Article
A novel method for extracting near-misses from AIS data involving collision avoidance behaviour
Ocean Engineering
— 2024 — Elsevier
Key information
Authors:
Published in
June 1, 2024
Abstract
This paper presents a novel method for the identification and analysis of near misses involving collision avoidance behaviour based on Automatic Identification System (AIS) data. While previous methods for near-miss extraction primarily focused on detecting potential collision risk, the novel method introduced in this paper not only considers potential collision risk but also evaluates the presence of avoidance behaviour. The novel method has three main stages: (1) Pre-processing of historical AIS data, which involves decoding, cleaning, and interpolating historical AIS data. (2) Identification of near misses by considering both potential collision risk and avoidance behaviour. (3) Analysis of near misses studying the intentions behind avoidance behaviour within near misses and the resulting outcomes, while extracting cases where the intentions align with the outcomes. To demonstrate the effectiveness of the proposed novel method, four typical encounter situations are used to extract the near misses. Additionally, the method is applied to coastal waterways in China, extracting near misses from one week of AIS data. The results demonstrate the capability of the novel method presented in this paper to effectively extract near misses involving collision avoidance behaviour.
Publication details
Authors in the community:
Carlos Guedes Soares
ist11869
Publication version
VoR - Version of Record
Publisher
Elsevier
Link to the publisher's version
https://www.sciencedirect.com/science/article/pii/S0029801824008035?via%3Dihub
Title of the publication container
Ocean Engineering
First page or article number
117466
Volume
301
ISSN
0029-8018
Fields of Science and Technology (FOS)
other-engineering-and-technologies - Other engineering and technologies
Keywords
- Near miss
- Avoidance behaviour
- AIS data
- Collision avoidance
Publication language (ISO code)
eng - English
Rights type:
Open access
Financing entity
Fundação para a Ciência e a Tecnologia
Identifier for the funding entity: UIDB-UIDP-00134-2020
Type of identifier of the funding entity: Crossref Funder