Affordable Access

Automatic Classification Using Machine Learning for Non-Conventional Vessels on Inland Waters

Authors
  • wlodarczyk-sielicka, marta
  • polap, dawid
Publication Date
Jul 10, 2019
Source
MDPI
Keywords
Language
English
License
Green
External links

Abstract

The prevalent methods for monitoring ships are based on automatic identification and radar systems. This applies mainly to large vessels. Additional sensors that are used include video cameras with different resolutions. Such systems feature cameras that capture images and software that analyze the selected video frames. The analysis involves the detection of a ship and the extraction of features to identify it. This article proposes a technique to detect and categorize ships through image processing methods that use convolutional neural networks. Tests to verify the proposed method were carried out on a database containing 200 images of four classes of ships. The advantages and disadvantages of implementing the proposed method are also discussed in light of the results. The system is designed to use multiple existing video streams to identify passing ships on inland waters, especially non-conventional vessels.

Report this publication

Statistics

Seen <100 times