prikaz prve stranice dokumenta Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja
No public access
undergraduate thesis
Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. urn:nbn:hr:168:779683
Ahac, Luka
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ahac, L. (2020). Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:779683

Ahac, Luka. "Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:779683

Ahac, Luka. "Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:779683

Ahac, L. (2020). 'Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 13 January 2025, https://urn.nsk.hr/urn:nbn:hr:168:779683

Ahac L. Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2025 January 13] Available at: https://urn.nsk.hr/urn:nbn:hr:168:779683

L. Ahac, "Duboki konvolucijski modeli za automatizirano praćenje i nadzor životinja", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:779683

Metadata
TitleDuboki konvolucijski modeli za automatizirano praćenje i nadzor životinja
Title (english)Tracking Animal Behavior Using Deep Convolutional Neural Networks
AuthorLuka Ahac
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberJosip Šarić (član povjerenstva)
Committee memberIvan Grubišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-07, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Tema rada su problemi detekcije i segmentacije objekata na fotografijama. Objašnjeni su koncepti neuronskih mreža te konvolucijskih neuronskih mreža. Nakon toga su opisani neki od popularnijih postojećih modela za detekciju objekata na fotografijama i dana je njihova usporedba u brzini i preciznošću. Zatim je model Mask R-CNN treniran na vlastito izrađenom skupu podataka u kojemu se nalaze slike lavova. Nakon toga model je primijenjen da samostalno detektira lavove na fotografijama koje nije do tada vidio, što je rezultiralo sa zadovoljavajućim rezultatima.
Abstract (english)
This paper examines the problem of object detection and segmentation. There are given an explanation to concepts of neural networks and convolutional neural networks. Afterward, some of the most popular existing object detection models are described and compared in speed and accuracy. The Mask R-CNN model was then trained on a self-created data set containing images of lions. The model was then applied to independently detect lions in photographs that were not seen before, resulting in satisfactory results.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:779683
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-14 08:17:16