Institutional Repository [SANDBOX]
Technical University of Crete
EN  |  EL

Search

Browse

My Space

Επεξεργασία βίντεο πραγματικού χρόνου για αναγνώριση και εντοπισμό προβλημάτων σε δίχτυα ιχθυοκαλλιέργειας

Paspalakis Stavros

Full record


URI: http://purl.tuc.gr/dl/dias/DD8A39C3-8ABD-4A5F-9C21-BDB2B3F3423B
Year 2020
Type of Item Diploma Work
License
Details
Bibliographic Citation Stavros Paspalakis, "Real-time video processing for detection and localization of irregular structures on fishing nets", Diploma Work, School of Electrical and Computer Engineering, Technical University of Crete, Chania, Greece, 2020 https://doi.org/10.26233/heallink.tuc.gr.86853
Appears in Collections

Summary

The objective of the current thesis is the processing of underwater images from fish nets cages and the detection of discontinuities on them (eg. holes). Such an application proves to be particularly useful as it reduces the economic loss of production units. Our implementation combines two different image processing approaches: the global process and the local process. In the first one we focus on the statistical analysis of segmented parts of the image through the value of intensity which is contained in these parts. While in the second we focus on the export of repetitive pattern (e.g. straight lines) based on the Hough transformation technique. Our methods were implemented on static images of fish nets of different shape and size. As for the advantages of our system, we could say that, through future combined implementation of the two methods, there is good indication that it can lead to a fully automatic system in order to be used under realistic conditions for real-time monitoring and interventions.

Available Files

Services

Statistics