method in unsupervised maritime anomaly detection. The results indicate that the proposed model can provide accurate anomaly detection on vessel trajectories without manual labeling.

Recommended citation: Liang, M., Weng, L., Gao, R., Li, Y., & Du, L. (2024). Unsupervised maritime anomaly detection for intelligent situational awareness using AIS data. Knowledge-Based Systems, 284, 111313. https://doi.org/10.1016/j.knosys.2023.111313

QSD-LSTM: Vessel trajectory prediction using long short-term memory with quaternion ship domain

Published in Applied Ocean Research, 2023

Vessel trajectory prediction is a critical aspect of ensuring maritime traffic safety and avoiding collisions. The long short-term memory (LSTM) network and its extensions have represented powerful ability of vessel trajectory prediction. However, the previous studies often did not take dynamic interactions between neighboring vessels into account. Additionally, in complex traffic conditions, trajectory prediction will acquire uncertainty, and these potential negative factors can limit the prediction of future trajectory. To enhance the prediction performance, we propose an interactive vessel trajectory prediction framework (i.e., QSD-LSTM) based on LSTM, which is embedded with the quaternion ship domain (QSD). The QSD is beneficial for avoiding unwanted collision between neighboring vessels. In addition, the operation of trajectory clustering is further incorporated into our trajectory prediction framework, potentially leading to more robust prediction results. Numerous experiments have been implemented on realistic automatic identification system (AIS)-based vessel trajectories to compare our QSD-LSTM with several state-of-the-art prediction methods. The prediction results have demonstrated the superior performance of our method in terms of both quantitative and qualitative evaluations.

Recommended citation: Liu, R. W., Hu, K., Liang, M., Li, Y., Liu, X., & Yang, D. (2023). QSD-LSTM: Vessel trajectory prediction using long short-term memory with quaternion ship domain. Applied Ocean Research, 136, 103592. https://doi.org/10.1016/j.apor.2023.103592

Ship collision risk analysis: Modeling, visualization and prediction

Published in Ocean Engineering, 2022

Ship collisions are the primary threat to traffic safety in the sea, which can seriously threaten human lives, the environment and material assets. Therefore, the detection and analyze of ship collision risks have important theoretical significance and application value. To improve maritime safety and efficiency, we propose a modeling, visualization and prediction framework to analyze ship collision risk. In particular, to fully consider the maneuverability of the ship, we introduce the quaternion ship domain (QSD) into the vessel conflict ranking operator (VCRO). In addition, to further analyze and better understand collision risk, the kernel density estimation (KDE) model is employed to visualize the ship collision risk. The ship collision risk usually contains underlying patterns and laws. Thus, we proposed a convolutional long short-term memory network (ConvLSTM) model, which can extract spatial?emporal features and predict spatial?emporal risk. Finally, to verify the reliability and robustness of the framework, we conducted extensive experiments on the automatic identification system (AIS) data of Chengshantou water. The results show that the framework demonstrates superiority in risk calculation, visualization and prediction. Theoretically, the framework proposed in this paper can serve maritime intelligent transportation system well.

Recommended citation: Liu, R. W., Huo, X., Liang, M., & Wang, K. (2022). Ship collision risk analysis: modeling, visualization and prediction. Ocean Engineering, 266, 112895. https://doi.org/10.1016/j.oceaneng.2022.112895

Fine-Grained Vessel Traffic Flow Prediction with a Spatio-Temporal Multi-Graph Convolutional Network

Published in IEEE Transactions on Intelligent Transportation Systems, 2022

The accurate and robust prediction of vessel traffic flow is gaining importance in maritime intelligent transportation system (ITS), such as vessel traffic services, maritime spatial planning, and traffic safety management, etc. To achieve fine-grained vessel traffic flow prediction, we will first generate the maritime traffic network (which is essentially a graph), and then propose a graph-driven neural network. In particular, to represent various correlations among spatio-temporal vessel traffic flow, we tend to extract the feature points (i.e., starting, way and ending points) by utilizing the knowledge of vessel positioning data. These feature points are essentially related to the geometrical structures of massive vessel trajectories collected from massive automatic identification system (AIS) records, contributing to the generation of maritime traffic network. We then propose a spatio-temporal multi-graph convolutional network (STMGCN)-based vessel traffic flow prediction method by exploiting multiple types of inherent correlations in the generated maritime graph. The proposed STMGCN mainly contains one spatial multi-graph convolutional layer and two temporal gated convolutional layers, beneficial for extracting spatial and temporal traffic flow patterns. The main benefit of our graph-driven prediction method is that it takes full advantage of the maritime graph and multi-graph learning. Comprehensive experiments have been implemented on realistic AIS dataset to compare our method with several state-of-the-art prediction methods. The fine-grained prediction results have demonstrated our superior performance in terms of both accuracy and robustness.

Recommended citation: Liang, M., Liu, R. W., Zhan, Y., Li, H., Zhu, F., & Wang, F. Y. (2022). Fine-grained vessel traffic flow prediction with a spatio-temporal multigraph convolutional network. IEEE Transactions on Intelligent Transportation Systems, 23(12), 23694-23707. http://10.1109/TITS.2022.3199160

STMGCN: Mobile Edge Computing-Empowered Vessel Trajectory Prediction Using Spatio-Temporal Multi-Graph Convolutional Network

Published in IEEE Transactions on Industrial Informatics, 2022

The revolutionary advances in machine learning and data mining techniques have contributed greatly to the rapid developments of maritime Internet of Things (IoT). In maritime IoT, the spatio-temporal vessel trajectories, collected from the hybrid satellite-terrestrial automatic identification system (AIS) base stations, are of considerable importance for promoting traffic situation awareness and vessel traffic services, etc. To guarantee traffic safety and efficiency, it is essential to robustly and accurately predict the AIS-based vessel trajectories (i.e., the future positions of vessels) in maritime IoT. In this work, we propose a spatio-temporal multigraph convolutional network (STMGCN)-based trajectory prediction framework using the mobile edge computing (MEC) paradigm. Our STMGCN is mainly composed of three different graphs, which are, respectively, reconstructed according to the social force, the time to closest point of approach, and the size of surrounding vessels. These three graphs are then jointly embedded into the prediction framework by introducing the spatio-temporal multigraph convolutional layer. To further enhance the prediction performance, the self-attention temporal convolutional layer is proposed to further optimize STMGCN with fewer parameters. Owing to the high interpretability and powerful learning ability, STMGCN is able to achieve superior prediction performance in terms of both accuracy and robustness. The reliable prediction results are potentially beneficial for traffic safety management and intelligent vehicle navigation in MEC-enabled maritime IoT.

Recommended citation: Liu, R. W., Liang, M., Nie, J., Yuan, Y., Xiong, Z., Yu, H., & Guizani, N. (2022). STMGCN: Mobile edge computing-empowered vessel trajectory prediction using spatio-temporal multigraph convolutional network. IEEE Transactions on Industrial Informatics, 18(11), 7977-7987. http://10.1109/TII.2022.3165886

Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime Internet of Things

Published in IEEE Transactions on Network Science and Engineering, 2022

The maritime Internet of Things (IoT) has recently emerged as a revolutionary communication paradigm where a large number of moving vessels are closely interconnected in intelligent maritime networks. However, the tremendous growth of vessel trajectories, collected from the combined satellite-terrestrial AIS (automatic identification system) base stations, could lead to unsatisfactory maritime safety and efficacy. To promote smart traffic services in maritime IoT, it is necessary to accurately and robustly predict the spatiotemporal vessel trajectories. It is beneficial for collision avoidance, maritime surveillance, and abnormal behavior detection, etc. Motivated by the strong learning capacity of deep neural networks, this work proposes an AIS data-driven trajectory prediction framework, whose main component is a long short term memory (LSTM) network. In particular, the vessel traffic conflict situation modeling, generated using the dynamic AIS data and social force concept, is embedded into the LSTM network to guarantee high-accuracy vessel trajectory prediction. In addition, a mixed loss function is reconstructed to make our prediction results more reliable and robust in different navigation environments. Several quantitative and qualitative experiments have been implemented on realistic AIS-based vessel trajectories. Our results have demonstrated that the proposed method could achieve satisfactory prediction performance in terms of accuracy and robustness.

Recommended citation: Liu, R. W., Liang, M., Nie, J., Lim, W. Y. B., Zhang, Y., & Guizani, M. (2022). Deep learning-powered vessel trajectory prediction for improving smart traffic services in maritime Internet of Things. IEEE Transactions on Network Science and Engineering, 9(5), 3080-3094. http://10.1109/TNSE.2022.3140529

MVFFNet: Multi-view feature fusion network for imbalanced ship classification

Published in Pattern Recognition Letters, 2021

The accurate classification of moving ships is of fundamental importance to maritime authorities for ensuring the safety and security of shipping operations. With the wide use of automatic identification systems (AISs), which allow ships to receive identification/location information from nearby ships, it is feasible to classify the types of ships by analysing ship behaviour from AIS-based trajectories. However, the imbalanced features of AIS data make it difficult to achieve satisfactory classification results in the presence of several different types of ships. To overcome these potential limitations, we propose a multi-view feature fusion network (MVFFNet) to achieve accurate ship classification with imbalanced data. To guarantee the powerful representation and generalization abilities of MVFFNet, we first extract several multi-view features (i.e., motion features and morphological features) from AIS-based ship trajectories. Several kinematic variables related to ship behaviour are empirically adopted as motion features. The morphological features are automatically extracted via convolutional auto-encoder (CAE) networks. CAE networks are capable of optimally learning the features from informative trajectory images, which are strictly related to the original ship trajectories. The bidirectional gated recurrent unit (BiGRU) network is then proposed to combine multi-view features to generate the ship classification results. In addition, a hybrid loss function is presented to handle the imbalance problem of ship types, potentially leading to enhanced robustness and accuracy of ship classification. Comprehensive experiments on two realistic datasets have demonstrated that our proposed MVFFNet consistently outperforms other competing methods in terms of classification accuracy and robustness.

Recommended citation: Liang, M., Zhan, Y., & Liu, R. W. (2021). MVFFNet: Multi-view feature fusion network for imbalanced ship classification. Pattern Recognition Letters, 51, 26-32. https://doi.org/10.1016/j.patrec.2021.07.024

CNN-enabled visibility enhancement framework for vessel detection under haze environment

Published in Journal of advanced transportation, 2021

Maritime images captured under haze environment often have a terrible visual effect, making it easy to overlook important information. To avoid the failure of vessel detection caused by fog, it is necessary to preprocess the collected hazy images for recovering vital information. In this paper, a novel CNN-enabled visibility dehazing framework is proposed, consisting of two subnetworks, that is, Coarse Feature Extraction Module (C-FEM) and Fine Feature Fusion Module (F-FFM). Specifically, C-FEM is a multiscale haze feature extraction network, which can learn information from three scales. Correspondingly, F-FFM is an improved encoder-decoder network to fuse multiscale information obtained by C-FEM and enhance the visual effect of the final output. Meanwhile, a hybrid loss function is designed for monitoring the multiscale output of C-FEM and the final result of F-FFM simultaneously. It is worth mentioning that massive maritime images are considered the training dataset to further adapt the vessel detection task under haze environment. Comprehensive experiments on synthetic and realistic images have verified the superior effectiveness and robustness of our CNN-enabled visibility dehazing framework compared to several state-of-the-art methods. Our method preprocesses images before vessel detection to demonstrate our framework has the capacity of promoting maritime video surveillance.

Recommended citation: Lu, Y., Guo, Y., & Liang, M. (2021). CNN-enabled visibility enhancement framework for vessel detection under haze environment. Journal of advanced transportation, 2021, 1-14. https://doi.org/10.1155/2021/5598390

An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation

Published in Ocean Engineering, 2021

To achieve reliable mining results for massive vessel trajectories, one of the most important challenges is how to efficiently compute the similarities between different vessel trajectories. The computation of vessel trajectory similarity has recently attracted increasing attention in the maritime data mining research community. However, traditional shape- and warping-based methods often suffer from several drawbacks such as high computational cost and sensitivity to unwanted artifacts and non-uniform sampling rates, etc. To eliminate these drawbacks, we propose an unsupervised learning method which automatically extracts low-dimensional features through a convolutional auto-encoder (CAE). In particular, we first generate the informative trajectory images by remapping the raw vessel trajectories into two-dimensional matrices while maintaining the spatio-temporal properties. Based on the massive vessel trajectories collected, the CAE can learn the low-dimensional representations of informative trajectory images in an unsupervised manner. The trajectory similarity is finally equivalent to efficiently computing the similarities between the learned low-dimensional features, which strongly correlate with the raw vessel trajectories. Comprehensive experiments on realistic data sets have demonstrated that the proposed method largely outperforms traditional trajectory similarity computation methods in terms of efficiency and effectiveness. The high-quality trajectory clustering performance could also be guaranteed according to the CAE-based trajectory similarity computation results.

Recommended citation: Liang, M., Liu, R. W., Li, S., Xiao, Z., Liu, X., & Lu, F. (2021). An unsupervised learning method with convolutional auto-encoder for vessel trajectory similarity computation. Ocean Engineering, 225, 108803. http://doi.org/10.1016/j.oceaneng.2021.108803