<abstract xmlns="http://www.w3.org/1999/xhtml"><p>This article presents an analysis of the possibilities of using the pre-degraded GoogLeNet artificial neural network to classify inland vessels. Inland water authorities monitor the intensity of the vessels via CCTV. Such classification seems to be an improvement in their statutory tasks. The automatic classification of the inland vessels from video recording is a one of the main objectives of the Automatic Ship Recognition and Identification (SHREC) project. The image repository for the training purposes consists about 6,000 images of different categories of the vessels. Some images were gathered from internet websites, and some were collected by the project’s video cameras. The GoogLeNet network was trained and tested using 11 variants. These variants assumed modifications of image sets representing (e.g., change in the number of classes, change of class types, initial reconstruction of images, removal of images of insufficient quality). The final result of the classification quality was 83.6%. The newly obtained neural network can be an extension and a component of a comprehensive geoinformatics system for vessel recognition.</p></abstract>

This article presents an analysis of the possibilities of using the pre-degraded GoogLeNet artificial neural network to classify inland vessels. Inland water authorities monitor the intensity of the vessels via CCTV. Such classification seems to be an improvement in their statutory tasks. The automatic classification of the inland vessels from video recording is a one of the main objectives of the Automatic Ship Recognition and Identification (SHREC) project. The image repository for the training purposes consists about 6,000 images of different categories of the vessels. Some images were gathered from internet websites, and some were collected by the project’s video cameras. The GoogLeNet network was trained and tested using 11 variants. These variants assumed modifications of image sets representing (e.g., change in the number of classes, change of class types, initial reconstruction of images, removal of images of insufficient quality). The final result of the classification quality was 83.6%. The newly obtained neural network can be an extension and a component of a comprehensive geoinformatics system for vessel recognition.

Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification

Polish Maritime Research

This work is licensed under the Creative Commons Attribution 4.0 International License.

This article presents an analysis of the possibilities of using the pre-degraded GoogLeNet artificial neural network to classify inland vessels. Inland water...

Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification

Online veröffentlicht: 24. Dez. 2020

Seitenbereich: 170 - 178

DOI: https://doi.org/10.2478/pomr-2020-0077

Schlüsselwörter
ship classification, image classification, geoinformatics, artificial intelligence, artificial neural network

© 2020 Katarzyna Bobkowska et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification

Online veröffentlicht: 24. Dez. 2020

Seitenbereich: 170 - 178

DOI: https://doi.org/10.2478/pomr-2020-0077

Schlüsselwörtership classification, image classification, geoinformatics, artificial intelligence, artificial neural network

© 2020 Katarzyna Bobkowska et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
ship classification, image classification, geoinformatics, artificial intelligence, artificial neural network