Home // SMART 2021, The Tenth International Conference on Smart Cities, Systems, Devices and Technologies // View article
Authors:
Natalia Wawrzyniak
Tomasz Hyla
Keywords: surveillance; ship identification; detection and tracking; river information services
Abstract:
The scope of the ship recognition and identification (SHREC) project covers development of three main system modules based on: detection and tracking, classification, and identification methods. First method allows to detect and track a moving ship while maintaining system performance, so it can be used to process data from multiple cameras (20 and more). Second method allows for classification of non-conventional ships into 5 to 7 classes using two Convolutional Neural Networks (CNN). This allows to recognize a type of ships when the identification is not possible. The identification method locates and recognizes hull inscriptions of detected units and matches them with records from available ships registers. Obtained information on ships can be automatically pushed into service oriented architecture of River Information Services (RIS) for alerting, statistics and authentication purposes. Currently, the integration and performance tests in marine and inland on-shore environment are close to finish. The obtained results imply that the SHREC is suitable for further integration with smart city services.
Pages: 29 to 31
Copyright: Copyright (c) IARIA, 2021
Publication date: May 30, 2021
Published in: conference
ISSN: 2308-3727
ISBN: 978-1-61208-805-1
Location: Valencia, Spain
Dates: from May 30, 2021 to June 3, 2021