Dbscan Optimization for Improving Marine Trajectory Clustering and Anomaly Detection

Han, Xuming; Armenakis, Costas; Jadidi, Mojgan A.

doi:10.5194/isprs-archives-xliii-b4-2020-455-2020

Cited by 18 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The THREAD model is able to both detect anomalies and predict trajectories by extracting the trajectory patterns and turning them into way points. In THREAD, the way points are clustered using the DBSCAN method [16]. Predictions are then made by grouping a new trajectory into a class with similar way points, and estimating the future trajectory using the same-class trajectories.…”

Section: Related Workmentioning

confidence: 99%

Probabilistic Maritime Trajectory Prediction in Complex Scenarios Using Deep Learning

Sørensen

Heiselberg

2022

Sensors

View full text Add to dashboard Cite

Maritime activity is expected to increase, and therefore also the need for maritime surveillance and safety. Most ships are obligated to identify themselves with a transponder system like the Automatic Identification System (AIS) and ships that do not, intentionally or unintentionally, are referred to as dark ships and must be observed by other means. Knowing the future location of ships can not only help with ship/ship collision avoidance, but also with determining the identity of these dark ships found in, e.g., satellite images. However, predicting the future location of ships is inherently probabilistic and the variety of possible routes is almost limitless. We therefore introduce a Bidirectional Long-Short-Term-Memory Mixture Density Network (BLSTM-MDN) deep learning model capable of characterising the underlying distribution of ship trajectories. It is consequently possible to predict a probabilistic future location as opposed to a deterministic location. AIS data from 3631 different cargo ships are acquired from a region west of Norway spanning 320,000 sqkm. Our implemented BLSTM-MDN model characterizes the conditional probability of the target, conditioned on an input trajectory using an 11-dimensional Gaussian distribution and by inferring a single target from the distribution, we can predict several probable trajectories from the same input trajectory with a test Negative Log Likelihood loss of −9.96 corresponding to a mean distance error of 2.53 km 50 min into the future. We compare our model to both a standard BLSTM and a state-of-the-art multi-headed self-attention BLSTM model and the BLSTM-MDN performs similarly to the two deterministic deep learning models on straight trajectories, but produced better results in complex scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Probabilistic Maritime Trajectory Prediction in Complex Scenarios Using Deep Learning

Sørensen

Heiselberg

2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Although DBSCAN clustering algorithm can determine the number of clusters center according to the classification of point cloud [36,37], in practical application, it is necessary to determine the distance between core points and the minimum number of sample points (MinPts) in the classification subset. Sometimes, due to the accuracy of point cloud computing, the actual application effect of the DBSCAN algorithm needs to be improved.…”

Section: Unsupervised Learningmentioning

confidence: 99%

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Zhang

Jin

2022

Scientific Programming

View full text Add to dashboard Cite

Point cloud local feature extraction places an important part of point cloud deep learning neural networks. Accurate extraction of point cloud features is still a challenge for deep learning networks. Oversampling and feature loss of point cloud model are important problems in the accuracy of image point cloud deep learning network. In this paper, we propose an adaptive clustering method for point cloud feature extraction—adaptive optimal means clustering (AOMC)—and apply it to point cloud deep learning network tasks. This method solves the problem of determining the number of clustering centers in the process of point cloud feature extraction so that the feature points contain the whole point cloud model and avoid the problem of losing detail features. Specifically, according to the loss characteristics of point cloud clustering, AOMC selects a different number of clustering centers for various models. Moreover, in light of the density distribution of the point cloud, the radius of the clustering subset is determined. This method effectively improves the accuracy of the point cloud deep learning network on object classification and parts segmentation. Our method reaches demand on Modelnet10 and shapenetcore_partanno_segmentation_benchmark datasets. In terms of deep learning network optimization, it has good performance. Additionally, our method has high accuracy and low algorithm complexity.

show abstract

“…Usually, the user selects the optimal parameters after a long and repetitive trial-and-error process. However, determining the optimal parameters can be very challenging under real-life conditions when the data and scale cannot be well understood [13][14][15][16][17][18][19][20][21][22]. The application of the traditional DBSCAN clustering method can also underperform with unevenly distributed data, which is challenging to be clustered ideally with a single designated Eps parameter [13][14][15][16][17][18][19][20][21][22].…”

Section: Dbscan Enhancementmentioning

confidence: 99%

“…However, determining the optimal parameters can be very challenging under real-life conditions when the data and scale cannot be well understood [13][14][15][16][17][18][19][20][21][22]. The application of the traditional DBSCAN clustering method can also underperform with unevenly distributed data, which is challenging to be clustered ideally with a single designated Eps parameter [13][14][15][16][17][18][19][20][21][22]. This leads to unreliable results when applying the traditional DBSCAN method to real AIS data without optimization.…”

Section: Dbscan Enhancementmentioning

confidence: 99%

“…Most of the existing optimizations are designed for clustering two-dimensional spatial data (i.e., x, y). When the data dimensions grow and the Mahalanobis distance metric is used, the distribution of the dataset becomes different [13,23,24]. Therefore, the existing adaptive parameter method needs to be modified prior to its application to the enhanced DBSCAN method.…”

Section: Dbscan Enhancementmentioning

confidence: 99%

See 1 more Smart Citation

Modeling Vessel Behaviours by Clustering AIS Data Using Optimized DBSCAN

2021

View full text Add to dashboard Cite

Today, maritime transportation represents a substantial portion of international trade. Sustainable development of marine transportation requires systematic modeling and surveillance for maritime situational awareness. In this paper, we present an enhanced density-based spatial clustering of applications with noise (DBSCAN) method to model vessel behaviours based on trajectory point data. The proposed methodology enhances the DBSCAN clustering performance by integrating the Mahalanobis distance metric, which considers the correlation between the points representing vessel locations. This research proposes applying the clustering method to historical Automatic Identification System (AIS) data using an algorithm to generate a clustering model of the vessels’ trajectories and a model for detecting vessel trajectory anomalies, such as unexpected stops, deviations from regulated routes, or inconsistent speed. Further, an automatic and data-driven approach is proposed to select the initial parameters for the enhanced DBSCAN approach. Results are presented from two case studies using an openly available Gulf of Mexico AIS dataset as well as a Saint Lawrence Seaway and Great Lakes AIS licensed dataset acquired from ORBCOMM (a maritime AIS data provider). These research findings demonstrate the applicability and scalability of the proposed method for modeling more water regions, contributing to situational awareness, vessel collision prevention, safe navigation, route planning, and detection of vessel behaviour anomalies for auto-vessel development towards the sustainability of marine transportation.

show abstract

Dbscan Optimization for Improving Marine Trajectory Clustering and Anomaly Detection

Cited by 18 publications

References 8 publications

Probabilistic Maritime Trajectory Prediction in Complex Scenarios Using Deep Learning

Probabilistic Maritime Trajectory Prediction in Complex Scenarios Using Deep Learning

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Modeling Vessel Behaviours by Clustering AIS Data Using Optimized DBSCAN

Contact Info

Product

Resources

About