Skip to the main content

Professional paper

https://doi.org/10.36978/cte.8.1.4

Object recognition in marine surveillance cameras

Miran Pobar ; University of Rijeka, Faculty of Informatics and Digital Technologies *

* Corresponding author.


Full text: croatian pdf 698 Kb

page 42-49

downloads: 85

cite


Abstract

Automatic object detection in maritime surveillance or panoramic camera images opens up possibilities for automatic traffic monitoring, unauthorized movement detection, and hazard or pollution identification. This study investigates the performance of models based on the YOLOv7 architecture for the task of detecting vessels and buoys in images captured by panoramic and surveillance cameras. The models are trained on a dedicated dataset comprising diverse maritime scenes created for this purpose, utilizing transfer learning from models trained on generic images. Additionally, two variants of input handling strategies are examined, and the use of the input image cropping strategy significantly improves detection results, especially for small objects, compared to the baseline model.

Keywords

computer vision; neural networks; small object detection; ship detection

Hrčak ID:

317944

URI

https://hrcak.srce.hr/317944

Publication date:

17.6.2024.

Article data in other languages: croatian

Visits: 404 *