Original title:
Evaluace metod zpracování obrazu pro úlohu sledování letícího objektu pomocí dronu
Translated title:
Evaluation of image processing methods for flying object tracking using drone
Authors:
Daniš, Stanislav ; Věchet, Stanislav (referee) ; Krejsa, Jiří (advisor) Document type: Bachelor's theses
Year:
2020
Language:
slo Publisher:
Vysoké učení technické v Brně. Fakulta strojního inženýrství Abstract:
[slo][eng]
Bakalárska práca bola zameraná na evaluáciu sledovacích algoritmov, obsiahnutých v knižnici OpenCV voči motion blur efektu. Bol vytvorený dataset videí s definovanými rozsahmi vybraných parametrov, ktoré ovplyvňovali vznik motion blur efektu (rýchlosť, vzdialenosť od objektu, pozícia svetla a ďalšie). Každé z videí bolo spracované pomocou sledovacieho algoritmu. Z týchto výsledkov boli v závere formulované zistenia o efektivite každého z algoritmov pre definovanú situáciu.
The bachelor thesis was focused on the evaluation of tracking algorithms contained in the OpenCV library against the motion blur effect. A dataset of videos was created with defined ranges of selected parameters that influenced the motion blur effect (speed, distance from the object, position of light and others). Each of the videos was processed using a tracking algorithm. From these results, findings on the effectiveness of each of the algorithms for a defined situation were formulated in the conclusion.
Keywords:
Color detection; Evaluation of tracking algorithms; Image processing; Motion blur efect; OpenCV; Tracking algorithm
Institution: Brno University of Technology
(web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library. Original record: http://hdl.handle.net/11012/193455