Classification of vessel motion pattern in inland waterways based on Automatic Identification System

With the development of terrestrial networks and satellite constellations, vessel movement information can be effectively collected based on Automatic Identification System (AIS) receivers. Vessel motion pattern classification using AIS plays an important role in maritime monitoring and management. However, classifying vast amounts of vessel motion information is prohibitive workload. The aim of this study is to develop effective methods that can aid in automatic vessel motion pattern classification in inland waterways. First, the Least-squares Cubic Spline Curves Approximation (LCSCA) technique is used to represent the vessel motion trajectory. Then, a traditional classification model based on Lp-norm (0 < p < 1) sparse representation is improved to classify vessel motion patterns. And a Matching Pursuit - Fletcher Reeves (MPFR) method is developed to find the sparse solutions of the proposed model. To validate the performance of the proposed model, two AIS datasets from the Yangtze River are collected and applied in the authors' experiment. According to the results, the authors can know that the proposed model can effectively classify vessel motion pattern in inland waterways. And the effectiveness of the proposed model is superior to those of other representative classification methods.

• Record URL:
  • https://doi.org/10.1016/j.oceaneng.2018.04.072
• Record URL:
  • http://www.sciencedirect.com/science/article/pii/S0029801818305808
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/00298018
• Supplemental Notes:
  • Abstract reprinted with permission of Elsevier.
• Authors:
  • Chen, Zhijun
  • Xue, Jie
  • Wu, Chaozhong
  • Qin, Lingqiao
  • Liu, Liqun
  • Cheng, Xiaozhao
• Publication Date: 2018-8-1

Language

• English

Media Info

• Media Type: Web
• Features: Appendices; Figures; References; Tables;
• Pagination: pp 69-76
• Serial:
  • Ocean Engineering
  • Volume: 161
  • Issue Number: 0
  • Publisher: Pergamon
  • ISSN: 0029-8018
  • EISSN: 1873-5258
  • Serial URL: http://www.sciencedirect.com/science/journal/00298018

Subject/Index Terms

• TRT Terms: Classification; Identification systems; Inland waterways; Ocean engineering; Ship motion; Water transportation crashes
• Subject Areas: Marine Transportation; Vehicles and Equipment;

Filing Info

• Accession Number: 01672661
• Record Type: Publication
• Files: TRIS
• Created Date: Jun 21 2018 9:27AM